{"origin": "fcv", "source_key": "fcv_pads_east_africa:000498:8:3", "occurrence_id": "5925c2b95d8a4c1c8c3da521", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: from PIMIS which is still being rolled out.|Corporate result indicator introduced recently. Baseline, actual, and targets to be updated
next reporting period using data from PIMIS which is still being rolled out.|Corporate result indicator introduced recently. Baseline, actual, and targets to be updated
next reporting period using data from PIMIS which is still being rolled out.|Corporate result indicator introduced recently. Baseline, actual, and targets to be updated
next reporting period using data from PIMIS which is still being rolled out.|Corporate result indicator introduced recently. Baseline, actual, and targets to be updated
next reporting period using data from PIMIS which is still being rolled out.|Corporate result indicator introduced recently. Baseline, actual, and targets to be updated
next reporting period using data from PIMIS which is still being rolled out.|\n|People with enhanced
resilience to climate
risks – Youth (Number
of people) CRI|||1,000,000|12-Jun-2025|1,000,000|10-Dec-2025|2,000,000|Dec/2028|\n|People with enhanced
resilience to climate
risks – Youth (Number
of people) CRI|Comments on
achieving targets|Comments on
achieving targets|Corporate result indicator introduced recently. Baseline, actual, and targets to be updated
next reporting period using data from PIMIS which is still being rolled out.|Corporate result indicator introduced recently. Baseline, actual, and targets to be updated
next reporting period using data from PIMIS which is still being rolled out.|Corporate result indicator introduced recently. Baseline, actual, and targets to be updated
next reporting period using data from\n\nMention: \"data from PIMIS\""}, {"role": "assistant", "content": "{\"role\": \"supporting\", \"usage_action\": \"source\", \"summary\": \"Corporate result indicators are to be updated next reporting period from PIMIS, which is still being rolled out.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "fcv", "source_key": "fcv_pads_east_africa:001487:35:0", "occurrence_id": "c85d0629fbae454bb57f3b1c", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: **The World Bank**\nEthiopia: National Quality Infrastructure Development Project (P160279) ICR DOCUMENT\n\n\n_Source: UN Comtrade data._\n\n\n**ANNEX 6. BORROWER, CO-FINANCIER AND OTHER PARTNER/STAKEHOLDER COMMENTS**\n\nReceived on Monday, December 29, 2025\n\n\n_Dear Bisrat,_\n\n\n_My sincere apologies for the late response, as I had unfortunately overlooked your message._\n\n\n_Thank you very much for sharing the draft Implementation Completion Report (ICR). I have reviewed the document carefully,_\n_and I appreciate the effort made in preparing a well structured and comprehensive report._\n\n\n_However, I would like to raise one important observation. In the final report, I could not find adequate reflection or_\n_acknowledgment of the role of the implementing ministry, including myself, as well as the focal persons and heads of the_\n_beneficiary institutions. The report appears to focus primarily on the task force team, while the contributions and_\n_responsibilities of the implementing ministry and beneficiary institutions are not sufficiently captured in one consolidated_\n_section._\n\n\n_I kindly request that this aspect be revisited and appropriately reflected in the final version of the report, to ensure balanced_\n_recognition of all key stakeholders involved in the implementation of the project._\n\n\n_Thank you again for sharing the draft, and I appreciate your continued collaboration._\n\n\n_Kind regards,_\n\n\n_Ato Endalew Mekonnen_\n_Minister of trade and regional integration of Ethiopia_\n\n\nPage 28\n\n\nOfficial Use Only\n\nMention: \"UN Comtrade data\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"A trade figure in the annex is credited directly to the UN Comtrade data.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "fcv", "source_key": "fcv_pads_east_africa:001708:10:0", "occurrence_id": "d0aaf89e9974c8249c2cf3f9", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: **UGANDA** **INVESTING** **IN** FORESTS **AND** PROTECTED **AREAS** FOR **CLIMATE** SMART **DEVELOPMENT**\n**PROJECT;** **IDA** **CREDIT-6592-UG** **AND** GRANT **D596-UG**\nAnnual Financial Statements for the year ended **3** **0th** June **2023**\n\n\n**2.0** **PROJECT** **OBJECTIVES**\n\n\n\nThe main project objective is to improve sustainable management of forests and\n\nprotected areas and increase benefits to communities from forests in target landscapes.\nThe project is impimented under four major components and consists of the following\n\nparts:\n\n\nPart **1:** Improved Management of Protected Areas\n\n\n\n**1.1** (a) Carrying out a program of activities designed to improve the basic management\nof Protected Areas, such a program to include such activities as: (i) grading and\n\nmaintenance of tracks and trails within the Proteced Areas; (ii) planning (including\ncommunity consultations) and demarcation of the Protected Areas' boundaries; (iii)\ninstallation of infrastructure such as fences, walls and gates as well as construction\nof rangers' housing and posts; (iv) undertaking of community-oriented activities to\n\nmanage human-wildlife conflict including providing equipment as neededl (v)\nprocurement of field vehicles, road equipment, communication equipment, field,\nand office equipment; and (vi) support for the National Forest Monitoring System.\n\n\n\n**(b)** Carrying out a program of activities designed to improve wildlife management\nand control of invasive plants in the Protected Areas, sucha a program to include\nsuch activities as: (i) provision of technical assistance and advisory services to\nsupport\n\nMention: \"National Forest Monitoring System\""}, {"role": "assistant", "content": "{\"role\": \"supporting\", \"usage_action\": \"curate\", \"summary\": \"Project financing includes support for the national forest monitoring system alongside equipment procurement.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "fcv", "source_key": "fcv_pads_east_africa:001746:4:0", "occurrence_id": "44753e927342e11cfc297c28", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: **The World Bank** Implementation Status & Results Report\nEthiopia General Education Quality Improvement Program for Equity (P163050)\n\n\n\nComments\n\n\n\nThe Steering committee has been held at national and sub-national level which co-chaired by\nrespective institutions.\n\n\n\n\n\n\n\n\n\n\n|Action Description|1.7 At least one Education Working Group meeting devoted to refugee issues, including both
WEO and ARRA, held annually in each main refugee-hosting Woreda|Col3|Col4|Col5|Col6|\n|---|---|---|---|---|---|\n|Source|DLI#|Responsibility|Timing|Timing Value|Status|\n|Technical|NA|WEO/ARRA|Recurrent|Yearly|Completed|\n|Completion
Measurement|Meetings held as stipulated|Meetings held as stipulated|Meetings held as stipulated|Meetings held as stipulated|Meetings held as stipulated|\n|Comments|Meetings held as stipulated.|Meetings held as stipulated.|Meetings held as stipulated.|Meetings held as stipulated.|Meetings held as stipulated.|\n\n\n\n\n\n\n\n\n|Action Description|1.8. Include full data for refugee primary and secondary schools, on a par with MoE schools,
in Educational Statistics Annual Abstract (ESAA)|Col3|Col4|Col5|Col6|\n|---|---|---|---|---|---|\n|Source|DLI#|Responsibility|Timing|Timing Value|Status|\n|Technical|NA|MoE|Recurrent|Yearly|Completed|\n|Completion
Measurement|ESSA published annually including information for refugee schools for all primary and
secondary indicators\n\nMention: \"Educational Statistics Annual Abstract\""}, {"role": "assistant", "content": "{\"role\": \"supporting\", \"usage_action\": \"curate\", \"summary\": \"A disbursement-linked action requires refugee school data to be included in the annual education statistics abstract on the same footing as ministry schools.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "fcv", "source_key": "fcv_pads_east_africa:002529:5:0", "occurrence_id": "fc62aad24570de6c16ce3235", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: **The World Bank** Implementation Status & Results Report\nStrengthen Ethiopia’s Adaptive Safety Net (P172479)\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n|Beneficiaries of cash-
based interventions -
Female (Number of
people) CRI|Comments on
achieving targets|Col3|Source FSCO FIC report for December 2025: Total 4,146,799 Minus Special woredas 59,230.|Col5|Col6|Col7|Col8|Col9|\n|---|---|---|---|---|---|---|---|---|\n|Beneficiaries of cash-
based interventions -
Youth (Number of
people) CRI|0|Jun/2020|0|30-Jun-2025|0|31-Mar-2026|0|Jun/2026|\n|Beneficiaries of cash-
based interventions -
Youth (Number of
people) CRI|Comments on
achieving targets|Comments on
achieving targets|The project does not track this indicator, but it cannot be deleted from the Operational
Workspace, as it is embedded in another indicator.|The project does not track this indicator, but it cannot be deleted from the Operational
Workspace, as it is embedded in another indicator.|The project does not track this indicator, but it cannot be deleted from the Operational
Workspace, as it is embedded in another indicator.|The project does not track this indicator, but it cannot be deleted from the Operational
Workspace, as it is embedded in another indicator.|The project does not track this indicator, but it cannot be deleted from the Operational5 [^5: World Bank, _Maintaining the Momentum While Addressing Service Quality and Equity: A Diagnostic of Water Supply, Sanitation,_\n_Hygiene, and Poverty in Ethiopia_ (Washington, DC: World Bank, 2018), 1.] About 67 million people gained access to a latrine, at an average\nrate of 2.6 million people per year. Sanitation and hygiene promotion were integrated into wider health-care delivery\nmechanisms and utilized behavioral change communication (BCC).\n4. **Notwithstanding the progress, much remains to be done.** At present, about 60 million people lack access to\nbasic drinking water, 112 million people lack access to basic sanitation, and about 22 million practice open defecation\n(JMP, 2022). In rural areas, basic drinking water 6 is accessible to only 42% of the population compared to 83% in urban\nareas 7 [^7: As per JMP 2022 report, 39% of urban population have access to safely managed, 76% have the service accessible on premises, 68% have water supply available when\nneeded and 39% free from contamination.] . About 76% and 39% of rural and urban schools, and 45% and 22% of rural and urban health facilities are without\nwater\n\nMention: \"JMP 2022 report\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"Urban access to safely managed water and its component conditions are quoted from the joint monitoring programme report.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "fcv", "source_key": "fcv_pads_east_africa:006890:30:0", "occurrence_id": "0e71e9458d03925bed1975bc", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: 5. Record national health facilities information using a database system (Master Facility Registry) and\navail full national data.\n6. Conduct national health facilities assessment according to the national standards, label health facilities\n(green, yellow and red) and take actions as necessary\n7. Capacity building and support for regional health regulatory bodies (training, technical and financial\nsupport).\n\nThe Healthcare Waste Management Directive (2005), Proclamation No. 661/2009, Regulation No.\n299/2013, Health facilities standards since 2012 and Health Facilities Promotion Directive (2014) are being\nutilized in guiding the activities of the directorate.\n\nThe health regulatory structures are not uniform from federal to woreda levels. Due to this, the\nimplementation of regulatory laws and standards are not uniform across the regulatory bodies at each level.\n\n\n**Hygiene and Environmental Health Directorate**\n\n\nHygiene and Environmental Health Directorate has four case teams: Sanitation, Water, Food safety and\nhygiene, Institutional WASH and Climate resilient and Social conformity. The Roles and responsibilities\nof the directorate include:\n\n\n - Environmental Health Impact Assessment,\n\n - Promoting hygiene and environmental health services,\n\n - Prepare policies, strategies, guidelines, and manuals, coordinate and support the implementation,\n\n - Strengthen institutional arrangement and implementation capacity for the program at all level,\n\n - Mobilize and properly utilize resources for program implementation,\n\n - Conduct research for evidence based decision,\n\n - Provide capacity building supports for concerned stakeholders,\n\n - Strengthen and coordinate multi-sectorial and private sector integration,\n\n - Monitor and evaluate progresses against targets,\n\n - Facilitate experience sharing and scaling up of good experiences,\n\n - Strengthening climate resilient health system,\n\n\nThe Health care waste management Manual (2020), Health Impact Assessment Guideline (2021) and\nWASH in health care facilities guidelines are being utilized in guiding the activities of the directorate.\n\n\n**Women, Youth and Children Affairs Directorate**\n\n\nThe Roles and responsibilities of the directorate include:\n\n\n - Facilitate Gender Mainstreaming in programs and operations,\n\n - Enhance women empowerment at institutional\n\nMention: \"Master Facility Registry\""}, {"role": "assistant", "content": "{\"role\": \"supporting\", \"usage_action\": \"curate\", \"summary\": \"A reform milestone requires health facility information to be recorded in the registry and full national data to be made available.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "fcv", "source_key": "fcv_pads_east_africa:008497:2:0", "occurrence_id": "4fea05d5007323f1aacb5426", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: local level along with normal food deliveries, did not work . Similarly, the school attendance program, meant to use\nfood or cash transfers to help maintain school attendance of girl pupils during the drought, was implemented in only a\nfew districts.\nThe project generated direct employment for over 900,000 individuals (who, according to an end-user survey, earned\nan average of 340 Birr (US$40.00) from working on a sub-project). This was no doubt an important source of\neconomic support, in part because it likely allowed the families to maintain (or reduce destocking of) their livestock.\nHowever, although the project created employment, it did not have a dedicated intervention for livelihood\ndevelopment. Therefore, many of the sub-projects with respect to soil and water conservation (described below) are\nlikely to produce more general environmental benefits and strengthen future drought resilience rather than directly\nenhance livelihood prospects.\n(ii) To put in place infrastructure and support mechanisms to mitigate the medium term effects of current and future\ndrought emergencies on vulnerable groups : rated **Substantial** .\nOn the community assets side, there was a large range and number of physical achievements . Achievements in\nwater development include 327 ponds, 127 micro-irrigation systems, 3 pump irrigation systems, 332 springs\n(development and maintenance), 119 hand dug wells, and 22 roof water harvesting structures. Achievements in soil\nand water harvesting included construction of bunds and terraces, check dams, cut -off drains and waterways as well\nas range management and 13.4 million of tree seedlings planted. In addition, this component financed construction\nand maintenance of 2,940 km of roads, and rehabilitated 368 schools and 88 health posts. Consistent with the\ncommunity-driven nature of these sub-projects, it had not been feasible to define ex -ante specific end-of-project\ntarget values; hence, that yardstick is unavailable to measure project success . As explained above\n\nMention: \"end-user survey\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"Average earnings per worker on sub-projects are reported from a survey of programme end users.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "fcv", "source_key": "fcv_pads_east_africa:008546:74:1", "occurrence_id": "c4cb56d366728755829bbbf3", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: CEmOC) services|20%|44.6%|24.6%||\n|Health facilities without stock-out of
medicines|26%|84%|58||\n\n\n\nSource: Data has been taken from the Annual Health Sector Performance Reports, 2010/11 and 2015/16, Ministry\nof Health, The Republic of Uganda\n\n\n69\n\nMention: \"Annual Health Sector Performance Reports\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"Service availability and stock-out percentages in the results table are taken from two annual sector performance rounds.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "fcv", "source_key": "fcv_pads_east_africa:008658:51:0", "occurrence_id": "fa6bbe320c80d543b47ec87a", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: **ANNEX 7.** **SUMMARY OF BORROWER'S ICR AND/OR COMMENTS ON DRAFT ICR**\n\n\n**Borrower’s ICR for the IDA Credit: Learning and Innovation Lending (LIL)**\n\nThe Conservation and Sustainable Use of Medicinal Plants Project (CSMPP) was developed and\nimplemented by the IBC in collaboration with stakeholders. The specific objectives of the project’s credit\ncomponent were to support the establishment of FGBs for medicinal plants, strengthen the capacity of\ntraditional healers, develop an IPR policy guideline, develop five phytomedicines for human and\nlivestock diseases, establish a national medicinal plant database, develop techniques for propagating\nmedicinal plants, and carry out a national economic survey on the use of medicinal plants. The IBC was\ndesignated in a government-signed MOU as the project’s lead implementing agency, to work with 12\ncollaborating institutions. IBC established a Project Monitoring and Coordination Unit (PCMU) to\nfacilitate implementation.\n\nThe project’s credit component was financed by IDA with a matching fund allotted by the Government of\nEthiopia. The project was originally to last four years, but a six-month extension was granted to complete\na validation study for one phytomedicine. The original allocation of IDA was US$ 2.5 million, but about\nUS$ 600,000 dollars were cancelled.\n\nBased on the its objectives and key performance indicators (KPIs), the project’s achievements can be\nsummarized as follows:\n\n - An M&E system manual, reviewed and approved by IDA, was developed and used.\n\n - A national consultant conducted an institutional and human resource capacity assessment to\nidentify training needs and other inputs. Based on the results, training and procurement plans\nwere prepared and implemented.\n\n - THAs conducted a number of workshops to raise members’ awareness of the importance of\nconserving medicinal plants, validating traditional medicines, following a code of ethics and\npractices, and other\n\nMention: \"national medicinal plant database\""}, {"role": "assistant", "content": "{\"role\": \"supporting\", \"usage_action\": \"curate\", \"summary\": \"Establishing the database is listed among the credit objectives, alongside propagation techniques and a use survey.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "fcv", "source_key": "fcv_pads_east_africa:008800:4:1", "occurrence_id": "2527138f98bceb2d6b7b5071", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: from entrenched and significant unequal\naccess to education. However, a focus on disadvantaged and vulnerable groups may mean that the\ninequalities between individuals within groups are overlooked. **Vertical inequalities within groups**\n(e.g. groups of adolescent girls) are often larger than **horizontal inequalities** between groups (e.g.\nrural-urban populations). Existing data collection and monitoring systems have to be expanded to\nconsider fully the range of vertical differences within the vulnerable and disadvantaged groups. This\nwill be needed in future, to support better targeting of limited resources and programmes which can\nfully address the diverse range of opportunities and barriers, to quality education, across vulnerable\nand disadvantaged groups and populations.\n\n\n**Enabling Background for GEQIP Phase 2**\nConstitutional rights, policies and programmes in Ethiopia strongly support and promote the equitable\ninclusion of regions and vulnerable groups lagging behind in access to quality education. The GoE\nhas moved on a range of fronts (laws, policies and programmes) to address both the supply and\ndemand side constraints affecting enrolment, repetition and drop-out.\n\n\nGEQIP Phase I included an explicit focus on gender. Attention was paid to the selection of female\nteachers for training courses and all data was disaggregated. EMIS data shows the following national\nachievements with respect to female participation in primary and secondary education since GEQIP\nPhase 1 was launched in 2009: the proportion of female teachers has increased from 33% to 34%;\ngirls primary completion rate has increased from 45% to 52% at grade 8; girls’ drop out has decreased\nfrom 19% to 15%and 17,000 more girls passed the grade 10 examination\n\nGEQIP Phase I included support to Alternative Basic Education Centres which are designed as low\ncost alternatives to formal schools and reach vulnerable and disadvantaged children, especially in the\nemerging regions. ABECs use locally recruited facilitators to deliver the curriculum in a flexible way.\n\nMention: \"EMIS data\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"analyze\", \"summary\": \"System data provide the female teacher share and girls' completion trends used to judge the gender focus of the first phase.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "fcv", "source_key": "fcv_pads_east_africa:008875:1:1", "occurrence_id": "b6ca2761929ef744faf09b8c", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: ** The State Department for Labour (SDL) has made progress in completing an informal sector survey, updating the Kenyan\nNational Occupational Classification (KNOCS), and setting up a Labour Market Observatory (LMO) that is implementing a roadmap for the Kenya\nLabour Market Information System (KLMIS).\n\n\n**Component 4** . National Youth Policy: The National Youth Policy was endorsed by the Cabinet in November 2019 and is now poised to be\ndisseminated to key stakeholders before moving to the Kenya National Assembly for legislation **.**\n\n\n**Risks**\n\n\n**Systematic Operations Risk-rating Tool**\n\n\nRisk Category Rating at Approval Previous Rating Current Rating\n\n\nPolitical and Governance Substantial Substantial Substantial\n\n\nMacroeconomic Moderate Substantial Substantial\n\n\nSector Strategies and Policies Low Low Low\n\n\nTechnical Design of Project or Program Substantial Substantial Substantial\n\nInstitutional Capacity for Implementation and\nHigh High High\nSustainability\n\nFiduciary High High High\n\n\nEnvironment and Social Low Moderate Moderate\n\n\nStakeholders Moderate Moderate Moderate\n\n\nOther -- -- -\n\nOverall Substantial Substantial Substantial\n\n\n**Results**\n\n\n**PDO Indicators by Objectives / Outcomes**\n\n\n6/12/2021 Page 2 of 8\n\nMention: \"informal sector survey\""}, {"role": "assistant", "content": "{\"role\": \"supporting\", \"usage_action\": \"curate\", \"summary\": \"Completing the survey is reported as progress alongside an occupational classification update and a labour market observatory.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "fcv", "source_key": "fcv_pads_east_africa:009114:6:0", "occurrence_id": "139d1ac5a54fccc7275f5902", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: **Independent Evaluation Group (IEG)** Implementation Completion Report (ICR) Review\nKE-Municipal Program (FY10) (P066488)\n\n\nto reduced repairs and business disruption. People interviewed in an audit of environmental and social\nsafeguards compliance, confirmed that the April May 2017 rains did not flood the usual areas.\n\n - 11 of the 14 integrated strategic urban development plans have been approved by county executive\ncommittees while the rest were awaiting approval. Three plans were approved by county assemblies.\nCounty governments, like Mombasa, were using the plans to inform future infrastructure projects, based\non evidence obtained from the Beneficiary Assessments. Under the 2012 County Government Act,\ncounties prepare 5-year county development plans. The project trained staff of nearly all 47 counties\nbased on the Handbook and built capacity of county staff who generated the integrated urban\ndevelopment plans.\n\nThe following outcome was partially achieved:\n\n\n - 69,200 urban residents (target 170,000) gained access to all season roads within a 500-meter range\nunder the project. The government dropped some contracts for roads and drainage following the 2015\nRestructuring primarily because the Mombassa drainage cost overruns reduced available resources(see\nSection 5. Efficiency).\n\nThe following indicators were dropped as a result of the 2015 Restructuring:\n\n\n - at the national level - strengthening of intergovernmental fiscal frameworks to enhance volume and\npredictability of resources transferred to municipalities based on their performance;\n\n - implementing a financial management information systems at the urban level;\n\n - implementing the annual performance assessment of participating municipalities;\n\n - developing revenue enhancement plans for each of the participating municipalities;\n\n - supporting the annual audits of municipal financial statements; and\n\n - strengthened accountability of municipalities.\n\n\n**Revised Rating**\nSubstantial\n\n\nPHEFFICACYTBL\n# **Objective 2**\n\n**Objective**\n\nTo improve service delivery to selected municipalities.\n\n\n**Rationale**\n**OUTPUTS** :\nThe following outputs were substantially achieved:\n\n\n - 15 km of\n\nMention: \"Beneficiary Assessments\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"analyze\", \"summary\": \"County governments used evidence from these assessments to inform future infrastructure investment plans.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "fcv", "source_key": "fcv_pads_east_africa:010190:1:1", "occurrence_id": "38d875647f70bcf9dd8b4b36", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: has actually fallen since 2006. Overall, most of the new jobs created in Kenya\nin recent years are in the informal sector, also known as the Jua Kali, which consists of the selfemployed, unpaid family workers, and those working for wages in small household enterprises. The\nfailure of the formal sector to generate sufficient wage employment to accommodate all new\nentrants to the labor force has led to many youths starting their own businesses.\n\n5. Poor employment and weak productivity growth in services exacerbate some of the employment\nand productivity constraints that already disproportionately affect youth in Kenya. Youth tend to\nlack relevant work experience and even if they are educated, come out of the education system\nlacking the cognitive, technical, socioemotional, and business skills needed to be productive in\ntoday’s labor markets. This is important both for self-employment and for wage employment. In\naddition, the lack of market information about what skills are in demand and where jobs can be\nfound, perpetuate these mismatches. Beyond experience and skills, youth also often lack the social,\nfinancial, and physical capital necessary to get a job or to successfully start or expand a business.\nWomen or disadvantaged youth—those living in conflict-affected areas or coming from poor\nfamilies, for example—face additional constraints related to family and household responsibilities\nor violence, respectively.\n\n6. As a result of all of these forces, youth in Kenya—especially the least educated—have\npoor employment prospects. Youth unemployment rates measured by the 2009 Kenya Population\nand Housing Census were highest for younger members of the youth cohort and those in urban\nareas (table 1). The rate of unemployment in 2009 for all Kenyans between 15 and 64 years of age\nwas 8.6 percent. For those aged 15 to 19 years, it was 15.8 percent, and for those aged 20 to 24\nyears, it was 13.1 percent, whereas unemployment rates for those over 25 years of age approached\nthat of the adult population. Unemployment\n\nMention: \"2009 Kenya Population\nand Housing Census\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"analyze\", \"summary\": \"Census-derived unemployment rates by age and urban residence support the argument that least-educated youth face the worst prospects.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "fcv", "source_key": "fcv_pads_east_africa:011200:13:0", "occurrence_id": "74179955b1685d930d14f3e3", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: **The World Bank**\nKenya Inclusive Growth and Fiscal Management DPO 2 (P172321)\n\n\n**Economic Impact of COVID-19**\n\n**2.2** **The COVID-19 global pandemic will have a large negative impact on the Kenyan economy.** The\nCOVID-19 shock is estimated to further reduce growth in 2020 to 1.5 percent with a twin shock both from\nthe external and domestic sources. On the external side, the decline in demand following implementation\nof measures to delay the spread of COVID-19 will hit hard travel, tourism and agricultural exports. Access\nto international markets is virtually shut to frontier issuers such as Kenya, adding vulnerability to its\nexternal payment position. Major stock markets, globally and the Nairobi Securities Exchange, are now in\na bear market, consistent with pricing in a global recession ( **Error! Reference source not found.** ). Dollar\nfinancing costs for Kenya and other emerging markets have risen dramatically ( **Error! Reference source**\n**not found.** ). On the domestic front, the top priority is to implement effective containment and mitigation\nmeasures to contain the spread of corona virus and to save lives. Measures being taken to slow down the\nrate of infection, including home confinement, travel restrictions, closure of schools and entertainment\nspots, suspension of public gathering and conferences, and a nightly curfew, are affecting both production\nand consumption. This revised growth estimate is subject to much uncertainty and potential further\nrevision, depending on how widespread COVID-19 becomes in the country and the intensity and duration\nof social distancing measures that are contributing to a slowdown in economic activity.\n\n\n\n**Figure 1: Stocks pricing in global recession**\n_(Nairobi-20 and DWJ Global, indexed: 27 Mar_\n_2019 = 100)_\n\n\n\n**Figure 2: Higher external financing costs**\n_(EMBIG index of sovereign\n\nMention: \"Nairobi-20 and DWJ Global\""}, {"role": "assistant", "content": "{\"role\": \"supporting\", \"usage_action\": \"source\", \"summary\": \"The two equity indices plotted in the figure are credited to these market series.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "fcv", "source_key": "fcv_pads_east_africa:011366:1:1", "occurrence_id": "c54073c00e139e45c1f5eae2", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: 37.00
Date
14-Dec-2010
Comment|Value
8400.00
Date
30-Jun-2013
Comment
POI#2|\n|Indicator|Baseline|Current|End Target|\n|Indicator Name
Proportion of sexually active youth 15- 24 who report having had sex
with a non-spousal, non-regular partner in the past 12 months.
Type
Unit of Measure
Custom Indicator
Text|Value
F=30%
M=84% (DHS 2003)
Date
01-Jan-2007
Comment|Value
F=33%
M=83% (DHS 2008)
Date
14-Dec-2010
Comment|Value
F=20%
M=70%
Date
30-Jun-2013
Comment
POI#3
Targets based on about 10%
reduction every three years and
apply if a KAIS or DHS will be done
in 2012 or 2013|\n\n\nPage 2 of 8\n\nMention: \"DHS 2003\""}, {"role": "assistant", "content": "{\"role\": \"supporting\", \"usage_action\": \"source\", \"summary\": \"The sex-disaggregated baseline value for the youth risk-behaviour indicator is taken from this survey round.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "fcv", "source_key": "fcv_pads_east_africa:011756:22:1", "occurrence_id": "2165094669a95c22a688ff2c", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: levels of disease and destitution characterize the proposed project area. Studies conducted in the area\nreveal linkages between:\n\n - Poverty and land investments. Poor households invest very little in agricultural inputs;\n\n - Agriculture, ill-health and poverty;\n\n - Wetland drainage for irrigation agriculture and land degradation; and\n\n - Low soil fertility and lack of technical advice.\n\n\nPoverty in Kenya remains a challenge requiring urgent attention. It is a multi-dimensional phenomenon,\nwhich includes inadequacy of income and deprivation of basic needs and rights, and access to productive\nassets as well as to social infrastructure and markets (PRSP, 2003). The quantitative approach of measuring\npoverty defines the poor as those who cannot afford basic food and non-food items. The 1997 Welfare\nMonitoring Survey estimated the absolute poverty line at KShs.1,239 per person per month and KShs.2,648\nrespectively for rural and urban areas. This poverty line is determined and based on the expenditure\nrequired to purchase a food basket that allows minimum nutritional requirements to be met. The minimum\nnutritional requirements are set at 2,250 calories per adult equivalent per day. Based on Welfare Monitoring\nSurvey (WMS III) of 1997, the proportion of the population that cannot purchase the basic basket of goods\nwas estimated to be 53 per cent of the rural and 50 per cent of the urban population.\n\n\nUsing the qualitative approach of Participatory Poverty Assessments (PPAs), people define, view and\nexperience poverty in different ways. In the 2001 PPA reports, people mainly defined poverty as the\ninability to meet their basic needs. Poverty was associated with features such as lack of land,\nunemployment, inability to feed oneself and one’s family, lack of proper housing, poor health and inability\nto educate children and pay medical bills.\n\n\nIn Kenya the poor tend to be clustered into certain social categories such as:\n\n\n - the landless;\n\n\n - people with disabilities;\n\n\n - female headed households;\n\n\n - households headed by people without formal education;\n\nMention: \"1997 Welfare\nMonitoring Survey\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"analyze\", \"summary\": \"The survey supplies the absolute poverty line, separately for rural and urban areas, on which the passage's poverty definition rests.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "fcv", "source_key": "fcv_pads_east_africa:011756:22:1", "occurrence_id": "f7493502493f57f9d82ec12f", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: levels of disease and destitution characterize the proposed project area. Studies conducted in the area\nreveal linkages between:\n\n - Poverty and land investments. Poor households invest very little in agricultural inputs;\n\n - Agriculture, ill-health and poverty;\n\n - Wetland drainage for irrigation agriculture and land degradation; and\n\n - Low soil fertility and lack of technical advice.\n\n\nPoverty in Kenya remains a challenge requiring urgent attention. It is a multi-dimensional phenomenon,\nwhich includes inadequacy of income and deprivation of basic needs and rights, and access to productive\nassets as well as to social infrastructure and markets (PRSP, 2003). The quantitative approach of measuring\npoverty defines the poor as those who cannot afford basic food and non-food items. The 1997 Welfare\nMonitoring Survey estimated the absolute poverty line at KShs.1,239 per person per month and KShs.2,648\nrespectively for rural and urban areas. This poverty line is determined and based on the expenditure\nrequired to purchase a food basket that allows minimum nutritional requirements to be met. The minimum\nnutritional requirements are set at 2,250 calories per adult equivalent per day. Based on Welfare Monitoring\nSurvey (WMS III) of 1997, the proportion of the population that cannot purchase the basic basket of goods\nwas estimated to be 53 per cent of the rural and 50 per cent of the urban population.\n\n\nUsing the qualitative approach of Participatory Poverty Assessments (PPAs), people define, view and\nexperience poverty in different ways. In the 2001 PPA reports, people mainly defined poverty as the\ninability to meet their basic needs. Poverty was associated with features such as lack of land,\nunemployment, inability to feed oneself and one’s family, lack of proper housing, poor health and inability\nto educate children and pay medical bills.\n\n\nIn Kenya the poor tend to be clustered into certain social categories such as:\n\n\n - the landless;\n\n\n - people with disabilities;\n\n\n - female headed households;\n\n\n - households headed by people without formal education;\n\nMention: \"Welfare Monitoring\nSurvey\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"analyze\", \"summary\": \"The same round gives the rural and urban shares unable to afford the basic consumption basket.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "fcv", "source_key": "fcv_pads_east_africa:012713:35:3", "occurrence_id": "5779c153b08502f05ec0900f", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: subregions by
end of project|N/A|
500|
1,309*|\n\n\n\n15 Deduced from subproject attrition trends (source: NUMU database)\n\n\n16 This is a proportion of the estimated number of CRCM beneficiaries.\n\n\n17 Listenership Survey (2008)\n\n\n27\n\nMention: \"Listenership Survey\""}, {"role": "assistant", "content": "{\"role\": \"supporting\", \"usage_action\": \"source\", \"summary\": \"A footnote credits this survey as the basis for estimating the beneficiary population behind a target.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "fcv", "source_key": "fcv_pads_east_africa:013446:29:0", "occurrence_id": "7e7d7f56fa315444f3022a40", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: productivity and competitiveness through the matching grants scheme and by supporting\nstartups through business plan competitions. The Project interventions supported\ntechnology and skills transfer under the matching grant schemes, enhanced the available\nskill supply for the private sector through support to the business school and provided\nsupport for market development, technology transfer, amendments of competition policy\nand WTO accession.\n\n79. Table 2 below shows the linkage between the results achieved and the project\ndevelopment objective. For ease of analysis, the PDO has been split into three intended\noutcomes: (i) increasing participation of the private sector, (ii) improving productivity,\nand (iii) export competitiveness.\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n|Table 2 Intended outcome|Intervention|Result achieved|\n|---|---|---|\n|
**Intended outcome**
|**Intervention**
|**Result achieved**
|\n|
Increasing
participation of the
private sector
|
- Privatization of
SOEs
- Matching Grants
Scheme
- BIZPLAN
|
- 44 SOEs were transferred to private
ownership and 77percent of SOE total
asset value SOE identified in the PAD
have gone through divestiture by the end
of the project
- Volume of exports by beneficiary firms
has increased by 29percent, with estimated
increase in revenue of US$ 35 million31.
- 5,719 new jobs were created by MGS
beneficiary firms (of which 60.4percent
were women)
- PPESA data shows that though redundant
employees were laid off during
privatizations of SOEs, the privatized
enterprises\n\nMention: \"PPESA data\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"analyze\", \"summary\": \"Project records are used to show that privatisation shed redundant staff yet raised output and exports among surviving firms.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "fcv", "source_key": "fcv_pads_east_africa:015756:19:1", "occurrence_id": "908ce84760e220a89d54bc74", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: s) and were able to bid and win contracts for other infrastructure projects. In summary, over the fiveyear program period, a total of 657,494 jobs were created of which 45% were female, comprising 485,209\ntemporary jobs (45% female) and 172,285 permanent jobs (43% female) 10 .\n\n57. **Increased income and Food Security.** Participants in the Beneficiary Assessment indicated that as a\nresult of increased business opportunities and jobs, their households were food secure, they were able to pay\nfor their utilities, had accumulated household assets and had saved and invested in business. 75.6 percent of\nthe respondents said they had invested; 76.2 percent had acquired household assets and 71.4 percent said\nthey were better positioned to pay their children’s fees.\n\n\n58. **Capacity Building.** Youth, women and persons with disabilities that participated in the construction of\ncobblestone roads acquired lifetime skills like chiseling and paving. For some, the knowledge and skills\nobtained laid the foundation for their transition to entrepreneurs or proprietors of MSEs that would\nindependently bid for works.\n\n\n10 Borrower ICR, page 40.\n\n\n12\n\nMention: \"Beneficiary Assessment\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"analyze\", \"summary\": \"Participant testimony is used to link jobs and business opportunities to household food security, asset building and saving.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "fcv", "source_key": "fcv_pads_east_africa:017547:33:0", "occurrence_id": "a2ee177ea650c515985f3b1f", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: _Environmental & Social Impact Assessment Project Report for the Rehabilitation and Improvement of Quarry_\n\n_Roads in Mulolongo Area of the Nairobi Metropolitan Region_\n\n\n**3.6** **Community Organizations/Non-State Actors**\n\n\nMajority of the county’s population is organized into community self-help groups,\nand both producer and marketing cooperative societies. There are a number of\nother non-state actors operating in the county including local and international NonGovernmental Organizations whose objective is to improve the socio-economic\nwell-being of the local people.\n\n\n**3.7** **Gender**\n\n\nGender disparities are minimal in primary and secondary education where\nenrolments are 50 per cent for both boys and girls. Women have been\ndiscriminated against when it comes to access to ownership of property and\nfinances. 80 per cent of women constitute the agricultural workforce but only a\nsmall percentage of them hold title deeds to land. This imposes a great constraint\non their ability to make major land-related investment decisions including obtaining\ncredit using title deeds as collateral.\n\n\n**3.8** **Poverty**\n\n\nThe county has high poverty levels which according to the 2005/2006 Kenya\nIntegrated Household Budget Survey, about 42 per cent of the population live\nbelow the poverty line. The poor are not able to access the basic necessities of life\nsuch as food, shelter and education.\n\n\n**3.9** **HIV and Aids**\n\n\nHIV and AIDS pandemic poses a serious threat to the development of the area as\nthe prevalence rate stands at 3.6 per cent for Machakos County compared to 4.6%\nfor the country as whole. The scourge is on the increase virtually in all the\nconstituencies of the county. AIDS related deaths are common and those mainly\naffected are those within the productive age group of 15-49 years of age. Also, the\nnumber of HIV/AIDS orphans\n\nMention: \"Kenya\nIntegrated Household Budget Survey\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"The county poverty share of about 42 per cent below the poverty line is taken from this survey round.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "fcv", "source_key": "fcv_pads_east_africa:017825:40:1", "occurrence_id": "7c4257eea2b5e1cf62f4a879", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: In order to provide greater\ntransparency and information dissemination, CAAPU’s composition should be expanded to more\nstakeholders, particularly representatives of the construction industries and universities.\n\n**Review urban structural plans to incorporate the new land value capture instruments.**\nMunicipalities should establish a new posture on the use and occupation of land, setting maximum\nurban indexes and coefficients for specific neighborhoods or regions, considering the local\ncharacteristics and needs of the community. When registering the property before a PPU or\ndetailed plan, holders of vacant and underused land should obtain permits from the municipality.\nIn case of noncompliance, they should be required to make social use of the property, under penalty\nof losing possession and returning it to the municipality.\n\n**Establish higher minimum penalties for nonpayment of property tax** . Higher fines could help\nincrease property tax collection. But penalties should be preceded or accompanied by a wide\ncampaign to encourage payment of the overdue property taxes. The current dual-payment system\n(bank and Finance Department) is archaic, prone to errors and fraud. IPRA invoices are issued and\ndelivered, and payment can be made at bank branches or directly to the Department of Finance of\nMaputo or Matola. Although payment at the Department of Finance is directly registered in the\nIPRA cadaster, those at banks are considered paid only when the actual payment slips are\nphysically presented to the Department of Finance (and subsequently recorded in the IPRA\ncadaster). Most taxpayers seem therefore prefer paying the IPRA directly at the Department of\nFinance.\n\n**Set a limited period (1 year) for individuals and firms to pay overdue IPRA before increasing**\n**penalties** . Preceding the amendments, fines and collection procedures, a campaign must be\nimplemented for the settlement of debts in arrears, to encourage payment, before the\nimplementation of new procedures.\n\n\n32\n\nMention: \"IPRA cadaster\""}, {"role": "assistant", "content": "{\"role\": \"supporting\", \"usage_action\": \"curate\", \"summary\": \"Property tax payments are recorded in the cadaster, but only once payment slips are physically presented, creating a lag.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:000027:18:0", "occurrence_id": "d09dc4aaec2deb3fa5bd0193", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: spending on subsequent operation quality. In Table 9 we find that prior analytical work is indeed linked to\nimproved project outcomes, especially in lower-income IDA settings and possibly even fragile and conflictaffected settings (FCVs). Analytical work completed up to three years before project approval is associated\nwith an increase of 0.12 in IEG outcome ratings (0.15 points for IDA countries); half the impact associated\nwith a one-point improvement in the CPIA. This suggests an important role for World Bank initiated\nanalytic work in country environments that may be relatively “knowledge scarce”, where the information\ngenerated by these analytic efforts informs subsequent project design.\n\n\n**5.** **Summary and discussion of unsettled questions**\n\nThis paper reviews the literature on the correlates of World Bank project outcome ratings and then extends\nprevious analytic work by identifying further staffing inputs into the production process, linking previous\nsector analytic work to individual projects, and extracting a richer set of design quality explanators from a\nsubset of projects. Results from these analytic extensions all point towards the importance of project design\nin ultimate project success, especially in the more sectoral complex settings of middle- and upper-middleincome countries (IBRD). Previous quantitative work has found fairly weak evidence for the importance of\nproject design; however, it appears that this is in part due to the paucity of relevant indicators captured in\nroutine World Bank administrative data. It would be an error to conclude from these earlier studies that\nproject design is not an especially influential determinant of project success.\n\n\nLike much of the project effectiveness literature, the analysis discussed here is descriptive in nature.\nHence, any observed association between project inputs and outcomes may either represent an underlying\ncausal relationship or may be confounded by further unobserved factors. While our understanding of the\nproject cycle leads us to consider these correlations as plausibly capturing the role certain inputs play in\nproject success, there are alternative explanations that render the correlations spurious. For example,\n\nMention: \"routine World Bank administrative data\""}, {"role": "assistant", "content": "{\"role\": \"supporting\", \"usage_action\": \"validate\", \"summary\": \"Earlier findings on project design are discounted because routine administrative records capture too few relevant indicators.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:000070:28:0", "occurrence_id": "df0f3d178558eaa55ca6611a", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: **Appendix Table A1. Results from Logit Regressions of**\n\n**Response Among IHPS Individuals Aged 18-64**\nVariable Marginal Effect\nAge 0.0002\n\n[0.53]\nFemale 0.088***\n\n[9.94]\nEducation:\n\nNone 0.193***\n\n[9.98]\nDid not complete primary 0.174***\n\n[7.75]\nCompleted primary 0.202***\n\n[9.22]\nCompleted secondary 0.173***\n\n[7.67]\n\n\n\n-0.064***\nCurrently married\n\n[-4.65]\n\n0.292***\nIndividual is head or spouse\n\n[11.65]\n\n-0.012***\nMonths member is away\n\n[-6.36]\n\nLog household size -0.046***\n\n\n\n\n[-4.65]\n\n\n\n\n[-6.36]\n\n\n\n\n[-4.19]\nHousehold: dependency ratio of children, and 0.027***\nelderly/adults 15-64 [3.47]\n\n\n\nHousehold: dependency ratio of children, and 0.027***\nelderly/adults 15-64 [3.47]\n\n\nDistrict FE Y\nInterview month FE Y\nEnumerator FE Y\n\nObservations 5,762\nPseudo R2 0.25\n**Notes:**\nAverage marginal effects are derived from logit models. Z-statistics in\nbrackets. * (p < 0.1), ** (p < 0.05) and *** (p < 0.01). The logit regression\ndropped 14 observations because one enumerator fixed effect predicted the\noutcome perfectly.\n\n\n\n27\n\nMention: \"IHPS\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"analyze\", \"summary\": \"Logit marginal effects on response behaviour are estimated for working-age individuals in this panel.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:000075:5:0", "occurrence_id": "6ce7be3de1a68ec511d4c5f6", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: 4\n\n\nindividual, however, is impractical, time consuming, and cumbersome, which may help explain\n\n\nwhy households share meals in practice. When sharing, diets would need to be sufficiently\n\n\nnutrient-dense to meet all nutrient needs of all individuals; they would need to be equally or\n\n\nmore nutrient-dense than individualized diets and have lower upper limits on certain nutrients\n\n\n(e.g., copper, zinc) to ensure that the most sensitive member would not exceed their limit\n\n\n(Schneider et al. 2021).\n\n\nAt the extreme, perfect sharing requires a food basket dense enough in each nutrient to\n\n\nprovide a sufficient amount such that every member will have their nutrient requirements\n\n\nsatisfied from the total quantity of the family meal meeting their energy need (Schneider et al.\n\n\n2021). Costing this shared diet provides an upper bound on the cost of adequate diets for the\n\n\nfamily. It must include more nutrient dense foods (i.e., have higher total nutrient density) to meet\n\n\nthat shared set of needs than the summation of individuals procuring a diet meeting only their\n\n\nindividual requirements, hence being higher in cost. But it also must optimize the combination of\n\n\nfoods to meet nutrient density constraints with smaller ranges between the minimum requirement\n\n\nand upper limit, hence potentially becoming less feasible.\n\n\nThe central contributions of this paper are twofold. The first is methodological. It extends the\n\n\nleast-cost diets framework from individuals to households and demonstrates that widely\n\n\navailable nationally representative household survey data on household composition and food\n\n\nconsumption can be linked with frequently collected sub-national monthly food prices and local\n\n\nfood composition data to estimate a bounded range of the cost of nutrient adequate diets that\n\n\nmeet the needs of all household members. This enables policy makers to assess the extent to\n\n\nwhich markets can supply their population with an adequate diet at an affordable cost. The range\n\n\nbetween the bounds offers a more useful policy indicator than either bound on its own, as both\n\nMention: \"local\n\n\nfood composition data\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"analyze\", \"summary\": \"Composition data are linked with household consumption and local prices to bound the cost of a nutrient-adequate diet.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:000082:71:1", "occurrence_id": "4099e4de76b6315102c17a18", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: _старт_ _работе_ _новых_ _железных_ _дорог_ _Жезказган_ - _Бейнеу_ _и_ _Аркалык_ - _Шубарколь_ . August 22, 2014.\n\n\nTemirZholy.kz/press-tsentr. \"President commences work on new Jezkazgan-Beyneu and Arkalyk-Shubarkol railways.\" In Russian..\n\n19. _Протяженность_ _железнодорожных_ _путей_ _Казахстана_ _на_ _начало_ _года_ _составила_ 15,3 _тыс_ . _км_ . _Ж_ / _д_ - _линии_, _проходящие_ _по_ _территории_ _страны_,\n\n_занимают_ 14,5 _тыс_ . _км_, _еще_ 275 _км_ _проходят_ _по_ _территориям_ _других_ _государств_ . s.l. : EnergyProm, July 12, 2016. EnergyProm.kz. \"Total length of\n\n\nrailways in Kazakhstan at the beginning of the year was 15.3 thousand kilometers. Railways that traverse the country's territory cover 14.5 thousand kilometers, while 257\n\nkm pass through other countries.\" In Russian. Cites Kazakhstan Ministry of Transport web portal as data source..\n\n20. Chu, Daye. Moscow-Kazan high-speed railway ‘may be built in stages’ for financial reasons . s.l. : Global Times, October 22, 2017. GlobalTimes.cn. Quotes Russian\n\nRailways (RZD).\n\nMention: \"Kazakhstan Ministry of Transport web portal\""}, {"role": "assistant", "content": "{\"role\": \"supporting\", \"usage_action\": \"source\", \"summary\": \"A footnote records this portal as the source for the reported railway length.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:000100:38:0", "occurrence_id": "ae8fee9043f6ac5e7f146eb3", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: **Figure 6. Distribution of Nonfarm Enterprises, by Formality Status and Region**\n\n\na. Enterprises (number, in thousands)\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\nb. Enterprises (in percent)\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n_Source_ : Authors’ estimates based on data from Phase I of the IBES.\n_Note_ : The 10 regions of Ghana are as defined prior to the 2019 expansion to the 16 regions that are in effect today.\nRegions are arranged according to regional average household consumption per adult equivalent in 2005/06 (based\non 2005/06 GLSS data), from the lowest to the highest (left to right). The sample is restricted to nonfarm enterprises.\nInformal enterprise = an enterprise that is not registered with the Registrar General’s Department (RGD) and does\nnot professionally maintain financial accounting records. In panel b, the distribution of enterprises across\ninformal/formal statuses and regions sum to 100 percent (rounding error notwithstanding).\n\n\n37\n\nMention: \"data from Phase I of the IBES\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"analyze\", \"summary\": \"Enterprise counts by formality and region are estimated from this business survey round.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:000100:38:0", "occurrence_id": "40e52beb7dd47858408a200a", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: **Figure 6. Distribution of Nonfarm Enterprises, by Formality Status and Region**\n\n\na. Enterprises (number, in thousands)\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\nb. Enterprises (in percent)\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n_Source_ : Authors’ estimates based on data from Phase I of the IBES.\n_Note_ : The 10 regions of Ghana are as defined prior to the 2019 expansion to the 16 regions that are in effect today.\nRegions are arranged according to regional average household consumption per adult equivalent in 2005/06 (based\non 2005/06 GLSS data), from the lowest to the highest (left to right). The sample is restricted to nonfarm enterprises.\nInformal enterprise = an enterprise that is not registered with the Registrar General’s Department (RGD) and does\nnot professionally maintain financial accounting records. In panel b, the distribution of enterprises across\ninformal/formal statuses and regions sum to 100 percent (rounding error notwithstanding).\n\n\n37\n\nMention: \"GLSS data\""}, {"role": "assistant", "content": "{\"role\": \"supporting\", \"usage_action\": \"source\", \"summary\": \"Regional consumption per adult is used only to order the regions in the figure.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:000112:8:0", "occurrence_id": "37d72acc182d11df43609cf5", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: ### **III. Implementation**\n\nThe primary sampling strategy was very standard. A nominal sample of 2,800 households was to be selected\nin two stages, with 200 Census sectors -hereafter referred to primary sampling units, or PSUs- in the first\nstage and 14 households per PSU in the second stage. However, the design departed from the standard in\nthe way it addressed stratification in both phases.\n###### III.1 First sampling stage\n\nThe 200 primary sampling units (PSUs) were stratified into three categories depending on the Venezuelan\nmigrant density, defined as the ratio between the number of Venezuelan cellphones in the PSU (as per\nTelefonica's prediction) and the total population of the PSU (as per INEC's population census), and allocated\ninto these strata as follows:\n\n`o` _100 High-density PSUs_ : where the density was more than 0.15.;\n\n`o` _80 Medium-density PSUs_ : where the density was between 0.05 and 0.15.; and\n\n`o` _20 Low-density PSUs_ : where the density was less than 0.05.\n\nWithin each stratum, the sample was selected with probability proportional to the number of households\nreported by the 2010 Census.\n###### III.2 Second sampling stage\n\nAll households in each of the selected sectors were listed and stratified into three categories considering\nnationality and demographic composition. In each stratum, households were selected as follow:\n\n`o` _Seven_ non-Venezuelan households (i.e. Ecuadoran, Peruvian, Colombian or any other nationality except\n\nVenezuelan).\n\n`o` Seven Venezuelan households without children aged less than 5 years. 13\n\n`o` All Venezuelan households with children aged less than 5 years.\n\n\nWithin each stratum, the sample was selected by systematic equal-probability sampling.\n\n\nThe second stage\n\nMention: \"INEC's population census\""}, {"role": "assistant", "content": "{\"role\": \"supporting\", \"usage_action\": \"analyze\", \"summary\": \"Census population is the denominator for migrant density used to stratify primary sampling units.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:000112:8:0", "occurrence_id": "39c1d01265a569798384a41a", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: ### **III. Implementation**\n\nThe primary sampling strategy was very standard. A nominal sample of 2,800 households was to be selected\nin two stages, with 200 Census sectors -hereafter referred to primary sampling units, or PSUs- in the first\nstage and 14 households per PSU in the second stage. However, the design departed from the standard in\nthe way it addressed stratification in both phases.\n###### III.1 First sampling stage\n\nThe 200 primary sampling units (PSUs) were stratified into three categories depending on the Venezuelan\nmigrant density, defined as the ratio between the number of Venezuelan cellphones in the PSU (as per\nTelefonica's prediction) and the total population of the PSU (as per INEC's population census), and allocated\ninto these strata as follows:\n\n`o` _100 High-density PSUs_ : where the density was more than 0.15.;\n\n`o` _80 Medium-density PSUs_ : where the density was between 0.05 and 0.15.; and\n\n`o` _20 Low-density PSUs_ : where the density was less than 0.05.\n\nWithin each stratum, the sample was selected with probability proportional to the number of households\nreported by the 2010 Census.\n###### III.2 Second sampling stage\n\nAll households in each of the selected sectors were listed and stratified into three categories considering\nnationality and demographic composition. In each stratum, households were selected as follow:\n\n`o` _Seven_ non-Venezuelan households (i.e. Ecuadoran, Peruvian, Colombian or any other nationality except\n\nVenezuelan).\n\n`o` Seven Venezuelan households without children aged less than 5 years. 13\n\n`o` All Venezuelan households with children aged less than 5 years.\n\n\nWithin each stratum, the sample was selected by systematic equal-probability sampling.\n\n\nThe second stage\n\nMention: \"2010 Census\""}, {"role": "assistant", "content": "{\"role\": \"supporting\", \"usage_action\": \"source\", \"summary\": \"Household counts determine the probability-proportional-to-size selection within strata.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:000131:7:1", "occurrence_id": "0710d1977d7b572a76636877", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: ij_ _∗_ _AFj_ (2)\n\n\n\nwhere _Shareij_ is the fraction of individual _i_ ’s time spent on activity _j_ . _AFj_\nis an activity factor for activity _j_ that measures the intensity of activity _j_\nrelative to rest (equal to one). Individual _AL_ are thus weighted averages\nof activity factors where the weights vary across individuals based on their\ntime-use.\n\nThe most detailed activity data for India comes from the Time-Use Survey\n(TUS) conducted in 1998-1999 by the National Sample Survey Organization\nfor six states (Gujarat, Haryana, Madhya Pradesh, Meghalaya, Orissa, and\n\n\n4Validation studies by (Shetty et al. 1986) and (Ferro-Luzzi et al. 1997) find that\nthese types of prediction equations, which are typically estimated on European descended\npopulations, have a reasonably good fit for subjects in India.\n\n\n6\n\nMention: \"Time-Use Survey\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"Activity weights come from this detailed survey of time use across six Indian states.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:000151:8:1", "occurrence_id": "1f655cc30e46dc2443b8368c", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: _ per child conditional on\nthe child’s school attendance and health checks. Families with income per capita above\nthe extreme poverty threshold but below a higher poverty threshold are only eligible for\nthe conditional variable benefits. Benefits are paid to families on a monthly basis from the\nfederal budget, typically into a bank account at _Caixa_, the main state bank in Brazil.\n\nThe relevant income per capita definition is the one recorded in _Cadastro Único_, which\nis a federal registry that is continuously updated. _Cadastro Único_ was created at the same\ntime as PBF and was the result of a similar consolidation effort. Yet, its purpose is to serve\nas basis for other social programs as well. For this reason, it aims to include families with\nincome per capita below one-half of the minimum wage (R$255 in 2010), which is much\nhigher than the two poverty thresholds for PBF eligibility (R$70 and R$140 in 2010). 16\n\nThe information in _Cadastro_ _Único_ is based on a standardized survey that asks families\nabout income, housing, and assets, among other characteristics. Families can apply to\ntheir municipality to take the survey and be registered in _Cadastro_ _Único_ . Municipalities\ncan also actively identify poor families and survey them, which was the main channel\n\n\n16For reference, the exchange rate in 2010 was about R$2=US$1.\n\n\n7\n\nMention: \"_Cadastro Único_\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"The income per capita used for eligibility is the continuously updated value recorded in this federal registry.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:000156:10:1", "occurrence_id": "f6e6ab0a0aff2cdbd5df0f70", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: \ncurrency, and banking sector risk scores of a given country. 12 [^12: See https://www.eiu.com/n/solutions/country-risk-model/.\n13. Anasashvili et al. (2020); see\n[https://openknowledge.worldbank.org/bitstream/handle/10986/33657/K880541.pdf?sequence=1&isAllowed=y.](https://openknowledge.worldbank.org/bitstream/handle/10986/33657/K880541.pdf?sequence=1&isAllowed=y)] W e included this variable in the\nanalysis to assess the macroenvironment in which central banks operate. Alternatively, we use\nthe number of currency crises and the current account balance as a percentage of GDP as another\nmeans of describing the macroenvironment in which the central bank operates.\n\n**_Reserve Adequacy Variables._** Finally, a central bank's risk tolerance and investment policy\n(number of eligible assets and currencies, portfolio duration, allocation to nontraditional asset\nclasses) are linked to reserve adequacy. All else being equal, a central bank with higher reserve\nadequacy typically has a higher risk tolerance and can deploy a broader range of asset classes,\ncurrencies, and longer duration. Therefore, we use reserve adequacy measures to control for\ndifferences in reserve adequacy across central banks. We include two reserve adequacy metrics\nas control variables: reserves to GDP and to M2. Separately, we also control for GDP per capita\nand other macroeconomic variables, such as short-term external debt stocks as a percentage of\ntotal reserves.\n\n**4.2** **RAMP Survey Variables**\n\nRAMP's global surveys on reserve management practices are the source for information on\ncentral banks' governance arrangements, investment policies, and measures of risk taking. RAMP\nconducted two surveys in 2017 and 2019 with responses from\n\nMention: \"RAMP Survey\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"Central bank governance, investment policy and risk-taking measures come from these global surveys.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:000163:1:0", "occurrence_id": "d36db438c79e7b707dc0a092", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: Policy Research Working Paper 9396\n\n##### **Abstract**\n\nThis paper uses Multiple Indicator Cluster Surveys data\n\nfrom the Republic of Congo and São Tomé and Príncipe\nto study the relationships between child stature, mother’s years of education, and indicators of early childhood\ndevelopment. The relationships are contrasted between two\nempirical approaches: the conventional approach whereby\ncontrol variables are selected in an ad-hoc manner and\nthe double machine-learning approach that employs datadriven methods to select controls from a much wider set\nof variables. Overall, the findings based on the preferable\ndouble machine-learning approach differ across the two\ncountries depending on the measures of early childhood\n\n\n\ndevelopment and child stature (height-for-age Z-score and\nstunting) used in the analysis. Double machine-learning\nestimates for the Republic of Congo suggest that heightfor-age Z-score and stunting have a direct causal effect on\nearly childhood development. In contrast, for São Tomé\nand Príncipe, no relationship is found. Thus, country-specific policy advice based on the relationships observed from\ndata in other countries may be quite risky, if not misleading. Double machine-learning provides a practical and\nfeasible approach to reducing threats to internal validity\nto derive robust inferences based on observational data for\nevidence-based policy advice.\n\n\n\nThis paper is a product of the Poverty and Equity Global Practice. It is part of a larger effort by the World Bank to\n\nprovide open access to its research and make a contribution to development policy discussions around the world. Policy\nResearch Working Papers are also posted on the Web at http://www.worldbank.org/prwp. The authors may be contacted\nat eskoufias@worldbank.org.\n\n\n_The Policy Research Working Paper Series disseminates the findings of work in progress to encourage the exchange of ideas about development_\n_issues. An objective of the series is to get the findings out quickly, even if\n\nMention: \"Multiple Indicator Cluster Surveys data\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"analyze\", \"summary\": \"Child stature, maternal education and early childhood development indicators are analysed on these surveys.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:000187:15:1", "occurrence_id": "79bb3b238bf76cb85269d317", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: .8 24.8 42.1 60.4 68.8\nRelative incidence 0.28 0.09 0.22 0.25 0.25 0.28 0.20 0.25 0.36 0.41 0.25\n_Source:_ Elaboration based on data derived from the WELCOM Stata Tool and the 2015/16 HCES; see CSA 2018.\n_Note:_ Consumption values are in birr of 2015.\n\nDespite the positive but unequalizing welfare effects of greater competition on new users, an\naccounting of only the welfare effects on new users shows that the relative welfare gain among\nhouseholds in the bottom decile of the consumption distribution is 6.9 percent, compared with an\naverage of 4.9 percent among households in the richest decile (figure 3).\n\n**Figure 3. Relative Welfare Gains of Greater Competition in Telecommunication, New Users**\n\n\n\n8.0%\n7.0%\n6.0%\n5.0%\n4.0%\n3\n\nMention: \"2015/16 HCES\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"Welfare incidences are derived from this household expenditure and consumption survey.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:000204:6:0", "occurrence_id": "a5b74f6adc65b0f051bda61a", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: (2006) find that larger countries may find it tougher to control corruption. In contrast, using\n\n\nTransparency International’s Corruption Perceptions Index for 1998, Root (1999) finds that in a\n\n\ncross-section of 60 countries, higher population is significantly associated with less corruption.\n\n\nRoot attributes the findings to economies of scale in governance. Similarly, Anoruo and Braha\n\n\n(2005) find that in Africa, population growth and corruption are negatively correlated. Knack and\n\n\nAzfar (2003) demonstrate that the corruption measures typically used in the literature suffer from\n\n\nsample selection bias and correcting for this bias causes the relationship between country size and\n\n\ncorruption to become much weaker or disappear. Similarly, when using total land area as a measure\n\n\nof country size, Goel and Nelson (2010) also find that country size has no significant impact on\n\n\ncorruption.\n\n\nThe broader literature on the determinants of corruption highlights several factors\n\n\n(discussed in detail in section 2). Treisman (2000) finds that states of government, colonial history,\n\n\ntrade openness, religious affiliation, and exposure to democracy have a significant impact on\n\n\ncorruption. At the same time, greater ethnic fractionalization or diversity in the country has also\n\n\nbeen found to contribute positively to corruption (Dincer 2008, Glaeser and Saks 2004, La Porta\n\n\net al. 1999). If members of one ethnicity are elected to a public position, they are more likely to\n\n\nmaintain the position even if they display corrupt behavior. Goel and Nelson (1998) and\n\n\nsubsequently, Kotera et al. (2012) report that larger government is associated with higher\n\n\ncorruption. They find that in larger government, there appears to be lesser individual accountability\n\n\nand greater layers of bureaucracy which eventually leads to more corruption. Fisman and Gatti\n\n\n(2002) also find that fiscal decentralization in government expenditure is strongly and significantly\n\n\nassociated with lower corruption. This was supported by a later study that found a negative\n\n\n5\n\nMention: \"Corruption Perceptions Index\""}, {"role": "assistant", "content": "{\"role\": \"supporting\", \"usage_action\": \"source\", \"summary\": \"A prior study's cross-country result on population size and corruption is based on this index.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:000217:11:0", "occurrence_id": "d9f30203519e9787d6f79f72", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: supply of other food products such as meat, cheese, milk, and fish. Other affected countries such as Brazil,\nEcuador, Malaysia and Indonesia also represent a significant share of world supply of respectively citrus\nfruit (48.7), bananas (30.4), palm oil (31.8), and coconut oil (46.6) (Appendix Table 1).\n\n\n**Figure 4. World imports from top-50 most affected by Covid-19**\n\n\n\nMeat\n\nFresh Fruits - Vegetables\n\nVegetable and animal oils\n\nSugar\n\nCereals\n\nFish\n\nLegumes and pulses\n\nDairy and eggs\n\nNuts and derived products\n\nOil-bearing\n\nStimulant crops\n\n\n\n\n\n\n\nWorld imports from 50 worst affected COVID Rest of the world\n\n\n_Source_ **_:_** [Espitia, Rocha, Ruta (2020). “Database on COVID-19 trade flows and policies”.](https://www.worldbank.org/en/data/interactive/2020/04/02/database-on-coronavirus-covid-19-trade-flows-and-policies)\n\nThe negative impact of disruptions in food supply as a result of Covid-19 will be potentially higher for\nimport food dependent countries, 11 with high levels of concentration of imports coming from the top-50\nmost affected countries. Import food dependent developing countries would be particularly vulnerable to\nsupply shocks in key staples such as cereals, meat and fresh fruits, where more than 74 percent of imports\non average come from the top-3 exporters that are most affected by Covid-19 (Table 2). 12 [^12: See Appendix Table 2 for results at the product level.] Import food\ndependent developing countries such as Botswana, Mexico and Jamaica import more than 95 percent of\nrice, wheat and corn from the top-3 exporters most affected by Covid-19. Least developed countries such\n\nMention: \"Database on COVID-19 trade flows and policies\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"World imports by agri-food product group are taken from this pandemic trade and policy database.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:000238:5:1", "occurrence_id": "3960940afb3228e3fb9eb70c", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: in order to assess which\nsource is responsible for the larger welfare loss. Next, when we seek to summarize the inter-country\ndistribution of welfare losses, we suggest a plausible range for α: between five and twenty years.\n\nThe rest of this short paper is organized as follows. The next section describes how we compute the\nnumbers of years of life lost (LY) and additional poverty years (PY) for each country, given the available\ndata, and presents the estimates for 145 countries. Building on those ingredients, Section 3 summarizes\nthe evidence on the relative importance of poverty and mortality in lowering welfare around the world.\nIt also investigates the global distribution of those losses under plausible values for the key normative\nparameter, both for a constant absolute poverty line and under a more relativist approach to poverty\nidentification. Section 4 concludes.\n\n\n**2.** **Estimating additional mortality and poverty with imperfect data**\n\nThe two key data sources for our mortality estimates are the UN Population Division database and the\nGlobal Burden of Disease Database (Dicker et al., 2018). Combining data from these two sources and using\nsmoothing procedures described in the Appendix to DFMS, we obtain estimates for the number of people\nof age _a_ living in country _j_, _Naj_, for 0 ≤𝑎𝑎≤99. 8 [^8: Those aged 100 or more are counted as being 99.] Using these country-specific population pyramids, we can\n19-induced mortality rates _maj_, for all countries in our sample, then our estimate of years of life lost due\nalso construct estimates for age-specific residual life expectancies, 𝜆𝜆𝑎 **𝑎** . If we observed age-specific COVIDto the pandemic in each country would be given by the sum across all ages of the number of deaths from\nthat age group ( 𝑁𝑁𝑎 **𝑎** 𝑚𝑚𝑎 **𝑎** ), times the average residual life-expectancy\n\nMention: \"UN Population Division database\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"Age-specific population counts by country are taken from this database to build mortality estimates.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:000238:5:1", "occurrence_id": "64f0961ec136560d9cd70c9b", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: in order to assess which\nsource is responsible for the larger welfare loss. Next, when we seek to summarize the inter-country\ndistribution of welfare losses, we suggest a plausible range for α: between five and twenty years.\n\nThe rest of this short paper is organized as follows. The next section describes how we compute the\nnumbers of years of life lost (LY) and additional poverty years (PY) for each country, given the available\ndata, and presents the estimates for 145 countries. Building on those ingredients, Section 3 summarizes\nthe evidence on the relative importance of poverty and mortality in lowering welfare around the world.\nIt also investigates the global distribution of those losses under plausible values for the key normative\nparameter, both for a constant absolute poverty line and under a more relativist approach to poverty\nidentification. Section 4 concludes.\n\n\n**2.** **Estimating additional mortality and poverty with imperfect data**\n\nThe two key data sources for our mortality estimates are the UN Population Division database and the\nGlobal Burden of Disease Database (Dicker et al., 2018). Combining data from these two sources and using\nsmoothing procedures described in the Appendix to DFMS, we obtain estimates for the number of people\nof age _a_ living in country _j_, _Naj_, for 0 ≤𝑎𝑎≤99. 8 [^8: Those aged 100 or more are counted as being 99.] Using these country-specific population pyramids, we can\n19-induced mortality rates _maj_, for all countries in our sample, then our estimate of years of life lost due\nalso construct estimates for age-specific residual life expectancies, 𝜆𝜆𝑎 **𝑎** . If we observed age-specific COVIDto the pandemic in each country would be given by the sum across all ages of the number of deaths from\nthat age group ( 𝑁𝑁𝑎 **𝑎** 𝑚𝑚𝑎 **𝑎** ), times the average residual life-expectancy\n\nMention: \"Global Burden of Disease Database\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"Cause-of-death information is combined with population data to estimate excess mortality.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:000258:41:1", "occurrence_id": "3ed9ad3ba8bad539b8b1f026", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: (i.e. outflows)**\n1. Withdrawals from the Fund occur automatically when actual oil revenues fall short from\nbudgeted oil revenues by 10 percent or more.\n2. Oil revenue shortfalls up to 10 percent of budgeted oil revenues will be accommodated\nthrough expenditure adjustment.\n3. Any shortfall beyond 10 percent of budgeted oil revenues will be compensated subject to\navailability of resources in the Fund.\n4. The Stabilization Fund may only be used to finance expenditure budgeted in a given fiscal\nyear. The Fund may not be utilized for the satisfaction of any sovereign or commercial debt\nof the government, and no legal or beneficial interest in the Fund may be created.\n**iii.** **Formula to budget oil revenues**\n\nBudgeted oil revenues are estimated using conservative assumptions: Future oil prices are\nestimated with a US$3/barrel discount on the forecast published in the World Economic Outlook\nby the IMF. The forecasted volume of production is set 10 % below the projected production\nvolumes estimated by petroleum companies operating in Chad.\n\n**Illustrated behavior of the mechanism**\n\nThe baseline scenario assumes a constant oil price of oil of US$60. Figures B1 and B2 below illustrate how\nthe oil revenue management mechanism for stabilization works under three alternative scenarios:\n\n - Scenario 1 corresponds to a fall in the price of oil of US$10 for one year.\n\n - Scenario 2 corresponds to a US$20 fall for one year.\n\n - Scenario 3 entails a US$10 increase in the price of oil.\n\n\n40\n\nMention: \"World Economic Outlook\""}, {"role": "assistant", "content": "{\"role\": \"supporting\", \"usage_action\": \"source\", \"summary\": \"Its price forecast, discounted by three dollars a barrel, sets budgeted oil revenues.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:000281:13:0", "occurrence_id": "6fb3633c7c3d1f9d90037e9d", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: extend the initial stocks forward and backward over time. 12 The required information is drawn\n\nfrom a number of standard sources: initial stocks of domestic capital are taken from the Penn\n\n\n\nWorld Tables, and combined with _flow_ data on gross domestic investment to build up capital\n\n\n\nstock series. For foreign holdings of domestic equity and domestic holdings of foreign equity, we\n\n\n\nrely primarily on data on stocks and flows of direct and portfolio equity investment reported in\n\n\n\nthe IMF's Balance of Payments Statistics Yearbook. Finally, stocks of borrowing and lending\n\n\n\nare obtained **by** combining stock data on the debt of developing countries reported in the World\n\n\n\nBank's Global Development Finance with data on debt stocksKose et al. (2017)|\n|
Debt/Reserves (short term)
|
Short term external debt stocks, % of reserves (External and private sector debt)
|
Short term external debt stocks, % of reserves (External and private sector debt)
|\n|
Government size
|
General government final consumption expenditure, % of GDP.
|World Development
Indicators (WDI)|\n|
External debt
|
Total external debt stocks to gross national income (GNI). Sum of public, publicly guaranteed, and private nonguaranteed long-
term debt, use of IMF credit, and short-term debt.
|
Total external debt stocks to gross national income (GNI). Sum of public, publicly guaranteed, and private nonguaranteed long-
term debt, use of IMF credit, and short-term debt.
|\n|Education
|
Education refers to the number of grades (years) in secondary school.
|
Education refers to the number of grades (years) in secondary school.
|\n|
Mineral rents
|
The difference between the value of production for a stock of minerals at world prices and their total costs of production.
Minerals included in the calculation are tin, gold, lead, zinc, iron, copper, nickel, silver, bauxite, and phosphate.
|
The difference between the value of production for a stock of minerals at world prices and their total costs of production.
Minerals included in the calculation are tin, gold, lead, zinc\n\nMention: \"Indicators (WDI)\""}, {"role": "assistant", "content": "{\"role\": \"supporting\", \"usage_action\": \"source\", \"summary\": \"Government size and external debt variables in the variable table are sourced from this indicator series.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:000317:11:0", "occurrence_id": "bf38c8d1aeb34a4f9ebfd60c", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: that limited use of instructional time is a contributor to poor student learning and high levels of student\ndisruption can lead to teacher burnout and decreased effectiveness (Bruns and others 2015; Ptero-Lopez\n2009). The majority of classroom observations have been conducted in regions outside MENA;\nhowever, a recent example from the West Bank and Gaza may illustrate the importance of teachers\nstaying on task (box 1).\n\n\nBox 1: Classroom Observations in the West Bank and Gaza\n\n\nThe Stallings’ classroom observation tool established a good practice benchmark of 85 percent of\ntotal class time to be used for instruction. In schools across the West Bank and Gaza, territories\nwhere students undoubtedly are faced with personal, economic and political stresses, student\nperformance is on average high compared to other MENA countries. The Stallings observations in\nclassrooms find that teachers are spending 90 percent of their time on instruction, 9 percent on\nclassroom-management and only 1 percent time-off-task (Yarrow and others 2014). While this is\nnot indicative of what could be occurring in classrooms with high levels of disciplinary issues, it is\nsuggestive that even in contexts of conflict and fragility, effective teaching practices can ensure\nhigh quality of learning. It is also indicative, that students with a higher ability for self-regulation\nare better able to learn.\n\n\n**Table 4. Marginal Impact of School Safety on Mathematics Performance, TIMSS data 2015**\n\n\nMENA countries Other countries\n\nEstimated sd error Estimated sd error\nSocioeconomic background (individual) 13.1 0.3 21.8 0.4\nSocioeconomic background (school) 56.0 2.7 55.7 2.1\nSchool safety 6.5 0.8 8.1 1.0\nN. obs. 80,218 150,382\nR\n\nMention: \"TIMSS data 2015\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"analyze\", \"summary\": \"Estimated effects of school safety on mathematics scores are computed separately for MENA and other countries.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:000338:8:0", "occurrence_id": "4a4bae81ca99ec359c0d20e8", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: 7\n\n\n\n7\n\n~~characteristics of households from the same caste but not having agriculture as their main activity,~~\n_UnonAGRc_ . Given the social structure of India, assuming that unobserved characteristics are correlated\nwithin castes across occupations seems reasonable. This assumption is discussed in more detail in section\n5. 5 [^5: It is also worth noting that _δ_ ˆ _o_ and _δ_ ˆ _nonAGRc_ provide insights into the bias in the estimates of the other parameters of the]\n\n\n\n**3.** **Data and Descriptive Statistics**\n\n\n\nData and Variables Definition\nThe data used to conduct this study are the ARIS-REDS data from the National Council of Applied Economic\nResearch (NCAER). Since 1971, the NCAER has been conducting surveys on a _sample_ of households in 232\nvillages in the 17 major states of India. Most of the results come from the round of 2006, which has the\nadvantage of providing a _listing_ of every household in the surveyed villages with basic information on\nhouseholds and heads of household such as their demographic characteristics (gender, age, education\nlevel, size of the household) and their main occupation. The average level of education of members from\nthe same caste can therefore be computed using all the heads of the households from the same caste in the\nvillage and not only the heads of the households that have been sampled, which makes the measure very\nprecise. The information on education from the listing is also useful to deal with measurement error in\neducation of the head of household, as is shown in section 4. The round of 1982 is used for robustness\nchecks.\n\nIn the round of 2006, detailed information about agricultural inputs, such as cultivated area or labor\nuse, is not provided in the listing, so the analysis is restricted to households that cultivate land in the\n\n\n\neducation of the head of household, as is shown in section 4. The round\n\nMention: \"ARIS-REDS data\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"Village-level household surveys across major states since 1971 provide the study's data, mostly the 2006 round.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:000367:18:0", "occurrence_id": "6dc7afd67c9980e0caca002f", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: **_Capital-output ratio_**\n\nThe consequence of these very different sectoral trends has been that the overall capital-output stock\nof government assets (schools, hospitals and offices _etc_ .) has only grown slightly faster than GDP, with\nthe ratio of the capital stock to overall GDP remaining low at between 0.2 and 0.3 (Figure 8, Panel A).\nThe increase in the overall capital-output ratio has been driven by the significant rise in the capitaloutput ratio in the infrastructure sector, predominately related to assets for transport and urban\ndevelopment.\n\nThe housing sector has been the other source of the rise in the overall capital-output ratio. Prior to\nthe reform of the housing sector at the turn of the century, investment in housing had been neglected.\nHousing investment picked up markedly a decade ago. Given the rapid increase in GDP after the\ncountry’s entry into the WTO, the pickup in growth of housing stock did not, at first, generate an\nincrease in the ratio of the housing stock to GDP. Housing investment rose to a new high in 2007,\nfueled by expectations that rapid price rises would continue. This coupled with a slackening in the\ngrowth of GDP has resulted in a steady increase in the ratio of the housing stock to GDP from 2007\nonwards (Figure 8, Panel A). The business sector capital-output ratio has increased somewhat whether\nmeasured relative to total GDP (Figure 8, Panel A) or relative to GDP in the business sector (Figure 8,\nPanel B).\n\n**Figure 8 Capital-output ratio by economic sector**\n\nConstant prices\n\nA. Capital stock by sector as ratio of total GDP B. Capital stock by sector as ratio of sectoral GDP\n\n\n\n\n\n\n\n\n\n\n\n_Source:_ Author estimates using NBS data\n\n\nThe above estimates include an estimate for the stock of R&D capital. The stock of this type of capital\nis, however, quite small. Using the revisions to the estimates GFC\n\nMention: \"NBS data\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"analyze\", \"summary\": \"Sectoral capital stock relative to output is estimated by the author from these national accounts.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:000372:26:2", "occurrence_id": "ee62714c56ab1b99ae36d2b1", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: Sample Survey Office (NSSO) Surveys.\n\nModel 1: Final Model\n\nModel 2: District dummies*Time Trend\n\nModel 3: Expenditures at the Extensive Margin\n\nModel 4: Constant Coefficient Model\n\n\nTable 8: Preferred Model vs. Typical Line-Up Method Predictions for 2014-15\n\n\n**Model** **Line-up**\nNational 14.6 11.0\nUrban 10.0 7.1\nRural 16.8 12.9\n\n\nSource: India National Sample Surveys\n\n(NSSO) Surveys.\n\n\n25\n\nMention: \"India National Sample Surveys\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"Model predictions of poverty for 2014-15 are benchmarked against these survey estimates.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:000387:15:0", "occurrence_id": "7da945d5189a9a007042183f", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: **Temporary employment and part-time work were relatively common in Kosovo.** Most employees in\nKosovo had temporary contracts (74.8 percent in 2018) and only 4.5 percent had a part-time job. Firms were\nconcentrated in the commerce and services sectors. The share of public sector employment constituted 41.6\npercent and the share of private sector employment was 58.4 percent.\n\n\nRecent trends in wages\n\n\n**There is a public-sector wage premium, and real wages in the public sector increased faster than in**\n**the private sector; gender, age and education wage disparities were also common.** In 2018, the average\nnet monthly wage in Kosovo was approximately 393 euros, constituting 457.3 euros in the public sector and\njust 344 euros in the private sector. Nevertheless, because the average wage may be overestimated or\nunderestimated due to the presence of outliers, the median wage tends to be a more useful comparison. Median\nwages were lower than mean averages, set at 378 euros in 2018. Median wages grew faster in the public sector\nthan in the private sector, as shown in Figure 7 Panel a and can be expected to grow even faster with approval\nof the new wage law for public sector employees in early 2019. 17 [^17: Average and median wage are estimated using Kosovo LFS and wages are deflated using CPI with 2015 as a base year.\n[Series for CPI are obtained from Kosovo Agency of Statistics estimates (http://ask.rks-gov.net/en/kosovo-agency-of-](http://ask.rks-gov.net/en/kosovo-agency-of-statistics/add-news/harmonized-index-of-consumer-prices-hicp-april-2018)\n[statistics/add-news/harmonized-index-of-consumer-prices-hicp-april-2018](http://ask.rks-gov.net/en/kosovo-agency-of-statistics/add-news/harmonized-index-of-consumer-prices-hicp-april-2018) ).] When using median wages, there is still a\nsizable public-sector premium, especially among workers with higher educational attainment (Figure 7 Panel\nb)\n\nMention: \"Kosovo LFS\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"analyze\", \"summary\": \"Average and median wages are estimated from this survey and deflated to a 2015 base.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:000398:20:7", "occurrence_id": "d814678e99c940cc7f81a4b2", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: .0750) (0.0520) (0.0582) (0.0475)\n\n\n_Policy Response_\nGovernment Response (GR) -0.0526\n_(Oxford tracker)_ (0.0316)\nStringency Index -0.0505* -0.0502* -0.0539* -0.0531* -0.0556* -0.0509* -0.0571** -0.0788** -0.0570** -0.0686** -0.0470*\n_(Oxford tracker)_ (0.0291) (0.0271) (0.0280) (0.0276) (0.0300) (0.0265) (0.0266) (0.0302) (0.0265) (0.0296) (0.0274)\n\n\n_Regional Dummies_\nDummy: Sub-Saharan 2.287* 1.967 2.463* 2.208* 0.412 1.435 1.857 1.274 3.520** 3.104** 2.477* 2.029\nAfrica (SSA) (1.261) (1.377) (1.291) (1.256) (1.154) (1.403) (1.144) (1.154) (1.363) (1.285) (1.357) (1.497)\n\n\nObservations 88 79 88 88 93 81 93 93 78 89 79 88\nR-squared 0.39 0.483 0.440 0.397 0.358 <\n\nMention: \"Oxford tracker\""}, {"role": "assistant", "content": "{\"role\": \"supporting\", \"usage_action\": \"source\", \"summary\": \"Government response and stringency variables in the regressions are attributed to this tracker.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:000412:5:1", "occurrence_id": "91ffe19be70cbd3dfc567162", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: ,\nvolumetric, load-based and time-of-use — have been fully incorporated (Box 1) (Briceno-Garmendia and\nShkaratan, 2011). This requires assumptions to be made regarding the average monthly electricity bill. For\nresidential customers, the average electricity consumption is derived from the IEA energy balances by\ntaking the total residential electricity consumption and dividing by the number of connected households.\nSince there are limited data on the distribution of electricity consumption within a given country, median\nelectricity consumption may lie below the lifeline tariff level in more cases than implied by the analysis.\nAs a result, the results might overestimate the average electricity tariff faced by households in certain\ndeveloping countries. For non-residential customers, a “representative” consumption level is adopted based\non expert consultations and the characteristics of each sector. Commercial, agricultural and public sector\nconsumption is assumed to be 1,000 kilowatt-hours per month, while industrial consumption is set at 5,000\nkilowatt-hours per month.\n\nSimilarly, assumptions were made about the representative load level for each customer group, as well as\nthe pattern of peak versus off-peak consumption in cases where time-of-use tariffs exist. Following internal\nconsultations, the commercial load factor was set to 11 kilovolts, while the industrial load factor was set to\n33 kilovolts. In cases where customer groups were not explicitly defined by the tariff schedule, these load\nfactors were used for categorization.\n\nIn order to apply time-of-use to a single average nominal tariff for each customer group, a weighted average\nvolumetric time-of-use charge was computed for each customer class based on the following time zones:\npeak times were defined as 6pm through 10pm for commercial customers, and as 6pm through 9pm for\nindustrial users. Day time was defined as 8am through 6pm, and nighttime as 10pm through 8am for all\nusers. Where a choice between linear tariffs and time\n\nMention: \"IEA energy balances\""}, {"role": "assistant", "content": "{\"role\": \"supporting\", \"usage_action\": \"analyze\", \"summary\": \"Total residential consumption divided by connected households gives the average bill assumption.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:000434:20:1", "occurrence_id": "7f79dde58aef565873dc157f", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: *\nRoad density 0.045 (0.003) *** 0.063 (0.004) *** 0.063 (0.004) ***\nTransport cost to port -0.005 (0.003) * -0.014 (0.003) *** -0.016 (0.003) ***\nln Population -0.225 (0.084) *** 0.556 (0.093) *** 0.604 (0.092) ***\nln Population density -0.417 (0.048) *** -0.826 (0.076) *** -0.856 (0.074) ***\nln Local wage 0.300 (0.081) *** 0.305 (0.078) ***\nSecondary school enrollment 0.012 (0.001) *** 0.011 (0.001) ***\nObs. 43808 43808 43808\nWald chi2 426.15 643.33 676.14\nPseudo R-squared 0.066 0.095 0.099\n\n\n7 According to the 2007 BEEP data, about 17 percent of the firms surveyed import materials and equipment\nfrom abroad. About 5 percent of the firms export their products.\n\nMention: \"2007 BEEP data\""}, {"role": "assistant", "content": "{\"role\": \"supporting\", \"usage_action\": \"source\", \"summary\": \"A footnote reports the share of surveyed firms that import inputs or export output.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:000438:10:1", "occurrence_id": "31d60c488ab85428a18c08b3", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: from 13,975 to 5,565. 28 Furthermore, this is even\nmore complicated for multiproduct plants where the methodology approximates TFPQ by considering only\nthe major product of the firm. 29 In an analysis where firm growth is measured by change in overall\nemployment, it would be misleading to consider plant TFPQ of the major product of the plant. 30\n\n**_Distances to Cities/Urban Agglomerations_**\n\nThis work uses GIS software to compute distances between every town in the LMMIS data and five major\nEthiopian cities that are considered to be centers of broader agglomerations. The five cities/urban\nagglomerations are Addis Ababa, Awassa, Bahir Dar, Dire Dawa and Mekele. Besides the agglomeration\ncenter itself, the following distance bands are defined from the nearest agglomeration center à la Ghani et\nal. (2016): 0-50 kilometer (km), 50-100 km, 100-150 km, and the residual category of towns that are located\nover 50 km away.\n\n**_Measuring Spatial Clustering_**\n\nThe Ellison-Glaeser index (EGI) measures the extent of spatial concentration in a given industry. It takes\nnegative values when the industry is more dispersed than what random assignment would lead to, while\npositive values where industries show greater levels of concentration. 31 The EGI for industry _s_ at time _t_ is\ndefined as:\n\n\n27 The project also experimented with alternative definitions of TFP and found the results to be robust to such changes. Another\nproblem related to TFP estimation is measurement errors; these are arguably all the more pervasive in the context of developing\ncountries.\n28 Examples of such products include bricks of clay, cement blocks, nails, sugar, bread and wheat\n\nMention: \"LMMIS data\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"analyze\", \"summary\": \"Town locations in this enterprise list are used to compute GIS distances to five urban centres.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:000449:39:0", "occurrence_id": "0ce07602226c96fbadb07cba", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: ## **Appendix**\n\n##### **A Data Appendix**\n\n**A.1** **Survey** **Questions** **in** **the** **SOEP**\n\n\nTable A.1 summarizes the construction of the outcome variables based on the survey questions from\nthe SOEP. In each of the years in Column (4), respondents are asked the survey question in Column\n(2) and presented the mutually exclusive answer options in Column (3). We use the answer options\nto create binary indicators, whereby for all questions except 5)), a value of one indicates an answer\nconsistent with greater social cohesion. With the question about concerns 5), a value of one indicates\nthat people are very concerned about crime. The classification of the binary indicators is shown in\nparentheses in Column (3).\n\nMention: \"SOEP\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"Outcome variables are constructed from the wording of this panel's survey questions.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:000452:12:0", "occurrence_id": "59a3e05c9151de1d4b6ac6e7", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: Ethiopian civil war not be correlated with year of birth and pre-reform levels of schooling in the same way\n\n\nas the FPE reform. Potential bias generated by contemporaneous changes in educational investments, the\n\n\nimpact of the civil war, and the 2000 law banning marriage for those under 18 are explored in more detail\n\n\nin Section 6.4. Additionally, it would be problematic if women and families relocated at the time of the\n\n\nreform’s implementation in such a way that higher-ability students sorted into areas with higher predicted\n\n\nintensity of the reform. However, this type of sorting is unlikely to occur in the studied setting. First, data\n\n\nfrom the 2016 Living Standards Measurement Study show that 86 percent of respondents in the relevant\n\n\ncohort range live in their region of birth. Furthermore, the intensity measure is explicitly designed to predict\n\n\na greater impact of the reform in areas with lower initial levels of schooling. A violation of this assumption\n\n\nwould entail the unlikely scenario that higher-ability students’ families were moving to areas that were worse\n\n\noff at the time of reform implementation, even though they could have received the same reduction in fees\n\n\nin their original education zone.\n\n##### **6 Results**\n\n\n**6.1** **Effect** **of** **FPE** **on** **Years** **of** **Schooling** **and** **Fertility**\n\n\nTo begin the analysis, the OLS relationship documents the general correlation seen in the data. This is\n\n\ndone by estimating equation (9) using the reported years of schooling from the data, not the predicted level\n\n\nfrom the first stage. A negative relationship between fertility and schooling has been well documented in\n\n\nthe literature (Ainsworth et al., 1996; Lam and Duryea, 1999; Schultz, 1994, 1997). The OLS estimates\n\n\nare shown in column 1 of\n\nMention: \"2016 Living Standards Measurement Study\""}, {"role": "assistant", "content": "{\"role\": \"supporting\", \"usage_action\": \"validate\", \"summary\": \"It shows most of the relevant cohort still live in their region of birth, arguing against sorting bias.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:000456:6:1", "occurrence_id": "f1898fcc7b6233ec164ea98a", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: area measurement\nthan self-reporting. Although the issues with GPS measurement error should not be overlooked and\nare discussed again in the conclusion of the article, here GPS measurement is considered closer to\nthe true land area and we refer to deviations from the GPS area as self-reported measurement error.\n\n_LSMS-ISA data_\n\nThe LSMS-ISA data sets create an opportunity for analyzing the different methods of land data\ncollection since the studies employ GPS measurement while continuing to collect self-reported land\nareas. Data are currently available for four LSMS-ISA countries: Malawi (2010/11), Uganda\n(2009/10), Tanzania (2010/11) and Niger (2011). For agricultural households in each of the\ncountries, the plot manager or head of household is first asked to estimate the plot areas and then the\nplots are measured using GPS, so as not to influence the farmer’s reported figure.\n\nDepending on the survey, farmers may be required to report in a single unit (as in Uganda,\nTanzania and Niger) or they may have the choice to report in a number of units (as in Malawi). In\neither scenario, the estimate is subject to previously noted errors. GPS devices allow for\nmeasurement in a variety of units, but are typically recorded in acres in LSMS-ISA projects and\nrounded to the nearest hundredth.\n\nThe exclusion of certain plots from GPS measurement was mandated by the survey manual for\nthe sake of time and budget. In Malawi, for example, enumerators were instructed to measure all\nplots within two hours of walking from the household. In Tanzania the guidelines were to measure\nall plots within one hour (via any mode of transportation) and Uganda required all plots within the\nenumeration area to be measured (Government of Malawi, NSO, 2010; World Bank Group, n.d.;\nUBOS, 2009). Table 1 provides basic information on the surveys considered in this study and how\nland\n\nMention: \"LSMS-ISA data sets\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"analyze\", \"summary\": \"Because they collect GPS and self-reported plot areas together, they allow the two methods to be compared.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:000458:23:2", "occurrence_id": "24e8e214460393310b5f14e6", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: are discussed subsequently in the paper.\n115 Twenty-five countries are included in the study, including: Benin, Botswana, Burkina Faso, Cameroon, Côte d’Ivoire,\nDemocratic Republic of Congo, Ethiopia, Ghana, Kenya, Malawi, Mali, Mauritius, Mozambique, Namibia, Nigeria, Rwanda,\nSenegal, Sierra Leone, South Africa, Swaziland, Tanzania, Togo, Uganda, Zambia, and Zimbabwe.\n116 While this number of data points allows for sufficiently significant and robust results, the n-size will be subsequently increased\nas more data become available in mid-/late-2019.\n117 For instance, comparing countries in Sub-Saharan Africa with OECD countries, Latin America, or East Asia would not be as\ninstructive as the latter are much closer to the frontier in key service delivery areas and would not have the same variation.\n118 Fortunately, the data available support this method, since annual OGD evaluations are released in January of each year, and\naccountability and service delivery indicators are released in October, thus allowing a nine-month lag.\n\n\n22\n\nMention: \"annual OGD evaluations\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"analyze\", \"summary\": \"Its January release timing creates the nine-month lag used in the identification.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:000458:23:2", "occurrence_id": "031fba02723f49bc7e1b5a8d", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: are discussed subsequently in the paper.\n115 Twenty-five countries are included in the study, including: Benin, Botswana, Burkina Faso, Cameroon, Côte d’Ivoire,\nDemocratic Republic of Congo, Ethiopia, Ghana, Kenya, Malawi, Mali, Mauritius, Mozambique, Namibia, Nigeria, Rwanda,\nSenegal, Sierra Leone, South Africa, Swaziland, Tanzania, Togo, Uganda, Zambia, and Zimbabwe.\n116 While this number of data points allows for sufficiently significant and robust results, the n-size will be subsequently increased\nas more data become available in mid-/late-2019.\n117 For instance, comparing countries in Sub-Saharan Africa with OECD countries, Latin America, or East Asia would not be as\ninstructive as the latter are much closer to the frontier in key service delivery areas and would not have the same variation.\n118 Fortunately, the data available support this method, since annual OGD evaluations are released in January of each year, and\naccountability and service delivery indicators are released in October, thus allowing a nine-month lag.\n\n\n22\n\nMention: \"accountability and service delivery indicators\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"These outcome indicators, released in October, are the dependent variables.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:000478:4:0", "occurrence_id": "4d7563c24686ad35a537adde", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: households, which can be either couples or individuals, make choices over time with regard\n\n\nto labor supply, private savings and retirement in an environment with uncertainty about\n\n\nfuture wages, returns on pension savings, fertility, divorce or widowhood and own survival.\n\n\nMen and women choose not only whether to work or not but also whether to work in the\n\n\nformal sector where pension contributions are mandatory or in the informal sector. The\n\n\ndistinction between formal and informal sector work is important in Chile (and most coun\n\ntries across the world) because many individuals work in the informal sector and reach old\n\n\nage having contributed little to the system. In addition, women choose whether to work\n\n\npart-time or full-time. The model is estimated on longitudinal microdata from the _Encuesta_\n\n\n_de_ _Protecci´on_ _Social_ _(EPS)_ merged with administrative data on pension funds. 4\n\n\nWe use the estimated model to study how labor supply and savings behavior changes\n\n\nwith the introduction of the 2008 pension reform in comparison to the previous pension\n\n\nsystem behavior and in comparison to alternative pension system designs. We estimate\n\n\nmodel parameters by the method of simulated moments using pre-reform data from the\n\n\n2004 and 2006 EPS Surveys. The estimation results reveal substantial heterogeneity in how\n\n\nindividuals value pecuniary and non-pecuniary dimensions of formal and informal work.\n\n\nSome individuals have strong comparative advantages to working in the formal or informal\n\n\nsectors, which dampens behavioral responses to pension rule changes.\n\n\nIncorporating the pension rules explicitly in our model allows us to construct counterfac\n\ntual simulations in which the reform did not happen, keeping everything else constant. In\n\n\nthis way, we perform an ex ante prediction of the short-run behavioral impacts of the pension\n\n\nreform and compare our predictions to some evidence from other causal impact studies of\n\n\nthe reform’s impacts. Consistently with other studies, we find that the more generous safety\n\n\nnet induces negative wealth\n\nMention: \"administrative data on pension funds\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"Contribution records are merged with the household panel to estimate the lifecycle model.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:000478:4:0", "occurrence_id": "db6199e831dddf8abfb67c85", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: households, which can be either couples or individuals, make choices over time with regard\n\n\nto labor supply, private savings and retirement in an environment with uncertainty about\n\n\nfuture wages, returns on pension savings, fertility, divorce or widowhood and own survival.\n\n\nMen and women choose not only whether to work or not but also whether to work in the\n\n\nformal sector where pension contributions are mandatory or in the informal sector. The\n\n\ndistinction between formal and informal sector work is important in Chile (and most coun\n\ntries across the world) because many individuals work in the informal sector and reach old\n\n\nage having contributed little to the system. In addition, women choose whether to work\n\n\npart-time or full-time. The model is estimated on longitudinal microdata from the _Encuesta_\n\n\n_de_ _Protecci´on_ _Social_ _(EPS)_ merged with administrative data on pension funds. 4\n\n\nWe use the estimated model to study how labor supply and savings behavior changes\n\n\nwith the introduction of the 2008 pension reform in comparison to the previous pension\n\n\nsystem behavior and in comparison to alternative pension system designs. We estimate\n\n\nmodel parameters by the method of simulated moments using pre-reform data from the\n\n\n2004 and 2006 EPS Surveys. The estimation results reveal substantial heterogeneity in how\n\n\nindividuals value pecuniary and non-pecuniary dimensions of formal and informal work.\n\n\nSome individuals have strong comparative advantages to working in the formal or informal\n\n\nsectors, which dampens behavioral responses to pension rule changes.\n\n\nIncorporating the pension rules explicitly in our model allows us to construct counterfac\n\ntual simulations in which the reform did not happen, keeping everything else constant. In\n\n\nthis way, we perform an ex ante prediction of the short-run behavioral impacts of the pension\n\n\nreform and compare our predictions to some evidence from other causal impact studies of\n\n\nthe reform’s impacts. Consistently with other studies, we find that the more generous safety\n\n\nnet induces negative wealth\n\nMention: \"EPS Surveys\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"analyze\", \"summary\": \"Pre-reform waves provide the moments used to estimate preferences over formal and informal work.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:000479:52:1", "occurrence_id": "7fbf20f6e4c73987e8c487f7", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: \nObservations 71,866 71,866 38,330\nNumber of districts 1,286 1,286 531\nMean dep. var 0.970 0.970 0.970\n\n\nDistrict FE YES YES YES\nProvince*Year FE YES YES YES\nCovariates YES YES YES\n\n\n_Notes:_ *** p _<_ 0.01, ** p _<_ 0.05, - p _<_ 0.1. The dependent variable is a dummy indicating whether the child is\ncurrently attending primary school. The independent variables measures the presence of a WJC within a 1km\nEuclidean buffer of the child’s cluster of residence and presence of a WJC center in the child’s district. Robust\nstandard errors (in parentheses) are clustered at the district level. The sample of primary school level includes\nchildren between the ages of 6 and 11. Covariates include age, gender, household’s head years of education,\nnumber of children in the household aged 0-18, number of children in the household aged 0-5, number of female\nadults, number of male adults, rural residence dummy, district fixed effect and province-by-year fixed effect.\nSource: Peru DHS 2006-2014.\n\n\n50\n\nMention: \"Peru DHS\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"District-level regressions on household composition and outcomes are estimated on these rounds.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:000482:17:0", "occurrence_id": "def956e4bb78308f4257f268", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: crop, livestock, forest, and fish allocation far outperforms the method of using rural population to\ndistribute the agricultural GDP, at least in the case of Brazil.\n\n#### References\n\n\nS. Angel, P. Lamson‐Hall, B. Guerra, Y. Liu, N. Galarza, and A. M. Blei (2018). Our Not‐So‐Urban World,\nWorking Paper No. 42 The Marron Institute of Urban Management, New York University.\n\n\nArvis, J. F., & Shepherd, B. (2013). The Poisson quasi‐maximum likelihood estimator: a solution to the\n‘adding up’ problem in gravity models. _Applied Economics Letters_, _20_ (6), 515‐519.\n\n\nArvis, J.F; Blankespoor, B. Downscaling Economic Variables: An Entropy Estimation. Mimeo.\n\n\nBlanchard, P.B.; Blankespoor, B. Rivera‐Fuentes, J.; Gunasekera, R.; Ishizawa O. and Jimenez L.F. Spatial\nDisaggregation of Gross Domestic Product for applications in Disaster Risk Management. Mimeo.\n\n\nBosker, M.; Park, J.; Roberts, M. (2018). Definition Matters : Metropolitan Areas and Agglomeration\nEconomies in a Large Developing Country (English). Policy Research working paper; no. WPS 8641.\nWashington, D.C. : World Bank Group.\n\n\nCenter for International Earth Science Information Network ‐ CIESIN ‐ Columbia University. (2017).\nGridded Population of the World, Version 4 (GPWv4): Population Count Adjusted to Match 2015\nRevision of UN WPP Country Totals, Revision 10. Palisades, NY: NASA Socioeconomic Data and\nApplications Center (SEDAC). https://doi.org/10.7927/H4JQ0XZW.\n\n\nChen, X., &\n\nMention: \"Gridded Population of the World\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"Gridded population counts are used to allocate agricultural output across space.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:000482:17:0", "occurrence_id": "ce17276bc6b969058b2620a5", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: crop, livestock, forest, and fish allocation far outperforms the method of using rural population to\ndistribute the agricultural GDP, at least in the case of Brazil.\n\n#### References\n\n\nS. Angel, P. Lamson‐Hall, B. Guerra, Y. Liu, N. Galarza, and A. M. Blei (2018). Our Not‐So‐Urban World,\nWorking Paper No. 42 The Marron Institute of Urban Management, New York University.\n\n\nArvis, J. F., & Shepherd, B. (2013). The Poisson quasi‐maximum likelihood estimator: a solution to the\n‘adding up’ problem in gravity models. _Applied Economics Letters_, _20_ (6), 515‐519.\n\n\nArvis, J.F; Blankespoor, B. Downscaling Economic Variables: An Entropy Estimation. Mimeo.\n\n\nBlanchard, P.B.; Blankespoor, B. Rivera‐Fuentes, J.; Gunasekera, R.; Ishizawa O. and Jimenez L.F. Spatial\nDisaggregation of Gross Domestic Product for applications in Disaster Risk Management. Mimeo.\n\n\nBosker, M.; Park, J.; Roberts, M. (2018). Definition Matters : Metropolitan Areas and Agglomeration\nEconomies in a Large Developing Country (English). Policy Research working paper; no. WPS 8641.\nWashington, D.C. : World Bank Group.\n\n\nCenter for International Earth Science Information Network ‐ CIESIN ‐ Columbia University. (2017).\nGridded Population of the World, Version 4 (GPWv4): Population Count Adjusted to Match 2015\nRevision of UN WPP Country Totals, Revision 10. Palisades, NY: NASA Socioeconomic Data and\nApplications Center (SEDAC). https://doi.org/10.7927/H4JQ0XZW.\n\n\nChen, X., &\n\nMention: \"UN WPP Country Totals\""}, {"role": "assistant", "content": "{\"role\": \"supporting\", \"usage_action\": \"validate\", \"summary\": \"The gridded counts have been adjusted to match these national population totals.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:000487:51:0", "occurrence_id": "080f002f8e332d2202405d94", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: In other words, to convert PovcalNet values to 2011 PPPs, we convert the 2005 PPP USD values\n\n\nto local currency units for 2005, then apply the CPI (available in PovcalNet) between 2005 and\n\n\n2011 to convert LCU values from 2005 to 2011 prices, and then finally apply the 2011 PPP\n\n\nconversion factors to obtain values in 2011 PPP USD. 35 [^35: When the CPI series in PovcalNet between 2005 and 2011 is incomplete, we use the CPI from WDI to\nextend the series. A previous version of this paper relied solely on the CPIs available in WDI.]\n\n\n**_C. Removing rural-urban adjustments for India, China and Indonesia_**\n\n\nIncome distributions derived in 2005 PPPs from PovcalNet contain implicit adjustments for\n\n\nseveral countries, including China, India and Indonesia, as described in Chen and Ravallion\n\n\n(2010). The PPP conversion factors used for these three countries are described in Table A1.2.\n\n\n**Table A1.2: PovcalNet 2005 PPP conversion factors for urban bias adjustment**\n\n\n\n**Adjusted**\n\n**Urban PPP**\n\n\n\n**Adjusted**\n\n**Rural PPP**\n\n\n\n**Ratio Adjusted**\n\n**Urban/Official**\n\n\n\n**Ratio Adjusted**\n\n**Rural/Official**\n\n\n\n**Country**\n\n\n\n**Official**\n\n**PPP**\n\n\n\nChina 4.09 4.09 2.98 1.00 0.73\n\nIndia 15.6 17.24 11.4 1.11 0.73\n\nIndonesia 4192 4795.9 3399.7 1.14 0.81\n\n\nFor these three countries, we undo the adjustments when applying the 2011 PPPs by adding an\n\n\nadditional factor of the ratio of the adjusted to official PPP (two last columns of Table A1.2) to\n\n\nequation\n\nMention: \"CPIs available in WDI\""}, {"role": "assistant", "content": "{\"role\": \"supporting\", \"usage_action\": \"source\", \"summary\": \"These price series extend incomplete consumer price series when converting between purchasing power vintages.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:000507:38:1", "occurrence_id": "c2d5cf3c26dbb4b3e6137cd2", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: and the vignettes; and in column (5) is the standardized index of the seven items that are reported by the caregiver\nfrom the internalizing/externalizing behaviors sections of the Parent/Caregiver Report Survey. The controls include age in years, girls and\nboys cared for by the respondent, and the educational level of the respondent for primary, high school, or tertiary education—the\nomitted category. Robust standard errors. *** p _<_ 0.01, ** p _<_ 0.05, * p _<_ 0.1.\n\n\n37\n\nMention: \"Parent/Caregiver Report Survey\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"analyze\", \"summary\": \"A standardised internalising and externalising behaviour index is built from this instrument's items.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:000528:6:1", "occurrence_id": "ff9348236783dd7d923334be", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: ; Salehyan and Gleditsch 2006). The surge’s\nupsetting of ethnic balances and the governing coalition explain Jordan’s subsequent economic reforms.\n\nThe last and best feature of this sudden natural experiment is that the Kuwaiti-Palestinians had full\nlegal, political, and economic rights immediately upon entering Jordan, a situation unique in the Arab\n\n\n\ngroups in the host country (Buhaug and Gleditsch 2008; Salehyan and Gleditsch 2006). The surge’s\nupsetting of ethnic balances and the governing coalition explain Jordan’s subsequent economic reforms.\n\nThe last and best feature of this sudden natural experiment is that the Kuwaiti-Palestinians had full\nlegal, political, and economic rights immediately upon entering Jordan, a situation unique in the Arab\nworld (Zureik 1994).\n\nThree features of this exogenous shock make it less useful as a natural experiment. The first is that the\nKuwaiti-Palestinians were overwhelmingly Sunni Muslims, just like Jordan’s population. The second is\n\n\n\nlegal, political, and economic rights immediately upon entering Jordan, a situation unique in the Arab\nworld (Zureik 1994).\n\nThree features of this exogenous shock make it less useful as a natural experiment. The first is that the\nKuwaiti-Palestinians were overwhelmingly Sunni Muslims, just like Jordan’s population. The second is\nthat Jordan did not have a democracy like other nations that accepted large numbers of immigrants.\nJordanians voted in the 1989 elections and expected future elections, but their impact on policy through\nvoting was limited. Third, Jordan did not have a welfare state as large as those in the developed world\n(Brynen 1992).\n\n**4.** This study uses **Data** Gwartney, Lawson, and Hall (2017) Economic Freedom of the World Annual Report (EFW)\n\nto measure changes in Jordan’s economic institutions. The EFW index is a reasonable proxy for economic\ninstitutions, incorporating 42 variables collected\n\nMention: \"Economic Freedom of the World Annual Report\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"Its composite of 42 variables is the proxy for changes in the country's economic institutions.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:000534:9:0", "occurrence_id": "ea549e95d428e9a9fe407198", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: _highly concentrated in a few producer countries or the main world supplier is China were_\n\n\n_more vulnerable to the pandemic._\n\n\nThe COVID-19 shock may have adversely affected productivity due to reduced mobility and\n\n\nthe disruption in in-person production activities but less so for more complex and knowledge\n\nintensive products. This is because, for such products, productivity relies more on knowledge\n\n\ncollaborations that were effectively shifted to virtual exchanges. The exponential growth of virtual\n\n\nonline interactions for research and innovation collaborations - critical for productivity - and the\n\n\nwider use of virtual platforms have proven to be highly effective as is illustrated by the surprisingly\n\n\nquick responses to the pandemic, namely the rapid development of vaccines (Paunov and Planes\n\nSatorra, 2021). Our third hypothesis to test in the empirical work is as follows:\n\n\n_H3: The productivity of complex and knowledge-intensive production processes may increase_\n\n\n_relative to that of less complex and knowledge-intensive processes since the former benefited_\n\n\n_more from remote work interactions. Hence less complex and knowledge- intensive products_\n\n\n_were more vulnerable to the pandemic._\n\n\n**2.** **Data**\n\n\n**High-frequency bilateral product level trade data**\n\n\nOur analysis relies on several sources of data. For trade outcomes, we use monthly data on\n\n\nimport flows at the product level by the major markets of the 27 EU countries, Japan, and the US\n\n\nfrom January 2018 to December 2020. The specific sources of data are, respectively, Eurostat\n\n\nmonthly trade flows for EU countries, the Ministry of Finance for Japan, and the United States\n\n\nInternational Trade Commission for the US. These data are exploited to examine the evolution of\n\n\nexport flows\n\n\n8\n\nMention: \"Eurostat\n\n\nmonthly trade flows\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"Product-level monthly import flows for EU markets are taken from this source.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:000542:31:1", "occurrence_id": "e5ac002f5011cbf99e161a59", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: ¯ _re_ = 2.8%.\n\nWe set the schooling transition probabilities _πs_ ( _·_ ) to match the schooling\n\ndistribution in developed and developing economies (I2D2). 49 We assume agents may\n\n\nonly accumulate up to 25 years of schooling as some countries only record schooling\n\n\nup to 25. Finally, we set the employment probabilities _πe_ ( _·_ ) using participation, youth\n\n\nunemployment and adult unemployment rate averages reported by World Bank (2018a).\n\n\nSee Table 5 for a summary of the values of the parameters we used. See\n\n\nWeb Appx. Section A.6 for details of the parameterization of the accounting framework.\n\n##### **6.3. Main Quantitative Findings**\n\n\nA typical developing economy has 24% of the GDP per capita of a typical developed\n\n\neconomy (World Bank, 2018a). In the simulations, we find a value of 48 _._ 5%. The gap\n\n\nbetween 48 _._ 5 and 100 is 68% of the gap between 24 and 100. Thus, in our accounting\n\n\nmodel, differences in education, experience and the returns thereof, plus demographic\n\nand labor market differences, account for two thirds of the income gap. 50 Demographic\n\n\nand labor market differences are small, however, with the exception of labor market\n\n\nparticipation. Assume instead that demographic and labor market factors are the same\n\n\nas in the developed economy, allowing only differences in the stock of schooling and the\n\n\nreturns to human capital. Then, we find that relative _pcGDP_ is 53 _._ 5 percent, accounting\n\n\n48See Web Appx. Fig. 8(a) for the mortality distributions.\n49See Web Appx. Fig. 8(b) for the distribution of schooling we use, based on the I2D2 data (1990-2016)\n\nMention: \"I2D2\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"analyze\", \"summary\": \"Schooling transition probabilities are calibrated to the schooling distribution in this dataset.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:000555:26:0", "occurrence_id": "9ad9870796a5511a730e312b", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: **Figure 1. Budget balance and gross government debt over the last two global crises**\n\n\n**A.** **Budget balance** **B.** **Gross government debt**\n\n\nS _ources:_ IMF World Economic Outlook; World Bank.\n_Notes:_ EMDEs = emerging market and developing economies _._ Country weights based on PPP GDP.\n_A._ Weighted averages of budget balance (as percent of GDP) for 35 advanced economies and 148 EMDEs. Data from\n\n2000 to 2021.\n_B._ Weighted averages of gross government debt (as percent of GDP) for 30 advanced economies and 144 EMDEs.\n\nData from 2000 to 2021.\n\n\n**Figure 2. Commodity prices**\n\n\n_Source:_ World Bank.\n_Note:_ Last observation is December 2022.\n\n\n25\n\nMention: \"IMF World Economic Outlook\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"Budget balances and gross government debt for advanced and emerging economies come from this source.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:000561:5:1", "occurrence_id": "8533a4e965494bfb0b9d0ac9", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: counteract the negative impact brought\n\n\nby mobility restrictions and a change in consumption patterns (see Watanabe and Omori (2020)).\n\nIn most of the paper, unless otherwise noted, the analysis restricts the sample to firms with 5 or\n\nmore employees, which was a threshold used in most countries for which data is available. 3\n\n\nThree main indicators regarding the digital response by firms were collected. First, whether the\n\n\nfirm has started or increased the use of digital platforms in response to the pandemic. Second, if the\n\nfirm invested in the implementation or use of digital solutions; and third, the share of sales done\n\n\nthrough online channels. Throughout the paper, analyses explore how firms differed in their digital\n\n\nresponse towards the pandemic, and the possible implications of such responses.\n\n\nFor the analysis, the paper will focus on the 57 countries 4 with data on digital changes. In total,\n\n\nthere is information on 65,130 firms, where 25,255 are panel firms. This feature of the data allows to\n\nanalyze how digital changes happened since the start of the pandemic 5 . The first wave of surveys\n\n\n3The WBES uses the threshold of 5+ employees.\n4Countries include: Argentina, Bangladesh, Benin, Brazil (Sao Paulo), Bulgaria, Cambodia, Chile, Croatia, Cyprus,\nCzechia, the Arab Republic of Egypt, El Salvador, Estonia, Georgia, Greece, Guatemala, Honduras, Hungary, India,\nIndonesia, Italy, Jordan, Kenya, Kosovo, Kyrgyzstan, Latvia, Lesotho, Lithuania, Madagascar, Malaysia, Malta, Moldova,\nMongolia, Morocco, Mozambique, Nepal, Nicaragua, Pakistan, Paraguay, Poland, Portugal, Romania, Senegal, Sierra\nLeone, the Slovak Republic, Slovenia, Somalia, South Africa, Sri Lanka, Tajikistan, Tanzania, Tunisia, Türkiye, Uzbekistan,\nVietnam, Zambia,\n\nMention: \"WBES\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"analyze\", \"summary\": \"Its panel of firms with a five-employee threshold allows digital changes since the pandemic to be tracked.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:000569:13:0", "occurrence_id": "67569eb046959cfbb9070203", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: 2016 (Table 2). Furthermore, by 2019, Figure 7 shows that these high-wealth individuals\ncontinued to report significantly larger assets, with their declared holdings nearly tripling\ncompared to 2015.\n\nOne concern in this analysis revolves around the possibility that disclosing assets\nmight lead to a reshuffling of individuals across different percentile groups over time.\nTo address this potential concern, we utilize data from Argentina’s income tax returns,\nwhere individuals must report assets held in both the current and previous tax years.\nThis approach lets us compare asset changes while keeping individuals’ income rankings\nconstant. 7 [^7: For example, the 2016 income tax tabulation, which ranks individuals based on their income, includes data\non assets held in 2015 and 2016 for each income bracket.\n8Argentina’s wealth tabulations rank individuals based on total assets. To recover the share of foreign assets\n(and the effective tax rate) for each fractile, we cumulate the amount of foreign assets (and wealth taxes)\nby total assets, interpolate the cumulative function for each fractile with a smooth cubic spline function,\nand differentiate the interpolated function. Reassuringly, a linear interpolation delivers virtually the same\nresults.] The results are depicted in Figure 8, highlighting that the most significant increases in reported assets are primarily observed among individuals in the top 0.1% of the\nincome distribution. In this group, reported assets more than doubled, with these individuals reporting roughly one-third more assets in 2016 than in 2015. Interestingly, the scale\nof the asset increase reported by Argentina’s richest individuals aligns with what has been\nobserved in other regions such as Colombia (Londoño-Vélez and Ávila-Mahecha, 2021),\nScandinavia (Alstadsæter et al., 2019), and the Netherlands (Leenders et al., 2023).\n\nLastly, Figure A.13 compares high-net-worth individuals’ likelihood of reporting a\nforeign asset, and the share of foreign assets declared. This information is presented separately by the top fractile groups, decomposing the top 1\n\nMention: \"data from Argentina’s income tax returns\""}, {"role": "assistant", "content": "{\"role\": \"supporting\", \"usage_action\": \"validate\", \"summary\": \"Assets reported for consecutive tax years let asset changes be compared while holding income rank fixed.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:000571:45:0", "occurrence_id": "6d51432c4264d3e7a44442c2", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: Figure 10: The marginal effect of education and location on employment\n\n\nSource: DHS rounds (see, for details, Table A2 in the annex). The marginal effects (measured as percentage points on the vertical axes) are\nestimated by regression the outcome variable on location (rural versus urban) or higher education (secondary and tertiary education versus no\nor primary education), its interactions with year of birth, age, and state fixed effects. Standard errors are clustered by the state. We focus on the\nslope of the marginal effects. Moving from left to right in the graph allows to compare the difference in the marginal effects between old and\nmore recent cohorts who are categorized into urban versus rural resident or higher versus lower education level.\n\n\n44\n\nMention: \"DHS rounds\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"analyze\", \"summary\": \"Marginal effects of education and rural location on employment are estimated across these rounds.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:000573:49:0", "occurrence_id": "24f9059eb69fb415fb08b894", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: #### Appendix C: Validation of the wave model\n\n\n\nThe wave transformation model is validated against field wave measurements collected\nat a salt marsh fringe by Vuik et al. (2016). Wave propagation through the salt marshes is\n\n\n\nat a salt marsh fringe by Vuik et al. (2016). Wave propagation through the salt marshes is\n\n\noffshore boundary. The bathymetry varies between an offshore water depth of 2 m, and a\n\nmodeled for a significant wave height of 𝐻𝐻𝑚𝑚0 = 0.6 m and a peak period of 𝑇𝑇𝑝𝑝 = 3.5 s at the\n\n\n\noffshore boundary. The bathymetry varies between an offshore water depth of 2 m, and a\nnearshore water depth of 0.5 m. The salt marshes extend over a length of 55 m and have\nvarying vegetation properties across the profile, but uniform properties over the vertical\ncoordinate. The vegetation properties are summarized in Table C1. A drag coefficient of\n\n\n\ncoordinate. The vegetation properties are summarized in Table C1. A drag coefficient of\n\n\n(2016).\n\n𝑐𝑐𝐷𝐷,𝑤𝑤 = 0.4 is used in the simulations, which is equal to the value calibrated by Vuik et al.\n\n\n\n(2016).\n\n\n\n_Table C1. Salt marsh properties used for the validation from Vuik et al. (2016), consisting of the mean vegetation height hv,_\n_the mean stem density Nv, and the mean stem width bv. The location of the sections across the profile is indicated in Vuik et al._\n\n_(2016)._\n\n|Section|h (m)
v, mean|N (plants/m2)
v|b (m)
v|\n|---|---|---|---|\n|
S1-S2|
0,2|944|
0,030|\n\nMention: \"field wave measurements\""}, {"role": "assistant", "content": "{\"role\": \"supporting\", \"usage_action\": \"validate\", \"summary\": \"Instrumented waves at a salt marsh fringe are used to test the wave transformation model.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:000577:34:0", "occurrence_id": "d14b89c4eba980e0f57fd06d", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: Western countries” (Buttorff and Welborne 2015, 1). 16 [^16: The study by Buttorff and Welborne primarily used data from the Arab Barometer’s 2006–2007 survey.] That said, there seems to be some gender\ndifferences in the use of _wasta_ depending on the country context. In a study comparing several Arab\ncountries, men and women appeared to use roughly comparable amounts of _wasta_ in Algeria, Morocco,\nand Lebanon, while men were using considerably more _wasta_ than women in Jordan, Palestine, and\nYemen (Buttorff and Welborne 2015).\n\n\nIn Sudan, the use of _wasta_ to shape current institutions can be traced back to colonial times. Mann\nexplains how the British colonial administration used the _wasta_ of Sudan’s sectarian and tribal leaders to\ndevelop Sudanese institutions modelled after British institutions. For example, following independence,\nGordon Memorial College became the University of Khartoum, and the children of the sectarian and tribal\nleaders, and their trusted circles, had an easier time securing positions in Gordon Memorial College and\nthen posts in the government. Similarly, Sudan’s post-1983 leaders used the _wasta_ of regional leaders in\nIslamic banking to Islamize Sudan’s banking system. Those whose personal connections brought them into\nthe fold of these banks, like the youth of the Colonial era who were educated in Gordon Memorial College,\nbecame the country’s future leaders in business and politics.\n\n\n_Wasta_ continues to play an important role in both accessing and rising within the Sudanese labor market.\nMore than half, 56 percent, of the Arab Barometer (2018) respondents believe that it is often impossible\nto get a job without _wasta_ . According to Mann’s fieldwork in Sudan, _wasta_ plays a greater role among the\ncurrent generation than it did among previous generations. 17 Mann writes, “[ _Wasta_ ] has become so\nimportant in\n\nMention: \"Arab Barometer\""}, {"role": "assistant", "content": "{\"role\": \"background\", \"usage_action\": \"source\", \"summary\": \"A footnote records that the cited study relied primarily on this survey round.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:000585:10:0", "occurrence_id": "10d7bbabc191ee928242db8d", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: _Figure IV.2: Female decision-making index in sampled districts in 2014_\n\n\n_Figure IV.3: Female decision-making index in sampled districts in 2021_\n\n\nb. Conflict event data: ACLED\n\n\nData on conflict come from the Armed Conflict and Location Event Database (ACLED) which codes\nthe location and date of a wide range of conflict-related events. We use this geolocated\ninformation to assign conflict data to subnational regions at the ADM 2 level (i.e., district). While\nthere have been some violent events before the start of the current conflict, we select the year(s)\n\n\n9\n\nMention: \"Armed Conflict and Location Event Database\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"analyze\", \"summary\": \"Geolocated conflict events are assigned to second-level administrative districts.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:000603:8:0", "occurrence_id": "3eaac87fc250811f54dc881f", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: It is important to note that, while the results of this study provide some evidence on the efficacy of\n\n\ngasoline and diesel price changes, many other avenues for reducing air pollution are available. Non\n\nprice measures, such as technology mandates and catalyzer regulations, are underused and could\n\n\nimprove air quality without diminishing consumption levels (UNEP 2021). And while 64 percent of\n\n\ncountries have ambient air quality standards in legislative instruments, their distribution is lopsided\n\n\ntoward developed countries. For example, while all EU countries have such regulation, only 40 percent\n\n\nof Commonwealth countries do. Therefore, encouraging the implementation of air quality\n\n\nlegislation—such as mandatory filters and fuel mileage requirements for cars—could improve urban\n\n\nair quality. A single price adjustment alone will not curb air pollution; rather, a combination of\n\n\nmeasures need to work in tandem. This paper documents the role prices could play.\n\n###### 3. Data and methods 3.1. Data\n\n\nTo evaluate the relationship between fossil fuel prices and air pollution, we combine three datasets\n\n\nto construct a panel dataset with PM2.5 readings, GDP per capita, and fossil fuel prices and\n\n\nconsumption for 133 countries.\n\n\nFirst, we take surface PM2.5 concentrations in μg/m³ from van Donkeelar et al. (2021), who estimate\n\n\nmean annual air pollution levels globally using satellite imagery from 1998 to 2019. PM2.5 measures\n\n\nanthropogenic fine particulate pollution, such as exhaust emissions from fuel combustion, and is\n\n\nadjusted to remove naturally occurring particles, such as desert dust and sea salt. As it is possible to\n\n\nchoose among a host of locations within a country that could affect readings, we homogenize our data\n\n\nto the center of each country’s capital city.\n\n\nSecond, we merge GDP per capita values, measured in 2017 international $ adjusted for purchasing\n\n\npower parity (PPP), from the World Bank’s World Development Indicators database (World Bank\n\n\n2021a).\n\n\nThird, we use\n\nMention: \"World Development Indicators database\""}, {"role": "assistant", "content": "{\"role\": \"supporting\", \"usage_action\": \"source\", \"summary\": \"GDP per capita in purchasing power adjusted terms is merged in as a country control.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:000648:5:0", "occurrence_id": "006d15984ff9b3d0f45e07a5", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: 2019), an essential predictor of stunting later in childhood (Christian et al., 2013). However, to the best of our\nknowledge no evidence yet exists that links the impacts of deforestation to stunting rates.\n\n\nIn this paper, we contribute to this emerging literature by taking a closer look at the water-borne channels and\nthe causal effects of forest loss on human health. Such an endeavor is challenging due to the multiple factors\ndetermining health outcomes and the degree of complementarity that must be accounted for by including\nsocioeconomic, demographic, infrastructure, environmental, behavioral, and institutional factors (Pattanayak &\nPfaff, 2009). We exploit the wealth of data available in the Demographic and Household Surveys (DHS), which\nincludes not only contemporaneous health and socioeconomic outcomes, but also full birth histories for all live\nbirths that occur in the years before the survey. We restrict our sample to 0.7 million children from rural areas 1 [^1: We restrict our sample to non-migrant children, i.e., children whose households have either always lived in their current\nlocation, or that have migrated to their current location before the child was conceived.]\nin 46 countries from 2000-2020 for which we have spatial coordinates. This allows us to link the health outcomes\nwith high-resolution deforestation data and study the effects of forest loss on the incidence of DD (by linking\nlags of forest loss to the survey year) as well as stunting (by linking lags of forest loss to the birth year).\n\n\nIdentifying health impacts of forest loss is challenging given a trade-off between health costs and economic\nbenefits that may be associated with agricultural expansion or urbanization following forest loss. To address the\npotential bias from non-random forest loss and confounding trends, we examine a possible water pathway from\ndeforestation to health outcomes by exploiting quasi-random variation in deforestation upstream to assess the\nimpacts on waterborne disease outcomes for rural households downstream. This allows us to isolate a waterspecific channel through which forest loss impacts health. We also\n\nMention: \"Demographic and Household Surveys\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"Health, socioeconomic outcomes and full birth histories are used, restricted to rural children.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:000657:19:0", "occurrence_id": "31e216e927085127852fe181", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: Figure 16: Household Food and Non-food Consumption, 2014/15\n\n\n\n\n\n\n\n\n\n_Source:_ Authors’ calculations using NBHS 2009 and NHBPS 2014/15.\n\n\nBoth food and non-food expenditures remain lower in rural Sudan compared to urban Sudan (Figure\n17). These differences are significantly higher for non-food expenditure, whereas only small differences\nexist for food expenditure. However, as there are differences in prices between the rural and urban\nareas, food consumption is likely higher in rural areas, something which is to be expected, due to the\nincreased physical demands of agrarian work. Differences in non-food consumption, where the urban\npopulation on average consumes almost twice the monetary amount as the rural sector, are unlikely to\nbe due to different prices. As we note in the next subsection, such non-food expenditure may account\nfor differences in asset ownership between urban and rural Sudan. Some assets, such as those that aid\nin communication and transport, can improve the productive capacity of farmers. Therefore, improving\nmarket infrastructure, to increase the opportunity for both food and non-food consumption in rural\nSudan, is vital for improving rural livelihoods and alleviating poverty.\n\n\nFigure 17: Per Capita Food and Non-food Consumption, 2014/15\n\n\n(a) Per Capita Non-food Consumption\n\n\n\n\n\n\n\n18\n\nMention: \"NBHS 2009\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"analyze\", \"summary\": \"Household food and non-food consumption is compared with the later round from this baseline.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:000657:19:0", "occurrence_id": "a3ca9e7d020baf29ca54161f", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: Figure 16: Household Food and Non-food Consumption, 2014/15\n\n\n\n\n\n\n\n\n\n_Source:_ Authors’ calculations using NBHS 2009 and NHBPS 2014/15.\n\n\nBoth food and non-food expenditures remain lower in rural Sudan compared to urban Sudan (Figure\n17). These differences are significantly higher for non-food expenditure, whereas only small differences\nexist for food expenditure. However, as there are differences in prices between the rural and urban\nareas, food consumption is likely higher in rural areas, something which is to be expected, due to the\nincreased physical demands of agrarian work. Differences in non-food consumption, where the urban\npopulation on average consumes almost twice the monetary amount as the rural sector, are unlikely to\nbe due to different prices. As we note in the next subsection, such non-food expenditure may account\nfor differences in asset ownership between urban and rural Sudan. Some assets, such as those that aid\nin communication and transport, can improve the productive capacity of farmers. Therefore, improving\nmarket infrastructure, to increase the opportunity for both food and non-food consumption in rural\nSudan, is vital for improving rural livelihoods and alleviating poverty.\n\n\nFigure 17: Per Capita Food and Non-food Consumption, 2014/15\n\n\n(a) Per Capita Non-food Consumption\n\n\n\n\n\n\n\n18\n\nMention: \"NHBPS 2014/15\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"analyze\", \"summary\": \"The 2014/15 consumption figures plotted are calculated from this household panel baseline.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:000649:40:2", "occurrence_id": "40c1168efc0a6f22f557a6cf", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: small flows (never above 1000 USD). Columns\n\n3–4 present the same estimates excluding large flows (top 1% of ODPs). Outcomes are\n\ndefined at the origin-destination-product-year level. FE stands for fixed effects. Tariffs are\n\ncontrolled for. Source: WITS and ALADI databases.\n\n\n39\n\nMention: \"WITS\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"Origin-destination-product trade outcomes and tariffs are compiled from this database.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:000649:40:2", "occurrence_id": "8e14e2b8509089ba3be538c8", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: small flows (never above 1000 USD). Columns\n\n3–4 present the same estimates excluding large flows (top 1% of ODPs). Outcomes are\n\ndefined at the origin-destination-product-year level. FE stands for fixed effects. Tariffs are\n\ncontrolled for. Source: WITS and ALADI databases.\n\n\n39\n\nMention: \"ALADI databases\""}, {"role": "assistant", "content": "{\"role\": \"supporting\", \"usage_action\": \"source\", \"summary\": \"The regional integration body's records complement the trade database.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:000661:7:0", "occurrence_id": "5ae89970d3b354c8565ab5aa", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: Looking at primary energy supply, combustible fuels (including coal, oil and gas) remain the most\npredominant energy source for MENA, accounting for over 87% of the region’s electricity in 2018.\nMeanwhile, the share of renewable energy remains relatively small and fell by 2.5 percentage points over\nthe observed timeframe, owing to a marginal rise in the use of other energy sources. On the other hand,\nECA presents a different profile. While combustible fuels are widespread in the region, they also utilize\nnuclear and other renewable energy sources for their supply. In 2018, the share of renewable energy\nincreased to 16.4% due to a decline in nuclear energy and combustible fuels. While this is positive, further\nefforts are required to transform the energy supply and cut emissions significantly. Given that renewables\nrepresent only a small portion of the total energy supply in both ECA and MENA, there is a large scope for\nintervention to switch to cleaner energy sources, especially in MENA. This will become increasingly\nimportant as there is growing pressure from governments and their citizens to respond to the climate\ncrisis.\n\n\nThe ECA region has experienced a steep and steady decline in energy intensity since 1990, having\ndecreased by almost 27% and narrowing the gap between energy intensity values compared to MENA.\nMeanwhile, similar to the trajectory of carbon emissions in absolute, per capita, and per US dollar of GDP\nterms, energy intensity in MENA has remained stable oscillating at around 100 and experiencing a 9.4%\ndecrease between 2005 and 2018. The discrepancy in the magnitude of the change between the two\nregions indicates that there is still much room for improvement for the MENA region, which could benefit\nsignificantly from further investments in energy efficiency.\n\n\n**_Figure 3. Breakdown of primary energy supply by fuel type (%)_**\n\n\nNote: Data represent unweighted averages across countries covered in Enterprise Surveys. Combustible fuels include\ncoal and peat, crude, natural gas liquids (NGL) and feedstocks\n\nMention: \"Enterprise Surveys\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"analyze\", \"summary\": \"The energy breakdown is an unweighted average across the countries these surveys cover.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:000675:33:0", "occurrence_id": "876d2435c2a1397d570ecf7b", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: **Figure 4.2: Regional Contributions to the Global Prosperity Gap**\n\n\n**Notes:** This figure reports the decomposition of the global estimate of 𝑊(𝑦, 𝑧) into contributions by regions using\nthe prosperity threshold of $25 per person per day in 2017 $PPP. See also Table 4.1.\n\n\nAlthough they measure different concepts, empirically changes over time in the prosperity\ngap and growth in the bottom 40 percent are similar at the country level. This can be seen in Figure\n4.3, which compares average annual growth in the bottom 40 percent (on the vertical axis) against\ngrowth in the prosperity gap (on the horizontal axis and multiplied by -1 so that positive growth\ncorresponds to an improvement in the prosperity gap). The left panel of Figure 4.3 considers the\nfull period 1990-2019 using the lined-up data discussed in Section 3.1, while the right panel\nfocuses on a smaller set of 53 “spells” of various lengths calculated between actual survey years\naround 2014 and around 2019. 31 Each panel includes the 45-degree line, with points above (below)\nthe line corresponding to episodes where average incomes in the bottom 40 percent improved\nfaster (slower) than the prosperity gap. Overall, the correlation between the two measures is high,\nwith most countries close to the 45-degree line.\n\n\n31 The comparable spells can be found in the Global Dataset for Shared Prosperity here:\nhttps://www.worldbank.org/en/topic/poverty/brief/global-database -of-shared-prosperity. Fifty-three countries have\ngrowth spells between -5% and 5%.\n\n\n31\n\nMention: \"Global Dataset for Shared Prosperity\""}, {"role": "assistant", "content": "{\"role\": \"supporting\", \"usage_action\": \"source\", \"summary\": \"Comparable growth spells are available in this dataset for the countries studied.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:000678:9:2", "occurrence_id": "99619d89c8c70f2a265eb712", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: a control and proxy\nfor the facility's resources.\n\n\n3.2. Key Variables and Summary Statistics\n\n\nWe first merge the SDI data set and the Master List of facilities which results in a subset of 2,578 facilities.\nThis means that 15% of the 2018 SDI facilities could not be found in Kenya's Master List of facilities. This final\nsample was complemented with information on road, electricity, and cellphone internet access, with\nadditional data described in the previous subsection. 11 [^11: The restricted sample works with the facilities that merges with the reviewed Master List. Moreover, an initial inclusion of “Distance to the nearest\nFacility” made it necessary to work with facilities in the 10,131 list.]\n\n\n7 D.J. Weiss, A. Nelson, H.S. Gibson, W. Temperley, S. Peedell, A. Lieber, M. Hancher, E. Poyart, S. Belchior, N. Fullman, B. Mappin, U. Dalrymple, J.\nRozier, T.C.D. Lucas, R.E. Howes, L.S. Tusting, S.Y. Kang, E. Cameron, D. Bisanzio, K.E. Battle, S. Bhatt, and P.W. Gething. A global map of travel time\nto cities to assess inequalities in accessibility in 2015. (2018). Nature. doi:10.1038/nature25181.\n8 For quality road we followed the definition of the Rural Access Index: “ _Good roads are paved roads that look dark and are not eroded. Fair roads_\n_are either paved roads in fair condition or good gravel roads that are motorable_ ” (Iimi, et al., 2016).\n9 10% of the Kenya Population and Housing Census (KPHC), randomly selected.\n10 The Kenya Integrated Household Budget Survey (KIHBS) conducted between 2015 and 2016.\n11 The restricted sample works with the facilities that merges\n\nMention: \"SDI data set\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"analyze\", \"summary\": \"Facility locations are merged with the national registry, leaving a sample of 2,578 matched facilities.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:000678:9:2", "occurrence_id": "0612a2cb2b24f9aa2168aaf2", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: a control and proxy\nfor the facility's resources.\n\n\n3.2. Key Variables and Summary Statistics\n\n\nWe first merge the SDI data set and the Master List of facilities which results in a subset of 2,578 facilities.\nThis means that 15% of the 2018 SDI facilities could not be found in Kenya's Master List of facilities. This final\nsample was complemented with information on road, electricity, and cellphone internet access, with\nadditional data described in the previous subsection. 11 [^11: The restricted sample works with the facilities that merges with the reviewed Master List. Moreover, an initial inclusion of “Distance to the nearest\nFacility” made it necessary to work with facilities in the 10,131 list.]\n\n\n7 D.J. Weiss, A. Nelson, H.S. Gibson, W. Temperley, S. Peedell, A. Lieber, M. Hancher, E. Poyart, S. Belchior, N. Fullman, B. Mappin, U. Dalrymple, J.\nRozier, T.C.D. Lucas, R.E. Howes, L.S. Tusting, S.Y. Kang, E. Cameron, D. Bisanzio, K.E. Battle, S. Bhatt, and P.W. Gething. A global map of travel time\nto cities to assess inequalities in accessibility in 2015. (2018). Nature. doi:10.1038/nature25181.\n8 For quality road we followed the definition of the Rural Access Index: “ _Good roads are paved roads that look dark and are not eroded. Fair roads_\n_are either paved roads in fair condition or good gravel roads that are motorable_ ” (Iimi, et al., 2016).\n9 10% of the Kenya Population and Housing Census (KPHC), randomly selected.\n10 The Kenya Integrated Household Budget Survey (KIHBS) conducted between 2015 and 2016.\n11 The restricted sample works with the facilities that merges\n\nMention: \"Master List of facilities\""}, {"role": "assistant", "content": "{\"role\": \"supporting\", \"usage_action\": \"validate\", \"summary\": \"Fifteen percent of mapped facilities could not be matched to this official registry.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:000690:33:1", "occurrence_id": "7d9d08a49d7d17e360e378a0", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: 285*** 0.349*** 0.350*** 0.592***\n(0.086) (0.049) (0.032) (0.082)\nPrecipitation -0.156** 0.474*** 0.267** 0.699***\n(0.072) (0.100) (0.110) (0.170)\nSubnational FE Yes No Yes No\nYear FE Yes No Yes No\nMean dependent var. 35.605 35.605 25.383 25.383\nObservations 4,129 1,019 4,129 1,019\nEquality test (Panel vs.\np = 0.383 p = 0.029\nlong differences)\n\nEquality test (country\np = 0.000 p = 0.000 p = 0.000 p = 0.000\nvs. subnational)\n\n\n\nNumber of countries 128 90 128 90\nNumber of regions 1,484 1,019 1,484 1,019\n_Notes:_ Robust standard errors in parentheses. Standard errors are clustered at the\ncountry level in Panel A and subnational level in Panel B. Regressions are\nweighted by region population. Inequality data are taken from the GSAP.\nInequality and weather variables in the long-differences model are measured by\nthe difference between averages of the earliest 3-year period and averages of the\nlatest 3-year period. The long differences estimation is based on cross-sectional\ndata with a smaller sample size compared with panel data. The data for the countrylevel analysis and the subnational-level analysis comes from our newly\nconstructed\n\nMention: \"GSAP\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"Subnational inequality measures are taken from this atlas for the weather regressions.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:000694:5:0", "occurrence_id": "2df4a08b7bd24093e35016f4", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: Before the pandemic hit, the labor market in Egypt faced persistent challenges. While Egypt’s GDP\ngrowth reached 5.6 percent in 2019, labor force participation continued to decline. This partly\nreflected challenges in absorbing the sustained growth in the country’s working-age population.\nEgypt's unemployment rate was high, particularly for women, youth, and the most highly educated,\nsignaling a difficulty in transitioning from school to work and in integrating women into the labor\nmarket. Furthermore, informality was high and increasing, reflecting the need to improve the quality\nof jobs. Jobs with no social security rose to encompass 67 percent of all jobs in 2018, up from 57\npercent in 2010. These trends reflected difficulties from the demand side of the labor market, where\nthe most productive sectors were not the most important in creating jobs. Pre-COVID labor market\ntrends pointed to the importance of accelerating private sector job creation. While about 78 percent\nof jobs in Egypt were in the private sector, this share remained well below the global average of 90\npercent, and about 3 in 4 private sector workers in Egypt were engaged in informal, low-quality\nactivities characterized by low productivity and low pay (Cortes et al. 2022).\n\nThe COVID-19 pandemic exerted its greatest impact on Egypt during the final quarter of FY20, with the\ndeclaration of a national public health emergency in mid-March 2020. That quarter overlapped with\nthe main lockdown implemented by the GoE. Mobility trends show how activity fell during the last\nquarter of FY20 and subsequently in workplaces, transit stations, and areas related to retail and trade.\nMobility and economic activity started to recover during FY21 (Figure 2).\n\n\nFigure 2: Mobility trends in Egypt, relative to February 2020 (pre-COVID-19)\n\n\n\n\n\n\n\nSource: Authors’ calculations based on Google COVID-19 Community Mobility Trends (as of March 2022).\n\n\nFollowing its mid-March 2020 emergency declaration, the\n\nMention: \"Google COVID-19 Community Mobility Trends\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"analyze\", \"summary\": \"Visits to place categories relative to February 2020 are calculated to show the recovery in activity.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:000686:5:0", "occurrence_id": "a41e4191af78cb0197dae294", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: We find that firms in the lower 25 th percentile of sales and the 75 th percentile of employment were more\naffected in the aftermath of Russia’s invasion of Ukraine than other firms. We try to explain the\nheterogeneity by examining two candidate structural factors: firms’ export links to Russia and digital gains\nprior to the invasion. Firms with export links to Russia are estimated to have suffered significantly more\nin terms of dropping sales and employment. We do not find any significant mitigating effect of digitization\nafter the invasion shock that the existing literature would suggest. However, the results suggest that\ndigitization helped firms increase employment on average during the studied period. While export links\nto Russia appear to increase sales on average during the studied period, this effect does not survive all\nthe robustness tests we apply.\n\n\nThe remainder of the paper is organized as follows. Section 2 describes the employed data and their\nsummary statistics. Section 3 explains the estimation approach and methodology. Section 4 discusses the\nresults. Section 5 concludes and highlights some policy implications.\n\n### 2. Data\n\nWe use data from the Business Pulse Survey (BPS) developed by the World Bank to measure the impact\nof the COVID-19 pandemic on the private sector. The Business Pulse Survey (BPS) is a novel dataset that\ntracks the potential impact of the pandemic on the private sector along critical dimensions of business\nperformance, such as sales revenue, liquidity, and solvency, labor adjustments, adoption of technology,\nbusiness expectations and uncertainty, and access to government support programs. In most countries,\nthe survey interviews were conducted over the phone. The data include micro, small, medium, and large\nbusinesses across all main sectors (i.e., agriculture, manufacturing, retail, and other services, including\nconstruction). The sampling frame excluded micro-firms and/or businesses in agriculture in some\ncountries. In other countries, when micro\n\nMention: \"Business Pulse Survey\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"This repeating survey tracks pandemic effects on the private sector across several dimensions.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:000705:2:0", "occurrence_id": "030ba8b990f17ebaa44b6728", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: #### **Digital Technology Uses among Microenterprises:** **Why Is Productive Use So Low across Sub-Saharan Africa?** Izak Atiyas and Mark A. Dutz 1\n\nKeywords: internet, smartphone, digital technologies, productivity, jobs, inclusion.\n\n\nJEL codes: D22, J24, L25, L86, O14, O33, O55.\n\n\n1 Affiliations: Atiyas (Economic Research Forum and TUSIAD-Sabanci University Competitiveness Forum), Dutz\n(Consultant, IFC). Corresponding author: mdutz@ifc.org. This research has received funding from the joint\nAfrica Chief Economist-Digital Development Research Program on Digital Transformation for Africa (project ID:\nP170151) and from IFC. The authors are grateful to Alison Gillwald and Onkokame Mothobi for making\navailable the RIA (Research ICT Africa) ICT Access business data for 2017-18 and for their support in the use of\nthese data.\n\nMention: \"ICT Access business data\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"Business ICT access data made available by the research network underpin the analysis.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:000715:13:1", "occurrence_id": "553ae74a0491e360eecba28f", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: and GWP data**\n\n\n**Notes:** Panel A shows the raw observed subjective well-being data circa 2000 from Desmet et al. (2018); Panel B shows\n\nthe scale for adjustment obtained with additional data on subjective well-being reflecting its subnational heterogeneity\n\nwithin countries; and Panel C shows the resulting adjusted well-being which is used in the quantification of migration\n\nfrictions.\n\n\n12 Further details on the data collection and assembling are provided in the appendix.\n\n\n12\n\nMention: \"GWP data\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"analyze\", \"summary\": \"Observed subjective well-being around 2000 and its subnational adjustment are drawn from this poll.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:000716:10:1", "occurrence_id": "48423e16228b08f2dfada1ce", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: -19 pandemic is still ongoing, and the surveys add a few\n\nnew interview questions over time, thus using the latest survey could help to examine the impact\n\nof COVID-19 more accurately. We also use the first-round survey to check the robustness and\n\ncompare the results with the results of the second-round survey to explore the dynamic of firm\n\nresponses during COVID-19.\n\n\nWe further collect country-level data from various sources. GDP per capita is from the World\n\nDevelopment Indicators database (WDI). The stringency of government policy to contain COVID\n19 is from Oxford COVID-19 Government Response Tracker (OxCGRT) database, which\n\nprovides information on the government policy responses to the COVID-19 pandemic across more\n\n\n9\n\nMention: \"World\n\nDevelopment Indicators database\""}, {"role": "assistant", "content": "{\"role\": \"supporting\", \"usage_action\": \"source\", \"summary\": \"Country-level GDP per capita is merged in as a control.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:000716:10:1", "occurrence_id": "1e1ac42a3fc011311baf1874", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: -19 pandemic is still ongoing, and the surveys add a few\n\nnew interview questions over time, thus using the latest survey could help to examine the impact\n\nof COVID-19 more accurately. We also use the first-round survey to check the robustness and\n\ncompare the results with the results of the second-round survey to explore the dynamic of firm\n\nresponses during COVID-19.\n\n\nWe further collect country-level data from various sources. GDP per capita is from the World\n\nDevelopment Indicators database (WDI). The stringency of government policy to contain COVID\n19 is from Oxford COVID-19 Government Response Tracker (OxCGRT) database, which\n\nprovides information on the government policy responses to the COVID-19 pandemic across more\n\n\n9\n\nMention: \"Oxford COVID-19 Government Response Tracker\""}, {"role": "assistant", "content": "{\"role\": \"supporting\", \"usage_action\": \"source\", \"summary\": \"Policy stringency across many countries is taken from this tracker.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:000717:4:0", "occurrence_id": "21ea5f564672a3f3e7e09309", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: From a policy perspective, the comprehensive environmental and tax structure of the\n\nIRENCGE-DF model makes it well suited for analyzing a wide range of policy scenarios. In\n\nparticular, the “Fit for 55” package is analyzed in the model by limiting the level of emissions and\n\nletting the model calculate the endogenous price consistent with this cap. Thanks to the extensive\n\nfocus on tax modeling, the IRENCGE-DF model is able to properly fit scenarios with new structures\n\nof tax rates based on the energy content and environmental performance of the fuels and electricity\n\nand also to simulate broader taxable bases by including more products in the scope and by removing\n\nsome of the current exemptions and reductions. Several simulation scenarios will be discussed in the\n\nfollowing sections.\n\n\nThe remainder of the paper is organized as follows. In Section 2, we present the data and\n\nmethodology, reviewing the main aspects of the IRENCGE-DF model. In the Section 3, we present\n\nthe results of our policy simulations. The final section concludes with some policy implications.\n\n##### **2 Data and Methodology** **2.1 SAM Construction**\n\nThe model is calibrated on the 2017 SAM. We update the benchmark data to 2020 by using\n\nmacroeconomic variations resulting from the latest public economic and financial documents (i.e.\n\nItalian annual budget law, etc.).\n\n\nThe information contained in the SAM is obtained by combining national account data, such as the\n\nnational account matrix for 2014, supply-use tables for 2017, and Eurostat data. In addition, we\n\nintegrate missing information with data from tax returns available at the Department of Finance.\n\n\nNational accounts data provide detailed information on the final and intermediate consumption at\n\nactivity and commodity levels, though they do not contain detailed information on taxation. Hence,\n\nwe use the tax return data to distribute taxes and subsidies per commodity. In Table 1, we provide a\n\ndescription of the sets and structure used in the analysis. For\n\nMention: \"Eurostat data\""}, {"role": "assistant", "content": "{\"role\": \"supporting\", \"usage_action\": \"source\", \"summary\": \"European statistics are combined with national accounts to construct the social accounting matrix.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:000727:47:14", "occurrence_id": "3acf8d49c197877a22ddaf73", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: 146\nsd 1.034 1.064 0.958 1.011 . 1.065 1.039 . . . 0.991 . 0.959\nobs 3325 3325 3324 3324 . 3323 3324 . . . 3324 . 3324\nCronbach's alpha 0.695 0.577 0.542 0.435 . . 0.400 . . . 0.421 . 0.505\n\n\n\nNote: nbr items stands for the number of items aggregated to construct the corresponding skills measure. sd stands for standard deviation and obs for the number of observations. Empty cells indicate that the project\ndoes not have data for the specified skill. PSDM stands for Problem Solving and Decision Making. The Facebook data is from the \"Future of Business (FoB)\" survey. This study includes only 15 Sub Saharan Africa (SSA)\ncountries namely: Angola, Benin, Botswana, Cameroon, Côte d'Ivoire, Ethiopia\n\nMention: \"Future of Business (FoB)\" survey\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"Skill measures for fifteen sub-Saharan countries come from this survey.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:000729:8:0", "occurrence_id": "ad721ce31a61a7747a3065f9", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: coupled with reforms that strengthen the private sector and improve the business environment. Furthermore,\n\n\nif the prevalence of training is to adapt and update skills of educated workers towards work in the private\n\n\nsector, then the policy implication is not only to increase university education, but also to ensure it serves\n\n\nthe private sector as well. Finally, firms with better management practices tend to provide more training in\n\n\nECA but not in MENA. This warrants further investigation and may be because managerial practices are\n\n\nquite poor in the region. These findings are important for the MENA context given the low provision of\n\n\ntraining in the formal private sector.\n\n\nIn summary, our study makes several contributions to the literature. First it explores the role of management\n\n\npractices and education of workers on formal training both at the intensive and extensive margin. Second\n\n\nit utilizes a panel data set to account for several firm-level characteristics to validate the findings. And\n\n\nfinally, it updates several studies in the literature by employing recent firm-level data that includes\n\n\neconomies across Europe, Central Asia, and the MENA region. The rest of the paper is structured as\n\n\nfollows. Section II describes the data. Section III provides the empirical specification and identification\n\n\nstrategy, while section IV provides the results, section V provides robustness checks, and section VI\n\n\nconcludes.\n\n\n**II.** **Data**\n\nThe main source of firm-level data is the World Bank’s Enterprise Surveys (ES). This includes two samples\n\n\nof medium and large enterprises. 3 The first sample includes cross-sectional firm-level surveys for 35\n\n\neconomies across ECA and MENA, all surveyed circa 2013 and 2019/2020, right before the Covid-19\n\n\n3 Medium and large enterprises are defined as having 20 or more employees. The choice of medium and large\nenterprises is due inclusion of management practices measures that were only collected for medium and large\nfirms. There are some small firms that are in the sample for two reasons\n\nMention: \"Enterprise Surveys\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"Two samples of medium and large enterprises across two regions form the main firm-level data.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:000767:43:0", "occurrence_id": "b8ff8874b3eb1f8b95be18d8", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: **A.1** **Example of data extraction and analysis**\n\n\nIn this section we exemplify how researchers can use our dataset for generating descriptive statistics about public procurement and budget execution across Brazilian municipalities.\nThe full documentation on using datasets hosted on the Data Basis platform can be found at\nhttps://basedosdados.github.io/mais (in Portuguese), including video tutorials and details on\nhow to create projects at Google BigQuery.\n\nHere we provide a simple example using the ‘basedosdados‘ R package. This package\nallows users to connect to their BigQuery projects (and billing ID) and directly make SQL\nqueries on BigQuery datasets, which are then loaded in R.\n\nThe SQL query presented below does the following: it connects to the _licitacao_ (tender)\ntable including tender-level information for all municipalities and years covered in our data\n(over 2.3 million unique tenders); it creates an indicator for when the modality is defined as\ncategories 8 (waiver) or 10 (non-requirement); then it computes the average share of tenders\nthat are non-competitive and the total number of tenders at the municipality-year level. The\nresulting table, loaded in the ‘data‘ object, includes 19,033 municipality-year observations.\nWhen executed, this query took 3 seconds to process the 2.3 million observations and provide\nus these summarized statistics.\n\nWe then can simply plot a histogram of the share of non-competitive tenders across municipality - year (in this case, we filter the dataset for observations with at least 50 tenders).\nWe present the results in Figure A.7. We can see that the average we describe in Table 2 of\n30%-40% masks substantial heterogeneity: while a substantial amount of municipalities in a\ngiven year do not use non-competitive modalities, in some municipalities the share of these\nis above three-quarters.\n\nMention: \"basedosdados\""}, {"role": "assistant", "content": "{\"role\": \"supporting\", \"usage_action\": \"inform\", \"summary\": \"This package connects users to cloud datasets so they can query them directly from the analysis environment.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:000807:22:1", "occurrence_id": "5616ef52509e7070d9dbf880", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: . 44 From\n\n\n38For the computation of fiscal multipliers below, we use quarterly data from IFS (IMF).\n39It is worth mentioning that the commodity price indices from Gruss and Kebhaj’s (2019) are countryspecific. Specifically, for each country, the change in the international price of up to 45 individual commodities is weighted using commodity-level data for the period 1962-2018.\n\n40If we use the Arellano-Bond estimator for dynamic linear panel methods to deal with lagged-dependent\nvariables, the same results hold for regressions (3) and (6). Also, using as controls world trade (as percentage\nof GDP) instead of terms of trade and public debt as percentage of GDP does not change the results.\n\n41Notice that regressions (4)-(6) control for the EMDE response by introducing an interactive term.\n42Since all variables are log-differences, the estimated coeffi cients are elasticities.\n43Comparing our quantitative estimates to those of other studies is not easy since empirical specifications\nvary considerably. With that caveat in mind, our estimates are very much comparable to those of, for\nexample, Richaud et al. (2019). Based on a sample of 87 EMDE commodity exporters, Richaud et al. report\na range of 0.34 to 1.25 percent for the cumulative impulse response of GDP to a one standard deviation shock\nin commodity prices. In our case, the sample is 11 EMDE with a coeffi cient range in the panel regressions\nin Table 3 of 0.063-0.085. Since the standard deviation of changes in commodity prices for EMDE is 14.4\npercent, the range for the impact on GDP is 0.92 to 1.22 percent. Notice that the comparison is valid\nbecause changes in commodity prices tend to be very persistent (see\n\nMention: \"IFS\""}, {"role": "assistant", "content": "{\"role\": \"supporting\", \"usage_action\": \"source\", \"summary\": \"Quarterly series from this fund statistic are used to compute fiscal multipliers.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:000818:47:1", "occurrence_id": "0d87565f1e81da335210840d", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: particularly in terms of its air, sea,\nland, and internet connections); 37 and its preparedness for rapid change and innovation (as\nmeasured by R&D expenditure, the number of new patents or the digital skills of the population,\nand the governments’ inability to provide a long-term vision). Since these supply gaps do not\nnecessarily constitute a binding constraint on growth and they are as much a cause as a\nconsequence of growth, the expected growth returns from filling the gaps are uncertain.\nNonetheless, they clearly point toward potential bottlenecks that must be assessed—and, if needed,\naddressed—as a matter of priority. 38\n\n\n36 The figure was constructed using the World Economic Forum’s Global Competitiveness Index (excluding those\nassociated with macro policy and the financial sector), which classifies indices of 130 indicators into seven categories:\n(i) Rule of law (security, violence, quality of police and the judiciary); (ii) Market support (the quality of laws and\nregulations in support of market activities); (iii) Infrastructure (transportation and communications); (iv) Social\ncapital; (v) Innovation (the country’s and the state’s preparedness for change); (vi) Health and human rights (the\nattention to basic human needs and rights); and (vii) Trade openness (the country’s openness to both foreign goods\nand foreign factors).\n\n37 For a recent assessment of LA’s shortfalls in infrastructure, which highlights the costly implications for growth and\nwelfare of gaps in transport infrastructure, see Perry, Guzmán and Benavides (2020).\n\n38 To better tailor policies to country circumstances, avoid unhelpful “laundry lists” of ill connected actions, and help\nidentify areas more amenable to reform and with larger expected impacts, policy makers can use a variety of tools\n\n\n46\n\nMention: \"Global Competitiveness Index\""}, {"role": "assistant", "content": "{\"role\": \"supporting\", \"usage_action\": \"source\", \"summary\": \"Selected indicators from 130 categories excluding macro policy and finance are used to build the connectivity figure.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:000819:40:0", "occurrence_id": "962dd43593895ff4f97787aa", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: **Figure 4: Total Number of Flight Departures over the Sample Period**\n\n\n**Notes:** The figure reports the total number of international flight departures observed in each year between\nthe African country pairs in our data sample. The value reported on top of each bar represents the number\nof bilateral country pairs contributing departures data to the reported totals, highlighting the unbalanced\nnature of our estimation sample. The reported number of international departures is measured in thousands.\nThe original data comes from the OAG flights database.\n\n\n39\n\nMention: \"OAG flights database\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"International flight departures between country pairs originate in this commercial flight schedule data.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:000836:33:1", "occurrence_id": "962da46515974759026e5cac", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: 462) (0.444) (0.431) (0.403)\n\nThriving 0.262 0.108 0.180*** 0.278*** 0.414***\n\n(0.440) (0.310) (0.385) (0.448) (0.493)\n\nStruggling 0.606 0.689 0.681*** 0.583*** 0.508***\n\n(0.489) (0.463) (0.466) (0.493) (0.500)\n\nSuffering 0.132 0.204 0.139*** 0.140*** 0.0781***\n\n(0.339) (0.403) (0.346) (0.347) (0.268)\n\nNumber of observations 388,602 69,101 106,410 100,728 112,363\n\n_Notes:_ Means calculated using sample-weighted individual-level data from the 2014-17 Gallup World Poll. Standard errors are in parentheses. Asterisks indicate\n\nwhether the difference in means is statistically significantly different from low-income countries.\n\n\n32\n\nMention: \"Gallup World Poll\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"analyze\", \"summary\": \"Sample-weighted individual means of thriving and struggling are computed on this poll.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:000847:10:0", "occurrence_id": "c75ede797b0a244bf96d7ebb", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: household’s recovery. While encouraging, these results show the joint effect\n\n\nof the basic program and top-ups, and not the isolated the effect of the latter.\n\n#### **3 The Pantawid Pamilyang Pilipino Program**\n\n\nThe 4P conditional cash transfer program was first introduced in 2008 by the\n\n\nDepartment of Social Welfare and Development (DSWD). After a very lim\n\nited pilot in 2007, the program started its geographic rollout in March 2008.\n\n\nOver the course of that year, 4P started operating in 160 municipalities in\n\n\n33 provinces representing all 17 regions. Geographic eligibility was based on\n\n\nthe poorest municipalities in the 20 poorest provinces, the poorest provinces\n\n\nin regions not covered by this criterion, and some pockets of poverty in ur\n\nban areas. In the first half of 2009, the program was expanded to cover all\n\n\nmunicipalities with a poverty index of 61.23 percent or more. This added\n\n\nanother 28 provinces and 140 municipalities to the area under coverage. In\n\n\n2010 the threshold for the municipal poverty index was dropped to 57.13 per\n\ncent and in 2011 to 36.99 percent. In 2011, the program also experienced its\n\n\nbiggest expansion by adding over 1.2 million households as beneficiaries as it\n\n\nextended to cover almost all provinces. After a further expansion in 2012 it\n\n\nfinally covered all municipalities in 2013. To determine household eligibility,\n\n\nsince 2010 it employs the proxy means test based _Listahanan_ registry. In ad\n\ndition to being considered poor according to _Listhanan_, eligible households\n\n\n9\n\nMention: \"_Listahanan_ registry\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"Household eligibility for transfers is determined by the proxy means test recorded in this registry.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:000854:10:0", "occurrence_id": "1a0ef27d1dadf17f5f9fe744", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: cashiers in a grocery store with 60 employees. When collecting the five data points under the _Parenthood_\n\nindicator, the research applies additional assumptions, such as that mothers and fathers have worked\n\nlong enough to accrue maternity, paternity, and parental benefits. 5 In each data collection cycle, specific\n\ntime frames are set, and only legislation entered into force in each time frame is measured. Only codified\n\nlaws (including codified customary laws) are considered in data collection. WBL data were collected from\n\nprimary legal sources and confirmed by local experts through the administration of standardized\n\nquestionnaires. Historical data on laws and regulations before 2009 and going back to 1970 were collected\n\nthrough desk research of the primary legal sources and consulted with secondary sources where the\n\nprimary ones could not be located. 6\n\n\nWe follow the WBL methodology in our analysis, and the total number of leave days available to a mother\n\nis calculated as the combination of maternity leave, parental leave days reserved for the mother and any\n\nadditional days that are not specifically reserved for the use of either parent. 7 Fathers’ leave is the sum of\n\npaternity leave days plus any days of parental leave specifically allocated to the father. In our analysis,\n\nonly paid leave is counted, and all leave days are calculated in calendar days. Continuing with the example\n\nof Germany, according to data for 2021, women in Germany are entitled to 98 days of maternity leave, 8\n\nwhile there is no provision in place granting paternity leave specifically (fathers’ leave is only covered\n\nunder parental leave policy). Thus, according to our method of counting leave days, total leave days for\n\nmothers is 458—of 98 maternity leave days, 60 parental leave days reserved for mothers, and 300\n\nunallocated parental leave days. Total leave days for fathers is 60 days, comprised\n\nMention: \"WBL data\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"Indicators are coded from primary legal sources and confirmed by local experts using standard questionnaires.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:000869:19:2", "occurrence_id": "78d83f5d4e0a5505f4af049e", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: lower-tax jurisdictions. A similar logic\napplies to top income earners. Consequently, corporate tax rates and personal income tax rates for the\ntop percentile declined in 65 countries over the period 1980-2007, whereas the median income tax\nrate rose, both of which have been attributed to rising globalization (Egger et al. 2019). This is\n\n\n6 “Trade taxes” is defined by the World Development Indicators as follows: “Taxes on international trade include import\nduties, export duties, profits of export or import monopolies, exchange profits, and exchange taxes.” As such, it does not\ninclude value added taxes levied on imported goods.\n\n18\n\nMention: \"World Development Indicators\""}, {"role": "assistant", "content": "{\"role\": \"supporting\", \"usage_action\": \"inform\", \"summary\": \"Its definition of trade taxes is quoted to clarify what the variable does and does not include.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:000870:21:0", "occurrence_id": "227e2ce843839f35f022df60", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: **Figure 4 Average MSE of Poverty Gap at 6.85 USD 2017 PPP, for LAC Countries**\n\n\n\n\n\nSource: Own estimations based on SEDLAC.\n\n\n**Inequality**\n\n\nThis section presents results for the three model variations when estimating the most standard inequality\nmeasure – the Gini coefficient. 22 [^22: This indicator measures how dispersed the income distribution is and takes values from 0 to 1, where 0 represents perfect\nequality and 1 stands for perfect inequality.] Results indicate that, like the case of the international upper poverty\nline, the prediction is similar for the three model variations in the short run, and the fit is generally\nreasonable (Figure 5). Still, errors increase with the distance between the baseline and the estimated\nyear. In addition, results show that the assessed variations tend to constantly overestimate inequality for\nsome countries (i.e., Bolivia, Costa Rica, El Salvador, Honduras, Mexico, Panama, Peru, and Paraguay)\nand underestimate it in others (like the Dominican Republic). Thus, the bias is not always in the same\ndirection or magnitude. For instance, the _new model with rescaling_ has the lowest gap in Bolivia in 2017\nbut the largest from 2018 through 2020.\n\n\nFigure 6 presents the MSEs for LAC countries by year and its trend to compare all the model variations\nover time. In this case, errors seem to increase in a linear pattern instead of the exponential-shaped trend\nobserved in the poverty and vulnerability indicators. Overall, results suggest that the _old model_ is the best\nvariation of the micro-simulation model to estimate inequality since its MSE is constantly lower than the\nother tested variations, except for atypical years such as 2020.\n\n\nIn summary, results suggest that no variation of the model should be considered a best-all-countries/allmeasures fit since country-specificities might arise. Depending on the purpose of the analysis, either the\n_new model without rescaling_ (poverty and vulnerability) or the _old model_ (inequality) might perform\nbetter.\n\nMention: \"SEDLAC\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"analyze\", \"summary\": \"Poverty gap estimates and their mean squared errors are computed on this regional household survey database.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:000910:25:1", "occurrence_id": "fbf521f7ea39a3f9c560f768", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: Distribution of Patients by Wealth Index and Treatment Status\n\n\n\n\n\n\n\n_Notes._ Kolmogorov-Smirnov test p-value = 0.325. Index range is observed range. Wealth\nindex is estimated following the methodology of the Kenya Demographic and Health Survey\nbased on household ownership of selected assets.\n\n\n24\n\nMention: \"Kenya Demographic and Health Survey\""}, {"role": "assistant", "content": "{\"role\": \"supporting\", \"usage_action\": \"inform\", \"summary\": \"Its asset-based methodology is followed to estimate the wealth index used for patient distribution.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:000923:23:0", "occurrence_id": "fa5284471880c27033a7e639", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: Table 2: Average treatment effects of German acquisition\non firm-level employment\n\n\nTWFE Doubly robust\n(1) (2)\n\n\nAverage treatment effect (German acquisition) 0.075** 0.112**\n(0.035) (0.038)\n\n\nEffect by treatment year\n2005 0.057** 0.059**\n(0.026) (0.028)\n2006 0.043* 0.045\n(0.026) (0.030)\n2007 0.040 0.068**\n(0.033) (0.029)\n2008 0.087** 0.117**\n(0.041) (0.047)\n2009 0.059 0.083*\n(0.039) (0.045)\n2010 0.096* 0.140**\n(0.052) (0.056)\n2011 0.117** 0.161***\n(0.052) (0.062)\n2012 0.070 0.177**\n(0.077) (0.079)\n\n\nNotes: Authors’ calculations based on Orbis data. Results include only firms\nestablished before 2004. The doubly robust estimator of Sant’Anna and Zhao\n(2020) in column (2) has been implemented using pre-treatment levels of employment, age, region and sectoral dummies as covariates. *10% level, **5%\nlevel, and ***1% level.\n\n\nTable 3: Effects of EU accession on firm performance across sectors\n\n\nDep. variable: Log TFPR Log revenue Log employment Log exports\n(1) (2) (3) (4)\n\n\nPost _×_ Germany’s export share (log) 0.048*** 0.082** 0.029 0.162**\n(0.017) (0.032) (0.023) (0.064)\nFirm FE Yes Yes Yes Yes\n\nMention: \"Orbis data\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"analyze\", \"summary\": \"Firm-level employment before and after German acquisition is estimated on this company database.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:000927:8:0", "occurrence_id": "125740a09eb2d717072c720d", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: estimated the number of poor people by calculating the number of individuals below the 2019 Guinean\n\n\npoverty line of 5,006,362 Guinean francs or $1,385 international dollars (purchasing power parity (2019);\n\n\n$) per year. [12] We considered total consumption expenditure as the wealth of individuals, and total\n\n\nconsumption expenditure minus OOP health expenditure as the impact of health expenditure on the\n\n\nwealth of individuals. We conducted the analyses for the entire population and by quintile. We calculated\n\n\nquintiles before and after health expenditures. For already poor individuals (individuals in quintiles 1 and\n\n\n2), the change in poverty was equal to their total consumption expenditures. [9]\n\n\nFor CHE and IHE, we considered all health expenditures as OOP health payments b ecause of the small\n\n\nproportion (3%) of individuals with some form of prepayment mechanism.\n\n\n**Identification of CHE and IHE drivers and estimation of the potential FRP of subsidies**\n\n\nWe defined the drivers of CHE and IHE as the expenditure categories resulting in the highest prevalences\n\n\nof CHE and IHE cases (previously calculated).\n\n\nWe estimated the FRP associated with THE and expenditure categories as the equivalent of the prevalence\n\n\nof CHE and IHE cases they induce. We estimated FRP for the entire population and by quintile. For IHE,\n\n\nquintiles were calculated before and after health expenditures.\n\n\nStatistical analyses were performed using STATA software (StataCorp LLC, College Station, TX, version\n\n\n16.1). We report the number of individuals at the national level rather than the number of respondents\n\n\nto the LSMS. Expenditure data were converted to 2019 international dollars using the rate 1 international\n\n\ndollar = 3,614 Guinean francs. [12]\n\n\n**\n\nMention: \"LSMS\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"analyze\", \"summary\": \"Expenditure data are converted to international dollars and used to count people below the national poverty line.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:000970:23:0", "occurrence_id": "5d68bc6e291ed771ca4609e3", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: Table 2: Village-Level Public Health Infrastructure\n\n\nHealth facility Connection Public program Auxiliary Female\nindex index index Nurse Midwife doctor\n(1) (2) (3) (4) (5)\n\n\nFraction of female leaders 1.730* 2.138*** 0.973** 0.980*** 0.837***\n(0.919) (0.528) (0.455) (0.246) (0.263)\nObservations 7,696 7,700 7,722 7,723 7,722\nOutcome mean 0.000 0.000 0.000 0.646 0.219\n\n\nState fixed effects x x x x x\nDistrict characteristics x x x x x\n\n\n_Notes_ : Data comes from the 2012-13 District-level Household and Facility Survey (DLHS) of India. The columns\npresent 2SLS estimates specified in the following equations:\n\n\n\n\n\n\n_j_\n\n\n\n\n\n\n_j_\n\n\n\n_Yvds_ = _β_ 0 + _β_ 1 _Fds_ + _β_ 2 _TCds_ +\n\n\n\n_φ_ 1 _jIjdsG_ ( _Mjds_ ) +\n\n\n\n_φ_ 2 _jIjds_ + _Zds_ _′_ _θ_ 2 + _δs_ + _ϵvds_ (4)\n\n\n\n_φ_ 2 _jIjds_ + _Z_ _′_\n\n\n\n\n\n\n_j_\n\n\n\n\n\n\n_j_\n\n\n\n_α_ 2 _jIjds_ + _Zds_ _′_<\n\nMention: \"District-level Household and Facility Survey\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"analyze\", \"summary\": \"Village-level public health infrastructure indices are constructed from this district survey.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:000988:21:0", "occurrence_id": "58e0d6d43a41f78464793985", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: **Figure 1. Timeline of Implementation and Data Collection**\n\n\n**Figure 1. Percent of Treatment Students that used ALEKS at least one Minute**\n\n\n\n\n\n\n\n\n\nSource: Authors using take-up data from ALEKS software.\n\n\n20\n\nMention: \"take-up data from ALEKS software\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"Software logs show the share of treatment students who used the programme at all.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:000994:49:0", "occurrence_id": "0e6c4cd4af7286822d74614f", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: **Figure** **A2:** Cross-sectional average earnings and transfers\n\n\nfactory earnings, both in the 3 months prior to the survey (in FCFA).\nEarnings from factory administrative data. Transfers from 2 rounds of\nworker phone surveys. Amount transferred in the 15 days prior to the\nsurvey. Observations residualized from survey fixed effects. Transfers\ntop-coded at the 99th percentile. Line of best linear fit reported. 349\nobservations, from workers not offered a Private savings account.\n\n\n47\n\nMention: \"factory administrative data\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"Earnings in the three months before the survey are taken from employer records.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:000997:13:0", "occurrence_id": "b225014c7e74bfd1b686437b", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: The regions of Bongolava and Sofia have the highest percentages of children weighing less than 2.5\nkg, with 19% and 17%, respectively. On the other hand, the regions of Ihorombe and Anosy have the\nlowest percentages of low-birth-weight children, at around 8%. In other words, stunting seems\nprevalent in the least poor regions of Madagascar and less prevalent in the poorest regions. These\nfindings emphasize the importance of regional context in addressing child undernutrition, highlighting\nthe need for tailored approaches that consider socioeconomic factors, health care access, and\nnutritional practices to improve child health outcomes across Madagascar.\n\nBut these heterogeneities also exist within regions at the commune level. We therefore applied the\nSAE approach in the DHS data to produce stunting estimates at the commune level and produce the\nmap presented under figure 3. The maps highlight higher stunting rates among communes located in\nhigh plateau of the regions in the center, also known for its better agro-ecological advantage for\nagricultural production. We also note the higher stunting rates among communes in the regions in the\neast and southeast of the country.\n\nLinguistic, historical, and DNA research suggests that the central highlands of Madagascar were settled\nby people with an Austronesian background 1,200 years ago (most likely South Borneo); the coastal\nareas were settled later by people mainly from East Africa (Hurles et al 2005). Can this partly explain\nthe stunting patterns? Our limited data does not allow us to verify this hypothesis.\n\nThe variables selected to predict stunting as well as the resulting coefficients from the linear mixed\nmodel is provided in table A2 of the annex. Table 4 presents a set of model diagnostics relating to\nthe fit of the model and the consistency of the normality assumptions with the sample data. Overall,\nthe model explains 7.5 percent of the variation in heigh for age Z score when not considering the\nconditional random effect, and 11.3 percent when the\n\nMention: \"DHS data\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"analyze\", \"summary\": \"A small-area estimation approach is applied to produce stunting estimates at commune level.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:001003:26:1", "occurrence_id": "bc734b335f2c1a94ea5ede6b", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: > 36.2\n\n\n\nSource: Author calculations based on HIES 2018-19 data\n\n\n**Comparability of expenditure and income data.** In most developing countries, consumption expenditure\nis used as a proxy for welfare. Theoretically, consumption is likely to remain more stable over time than\nincome, which can be affected by seasonality and other shocks. Practically, it is extremely difficult to\ncollect accurate income data in developing economies with high informality, a large prevalence of self-\nemployment or own-account workers, reliance on foreign remittances, in addition to smallholder\nagricultural production for home use. Income measures are especially problematic due to difficulties in\nestimating self-employment profits, falsified responses and underestimation (Deaton and Zaidi 2002;\nDeaton 2019). For these reasons, even though the HIES collects data on income, it is more reliable to\ncontinue using consumption as a proxy for income in the REM approach.\n\nFor comparison, household income aggregates were estimated using the data in HIES 2018-19. A\nhousehold’s total income is given by the sum of all the following sources:\n\n\n1) Work or job-related annual income from main, secondary and other occupations;\n2) In-kind payments for employment as well as transfers such as pensions;\n3) Main and secondary income from agriculture (including in-kind transfers) for those in\nagriculture;\n4) Unearned income sources including local and international remittances, Zakat/Ushr,\ninheritances, income from insurance, the Benazir Income Support Programme;\n5) Income earned (rents or sales)\n\nMention: \"HIES 2018-19\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"analyze\", \"summary\": \"Household income aggregates are built from its multiple income sources to compare with consumption.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:001013:11:0", "occurrence_id": "f8cbb1532a84ed86fdd47093", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: We contribute to this literature by tracking monthly changes in household expenditure\n\n\nand income following the Kerala floods. The results in section 6 show a persistent decline in\n\n\nhousehold expenditure, particularly non-essential expenditure, despite a quick recovery and\n\n\nsubsequent increase household income. The flood also affected the composition of household\n\n\ndebt and savings. In section 7, we show that households were more likely to borrow for\n\n\nhousing and medical purposes, and less likely to borrow for consumption.\n\n\n**4.** **Data,** **Samples,** **and** **Summary** **Statistics**\n\n\nOur analysis employs numerous district-level and household-level variables from various\n\n\nsources. This section describes the data, discusses the sample selection, and reports summary\n\n\nstatistics.\n\n\n**4.1** **Data**\n\n\n_Nighttime_ _Lights_\n\n\nNighttime lights are a widely used proxy for aggregate economic activity. 14 Felbermayr et\n\n\nal. (2022) use nighttime lights to investigate the impact of weather anomalies on economic\n\n\nactivity. In India, they have been used to analyze the spatial impact of demonetization\n\n\n(Chodorow-Reich et al. 2020), regional convergence (Chanda and Kabiraj 2020), and the\n\n\nheterogeneous impact of the COVID-19 pandemic (Beyer, Franco-Bedoya, and Galdo 2021,\n\n\nBeyer, Jain, and Sinha 2021). To translate changes in nighttime lights into changes in\n\n\neconomic activity, we rely on the quarterly elasticity estimated by Beyer, Hu, and Yao (2022).\n\n\nAlthough nighttime lights data are very noisy over time, they are useful for difference-in\n\ndifference analyses since most of the noise is common across the treated and untreated units.\n\n\nWe extract district level nighttime light data from the Visible and Infrared Imaging\n\n\nSuite Day Night Band (VIIRS-DNB) Cloud Free Monthly Composites (\n\nMention: \"Visible and Infrared Imaging\n\n\nSuite Day Night Band\""}, {"role": "assistant", "content": "{\"role\": \"supporting\", \"usage_action\": \"analyze\", \"summary\": \"District night-time light values are extracted to support the difference-in-differences design.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:001013:11:0", "occurrence_id": "f1ec71dc7b0ecf5b5c378296", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: We contribute to this literature by tracking monthly changes in household expenditure\n\n\nand income following the Kerala floods. The results in section 6 show a persistent decline in\n\n\nhousehold expenditure, particularly non-essential expenditure, despite a quick recovery and\n\n\nsubsequent increase household income. The flood also affected the composition of household\n\n\ndebt and savings. In section 7, we show that households were more likely to borrow for\n\n\nhousing and medical purposes, and less likely to borrow for consumption.\n\n\n**4.** **Data,** **Samples,** **and** **Summary** **Statistics**\n\n\nOur analysis employs numerous district-level and household-level variables from various\n\n\nsources. This section describes the data, discusses the sample selection, and reports summary\n\n\nstatistics.\n\n\n**4.1** **Data**\n\n\n_Nighttime_ _Lights_\n\n\nNighttime lights are a widely used proxy for aggregate economic activity. 14 Felbermayr et\n\n\nal. (2022) use nighttime lights to investigate the impact of weather anomalies on economic\n\n\nactivity. In India, they have been used to analyze the spatial impact of demonetization\n\n\n(Chodorow-Reich et al. 2020), regional convergence (Chanda and Kabiraj 2020), and the\n\n\nheterogeneous impact of the COVID-19 pandemic (Beyer, Franco-Bedoya, and Galdo 2021,\n\n\nBeyer, Jain, and Sinha 2021). To translate changes in nighttime lights into changes in\n\n\neconomic activity, we rely on the quarterly elasticity estimated by Beyer, Hu, and Yao (2022).\n\n\nAlthough nighttime lights data are very noisy over time, they are useful for difference-in\n\ndifference analyses since most of the noise is common across the treated and untreated units.\n\n\nWe extract district level nighttime light data from the Visible and Infrared Imaging\n\n\nSuite Day Night Band (VIIRS-DNB) Cloud Free Monthly Composites (\n\nMention: \"Cloud Free Monthly Composites\""}, {"role": "assistant", "content": "{\"role\": \"supporting\", \"usage_action\": \"source\", \"summary\": \"The monthly cloud-free product is the specific extract used.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:001066:6:0", "occurrence_id": "34da31540e93b7d7c1157d26", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: descriptive statistics and trends of the data, using some country specific examples. Section 4 outlines the\nmethodology and framework we use for our empirical specifications. Section 5 presents the results of our analysis,\nand section 6 concludes.\n\n\n**2. Data**\n\n\nWe use data from a global survey on _COVID-19 Beliefs, Behaviors and Norms_ jointly conducted by researchers at\nthe Massachusetts Institute of Technology, Facebook, Johns Hopkins University (JHU), the World Health\nOrganization (WHO), and the Global Outbreak Alert and Response Network (GOARN). The survey was\nadministered via Facebook to a sample of its users in 67 countries from August 2020 to March 2021. We restrict\nour main analysis to 18 countries for which data is available over multiple waves. 5 While survey respondents are\nmostly urban, aged between 20-50 years and with tertiary education, the data contain weights to represent each\ncountry's adult or Internet-using population, rather than just Facebook users, and to reduce bias due to\nnonresponse.\n\n\nThe survey contains information on willingness to be vaccinated, perception of community norms around\npreventive behaviors, access to information about the virus and trust in media and the government. It also\nincludes data on individual characteristics and personal experience of the pandemic, with regard to health and\nemployment. Some summary statistics of the data are presented in Table 1. 6 Globally, 69 percent of the sample\nreport that they will accept the vaccine with some regional variation ranging from slightly above 50 percent in\nNorth America to relatively higher acceptance in South Asia at around 75 percent (Figure 1). 7\n\n\n**Figure 1** : Vaccine acceptance around the world\n\n\nSource: Authors calculations using the Facebook COVID-19 Beliefs, Behaviors & Norms Survey (2021). Data are weighted using sample\nsurvey weights.\n\n\n5\n\nMention: \"Facebook COVID-19 Beliefs, Behaviors & Norms Survey\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"Weighted responses give vaccine acceptance by region.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:001083:17:1", "occurrence_id": "733db22aeb97f509a7323e69", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: >model.|Endogenous LBD|\n|**WITCH**|transport, industry and
residential/commercial|Passengers and freight vehicles (both distinguished
according to traditional combustion, hybrid, plug in
hybrid and electric). The composition of vehicles is
determined by a Leontief function of a range of costs
(including battery, O&M, fuel and carbon costs)|Partly endogenous|\n|**C3IAM**|transport, industry and
residential/commercial|Intercity passenger transport, urban passenger
transport and freight transport. Urban passenger
transport is divided into public transport (bus and rail
transit), taxi, and private vehicles (cars and electric
bikes). Intercity passenger transport is divided into
private vehicles and four main business intercity
passenger transport (road transport, railway
transport, aviation and waterway transport). Freight
transport is divided into five main types: road
transport, railway transport, aviation transport,
waterway and pipeline transport.|Exogenous|\n|**BET EMF33**|Transport, Power, Heat|Passenger and freight|Exogenous|\n|**AIM-CGE**|Industry, residential,
commercial, transport|Road, Railway, Waterways, Air transport|Exogenous|\n|**GEM-E3-ICCS**|Firms, households|As regards the transport modes, the sectorial split
follows and further extends the classification used by
the GTAP database. This extension splits the GTAP
data in passenger and freight transport by mode and
further disaggregates the modes into rail and road as|Exogenous\n\nMention: \"GTAP database\""}, {"role": "assistant", "content": "{\"role\": \"supporting\", \"usage_action\": \"inform\", \"summary\": \"Its sectoral classification is the base that the model's transport split extends.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:001120:11:0", "occurrence_id": "5f4937a15286b781f506ba7f", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: The analysis using the customs data, which helps validate the results from BPS data, estimates\n\na simpler version of Equation (1) described in Appendix B. The results of this estimation are\n\nrepresented graphically, as before showing marginal effects along with 95% confidence intervals.\nThere are two important differences across the BPS and the customs data analyses. _First_, monthly\ncustoms outcomes are aggregated and the analysis is conducted with data at the country-firmquarterly level. _Second_, since the customs data comprise only trading firms, only trade-related\n\noutcomes from BPS data are compared using the customs data. Further, when drawing comparisons\n\n\nwith the customs data, we restrict the sample of BPS data to include only exporters or importers.\n\n\nTo capture the global engagement of firms, we construct several measures using the BPS data. Two\n\n\nstandard measures are indicator variables, one for whether the firm exports and one for whether the\n\n\nfirm imports before the pandemic in 2019. These two measures capture firms’ direct engagement in\n\nglobal markets. Another measure is an indicator variable for firms that both export _and_ import, that\n\nare designated as GVC firms. The final and more novel measure captures firms’ indirect engagement\n\n\nin global markets through an indicator variable for whether the firm sold to domestic exporters or\n\nmultinationals in 2019 but did not directly export or import. We refer to these firms as suppliers\n\nof GVC firms. Since these four measures may not be mutually exclusive, we also construct four\n\n\nmutually exclusive categories of global engagement to contrast with firms that had no engagement\n\n\nat all: only indirect engagement; only direct engagement (export or import); both indirect and direct\n\nengagement (with direct engagement being measured with either export or import), and finally\n\n\nfirms that are indirectly engaged and are also a GVC firm in 2019. Except for the indicator variable\n\nfor firms that export, other measures of global engagement are only available for the countries\n\n\nsurveyed in round 3 including the trade module. Hence, the analysis\n\nMention: \"BPS data\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"validate\", \"summary\": \"Customs records are used to check the results previously obtained from this business survey.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:001131:4:1", "occurrence_id": "79b5edb466e436ca61dec611", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: the last 50 years. Our idea was to elicit their views\n\n\nwithout specifically referring to certain crises. The second question asked them to order from first to third the worst\n\n\ncrises in Colombia during the last 10 years, with the following options: illegal drug trafficking, internal armed conflict,\n\n\nand COVID-19. 4 Responses to both questions confirmed that our treatment increased the salience of the pandemic.\n\n\nIndividuals in the treatment group raised the COVID-19 crisis in the open-ended question more often than did the\n\n\ncontrol group. They also ranked COVID-19 as a worse crisis than illegal drug trafficking and internal armed conflict.\n\n\nWe document four main findings. First, our results strongly support the validity of the _resentment channel_ whereby\n\n\ntreated natives resent migrants during economic crises. In particular, treated individuals consistently reported more\n\n\nnegative attitudes towards migrants than did the control group. Natives primed with the COVID treatment were less\n\n\nlikely to think an immigrant was poor due to circumstances beyond their control (0.07 standard deviations (sd) lower\n\n\nthan the control group). These same natives were more likely to hold negative opinions about both the economic\n\n\nimpacts of migrants (0.07 sd lower than the control group) and about their tax contributions (0.19 sd lower than the\n\n\ncontrol group). The effects are small for the first two outcomes but larger for the latter case. These responses may\n\n\n2In practice, migration from Venezuela to Colombia is likely higher still as many migrants may never formally register due to fear of deportation.\n3There is also evidence that attitudes towards migrants in Colombia have deteriorated: according to Gallup’s Migrant Acceptance Index, it ranks\nthird among countries where acceptance dropped the most between 2016 and 2019.\n\n4Of course, there have been other crises in Colombia during this period; this list did not intend to be comprehensive but only to offer relevant\noptions besides COVID-19).\n\nMention: \"Migrant Acceptance Index\""}, {"role": "assistant", "content": "{\"role\": \"supporting\", \"usage_action\": \"source\", \"summary\": \"Its ranking documents the fall in acceptance of migrants over this period.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:001150:6:0", "occurrence_id": "db806eca418634260004f790", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: To better understand how our experimental sample compared to the average property in\n\n\nDar es Salaam, we matched our experimental data to a set of data comprising every parcel in\n\n\nTRA’s database for the city. Out of approximately 830,000 parcels in the city, nearly 30 percent\n\n\nare owned by a taxpayer in our experimental sample. Parcels included in our experiment were\n\n\nonly slightly (1.4 percentage points) less likely to have been issued a bill. Of those that were\n\n\nissued bills, only 35 percent of properties in the experimental sample had been valued by the\n\n\nTRA, as opposed to 74 percent in the rest of the city (those that were not valued were charged\n\n\na TSh 10,000 flat tax). Conditional on being billed and rated, the median value for properties\n\n\nincluded in the experiment was higher, approximately 31.2 million TSh (13,500 USD) versus 20\n\n\nmillion TSh (8,600 USD) for the rest of the city. Properties that were billed and rated faced,\n\n\non average, an annual tax rate of approximately 0.16% of the property’s rated value.\n\n\n**3.2** **Treatments**\n\n\nIn collaboration with the Tanzania Revenue Authority, we randomized each property owner\n\ninto one of five groups. 3 The treatments are summarized in Table 1. The control was not to\n\n\nreceive any message from the TRA. Group T1 received a simple message reminding them to pay\n\n\ntheir property tax, indicating the due date (June 30th) and providing information the taxpayers\n\n\ncould use to contact the TRA in case they had any questions. All other treatments included\n\n\nthis reminder message.\n\n\nTreatment 2 added a ‘reciprocity’ message, where taxpayers were reminded that taxes fund\n\n\nsocial services and infrastructure and finished with the TRA’s slogan “Together we build our\n\n\nNation.” Treatment 3 included the simple reminder as well as a ’social pressure’\n\nMention: \"TRA’s database\""}, {"role": "assistant", "content": "{\"role\": \"supporting\", \"usage_action\": \"validate\", \"summary\": \"Every parcel in the city is compared with the experimental sample to assess representativeness.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:001132:1:0", "occurrence_id": "a229b88ed9f7eff2509c3cb3", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: Policy Research Working Paper 1394\n\n##### **Abstract**\n\nThis paper quantifies the impact of effective corporate tax\n\nrates on aggregate total factor productivity. Using Chilean manufacturing data, the paper documents a large\ndispersion in the effective tax rate faced by firms and a\nmass of firms facing a 0 percent tax rate. These empirical\npatterns are incorporated into a standard monopolistic\ncompetition model with corporate tax rates. The paper’s\nquantitative findings show that the TFP gains between the\n\n\n\neconomy implied by the Chilean tax code of 1998–2007\nand a hypothetical economy without effective corporate\ntax rate inefficiencies are between 4 and 11 percent. The\npaper considers counterfactual policies in which all firms\nface the same tax rate and finds a monotonically decreasing\nrelationship between the level of the tax rate and total factor\nproductivity.\n\n\n\nThis paper is a product of the Finance, Competitiveness and Innovation Global Practice. It is part of a larger effort by the\nWorld Bank to provide open access to its research and make a contribution to development policy discussions around the\n\nworld. Policy Research Working Papers are also posted on the Web at http://www.worldbank.org/prwp. The authors may\nbe contacted at fpatinopena@worldbank.org and mdiner@wharton.upenn.edu.\n\n\n_The Policy Research Working Paper Series disseminates the findings of work in progress to encourage the exchange of ideas about development_\n_issues. An objective of the series is to get the findings out quickly, even if the presentations are less than fully polished. The papers carry the_\n_names of the authors and should be cited accordingly. The findings, interpretations, and conclusions expressed in this paper are entirely those_\n_of the authors. They do not necessarily represent the views of the International Bank for Reconstruction and Development/World Bank and_\n_its affiliated organizations, or those of the Executive Directors of the World Bank or the governments they represent._\n\n\nProduced by the Research Support\n\nMention: \"Chilean manufacturing data\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"analyze\", \"summary\": \"Firm-level effective tax rates and productivity are documented from these plant records.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:001175:3:1", "occurrence_id": "ce28411da4e03e3df41e6cc6", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: activity, owing to Nepal being a highly rural economy. And while the\neconomy is shifting away from agriculture, and jobs created over the last decade have been a mix of low- and\nhigh-productivity in industry and service sectors, men have benefitted disproportionately. Of the 3.8 million\nnew wage jobs added to the economy by 2018, men took up over two-thirds of those jobs (Ruppert Bulmer,\n2020), including jobs in manufacturing, finance, and business services sectors. These outcomes cannot be\nexplained by Nepali women’s education levels – progress in educational attainment of girls is sizable and\nwomen enjoy high returns to education (Ruppert Bulmer et al., 2020). 4 [^4: Over the last three decades, women achieved strong education gains. Average years of schooling rose from 2 years for\nfemales born in 1960 to over 9 years for those born after 1990. A woman with a college degree, on average, earns double\nwhat a woman with incomplete primary earns, controlling for sector of work and other factors (Ruppert Bulmer et al. 2020).]\n\n\nYoung women, particularly married ones, have low attachment to the labor market. Nearly half (47 percent)\nof them are not in employment, education, or training (NEET), vs. 22 percent of young men. 5 [^5: Nepal Labor Force Survey 2017/2018.] Over a third\nof young married women aged 20 and 24 report to not have done any work other than housework in the 12\nmonths before the 2022 Nepal Demographics and Health Survey (DHS), as compared to three percent of\nyoung married men within the same age group. Social norms related to the unequal gender roles in families may\ncompel women to shoulder a disproportionate burden of household work, thereby reducing their availability\nfor wage employment and restricting them to jobs with lower employment potential than men. Women are\nmore likely than men to be in unpaid farm work\n\nMention: \"Nepal Labor Force Survey\""}, {"role": "assistant", "content": "{\"role\": \"supporting\", \"usage_action\": \"source\", \"summary\": \"The share of young people not in employment, education or training is reported from this survey.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:001175:3:1", "occurrence_id": "b5af68a3cee1b92c72585527", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: activity, owing to Nepal being a highly rural economy. And while the\neconomy is shifting away from agriculture, and jobs created over the last decade have been a mix of low- and\nhigh-productivity in industry and service sectors, men have benefitted disproportionately. Of the 3.8 million\nnew wage jobs added to the economy by 2018, men took up over two-thirds of those jobs (Ruppert Bulmer,\n2020), including jobs in manufacturing, finance, and business services sectors. These outcomes cannot be\nexplained by Nepali women’s education levels – progress in educational attainment of girls is sizable and\nwomen enjoy high returns to education (Ruppert Bulmer et al., 2020). 4 [^4: Over the last three decades, women achieved strong education gains. Average years of schooling rose from 2 years for\nfemales born in 1960 to over 9 years for those born after 1990. A woman with a college degree, on average, earns double\nwhat a woman with incomplete primary earns, controlling for sector of work and other factors (Ruppert Bulmer et al. 2020).]\n\n\nYoung women, particularly married ones, have low attachment to the labor market. Nearly half (47 percent)\nof them are not in employment, education, or training (NEET), vs. 22 percent of young men. 5 [^5: Nepal Labor Force Survey 2017/2018.] Over a third\nof young married women aged 20 and 24 report to not have done any work other than housework in the 12\nmonths before the 2022 Nepal Demographics and Health Survey (DHS), as compared to three percent of\nyoung married men within the same age group. Social norms related to the unequal gender roles in families may\ncompel women to shoulder a disproportionate burden of household work, thereby reducing their availability\nfor wage employment and restricting them to jobs with lower employment potential than men. Women are\nmore likely than men to be in unpaid farm work\n\nMention: \"2022 Nepal Demographics and Health Survey\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"Unpaid housework reported by young married women and men is measured in this survey.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:001180:6:0", "occurrence_id": "ab5ec6469f88f558b26d63bd", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: The second set of findings focuses on the magnitude and persistence of the parenthood penalty\n\n\nacross various subgroups in Indonesia. These results offer important insights for policymakers\n\n\nseeking to target interventions effectively. First, we found that households with an extended fam\n\nily member living in the household experienced the fastest recovery from the birth penalty. For\n\n\nthese households, the penalty became insignificant by the second year after childbirth. In con\n\ntrast, for households without extended family members, the penalty persisted until year seven.\n\n\nSecond, we observe significant differences in the magnitude and persistence of the birth penalty\n\n\nbased on education level. Highly educated individuals faced larger penalties (approximately 30%\n\n\nin the first year) and for a longer period compared to their less educated counterparts (around\n\n\n20% in the first year). Furthermore, we find that rural women experienced the highest birth\n\n\npenalty in year three, after which the trend began to reverse. In contrast, urban women saw\n\n\nthis reversal begin in year four. These results suggest that expanding access to childcare could\n\n\nsignificantly reduce the persistence of the birth penalty, particularly for highly educated urban\n\n\nwomen, who experienced the largest and most persistent penalties. This subgroup represents\n\n\nan important target for policy interventions, where childcare provision could have the greatest\n\n\nimpact.\n\n\nThe rest of the paper is structured as follows. Section 2 provides an overview of the Indonesia\n\n\nFamily Life Survey (IFLS) data and the institutional context of the Indonesian labor market.\n\n\nSection 3 outlines our empirical strategy, including the DID methodology and the identification\n\n\nassumptions. Section 4 presents our main findings, including a detailed heterogeneity analysis\n\n\nand robustness checks. Finally, Section 5 discusses the policy implications of our findings and\n\n\nconcludes with suggestions for future research.\n\n##### **2 Institutional Context, Data, and Descriptive Statistics**\n\n\n**2.1** **The Indonesia Family Life Survey**\n\n\nThe Indonesian Family Life Survey (IFLS) is a longitudinal multitopic household survey that is\n\n\nrepresentative of 83% of\n\nMention: \"Indonesia\n\n\nFamily Life Survey\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"Its household panel provides the data underlying the difference-in-differences design on parenthood penalties.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:001185:24:0", "occurrence_id": "1917605a10ed2946947df45e", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: ##### **Appendix A Additional Figures**\n\n**Figure A.1:** Percent Change in Speed based on Google Data and Uber Data\n\n\n**Figure A.2:** Speed versus Congestion Hourly, Before and After the Curfew Policy in 2020\n\n\n23\n\nMention: \"Google Data\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"analyze\", \"summary\": \"Travel speed changes are computed from this navigation data alongside ride-hailing records.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:001185:24:0", "occurrence_id": "231feec0b6b50812cbf6265e", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: ##### **Appendix A Additional Figures**\n\n**Figure A.1:** Percent Change in Speed based on Google Data and Uber Data\n\n\n**Figure A.2:** Speed versus Congestion Hourly, Before and After the Curfew Policy in 2020\n\n\n23\n\nMention: \"Uber Data\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"analyze\", \"summary\": \"Trip speeds from this operator are used with the other source to assess the curfew's congestion effects.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:001190:18:0", "occurrence_id": "72a5b182992de6978be64071", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: interaction term between bank credit and a proxy measure of the level of competition in the\n\n\nbanking industry which equals the assets of the five largest banks in the country-year as a share of\n\n\ntotal commercial banking assets ( _5-bank asset concentration_ ). For robustness, we also report\n\n\nresults using a similar index for the three largest banks (3 _-bank asset concentration_ ). Higher values\n\n\nof the concentration indices imply less competition in the banking industry. The data source is\n\n\nGFDD, World Bank.\n\n\nIn all the heterogeneity estimations, we include as controls interaction terms between bank\n\n\ncredit and the following variables (defined above): log of GDP per capita, log of number of\n\n\nworkers at the firm (firm size), log of age of the firm., and labor productivity of the firm (logs).\n\n\nThese controls guard against the possibility that our main interaction term (as stated in Hypotheses\n\n\n1-3) is spuriously picking up the differential effect of bank credit in countries with high vs. low\n\n\nGDP per capita, and firms of different size, age, and labor productivity.\n\n\n**4. Base regression results**\n\n\nBase regression results are provided in table 1. Panel A in table 1 contains the estimated log odds\n\n\nratios while Panel B contains the estimated marginal effects of the bank credit to GDP ratio. 4 [^4: Unless stated otherwise, all marginal effects throughout the paper are evaluated at the mean value of the various\nexplanatory variables.] Table\n\n\n1 shows that regardless of the controls, the relationship between the bank credit to GDP ratio and\n\n\nthe likelihood (log odds ratios and marginal effect) of a having a woman top manager is positive\n\n\nand statistically significant at the 1 percent level. Without any controls (except for country, year,\n\n\nand industry fixed effects), the odds of having a woman top manager increase by 2.0 log points\n\n\ndue a unit increase in the bank credit to GDP ratio (column 1, Panel A). The corresponding increase\n\n\nwith various\n\nMention: \"GFDD\""}, {"role": "assistant", "content": "{\"role\": \"supporting\", \"usage_action\": \"source\", \"summary\": \"Bank asset concentration indices measuring competition are constructed from this financial structure database.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:001231:25:0", "occurrence_id": "92a239422faf4e66129b930d", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: 24\n\n\n\n**Table** **SI5-2:** Impact of heat on the difference in reported crimes and arrests in Houston\n\n\nContemporaneous arrests 3-day pooled arrests\n\n\nT above 100F 0.045 0.047\n(0.010) (0.012)\nT 95-100F 0.034 0.040\n(0.005) (0.007)\nT 90-95F 0.022 0.023\n(0.005) (0.007)\nT 85-90F 0.016 0.021\n(0.004) (0.006)\nT 80-85F 0.018 0.020\n(0.004) (0.006)\nT 75-80F 0.015 0.015\n(0.004) (0.005)\nN 1,840,860 1,839,600\nOutcome mean, T60-65 0.33 0.03\n**Fixed** **Effects:**\nTract Yes Yes\nMonth Yes Yes\nYear Yes Yes\nDOW Yes Yes\n\n\nNotes: All columns report the results of a linear fixed effects specification. We estimate the impact of\na hot day on the difference between the number of incidents reported to the Houston Police Department\n(Houston PD) and the number of arrests reported to the Texas Department of Public Safety (TDPS). In\nall cases we aggregate the count of incidents (Houston PD) data or arrests (TDPS data) to the tract-day\nlevel and conduct analysis at that level of aggregation. The sample in all cases is a balanced panel of tracts\nthat contain at least one Houston PD crime report at the daily level from 2010 to 2017. In column 2, we\npool arrests across the day of interest and the following two days. Errors are clustered at the tract level\nand are reported in parentheses. All regressions are weighted by the total population in each tract-year.\nAll regressions include the full set\n\nMention: \"TDPS data\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"Arrest counts are aggregated to the census tract-day level for the heat-crime analysis.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:001233:9:1", "occurrence_id": "c5758c976d46f8fe726a1a2f", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: 𝑑𝑑ℎ�= Pr (𝑘𝑘ℎ−1 < 𝜶𝜶𝑑𝑑𝑿𝑿𝑖 **𝑖** + 𝜸𝜸𝑑𝑑𝑮𝑮𝑖 **𝑖** + 𝜗𝜗𝑐𝑐 + 𝜀𝜀𝑖 **𝑖** ≤𝑘𝑘ℎ)\n\n(3).\n\nAssuming 𝜀𝜀𝑖 **𝑖** is normally distributed, we can use an ordered probit to estimate the parameters of\n\n\n\n(3).\n\n**𝑖**\n\n\n\n**𝑖**\n\n𝑑𝑑 have a large number of “ _do not know_ ” responses. We assume there\n\n𝑖\n\n\n\n(3).\n\n**𝑖**\n\n𝑑𝑑\n\nare two reasons why respondents would choose “\n\nQuestions used to construct 𝑂𝑂𝑖\n\n\n\nare two reasons why respondents would choose “ _do not know_ ”. They may be genuinely unaware\n\nof the number of fatalities in a disaster, or they may simply want to finish the interview sooner and\n\ngive that response to speed up the process. If “ _do not know_ ” responses are non-random, for\n\nexample, if respondents who are more likely to overestimate fatalities are also more likely to be\n\nimpatient about the interview process, the estimates in equation (3) could be biased.\n\n\nTo address this potential source of bias, we model the non-response process by estimating the\n\nprobability of giving a response (other than “ _do not know_ ”) as a function of the respondent\n\ncharacteristics jointly with estimating the ordered probit in equation (3). We use the number of\n\n“ _do not know_ ” responses to other questions in the section of the LiTS that contains the disaster\n\nquestion (module 4) as an instrument for the selection equation. The exclusion restriction here is\n\nbased on the assumption that the desire to finish the interview sooner is not related to factual\n\nknowledge about disaster fatalities but is correlated with the probability of giving “do not know”\n\n\n\nanswers to the disaster questions. The selection equation could be then expressed as follows:\n\n**𝑖** **\n\nMention: \"LiTS\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"analyze\", \"summary\": \"Counts of \\\"do not know\\\" responses in the disaster module serve as the instrument in the selection equation.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:001245:5:0", "occurrence_id": "1ce521a3b7b67faef6387e6f", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: to inclusion in commercial lending? Finally, what are the implementation conditions needed to promote\n\nadditionality and effective targeting of MSME finance operations?\n\n\nTo answer these questions, we use administrative loan-level data from the KUR program itself, which\n\nincludes information on over 8 million debtors between 2015 and 2020. Using the program database as a\n\nsampling frame, we complement the administrative data with surveys of a representative sample of 1,402\n\nKUR borrowers as well as qualitative interviews with separate samples of 100 KUR borrowers and 100 non\nborrowers. In sum, these data sources provide a rich and novel set of insights into the profiles, perspectives,\n\nand experiences of KUR borrowers since 2015 and shed light on the ways in which the publicly supported\n\nscheme plays out in supporting MSMEs on the ground.\n\n\nOur main and novel finding is that the subsidized credit provided through KUR enhances financial inclusion by\n\nreaching previously excluded micro and small businesses; however, it does not serve as a stepping- stone to\n\nunsubsidized commercial lending. Prior to receiving a subsidized KUR loan for the first time, only 11 percent\n\nof borrowers had ever received a commercial loan from a bank. Although successful at reaching first-time\n\nborrowers, the longer-term impacts on their financial inclusion are uncertain because KUR borrowers do\n\nnot move into unsubsidized commercial lending. Approximately half of KUR borrowers went on to receive\n\nKUR loans multiple times within a 5-year period, and only 3 percent of firms who received KUR financing\n\ngraduated to other forms of commercial lending. Until recent regulatory changes, firms had little incentive\n\nto choose commercial sources of financing over KUR’s below-market interest rates, and banks preferred to\n\nencourage repeat lending to minimize risk.\n\n\nWe also identify key design features of the KUR scheme which pose challenges for inclusivity and consumer\n\nprotection and hold important lessons for the design of public MSME finance support schemes. First,\n\nwe find that although the KUR program targets firms with insufficient collateral, in practice, 96% of KUR\n\nborrowers submit collateral for loans,\n\nMention: \"administrative loan-level data from the KUR program\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"Over eight million debtors form both the analytical sample and the sampling frame for the borrower surveys.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:001252:13:1", "occurrence_id": "2380c35c5c03fd9ffe352c31", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: which is\n\n\nour preferred model for interpretation. Table 4 shows that the estimated results for per capita\n\n\nexpenditure vary somewhat between model 1 and model 2, which is perhaps due to unobserved\n\n\ntrends occurring in different years. But more importantly, once we control for both the province\n\n\nand year FE, overall, the results remain similar between model 2 and model 3.\n\n\nIn particular, Table 4 shows that, holding all other factors constant, a 1 percent rise in a\n\n\nprovince’s per capita expenditure reduced its poverty rate by 0.26 percentage points (column 3),\n\n\nits poverty gap by 0.10 percentage points (column 6), and its poverty severity index by 0.05\n\n\npercentage points (column 9). Interestingly, holding fixed the per capita expenditure levels, a 1\n\n\n11 We also estimate a variant of equation (1) where we include the explanatory variables in lagged forms using both\nprovince FE and GMM models. The results are qualitatively similar (Dang et al., 2023). We further show the\nestimation results with additional control variables for public infrastructure such as the share of villages with yearround passable roads, the share of villages with a daily market, and the distance from the village to the nearest town\nin Appendix A, Tables A.3 and A.4. Since these variables are computed from the commune module of the VHLSSs,\nwe do not have complete data for these control variables for the whole period of our study. Yet, these tables show that\nprovinces with more villages that have year-round passable roads could reduce poverty and have faster economic\ngrowth.\n\n12\n\nMention: \"VHLSSs\""}, {"role": "assistant", "content": "{\"role\": \"supporting\", \"usage_action\": \"analyze\", \"summary\": \"Its commune module yields road access, market presence and distance controls, though not for the whole period.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:001254:28:0", "occurrence_id": "a80ad86800a5cfffbdc8adb5", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: high inflation, and an overvalued exchange rate; (ii) a highly distorted incentive structure derived\nfrom an overly protective, arbitrary, and non-transparent trade regime, a multiple exchange rate\nsystem that penalized exports, domestic price controls and administrative impediments, a complex\ntax system, restrictive foreign investment rules, and widespread corruption; and (iii) financial\nrepression and an unstable and inefficient banking sector. Economic reform efforts supported by\nthe IMF and World Bank were half-hearted and short-lived, as popular unrest (notably in April\n1984) or balance of payments crises (notably in June 1987) forced the government to backtrack.\nAccording to the CPIA index, the state was in fragile territory throughout this period. In 1990, the\neconomic situation deteriorated further owing to a pre-electoral loosening of financial policies, a\nsharp deterioration in the terms of trade, and a drought, leading to a spike of year-on-year inflation\nto 80 percent, a widening balance of payments deficit, and external arrears, including to the IMF\nand World Bank. In August 1990, the government launched the “New Economic Program,” a raft\nof reforms including fiscal consolidation, trade reforms to enhance the outward orientation of the\neconomy, unification of the multiple exchange rates and a devaluation, liberalization of interest\nrates, and steps to strengthen the banking system. Refinancing and rescheduling agreements with\nthe Paris Club (1991) and with private creditors (1994) resulted in a halving of public external\ndebt, and a new foreign investment law (1995) led to a surge in foreign direct investment. Growth\naccelerated and inflation fell sharply and stayed in the single digits. International pressure after the\nflawed 1994 elections led to a new government in 1996, which reduced tensions with Cuba,\nintroduced judicial reforms, and signed the Free Trade Agreement for Central America. Although\neconomic volatility continued, the cumulative impact of economic and political reforms led to the\nDominican Republic’s exit from fragility in 1997.\n\n\n**Rwanda\n\nMention: \"CPIA index\""}, {"role": "assistant", "content": "{\"role\": \"supporting\", \"usage_action\": \"source\", \"summary\": \"Its rating is cited to show the country was in fragile territory throughout the period.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:001260:52:0", "occurrence_id": "0f0915477f0e24a592168aaf", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: **Table A.3. Summary statistics of Green and Carbon-intensive occupations in India**\n\n\nSource: Own elaboration based on microdata from the 2019 Periodic Labour Force Survey (PLFS) for\nIndia.\nNotes: The column shows in parenthesis the sample standard deviations of the means and the standard\nerror of the difference in sample means estimated as the robust standard error of the coefficient of a\nregression of the green/carbon-intensive/rest job variable on the group membership dummy variable. (1)\nGreen occupations are those 4-digit ISCO-08 occupations with any of the 44 green qualifications defined\nby the Skill Council for Green Jobs (see Table 0). To estimate the proportion of green jobs for each 3digit ISCO-88 (as specified in the Indian labor force survey), 4-digit ISCO-08 occupations are mapped to\nthe 4-digit ISCO-88 classification using the ILO's crosswalk (when a single ISCO-88 occupation code is\nmapped to more than one ISCO-08, a green proportion measure is used to reflect the proportion of the\ncorresponding ISCO-08 occupations that have been classified as green) and then estimated at the ISCO88 3 digit level assuming an equal distribution of workers in 4-digits occupations within each 3-digit\noccupation. (2) Carbon-intensive occupations are those defined by Vona et al. (2018) at the 6-digits level\nof the 2010-SOC, mapped to the 4-digit ISCO-08 classification using a crosswalk from the US Bureau of\nLabor Statistics (when a single ISCO occupation code is mapped to more than one 6-digit SOC, a carbonintensive proportion measure is used that reflect the proportion of corresponding 6-digit SOC occupations\nthat have been classified as carbon-intensive), converted to ISCO-88 at 4-digits using ILO's crosswalk\nand then estimated at the ISCO-\n\nMention: \"2019 Periodic Labour Force Survey\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"analyze\", \"summary\": \"Microdata on green and carbon-intensive occupations are summarised from this survey.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:001276:30:0", "occurrence_id": "3c3e4bca55e12c142e7dc339", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: Figure 5. Change in preparedness to cope with a disaster or emergency after COVID-19, household\n(%)\n\n\n\n\n\n\n\n_Source:_ World Bank – UNDP LAC High-Frequency Phone Survey, 2021 - Wave 2.\n_Note:_ The sample is restricted to households exposed to at least one risk.\n\n\n28\n\nMention: \"LAC High-Frequency Phone Survey\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"Its second wave measures changes in disaster preparedness among risk-exposed households.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:001291:20:1", "occurrence_id": "cab16ff3a9075a7052f4bb02", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: homicide rate and women's labor participation. These coefficients\n\nhighlight the limited impact of changes in the male homicide rate on women's labor participation from\n\n1960 to 1989.\n\n\nDuring the 1990s and the early 2000s, a positive relationship existed between these two variables. As\n\nthe violence related to drug trafficking escalated in Colombia, resulting in the murder of many men,\n\nwomen began to enter the labor market at a higher pace (Iregui-Bohórquez et al., 2021). This increase\n\nin women's labor participation can be attributed to the need to offset income losses and the demand\n\nfor women's skills in urban labor markets (Calderón, Gáfaro, and Ibáñez, 2011); hence, their\n\nparticipation showed a slight improvement compared to men. The employment rate also displayed a\n\npositive trend, reaching approximately 50% by the end of the period, indicating a modest\n\n\n10 Data from Global Burden of Disease Collaborative Network. Global Burden of Disease Study 2019 (GBD\n2019) Results. Seattle, United States: Institute for Health Metrics and Evaluation (IHME), 2021.\n[https://ourworldindata.org/homicides.](https://ourworldindata.org/homicides)\n\n19\n\nMention: \"Global Burden of Disease Study 2019\""}, {"role": "assistant", "content": "{\"role\": \"supporting\", \"usage_action\": \"source\", \"summary\": \"Homicide rates used alongside labour participation come from this study's results.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:001293:18:0", "occurrence_id": "c67424897f060df45919f53b", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: _Income and consumption index:_ includes the logarithm of monthly household income and\n\n\nconsumption. Because these variables are continuous the index is constructed following\n\n\nthe methodology outlined in Kling, Liebman and Katz (2007).\n\n\n_Labor market index:_ includes a dichotomous variable for employment, and the logarithm\n\n\nof monthly wages and weekly hours worked.\n\n\nDescriptive statistics for each of the outcomes and their components variables are de\n\nscribed in Table 1.\n\n\n**III.B** **Data for the Taliban’s Geographical Presence**\n\n\nTo obtain information on the Taliban’s geographical presence, we scraped online data\n\n\nfrom the Foundation for Defense of Democracies’ Long War Journal on the districts con\ntrolled by Taliban, by U.S. Allies, and contested territories between the two groups. 9 The\n\n\ndata includes a yearly evolution of the territorial control in Afghanistan. The classification\n\n\nis based on open-source information from NATO’s data in Afghanistan, press reports, in\n\nformation provided by government agencies, and the Taliban. To categorize the districts,\n\n\nthey identify who provides government services, ensures security within the district, ad\n\nministers the district openly, and oversees local courts (see Appendix B.B for a detail\n\n\ndescription of the variable’s construction). 10\n\n\nFigures 3 to 5 report province-yearly changes in the share of districts controlled by the\n\n\nTaliban, the U.S. allies, and the contested districts in dispute between the Taliban and\n\nthe U.S. allies. 11 As seen in the figures, Taliban control was relatively stable from 2017\n\n\nthrough 2019, after which drastic shifts took place across regions, in parallel with the U.S.\n\n\nwithdrawal from Afghanistan.\n\n\n9The Foundation for Defense of Democracies is Washington, DC-based nonpartisan research institute\nfocusing on national security and foreign policy. It aims to strengthen US national security\n\nMention: \"NATO’s data in Afghanistan\""}, {"role": "assistant", "content": "{\"role\": \"supporting\", \"usage_action\": \"source\", \"summary\": \"Open-source NATO information helps classify yearly district territorial control.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:001299:11:1", "occurrence_id": "11484ad73fc9b5afb61eae5a", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: 15 [^15: This is denoted as the layer of ownership. For instance, a firm linked to the state through another BOS has 2 layers or degree of connection to the\nstate.]\n\n\n_Table 5. Degree of state ownership – WB BOS database_\n\n\n\n\n\n\n\n|Degree of State
participation|Definition|\n|---|---|\n|Minority|Firms in which the state holds 10-24.9% of the stakes|\n|Blocking minority|Firms in which the state holds 25-49.9% of the stakes|\n|Majority ownership|Firms in which the state holds 50-99.9% of the stakes|\n|Full ownership|Firms in which the state holds 100% of the stakes|\n|Direct|Firms directly owned by a Public Authority (national or subnational), which holds at
least 10% participation.|\n|Indirect|Firms participated by the government through another firm or chain of firms owned
by the State where it holds at least 10% participation.|\n\n\nSource: Author’s elaboration based on World Bank (BOS) database and (Dall'Olio, et al., 2022).\n\n#### **5. EMPIRICAL METHODOLOGY**\n\n\nThis paper explores two main econometric exercises. First, it estimates the conditional correlation\nof the state participation and the performance differentials between BOSs and POEs. For this\npurpose, we analyze the role of state ownership on firm performance through the following\nspecification:\n\n\n(1) 𝑌𝑖𝑡= 𝛼+ 𝛽1𝐵𝑂𝑆𝑖 + 𝛽2𝑿𝑖𝑡 + 𝜕𝑐 + 𝜕𝑠 + 𝜕𝑡 + 𝜀𝑖𝑗𝑡\n\n\nWhere, 𝑌𝑖 denotes the performance indicator for the firm 𝑖 using several performance\nmeasurements to have a comprehensive overview of the soundness of BOSs vis-à-vis POEs. First,\nwe assess the operational performance in terms of productivity, followed by the financial\nperformance measured by indicators of profitability, liquidity, and returns on investment. Thus,\n\n\n14 Alternative\n\nMention: \"World Bank (BOS) database\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"Direct and indirect state ownership through chains of firms with at least ten percent participation is identified here.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:001303:22:0", "occurrence_id": "455bd8a8a7a99c4919bb8a39", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: Data availability statement\n\n\nThe data underlying this article are available in the article and in its online supplementary\nmaterial. Data availalbe from the ICRG database were provided under licence and cannot be\nshared.\n\n\nReferences\n\n\nAlesina, Alberto and Roberto Perotti. 1995. “Fiscal Expansions and Adjustments in OECD\n\nCountries.” Economic Policy 10: 205-248.\nAvom, Désiré, Brice Kamguia, and Henri Njangang. 2021. “Understand Growth Episodes in Sub\nSaharan Africa: Do Exogenous Shocks Matters?” The Journal of International Trade &\nEconomic Development 30: 596–624.\nAiyar, Shekhar Shekhar, Romain Duval, Damien Puy, Yiqun Wu, and Longmei Zhang. 2018.\n\n“Growth Slowdowns and the Middle-income Trap.” Japan and the World Economy 48:\n22-37.\nBarro, Robert and Xavier Sala-i-Martin. 1991. “Convergence Across States and Regions.”\n\nBrookings Papers on Economic Activity 22(1): 107 - 182.\nBarro, Robert and Xavier Sala-i-Martin. 1992. “Convergence.” Journal of Political Economy\n\n100(2): 223-251.\nBen-David Dan, and David H. Papell. 1998. “Slowdowns and Meltdowns: Postwar Growth\n\nEvidence from 74 Countries.” Review of Economics and Statistics 80(4): 561–571.\nBerg, Andrew, Jonathan Ostry, and Jeromin Zettelmeyer. 2012. “What Makes Growth\n\nSustained?” Journal of Development Economics 98 (149–166).\nBosworth, Barry, and Susan Collins. 2008. “Accounting for Growth: Comparing China and\n\nIndia.” Journal of Economic Perspectives 22: 45–66.\nCaselli, Franceso, Gerardo Esquivel, and Fernando Lefort. 1996. “Reopening the Convergence\n\nDebate: A New Look at Cross-\n\nMention: \"ICRG database\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"inform\", \"summary\": \"Licence terms prevent the underlying data from being shared with readers.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:001305:16:2", "occurrence_id": "a7696d749666bcfb2b636cb5", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: . We\nuse the commands feols and sunab from the R package fixest to perform the estimation\nprocedure [94]. We present all relative period estimates in the SI figures. The Average\nTreatment effect on the Treated (ATT) estimates shown in the main text tables are\nthe weighted averages over the post-transference relative treatment period coefficients\n(0 _≤_ _ℓ_ _≤_ 10), where the weights for each relative period coefficient are based on the\nproportion of the treated group (areas managed by AP) in the overall population\nduring that specific relative period [49].\n\nOur control group comprises protected areas that AP has determined meet their\nestablished criteria for potential future management, which AP refers to as “anchor\nareas.” Polygons demarcating the boundaries of AP’s anchor areas are publicly available [51]. We identify individual protected areas in our control group in three steps.\nFirst, we used Quantum GIS to manually select all polygons from each of the World\nDatabase of Protected Areas’ (WDPA) shapefiles that overlapped with the boundaries of AP’s anchor areas. Second, we eliminated duplicate entries from the selected\nWDPA boundaries. Finally, we manually validated the remaining WDPA boundaries\nto confirm that protected areas in our control group match the set of polygons displayed on AP’s map of anchor areas. In three cases, we used QGIS and georeferenced\npolygons from either UNESCO or the literature [95, 96] to manually create shapefiles\nfor AP anchor areas that did not have shapefiles in the WDPA.\n\nSeveral protected areas in our control group are partly managed by governments\nand partly managed by an NGO other than AP. We retain these protected areas in\nour control group because they do not employ a “delegated” management model like\nAP, where the NGO has full control over management decisions [29]. Several of AP’s\n\n\n15\n\nMention: \"World\nDatabase of Protected Areas\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"curate\", \"summary\": \"Polygons overlapping the intervention areas are selected, de-duplicated and manually validated to build the control group.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:001313:21:1", "occurrence_id": "0e57513f783b2067401d0e01", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: 0.06%|0.06%|0.06%|\n\n\n\nSource: Estimates based on POF 2017/2018; Global Burden of Disease 2019; and SIH/SUS. Estimates assume a price shock of 20%.\n\n\nFigure 5 depicts the progressive pattern of the long-term estimated medical expenditure changes after\nimplementing a taxation on processed and ultra-processed foods. The lowest consumption decile presents\nthe highest gains, with estimated changes in medical expenditure being almost twice as large as the\nsecond decile, three times as large as the third, and 113 times as large as the top consumption decile.\nWhile our analysis does not allow us to estimate fiscal impacts on SUS, the public health care system, it\nsuggests that a taxation on processed and ultra-processed foods would have a positive impact in terms of\nreduced demands and medical expenditure.\n\n_Figure 5_ - Changes in medical expenditure\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n20\n\nMention: \"Global Burden of Disease 2019\""}, {"role": "assistant", "content": "{\"role\": \"supporting\", \"usage_action\": \"source\", \"summary\": \"Disease burden parameters enter the estimated medical expenditure response to a price shock.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:001316:4:1", "occurrence_id": "8492ad8a29583aad13601317", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: 5 bandwidth of a multi-dimensional poverty score cut\n\n\nof Punjab, Pakistan. All surveys were conducted by female enumerators. 2 Respondents belong\n\nto poor households which were within a +/- 5 bandwidth of a multi-dimensional poverty score cut\noff used to determine eligibility for Pakistan’s national unconditional cash transfers program. All\n\n\n\nto poor households which were within a +/- 5 bandwidth of a multi-dimensional poverty score cut\noff used to determine eligibility for Pakistan’s national unconditional cash transfers program. All\n\nrespondents are under the age of 60 years and the average age is 48 years. The vast majority of\n\n\n\noff used to determine eligibility for Pakistan’s national unconditional cash transfers program. All\n\nrespondents are under the age of 60 years and the average age is 48 years. The vast majority of\n\nthese women (93%) are illiterate. We relied on questions from the standard IPV module of the\n\n\n\nrespondents are under the age of 60 years and the average age is 48 years. The vast majority of\n\nthese women (93%) are illiterate. We relied on questions from the standard IPV module of the\n\nDemographic and Health Surveys (DHS), and asked 7 questions on experience of physical violence,\n\n\n\nthese women (93%) are illiterate. We relied on questions from the standard IPV module of the\n\nDemographic and Health Surveys (DHS), and asked 7 questions on experience of physical violence,\n\n4 on sexual violence and 4 related to injuries due to violence.\n\n\n\n4 on sexual violence and 4 related to injuries due to violence.\n\n\n\n4 on sexual violence and 4 related to injuries due to violence.\n\nThe literature so far has focused on comparing the measurement of IPV using ACASI with\n\nF2F interviews by randomizing respondents to _either_ answer questions using ACASI or F2F surveys\n\n\n\nThe literature so far has focused on comparing the measurement of IPV using ACASI with\n\nF2F interviews by\n\nMention: \"Demographic and Health Surveys\""}, {"role": "assistant", "content": "{\"role\": \"supporting\", \"usage_action\": \"inform\", \"summary\": \"Its standard intimate partner violence module supplies the question wording adopted in the study.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:001323:55:6", "occurrence_id": "b01791eef5e1cfc85868d6b4", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: upstreamness index _>_ 1 _._ 3. The LHS variable on all models is _Mj,t_ _k_ , the total value imported\n\nin Dominican Republic _i_ from place of origin _j_ of product _k_ in year _t_ . All models are estimated using the PPML\nestimator on Dominican Republic’s import data pooled across observations at the year, HS6 digit product, and placeof-origin level, with year fixed effects included in the estimation model. _σ_ _k_ estimates from Fontagné et al. (2022) are\ninteracted with geographic frictions, and enter separately in the regression itself. Pharmaceutical products are excluded\nfrom the estimation. IHST denotes the Inverse Hyperbolic Sine Transformation. Model (5) is estimated using fewer\nobservations due to missing trade tariff data.\n\n\n53\n\nMention: \"import data\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"analyze\", \"summary\": \"Import values by origin, year and six-digit product are pooled for the gravity estimation.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:001323:55:6", "occurrence_id": "e554ecf52df949e3a463ce68", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: upstreamness index _>_ 1 _._ 3. The LHS variable on all models is _Mj,t_ _k_ , the total value imported\n\nin Dominican Republic _i_ from place of origin _j_ of product _k_ in year _t_ . All models are estimated using the PPML\nestimator on Dominican Republic’s import data pooled across observations at the year, HS6 digit product, and placeof-origin level, with year fixed effects included in the estimation model. _σ_ _k_ estimates from Fontagné et al. (2022) are\ninteracted with geographic frictions, and enter separately in the regression itself. Pharmaceutical products are excluded\nfrom the estimation. IHST denotes the Inverse Hyperbolic Sine Transformation. Model (5) is estimated using fewer\nobservations due to missing trade tariff data.\n\n\n53\n\nMention: \"trade tariff data\""}, {"role": "assistant", "content": "{\"role\": \"supporting\", \"usage_action\": \"validate\", \"summary\": \"Missing entries reduce the observations available for one specification.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:001333:10:1", "occurrence_id": "cac145a6b72dff05414cac9d", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: shock in 2020Q3 that carries over to Q4. We expect the\n\ncommuters’ outcomes to instead track events in Israel and occupied territories more\n\nclosely, with a major shock in 2020Q2, recovery in Q3, and another dip in Q4.\n\n### **3 Data**\n\n##### **3.1 Data sources and definitions**\n\n\nWe employ data from the Labor Force Surveys (LFS) of the West Bank and Gaza,\n\ncollected by the Palestinian Central Bureau of Statistics and prepared by the Economic\n\nResearch Forum. The surveys are conducted on a quarterly basis, covering periods\n\nfrom 2000 onwards. The LFS is meant to represent all households whose ordinary\n\nresidence is in the West Bank and Gaza, though their place of work need not be. The\n\nLFS is representative at the region level (respectively of the West Bank and Gaza),\n\nas well as at the level of locality types (urban, rural, and refugee camps) ( _Palestine_ _-_\n\n_Labor_ _Force_ _Survey,_ _LFS_, 2021).\n\n\nImportantly for the purpose of our analysis, the data have a panel dimension, en\nabling the study of labor market transitions. The sample rotation scheme is described\n\n\n9\n\nMention: \"Labor Force Surveys\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"Quarterly surveys from 2000 onwards, prepared by the Economic Research Forum, supply the commuter outcomes.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:001336:47:0", "occurrence_id": "29c0aa4edf2d47ec6f73a8ec", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: Table A3.2: Total number of concentrations and share of treated concentrations by academic\nprogram\n\n\nNumber of concentrations % ever treated\n\nAgriculture 136 23\n\nComputer Science 37 51\n\nEconomics 73 0\n\nEducation 274 12\n\nEngineering 73 49\n\nGeology and Environmental studies 33 61\n\nIslamic Studies 26 0\n\nJournalism 29 0\n\nLaw and Political Sci 46 0\n\nLiterature 95 5\n\nMedical Studies 23 83\n\nPsychology 13 0\n\nPublic Administration and Policy 16 100\n\nScience Education 16 81\n\nSocial Science 63 11\n\nTechnician (e.g., chemical tech, food tech) 9 44\n\nVeterinary 12 0\n\nTotal 975 21\n\n\nNote: Author created the academic programs according to the NEXA selection sheet classification.\nSource: Kankor matriculation dataset 2013-2018.\n\n\n44\n\nMention: \"Kankor matriculation dataset\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"analyze\", \"summary\": \"Concentrations of treated students across academic programmes are counted from these matriculation records.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:001320:3:1", "occurrence_id": "f9ed268a39bb3d05297eb951", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: \npart due to population structure (Demombynes et al. 2022). This suggests that the extent to\nwhich the gender gap in mortality increased likely differs across country income levels. In\npart due to the lack of data, previous detailed analysis of COVID-19 mortality patterns by age\nhave combined both sexes, neglecting this well-established fact that mortality rates of men\nare higher than those of women, and that this might vary by country income level.\nThis study draws on recent data which were not available for earlier studies to examine the\nextent to which the gender gap in mortality shifted in high- and middle-income countries\nduring the COVID-19 pandemic. Unfortunately, underdeveloped civil registration systems\nfor reporting on male and female deaths limits data availability in low-income countries, a\npersistent limitation in the study of global population-level mortality patterns.\n\n\n\n**Introduction**\n\n\n\n**Methods**\n\n\n\n_Data sources_ We use the “Global excess deaths associated with COVID-19 (modelled estimates)” dataset\n\n(May 19, 2023 update), produced by WHO’s Technical Advisory Group (TAG) on COVID-19\nmortality assessment. This dataset contains estimates of expected all-cause deaths, all-cause\ndeaths (actual or predicted if actual was not available), and excess deaths by age-group and\nsex for 194 countries for 2020 and 2021. Expected all-cause deaths were forecasted using\nhistoric country-level monthly mortality data prior to the pandemic and serve as reference\npoint in the absence of COVID-19. Excess deaths were computed as \"the mortality above\nwhat would be expected based on the non-crisis mortality rate in the population of interest”\nby differencing actual/predicted all-cause deaths from expected all-cause deaths (World\n\n\n\n_Data sources_\n\n\n\n2\n\nMention: \"Global excess deaths associated with COVID-19\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"Modelled expected and actual all-cause deaths provide the mortality series analysed by sex.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:001347:36:0", "occurrence_id": "894fc6fc43c352c80eaa6ae4", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: Figure 5. Geographical Distribution – Night Light Density\n\nBefore and After the Rohingya Influx\n\n\n\n**Before 2017 (Average 1992 - 2016)**\n**Night Light Density**\n\n\n\n**After 2017 (Average 2017-2021)**\n**Night Light Density**\n\n\n\n0.000\n0.001 - 1.400\n1.401 - 1.750\n1.751 - 2.700\n2.701 - 17.000\n**Refugee Camps**\n\n\n\n0.000\n0.001 - 1.400\n1.401 - 1.750\n1.751 - 2.700\n2.701 - 17.000\n**Refugee Camps**\n\n\n\nRefugee Camps\n\n\n\nRefugee Camps\n\n\n\n_Notes:_ The maps illustrate the Cox’s Bazar district in Bangladesh segmented into one-square-kilometer grids. The Cox’s Bazar area has 2,392\ngrid cells. The left panel displays the distribution of night light density between 1992 and 2016, prior to the influx of Rohingya individuals into\nBangladesh. The right panel portrays the distribution of night light density between 2017 and 2021, following the start of the Rohingya influx. The\nmaps were generated using the harmonized night light data series spanning from 1992 to 2021, as developed by Li et al. (2020).\n\nMention: \"harmonized night light data series\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"analyze\", \"summary\": \"A single continuous series lets light density be compared before and after the influx.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:001364:18:0", "occurrence_id": "7a1fbce81a53748e653eb324", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: effect of the pandemic is insignificant. The results for reading and science should be interpreted\n\n\nwith caution. The negative trends in student achievement started before the pandemic. Thus,\n\n\nour identification strategy, which relies on stable long-term trends, cannot be applied without\n\n\ndoubts to reading and science. Our robustness checks for reading and science results confirm\n\n\nthat indeed in these two domains the time trends are not linear, and one cannot distinguish\n\n\nbetween the effects of the pandemic and the long-term decline in achievement. What causes\n\n\nthese long-term declines is beyond the scope of this paper. We can only note that both reading\n\n\nand science were minor domains in PISA 2022, meaning the measurement of student\n\n\nachievement was less precise than in mathematics.\n\n\n**Table 4. Impact of Pandemic on Student Reading and Science Achievement**\n\n\nReading (2000 to 2022) Science (2006 to 2022)\n\n(1) (2) (3) (4) (5) (6)\n\n\n\n-6.96***\n\n(0.75)\n\n-0.33***\n\n(0.04)\n\n\n\n-8.43***\n\n(1.10)\n\n\n-0.14***\n\n(0.04)\n\n\n\n-0.78\n\n(0.46)\n\n\n\n6.16***\n\n(0.84)\n\n-0.44***\n\n(0.04)\n\n\n\n8.13***\n\n(1.15)\n\n\n-0.38***\n\n(0.04)\n\n\n\nDeparture from linear\ntrend in 2022\n\n\nUNESCO: number of\nweeks with full closures\n\nPISA: country average\nstudent-provided number\nof weeks of closures\n\n_Additional controls_\n\nIndividual level: gender,\nimmigrant background,\nSES\n\nCountry average: gender,\nimmigrant background,\nSES\n\n\n\n-12.10***\n\n(0.43)\n\n\n\nYes Yes Yes Yes Yes Yes\n\n\nYes Yes Yes Yes Yes Yes\n\n\n\n\n- country fixed effects Yes Yes Yes Yes Yes Yes\n\n- country*time Yes Yes Yes Yes Yes Yes\n\nN 3,\n\nMention: \"PISA 2022\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"validate\", \"summary\": \"Reading and science were minor domains, so achievement is measured less precisely than mathematics.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:001375:16:1", "occurrence_id": "b99f43b01f3d0431ca0968c7", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: build the SOE variable, we first clean the raw Links files and eliminate branches\n\n\n(See Appendix C for details). Then, we merge the Links and Entities files to identify\n\n\nthe shareholders that are public authorities. We do so using the entity category S,\n\n\nwhich corresponds to governmental agencies, public departments, and local authori\n\nties. We exclude sovereign wealth funds and institutional investors from this set, as\n\n\n7Each BvD firm ID has two components: a country code that refers to the country where the\nfirm operates and a number.\n\n8Austria, Belgium, Bosnia and Herzegovina, Bulgaria, Croatia, Czechia, Estonia, Finland, France,\nGermany, Hungary, Italy, Luxembourg, Montenegro, North Macedonia, Norway, Poland, Portugal,\nRomania, Slovak Republic, Slovenia, Spain, Serbia and Ukraine.\n\n9The authors develop a methodology and SQL code to recreate the ownership trees for all the\nfirms in the ORBIS database.\n\n\n15\n\nMention: \"ORBIS database\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"curate\", \"summary\": \"Ownership trees are recreated for all firms with bespoke SQL code after branches are removed.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:001389:39:1", "occurrence_id": "80af563a524170ee12d1d506", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: square 0.803 0.802 0.825 0.804 0.523 0.851 0.828\n\n_Standard errors in parentheses. * p < 0.05, ** p < 0.01, *** p < 0.001. The models use administrative data from INVALSI and the_ Obs 2873 1851 2880 2890 13242 2073 1500\n\n\n\n_Standard errors in parentheses. * p < 0.05, ** p < 0.01, *** p < 0.001. The models use administrative data from INVALSI and the_\n_Ministry of Education for the 2022-23 academic year, including Ukrainian refugees and foreigners arrived in the country after_\n_February 2022 and enrolled in Grades 8 through 13. “Ukr Post Feb 2022 is a variable identifying Ukrainian refugees. The_\n_“recommended for high-track” variable is relevant for grade 8 only._\n\n\n\n38\n\nMention: \"administrative data from INVALSI\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"analyze\", \"summary\": \"Student test records supply the outcomes in the estimated models.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:001409:13:0", "occurrence_id": "6916e6c464dbfabda65355ab", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: **c) Women**\n\n\n\n\n\n\n\n100%\n\n\n80%\n\n\n60%\n\n\n40%\n\n\n20%\n\n\n\n\n\n0%\n\n2009 2014 2019\nAgriculture and forestry Mining Food, beverage and tobacco\nTextile and apparel Wood Construction\nSales Transport Public administration\nOthers\n\n**Source:** Authors’ elaboration using data the CSES household survey.\n\n**3. Trade Policies and Trade Flows**\n\nCambodia's dedication to trade liberalization is apparent through the implementation of a\nseries of trade-related policies. Besides the measures noted, in 1996, the U.S. granted\nCambodia most favored nation (MFN) status, followed by the Generalized System of\nPreferences (GSP) in 1997, and the European Union's Everything-but-Arms (EBA)\nagreement in 2001. It is also a signatory of the 2006 Trade and Investment Framework\nAgreement (TIFA) with the U.S. These agreements facilitated intra-regional and\ninternational exchange of garment manufacturing and the entry of new investors from\nSoutheast Asia into Cambodia.\n\nOther measures further promoted private sector development, including the 1994 law on\ninvestment, which allowed 100% foreign-owned investment and provided guarantees against\nnationalization and price regulation. To facilitate foreign investment, the country created the\nCouncil for the Development of Cambodia (CDC), which functioned as a one-stop for\ninvestors. In recent years, Cambodia has also introduced significant cross-border trade\nfacilitation improvements, resulting in faster export and import procedures. Compared to\nother Southeast Asian countries, Cambodia is known for having the least trade restrictions in\nservices.\n\nTrade plays a critical role in Cambodia’s economy. Since Cambodia’s economic and political\ntransition of the 1990s, it has fostered an export-led economy. Since 2000, gross domestic\nproduct (GDP) and GDP per capita have increased significantly. In fact, several estimates\nhave projected that Cambodia will transition out of Least Developed Country (LDC) status\nas early as 2027. Table 3.1 summarizes Cambodia’s trade\n\nMention: \"CSES household survey\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"Sectoral shares of female employment across three survey years are tabulated from this survey.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:001412:42:1", "occurrence_id": "a818c3bbab952f7654828149", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: the sample to competitive\n\nindustries at the 2-digit level. Table 17 reports that all of the results described previously\n\n- considering the entirety of the economy - persist. Additionally, we find a statistically\n\nsignificant negative correlation between exit rates and the concentration of BOS in com\npetitive industries. Our results suggest that industries with a higher presence of BOS are\n\ncharacterized by lower shares of young firms, lower levels of selection and higher market\n\nconcentration, all of which contribute to restricting business dynamism and firm life growth\n\n(Hsieh and Klenow, 2014). However, we do not find a statistically significant relationship\n\nbetween the employment share of BOS and entry rates, which would corroborate the nega\ntive relationship reported for entrepreneurship activity, measured by the employment share\n\nof young firms. In terms of the labor market, a positive correlation between the presence\n\nof BOS and job creation could be reflecting the ability of these firms to grow even in an\n\nenvironment of overall lower business dynamics. As we have shown in section 3, firms with\n\nstate participation have higher employment growth rates relative to private firms.\n\n\n16Since no information about firm output or sales is contained in RAIS, we compute the HHI using\nfirm-level employment.\n\n\n41\n\nMention: \"RAIS\""}, {"role": "assistant", "content": "{\"role\": \"supporting\", \"usage_action\": \"validate\", \"summary\": \"It contains no output or sales information, so concentration is computed from employment.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:001475:12:4", "occurrence_id": "4b7563ef0d3155defedb1853", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: >**7.2**
0.00
**472.6**
**148.2**
0.00
(1532.5)
(760.4)
**711**
**663**
|\n|
% of enterprises in presumptive tax net
**44.1**
**29.9**
0.01
Average presumptive tax (birr, imputed)
**641.9**
**224.7**
0.00
(1825.3)
(724.7)
% in sectors with tax-free threshold
68.6
74.6
0.26
**Number of enterprises**
**478**
**458**
|
**61.0**
**16.8**
0.00
**1222.0**
**262.5**
0.00
(472.6)
(148.2)
**63.2**
**91.9**
0.00
**498**
**449**
|\n\n\nSource: Authors’ calculations using ESS 2018/2019 (period 1) and ESS2021\n\nMention: \"ESS2021\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"analyze\", \"summary\": \"Enterprise survey results are compared with the earlier 2018/2019 period.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:001476:4:0", "occurrence_id": "bf75ba272510e4d88ecbb579", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: agricultural trade policy that encourages private investment, and investments in public goods that\nencourage productivity growth (World Bank, 2019).\n\n\n**Figure 2: Poverty among agricultural households in 2014**\n\n\n\n\n\n\n\n\n\n\n\n_Source:_ 2014 Timor-Leste Survey of Living Standards\n\n\nNotwithstanding the role that agriculture can potentially play in reducing poverty in Timor-Leste,\nthe country has one of the least developed agricultural production systems in the world. All\nsubsectors are dominated by subsistence systems and by farmers who are very risk averse\n(Denning 2013; World Bank 2017). Only 30 percent of the country’s arable land is currently under\ncrop production and grazing, and the sector’s productivity has been very low. Agricultural\nproductivity as measured by the value of crop output per hectare in Timor-Leste is well below that\nof other small island developing states and has fallen below the average for other low-income,\nfood-deficit countries in recent years (Figure 3a). Also, agricultural value added per worker has\nbeen falling since 2012 (Figure 3b). The estimated 64,000 metric tons of maize and 65,000 metric\ntons of rice produced in 2015 are 30 percent below the five-year average and well below the\ncountry’s estimated requirements (245,000 metric tons) of these staples (FAO statistics). The\ncountry’s cereal yield is also among the lowest in the East Asia and Pacific region (UN Women\nand World Bank 2018). The agriculture sector is therefore underperforming in terms of its\ncontribution to food security, sufficient livelihood, and overall economic growth.\n\n\n3\n\nMention: \"2014 Timor-Leste Survey of Living Standards\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"Poverty among agricultural households is measured from this living standards survey.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:001476:4:0", "occurrence_id": "b26afc9706dea570f60ae547", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: agricultural trade policy that encourages private investment, and investments in public goods that\nencourage productivity growth (World Bank, 2019).\n\n\n**Figure 2: Poverty among agricultural households in 2014**\n\n\n\n\n\n\n\n\n\n\n\n_Source:_ 2014 Timor-Leste Survey of Living Standards\n\n\nNotwithstanding the role that agriculture can potentially play in reducing poverty in Timor-Leste,\nthe country has one of the least developed agricultural production systems in the world. All\nsubsectors are dominated by subsistence systems and by farmers who are very risk averse\n(Denning 2013; World Bank 2017). Only 30 percent of the country’s arable land is currently under\ncrop production and grazing, and the sector’s productivity has been very low. Agricultural\nproductivity as measured by the value of crop output per hectare in Timor-Leste is well below that\nof other small island developing states and has fallen below the average for other low-income,\nfood-deficit countries in recent years (Figure 3a). Also, agricultural value added per worker has\nbeen falling since 2012 (Figure 3b). The estimated 64,000 metric tons of maize and 65,000 metric\ntons of rice produced in 2015 are 30 percent below the five-year average and well below the\ncountry’s estimated requirements (245,000 metric tons) of these staples (FAO statistics). The\ncountry’s cereal yield is also among the lowest in the East Asia and Pacific region (UN Women\nand World Bank 2018). The agriculture sector is therefore underperforming in terms of its\ncontribution to food security, sufficient livelihood, and overall economic growth.\n\n\n3\n\nMention: \"FAO statistics\""}, {"role": "assistant", "content": "{\"role\": \"supporting\", \"usage_action\": \"source\", \"summary\": \"Maize and rice production estimates are compared with the five-year average and requirements.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:001494:9:0", "occurrence_id": "1411f88084ba296f77248355", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: twice the growth rate in high-skill and low-skill services (around 1.5%). In upper middle-income countries,\n\n\nagriculture and manufacturing report the highest labor productivity growth of around 3%, followed by\n\n\n2% in high-skill services, and 1.2% in low-skill services. In lower middle-income and low-income countries,\n\n\nagricultural productivity growth is only 1.5%, followed by high-skill services at 1.2%. Productivity growth\n\n\nin manufacturing is only 0.7%, and a mere 0.4% in low-skill services.\n\n\nFigure 2: Labor productivity growth across sectors\n\n\nSource: GGDC 10-sector Database. Labor productivity is calculated as value-added at 2005 fixed prices\n\n\nin each sector divided by sectoral employment. See Appendix A for more details.\n\n\n**International** **production** **specialization** **and** **premature** **de-industrialization**\n\n\nTechnology-enabled globalization has impacted the dynamics of employment and output shares through\n\n\npatterns of international specialization. Advances in transportation and communication technologies in\n\n\nthe late 20th century enabled production unbundling, outsourcing, and offshoring on a massive scale,\n\n\nleading to unprecedented growth in international trade and investment. Many studies have documented\n\n\nthe effects of trade and multinational corporations’ offshoring on de-industrialization in the US (D. H. Au\n\ntor, Dorn, and Hanson 2013; Acemoglu, D. Autor, et al. 2016; Boehm, Flaaen, and Pandalai-Nayar 2020).\n\n\nSuch forces may be even stronger for smaller developing countries, which typically act as price takers in\n\n\nworld markets. Theory suggests that international trade can create patterns of structural change dis\n\ntinct from closed economy models (Matsuyama 2009; Matsuyama 2019). Globalization amplifies, rather\n\n\nthan reduces, the power of endogenous domestic demand composition differences\n\nMention: \"GGDC 10-sector Database\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"Value added at 2005 prices and sectoral employment are combined to compute labour productivity growth.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:001497:22:1", "occurrence_id": "e4063f4cb1df3d022dc59033", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: constitutes a random sample of EAs, households, and\nindividuals.\n\nThe LSMS-ISA samples are meant to be nationally representative of households and of\n\n\n\nindividuals.\n\nThe LSMS-ISA samples are meant to be nationally representative of households and of\nindividuals. Ideally, longitudinal studies preserve representativeness over time, indicating that\nthe sample should represent both the current population at each survey occasion and the\ndynamics over time of the initial population. To maintain both types of representativeness,\nlongitudinal surveys follow up with people interviewed in previous survey rounds and add new\nindividuals to ensure that new members of the population such as migrants and newborns are\nincluded (Glewwe and Jacoby 2000). To this end, panel surveys establish rules to define\ninterview targets in follow-up rounds and create specific protocols to track households and\nindividuals that move away from their original location. Moreover, they adopt refreshed\nsamples (i.e., rotating panel or split panel) and protocols for the inclusion in the survey of\nindividuals not previously involved in the study.\n\nWhen discussing tracking in panel surveys, Witoelar (2011) introduced the concept of\n\n\n\nindividuals not previously involved in the study.\n\nWhen discussing tracking in panel surveys, Witoelar (2011) introduced the concept of\ninterview targets and tracking targets. Interview targets are those that need to be interviewed;\ntracking targets are those individuals or households that should be tracked if they have moved\nand, if found, should be interviewed. Similarly, the author distinguished between following-up\nrules and tracking rules in defining the criteria for individuals or households to be interviewed\ndepending on whether they are found in the same location or are movers. To some extent, the\nLSMS-ISA panel surveys can be seen as a panel of both households and individuals. All\nhouseholds and individuals found and interviewed during the baseline are interview targets\nacross the entire history of the panel sample.\n\nThe LSMS-ISA tracking approaches are more heterogeneous and mainly diverge in terms of: (i)\n\nMention: \"LSMS-ISA panel surveys\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"inform\", \"summary\": \"Its follow-up and tracking rules make it a panel of both households and individuals.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:001507:9:0", "occurrence_id": "c4f83c047175a88d26b39b26", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: increased from 2.0 to 2.5. Similarly, for the case of women, the ratio in manufacturing increased\nfrom 1.8 to 2.9.\n\n\n**Figure 5: Relative Syrian Prevalence, by sector and gender (2017-2019)**\n\n\n**Source:** Authors’ calculations with data from Jordan LFS and UNCOMTRADE\n\nThe limitations for Syrians entering the job market to a larger extent may stem from a skill\nmismatch, as highlighted in Visintin et al. (2015) and McGowan and Andrews (2015). Although\nworking-age Syrians are less educated than their Jordanian counterparts (see Figure 8), this\nmismatch can manifest in highly educated Syrians performing low-skilled jobs and less educated\nSyrians struggling to compete. To analyze this, we can compare the distribution of Jordanians and\nSyrians across sectors for a given educational level. The distribution of native Jordanians can serve\nas a benchmark, reflecting the structural characteristics of the labor market. Significant\ndifferences in the allocation of Syrian workers, compared to Jordanians with the same educational\nbackground, would suggest a skill migration mismatch. Figures 6 and 7 support this hypothesis:\n66% of Jordanians in manufacturing, less than 8% in FIRE (Finance, Insurance, and Real Estate),\nand 25% in EGW (Electricity, Gas, and Water) have not completed secondary education. In\ncontrast, 81% of Syrians in manufacturing, 36% in FIRE, and 91% in EGW have not completed\nsecondary education, indicating a significant deviation from the structural benchmark.\n\n\n8 | P a g e\n\nMention: \"Jordan LFS\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"analyze\", \"summary\": \"Sectoral prevalence of Syrian workers by gender is computed from this labour force survey.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:001507:9:0", "occurrence_id": "f269c68f1a1318276c675e56", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: increased from 2.0 to 2.5. Similarly, for the case of women, the ratio in manufacturing increased\nfrom 1.8 to 2.9.\n\n\n**Figure 5: Relative Syrian Prevalence, by sector and gender (2017-2019)**\n\n\n**Source:** Authors’ calculations with data from Jordan LFS and UNCOMTRADE\n\nThe limitations for Syrians entering the job market to a larger extent may stem from a skill\nmismatch, as highlighted in Visintin et al. (2015) and McGowan and Andrews (2015). Although\nworking-age Syrians are less educated than their Jordanian counterparts (see Figure 8), this\nmismatch can manifest in highly educated Syrians performing low-skilled jobs and less educated\nSyrians struggling to compete. To analyze this, we can compare the distribution of Jordanians and\nSyrians across sectors for a given educational level. The distribution of native Jordanians can serve\nas a benchmark, reflecting the structural characteristics of the labor market. Significant\ndifferences in the allocation of Syrian workers, compared to Jordanians with the same educational\nbackground, would suggest a skill migration mismatch. Figures 6 and 7 support this hypothesis:\n66% of Jordanians in manufacturing, less than 8% in FIRE (Finance, Insurance, and Real Estate),\nand 25% in EGW (Electricity, Gas, and Water) have not completed secondary education. In\ncontrast, 81% of Syrians in manufacturing, 36% in FIRE, and 91% in EGW have not completed\nsecondary education, indicating a significant deviation from the structural benchmark.\n\n\n8 | P a g e\n\nMention: \"UNCOMTRADE\""}, {"role": "assistant", "content": "{\"role\": \"supporting\", \"usage_action\": \"source\", \"summary\": \"Trade flows accompany the labour data in the sectoral comparison.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:001510:14:0", "occurrence_id": "27f3aebfc37e2ca5a42ca6d0", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: stimulating activities with any caregiver in the previous three days). A Z-score of 0 would indicate\nthat a child in this sample has a similar developmental status to that of a child in the CREDI\nreference sample who is the same age. As demonstrated by Figure 1, the average child in this\nsample has a developmental status almost 2 standard deviations (1.72) below the mean, indicating\nmuch lower levels of child development in this sample compared to the global population.\nDistributions varied by various characteristics of interest, such as maternal education, living in a\nrural area and refugee status (Figures 2-4).\n\n**Figure 1**\n\n\n\n**Figure 2**\n\n\n\n_Sample Distribution for Children with Mothers with Less than a Primary Education Compared_\n\n\n\n\n\n13\n\nMention: \"CREDI\nreference sample\""}, {"role": "assistant", "content": "{\"role\": \"supporting\", \"usage_action\": \"inform\", \"summary\": \"Its age-specific distributions define the zero point against which children's z-scores are read.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:001513:16:1", "occurrence_id": "36ceefc156e11d049f1e68ac", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: score of 31.2 8 (out of a possible score of 100).\n\n\nConsequently, there is an urgent need to provide funds specifically for health security. Thus, there\n\n\nis a dire need to make a dedicated financial investment in health security. Policy makers in Côte\n\n\nd'Ivoire could, therefore, allocate pandemic funds in national budgets and explore opportunities to\n\n\ncollaborate with philanthropic and multilateral organizations to increase domestic resource\n\n\nmatching. As a result of their collaboration, for every dollar spent by policy makers in Côte d'Ivoire\n\n\non pandemic preparedness and response, the matching donor contributes U$2 (a 2:1 matching\n\n\nratio). Policy makers could use these funds to invest more in the surveillance system, allowing\n\n\noutbreaks to be contained before they spread. Furthermore, modern, and strong laboratory\n\n\n7 [https://data.who.int/dashboards/covid19/vaccines?m49=384&n=c](https://data.who.int/dashboards/covid19/vaccines?m49=384&n=c)\n\n8 [The data are from the 2021 Global Health Security index (https://www.ghsindex.org/country/cote-divoire/). The data](https://www.ghsindex.org/country/cote-divoire/)\nsuggest that Côte d’Ivoire has low score in preventing (12.4), detecting (29.6), responding (35.3), health (17.1), norms\n(47.7), and risk (45.2).\n\n\n15\n\nMention: \"2021 Global Health Security index\""}, {"role": "assistant", "content": "{\"role\": \"supporting\", \"usage_action\": \"source\", \"summary\": \"Its country score is cited as evidence of low preparedness.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:001514:3:1", "occurrence_id": "2b7409bc49e95393eda14ab7", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: blueprint exists, for any solution to function well, the country, political and economic context\nmatters. At this juncture, the experimentation continues. However, valuable lessons can be drawn from past\nand current experience of countries under different power market design options.\n\nThis paper undertakes a comprehensive stock-take of the evolution of the power market structure in every\neconomy in the world between 1989 and 2024. We rely on a new unique database, the “Global Power\nMarket Structures Database 1 ” developed by one of the co-authors of this paper. The database examines all\n230 global economies, documenting the changes in the power market structure for every year between 1989\nand 2024. The database’s objective is to present different designs pursued by countries globally in\nstructuring their power markets. To the best of our knowledge this is the first such database and this is the\nfirst paper to analyze power markets in such a comprehensive global manner.\n\nThe paper is structured as follows: Section 2 provides a global overview of each power market structure;\nwe also delve into the different design options adopted by countries globally within each structure. Section\n3 presents the global experience of countries transitioning between different market structures, highlighting\nboth enablers and challenges countries faced during these transformations. Section 4 discusses the\nexperience of countries that experimented with different designs within their respective power market\nstructure. Section 5 contains our conclusions and distills the key policy recommendations for each power\nmarket structure based on 35 years of global experience.\n\n\n1 [Global Power Market Structures Database](https://datacatalog.worldbank.org/search/dataset/0065245/global-power-market-structures-database) (Akcura 2024).\n\n\n2\n\nMention: \"Global Power\nMarket Structures Database\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"Changes in power market structure across 230 economies are documented in this new database.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:001525:28:2", "occurrence_id": "c0e38d3e0c1a6126d80e6179", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: Table 5.7. Robustness check: Impact of PqTR reduction on repetition rate (PqTR 80)**\n\n**Overall** **Lower Primary**\nControl in 2018 0.260*** 0.272***\n(0.007) (0.008)\nTime (year=2019) -0.009 -0.010\n(0.010) (0.011)\nLagged Treatment 0.012 0.016\n(0.009) (0.010)\nLagged Treatment (DiD) -0.034*** -0.040***\n(0.012) (0.014)\nControl (N) 216 216\nTreatment (N) 424 424\nr2 0.03 0.03\n_Data Source: EMIS 2018 and 2019_\n_Note: Robust standard errors in parentheses. * p<0.10, ** p<0.05, *** p<0.01_\n_Compares rates at end 2017/18 and end 2018/19. Treated schools are those where PqTR brought below 90 in_\n_2018._\n\n\n27\n\nMention: \"EMIS\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"analyze\", \"summary\": \"Rates at the end of two school years are compared between treated and control schools.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:001526:1:0", "occurrence_id": "99939b3215cc12f880db60eb", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: Policy Research Working Paper 10911\n\n##### **Abstract**\n\nThe arrival of cloud computing provides firms a new way\n\nto access digital technologies as digital services. Yet, capital\nincentive policies present in every OECD country are still\ntargeted towards investments in information technology\n(IT) capital. If cloud services are partial substitutes for\nIT investments, the presence of capital incentive policies\nmay unintentionally discourage the adoption of cloud and\ntechnologies that rely on the cloud, such as artificial intelligence (AI) and big data analytics. This paper exploits a tax\n\n\n\nincentive in the UK for capital investment as a quasi-natural\nexperiment to examine the impact on firm adoption of\ncloud computing, big data analytics and AI. The empirical results find that the policy increased investment in IT\ncapital as would be expected; but it slowed firm adoption\nof cloud, big data and AI. Matched employer-employee\ndata shows that the policy also led firms to reduce their\ndemand for workers that perform data analytics, but not\nother types of workers.\n\n\n\nThis paper is a product of the Office of the Chief Economist, East Asia and the Pacific Region. It is part of a larger effort by\n\nthe World Bank to provide open access to its research and make a contribution to development policy discussions around\nthe world. Policy Research Working Papers are also posted on the Web at http://www.worldbank.org/prwp. The authors\nmay be contacted at timothy.destefano@georgetown.edu, nick.johnstone@iea.org, richard.kneller@nottingham.ac.uk, and\njtimmis@worldbank.org.\n\n\n_The Policy Research Working Paper Series disseminates the findings of work in progress to encourage the exchange of ideas about development_\n_issues. An objective of the series is to get the findings out quickly, even if the presentations are less than fully polished. The papers carry the_\n_names of the authors and should\n\nMention: \"Matched employer-employee\ndata\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"analyze\", \"summary\": \"Linked firm-worker records show demand fell for data analytics workers but not others.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:001531:36:1", "occurrence_id": "9af671eedce6bf616e57d3ee", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: ] Interest rate 0.00 0.73 0.01 575\n(0.01)\n\n[13] Kindness -0.01 0.77 0.38 575\n(0.04)\n\n[14] Comfortable installments 0.00 1.00 0.04 575\n(0.02)\n\n\nNotes: Data based on phone survey conducted by the lender. From December 2015 to April 2017 the lender called a random 5% sample of clients\nin the study at that time per month (stratified additionally by loan officer and credit type, with one client minimum per credit officer, month and\ncredit type). Questions about reasons for pass use were open-ended with both pre-coding of answers by enumerators and free text detail\nexplanation. The knowledge and pass use questions from Panel A were only asked to clients with a flexible loan. A total of 285 flexible loan clients\nwere surveyed, for a total of 345 survey responses (clients could be selected in more than one month's sample). Mean pass use for the December\n2015 to April 2017 period was 0.187 for all flexible loan clients according to lender administrative data. This is similar to the self-reported pass use\nmean reported in row 2. Out of the 345 survey responses, 320 (93%) had pass use recall that was congruent with the lender administrative data.\nAn additional 3% of the 345 survey responses had discrepancies between self-reported pass use and pass use from administrative data that were\nlikely due to minor lags in the reporting of pass use in the administrative records. In these instances, clients claimed to have used a pass already\nand the administrative records indicated they had not. The following month the adminsitrative records indicated the clients had indeed used a\npass, which is an indication that these discrepancies were due to minor lags in recording pass use. Panel B: Columns 1 and 2 show results for\nregressions with Flexible Contracts (pooled Std-Flex and Flex\n\nMention: \"phone survey\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"validate\", \"summary\": \"A monthly random five percent sample of clients was called to check self-reported behaviour.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:001531:36:1", "occurrence_id": "60ea7ac522325b193f808ebe", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: ] Interest rate 0.00 0.73 0.01 575\n(0.01)\n\n[13] Kindness -0.01 0.77 0.38 575\n(0.04)\n\n[14] Comfortable installments 0.00 1.00 0.04 575\n(0.02)\n\n\nNotes: Data based on phone survey conducted by the lender. From December 2015 to April 2017 the lender called a random 5% sample of clients\nin the study at that time per month (stratified additionally by loan officer and credit type, with one client minimum per credit officer, month and\ncredit type). Questions about reasons for pass use were open-ended with both pre-coding of answers by enumerators and free text detail\nexplanation. The knowledge and pass use questions from Panel A were only asked to clients with a flexible loan. A total of 285 flexible loan clients\nwere surveyed, for a total of 345 survey responses (clients could be selected in more than one month's sample). Mean pass use for the December\n2015 to April 2017 period was 0.187 for all flexible loan clients according to lender administrative data. This is similar to the self-reported pass use\nmean reported in row 2. Out of the 345 survey responses, 320 (93%) had pass use recall that was congruent with the lender administrative data.\nAn additional 3% of the 345 survey responses had discrepancies between self-reported pass use and pass use from administrative data that were\nlikely due to minor lags in the reporting of pass use in the administrative records. In these instances, clients claimed to have used a pass already\nand the administrative records indicated they had not. The following month the adminsitrative records indicated the clients had indeed used a\npass, which is an indication that these discrepancies were due to minor lags in recording pass use. Panel B: Columns 1 and 2 show results for\nregressions with Flexible Contracts (pooled Std-Flex and Flex\n\nMention: \"lender administrative data\""}, {"role": "assistant", "content": "{\"role\": \"supporting\", \"usage_action\": \"validate\", \"summary\": \"Its recorded pass use of 0.187 is compared with clients' recall in the survey.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:001543:8:0", "occurrence_id": "940093ee0de8e30bfcd3bb05", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: **3.** **Growth drivers in the business-as-usual baseline**\n\n\nIn this section we calibrate the LTGM-NR model to simulate Peru’s business-as-usual baseline over the\n2023-50 period. To create a baseline for the Peruvian economy in the long run, we calibrate the future\npaths of the growth drivers such as investment, human capital, the growth of TFP in the non-resource and\nnatural resource sectors, 6 as well as other key parameters. These assumptions are summarized in Table\n1. We calibrate the LTGM-NR as the foundation of the analysis and add the LTGM-TFP extension and the\nLTGM-HC extension to simulate non-resource sector TFP growth and human capital growth, respectively.\nWe use population growth projections (by age cohort) from the UN for demographic trends until 2050.\n\n\n6 The resource sector is composed of the copper mining sector, which is around 8 percent of the total GDP and is\nexpected to grow in the short run by around 2 percent due to the entrance of the Quellaveco mine. In the long\nrun, the depletion in reserves will shrink the sector to 6 percent of GDP and grow below 1 percent on average.\n\n\n7\n\nMention: \"population growth projections\""}, {"role": "assistant", "content": "{\"role\": \"supporting\", \"usage_action\": \"source\", \"summary\": \"Projections by age cohort drive demographic trends in the long-term simulation.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:001547:6:0", "occurrence_id": "765368e71c47557deede6dad", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: of the population of Myanmar (around 10 million people) had migrated, either internally or\nabroad (MAPSA 2024).\n\n\nAs economic and security prospects remain bleak, there may be sustained pressure on the\npopulation to migrate outside Myanmar. This may be particularly concerning in the case of highskilled workers that play a critical role in key professions and occupations in Myanmar, especially\nbecause of the low share of the population with higher education, relative to regional and\nneighboring peers (figure 1). High levels of emigration among the already limited numbers of\nhigh-skilled workers, such as medical professionals, educators, and engineers, can result in\nshortages in critical sectors of activity, which in turn can be detrimental to long-term\ndevelopment.\n\n\nFigure 1. Educational attainment, Bachelor’s or equivalent / at least Master's or equivalent,\npopulation 25+, total (%) – Myanmar and selected regional and neighboring comparator countries\n\n\n\n\n\n\n\n\n\nSource: Authors’ calculations using World Development Indicators, for latest available year since 2010. *Data for population 25+\nwith bachelor’s degree or equivalent not available for Cambodia.\n\n\nAgainst this backdrop, we attempt to answer the following research questions:\n\n\n(i) How much do high-skilled youth value the prospects of migrating abroad for undertaking\nwork that is similar to their current jobs?\n\n\n(ii) How would the emigration of high-skilled youth respond to prospects of political or\neconomic stabilization? What form of stabilization – political, or economic – matters (more) for\nthe emigration considerations of high-skilled youth?\n\n\n(iii) Which individual characteristics determine migration responses to signals of political or\neconomic stabilization?\n\n\n5\n\nMention: \"World Development Indicators\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"Educational attainment shares for the region are compiled from these indicators.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:001553:31:0", "occurrence_id": "4a1f64f713881b6e86f29a7c", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: ##### **B Data**\n\nTable 1: Sources and definition of the main variables\n\n\nVariable Source Definition\n\n\nFixed_broadband_USD_log ITU’s ICT Price Basket Price of the fixed broadband basket is the\n\n\nleast expensive offer with a minimum monthly\n\n\nusage of 5 Gigabytes (GB) and an advertised\n\n\ndownload speed above 256 Kilobits per sec\n\nond (Kbps). Price is expressed in USD PPP\n\n\nand used in logarithm form.\n\n\nData_only_mobile_bdb_USD_log ITU’s ICT Price Basket Price of data-only mobile broadband basket\n\n\nis the least expensive offer with a minimum\n\n\nmonthly usage of 2 GB based on 3G or newer\n\n\ntechnologies. Price is expressed in USD PPP\n\n\nand used in logarithm form.\n\n\nn_cables /n_cables_log Telegeography Number of Submarine cables laid in a given\n\n\ncountry.\n\n\nBandwidth / Bandwidth_log Telegeography International used Internet bandwidth corre\n\nsponding to the inventory of capacity used\n\n\nby four categories of users: Internet back\n\nbone providers, content providers, research\n\neducational networks, and enterprises and\n\n\nothers. The capacity is measured in Gbps.\n\n\nRegulationScore ITU ICT regulatory tracker is an index pinpoint\n\ning the changes taking place in the ICT reg\n\nulatory environment based on 4 sub-indexes\n\n\n(regulatory authority, regulatory mandate,\n\n\nregulatory regime, and competition frame\n\nwork) and 50 indicators.\n\n\nHHI_fixedBdb / HHI_fixedBdb_log Telegeography Herfindahl-Hirschman Index (HHI) of the top\n\n\n5 retail fixed-broadband operators.\n\n\nHHI_mobileBdb / HHI_mobileBdb_log GSMA Intelligence Herfindahl-Hirschman Index (HHI) in the re\n\ntail mobile broadband markets.\n\n\nGDP_log WDI GDP in 2015 constant USD\n\n\nGDPpC_log WDI GDP per capita in 2015 constant USD\n\n\nPopulation_log WDI Total Population size, proxi\n\nMention: \"ITU ICT regulatory tracker\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"Four sub-indexes on regulatory authority and management are combined into a regulation score.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:001555:8:0", "occurrence_id": "99a450bbbc2a73cfd0c733ff", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: weighted to adjust for non-response and other sampling errors. See **Table 0** for the response rates\n\n\nby treatment.\n\n\nThe survey was implemented using the World Bank’s _Survey Solutions_ software for\n\n\nComputer Assisted Personal Interviews (CAPI). This allowed for daily upload of completed\n\n\ninterviews by the field teams, as well as frequent data download and review by the NBS and OCGS\n\n\nheadquarters teams to ensure the quality of the data being collected, while providing feedback to\n\n\nthe enumerators for further quality control.\n\n\n**3.2. Study design**\n\n\nThree approaches to collecting household food consumption data – 14-day diary, 7-day recall with\n\n\nshort items list, and 7-day recall with long items list – are compared in this study. To better\n\n\nunderstand the differences in household food consumption data collection, this methodological\n\n\nstudy replicated the HBS 2017/18 (14-day diary) and the NPS (7-day recall with short list)\n\n\nmethodologies, as well as a variant/combination of the NPS (7-day recall with long list). Given\n\n\nthat the HBS is the survey that NBS and OCGS use to produce official poverty statistics, the diary\n\n\nmethodology served as the benchmark and households assigned to this group served as the control\n\n\ngroup, and the two 7-day recall arms are compared to the diary. In addition, all households in the\n\n\nstudy received a Food Away from Home (FAFH) module implemented at the individual level to\n\n\ncapture expenditure on food consumed outside the home, such as from restaurants, joints, etc.\n\n\nHouseholds were randomly assigned to each study arm in all clusters to ensure non-contamination\n\n\n(Beegle et al. 2012; Brzozowski et al 2017). The design details of each method are described\n\n\nbelow.\n\n\n7\n\nMention: \"HBS\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"validate\", \"summary\": \"Because it produces the official poverty statistics, the diary method is benchmarked against it.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:001558:10:0", "occurrence_id": "b514fc8c98a2606a49f1abb0", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: obtain shapefiles with land use typologies from the municipal government, which allows us\n\n\nto approximately classify floor space in each location as either commercial or residential. We\n\n\nfurther obtain the Amman zoning restriction rules, which assign to each building type the\n\n\npercentage of the plot that can be used for construction and the maximum number of floors\n\n\nthat can be constructed (among other constraints not modeled here). We merge the land use\n\n\ntypology of each plot to the relevant building categories from the zoning rules to calculate\n\n\nthe maximum floor space that can legally be developed in each location. We perform this\n\n\nstep separately for commercial and residential building types.\n\n\n**Travel Times with Road Travel.** To compute average travel times between all locations,\n\n\nwe use the road network for Amman and assign average travel speeds to different types of\n\n\nroad segments based on estimates from the World Bank Transportation Unit. Specifically,\n\n\nwe assign a speed of 35 km/hour for primary roads, 20 km/h for secondary roads, 10 km/h\n\n\nfor tertiary roads, 8 km/h for other road types, and 5 km/h for walking. For metro lines we\n\n\nassign a speed of 35 km/h and for monorail 45 km/h. In the counterfactual, we compute\n\n\ncommuting times with the new BRT routes to which we assign a traveling speed of 25 km/h.\n\n\nFigure 4 shows average commuting times for each residency neighborhood to all possible\n\n\nwork locations where we weigh travel times of each work destination by the number of jobs\n\n\navailable in this destination. Aligned with the previous results on employment density, we\n\n\nsee that central neighborhoods are best connected to jobs while the outskirts have larger\n\n\naverage commuting costs to available employment opportunities. Commuting times are par\n\nticularly large for the south and some of the most western and northern neighborhoods.\n\n### **5 Calibration Results**\n\n\n9\n\nMention: \"shapefiles with land use typologies\""}, {"role": "assistant", "content": "{\"role\": \"supporting\", \"usage_action\": \"source\", \"summary\": \"These municipal layers allow floor space to be classified as commercial or residential.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:001561:8:0", "occurrence_id": "5dc2441b4670becd1e2255d4", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: If a regression approach were used, the additional consumption in 2016 would be completed by adding\n\nused to find the most similar household heads in both surveys (within the set of observations that share\nsome residuals to 𝑦𝑦�𝑖𝑖2016. That differs from the method presented in this paper since 𝑦𝑦�𝑖𝑖2016 and 𝑦𝑦�𝑖𝑖2022 are\ncommon characteristics). For every observation in the 2016 survey, a set of neighbors (in terms of 𝑦𝑦�𝑖𝑖2016\ndifference between the two linear predictions. Among these neighbors, one is randomly selected using\nand 𝑦𝑦�𝑖𝑖2022 closeness) is found in the 2022 HIES by looking for observations with the smallest absolute\nuniform selection probabilities within the subset of closest neighbors. In addition, the matching method\nrequires that the closest neighbors are searched only within a pre-defined subset of households having\nthe same stratum and per capita consumption decile. The observed share of additional consumption with 𝑎 **𝑎** 𝑎𝑎 ) from that neighbor in 2022 is\nrespect to the comparable consumption (𝑠𝑠ℎ𝑓 **𝑓** 𝑓 **𝑓** 𝑖𝑖2022𝑎 **𝑎** 𝑎𝑎 and 𝑠𝑠ℎ𝑛 **𝑛** 𝑛 **𝑛** 𝑛𝑛𝑖𝑖2022\n\n𝑎 **𝑎** 𝑎𝑎,\n\nthen imputed to the corresponding observation in 2016 (obtaining 𝑠𝑠ℎ𝑓 **𝑓** 𝑓 **𝑓** 𝑖𝑖2016𝑎 **𝑎** 𝑎𝑎 and 𝑠𝑠ℎ𝑛 **𝑛** 𝑛 **𝑛** 𝑛𝑛𝑖𝑖2016\n\n\n\n𝑎 **𝑎** 𝑎𝑎\n\n**𝑓** **𝑓** 𝑖𝑖2022𝑎 **𝑎** 𝑎𝑎 and 𝑠𝑠ℎ𝑛 **𝑛** 𝑛 **𝑛** 𝑛𝑛𝑖𝑖2022\n\n**𝑓** **𝑓**\n\n\n\n**𝑎** ) from that neighbor in 2022 is\n\n𝑎 **𝑎** 𝑎𝑎\n\n**𝑓**\n\nMention: \"2022 HIES\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"analyze\", \"summary\": \"Closest neighbours are matched by selecting observations with the smallest absolute differences.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:001595:28:2", "occurrence_id": "617e5eaf2483e0eb0522d5d2", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: . Indicators were collected across different data collection rounds\nand, due to attrition between rounds, the sample for psychological well-being outcomes is reduced to\nhouseholds surveyed in all rounds in order to have a complete set of indicators. Each psychological\nwell-being measure is estimated as a score on the variable’s scale, normalized to the unit SD of\ncontrol HHs, with mean equal to zero. Impacts on the normalized measures can be found in Table\nA9 of the Online [Appendix.](https://www.dropbox.com/scl/fi/bioyi778lybxemivdq8g4/Long-term-impacts-of-the-TUP-program_OnlineAppendix.pdf?rlkey=2xjb0z4fygh9czw406av7gqlm&dl=0) The psychological well-being index is an index of the three previous\nmeasures, normalized in the same way. School enrolment is estimated for school-age children (ages\n6 to 18 years), with the unit of observation being the child, hence all SEs are clustered at the\nhousehold level. PW = primary woman; SE = standard error; SD = standard deviation; PRA =\nparticipatory rural appraisal; WVS = World Values Survey; CES-D = Center for Epidemiological\nStudies Depression.\n\n\n27\n\nMention: \"World Values Survey\""}, {"role": "assistant", "content": "{\"role\": \"background\", \"usage_action\": \"inform\", \"summary\": \"The table's abbreviation list expands the survey whose values appear in the notes.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:001597:44:1", "occurrence_id": "c630469f0885c27d546c8e26", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: -83\nOptical Equipment 90-92\n\n\n\nPlastic and Rubber 39-40\nPlastic, Rubber and Toys\nToys 95\n\n\nWood Products 44-49\nFurniture and Wood Products\nFurniture 94\n\n\n\nMiscellaneous\n\n\n\nFoodstuffs and Beverage 16-24\nRaw hides and Leather 41-43\nFootwear and Headgear 64-67\nStone and Glass 68-71\n\n\n\n²⁵Please refer to Brandt et al. (2023) for a detailed and comprehensive discussion about the reporting and sample issues\nof both the ASIF data and the NTSD data and a review of the literature using these two datasets.\n\n\n42\n\nMention: \"ASIF data\""}, {"role": "assistant", "content": "{\"role\": \"background\", \"usage_action\": \"validate\", \"summary\": \"A cited reference documents its reporting and sample problems.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:001597:44:1", "occurrence_id": "742d31e8abcf80dbcb572f23", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: -83\nOptical Equipment 90-92\n\n\n\nPlastic and Rubber 39-40\nPlastic, Rubber and Toys\nToys 95\n\n\nWood Products 44-49\nFurniture and Wood Products\nFurniture 94\n\n\n\nMiscellaneous\n\n\n\nFoodstuffs and Beverage 16-24\nRaw hides and Leather 41-43\nFootwear and Headgear 64-67\nStone and Glass 68-71\n\n\n\n²⁵Please refer to Brandt et al. (2023) for a detailed and comprehensive discussion about the reporting and sample issues\nof both the ASIF data and the NTSD data and a review of the literature using these two datasets.\n\n\n42\n\nMention: \"NTSD data\""}, {"role": "assistant", "content": "{\"role\": \"background\", \"usage_action\": \"validate\", \"summary\": \"Its reporting and sample issues are discussed alongside the other firm dataset.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:001598:34:2", "occurrence_id": "508d3548386c541e01a8c25d", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: country fixed effects and (world) region by year\nfixed effects. Countries are classified into 7 regions based on World Bank classifications.\nDestination-specific control variables include the logarithms of population and GDP (source:\nConte et al. (2022)) and the average exchange rate over the three years preceding the\ninvestment (national currency/USD, Penn World Tables, mark 10.1, Feenstra et al. (2015)).\nStandard errors are clustered at the destination country level. Significance levels: ***\n_p <_ 0 _._ 01, ** _p <_ 0 _._ 05, - _p <_ 0 _._ 1.\n\n\n33\n\nMention: \"Penn World Tables\""}, {"role": "assistant", "content": "{\"role\": \"supporting\", \"usage_action\": \"source\", \"summary\": \"Three-year average exchange rates against the dollar are taken from this release.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:001618:33:1", "occurrence_id": "d376974c55e7d04a72c08688", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: 28\nLAC 39.77 25.59 12.98\nMENA 11.03 17.55 5.10\nSAR 9.33 42 4.25\nSource: Constructed by the authors using the WBES.\nNote: SAR stands for South Asia, MENA Middle East and North Africa, EAP East Asia and Pacific, SSA Sub-Saharan\nAfrica, LAC Latin America and the Caribbean and ECA Europe and Central Asia.\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\nNotes: (i) SAR stands for South Asia, MENA Middle East and North Africa, EAP East Asia and Pacific, SSA SubSaharan Africa, LAC Latin America and the Caribbean and ECA Europe and Central Asia. (ii) GVC1 refers to firms\nthat export and import simultaneously, GVC2 = GVC1 + international certification, GVC3= GVC1+ share of its\ncapital owned by a foreign firm, GVC4 combines the four criteria altogether.\n\n\n\n11 Given that some firms might have one of the variables missing, the sum of production and non-production does\nnot necessarily add to the total number of employees.\n\n32\n\nMention: \"WBES\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"Regional shares are constructed from the enterprise survey across regions.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:001629:12:0", "occurrence_id": "019c511c5fb3812c1716b490", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: After applying the basic background noise filters, the total luminosity mask contains 76,754 pixels. To\n\nconstruct the mask of civilian nighttime lights, we subtract 1,324 pixels identified as military bases,\n\nwhereas 1,110 pixels come from the OSM-military dataset. The paper results use the sum of all the\n\nlight captured in each pixel of the civilian and military masks, which, in the case of the VIIRS, data, is\n\navailable at monthly intervals and yearly for the VIIRS-like series. This pixel-level processing allows\n\nus to produce civilian and military luminosity series at any level of geographical aggregation.\n\n\n**4.** **Results**\n\n\nOur analysis is divided into three main components. As a first step, we show that civilian night lights\n\ncorrelation with GDP is higher than for total luminosity (including light from military bases).\n\nMoreover, we show that the spatial distribution of civilian and total nighttime lights differs due to the\n\nconcentration of military bases in strategically important areas. Using these two results, we argue\n\ncivilian lights provide a better benchmark for local economic activity, especially after the withdrawal\n\nof the international military presence began in 2014.\n\n\nOur second set of results compares the contraction of luminosity and GDP in 2021 and its evolution\n\nin the following years. We show that most of the reduction in total luminosity would have occurred\n\nin the absence of any economic dislocation since two-thirds of the contraction was driven by the\n\nshutdown of foreign military installations. Tracking the evolution in civilian nighttime light post-2021,\n\nwe find that civilian luminosity by 2023 is above its 2020 levels, a result we interpret as local economic\n\nactivity also displaying a significant recovery. We further validate this result using a synthetic control\n\napproach that benchmarks civilian luminosity in Afghanistan with that of neighboring countries.\n\nFinally, we explore the spatial changes in the distribution of economic activity. Results highlight that\n\nall regions experienced the 2021 shock (and its latter recovery) equally. We conclude by arguing for\n\nthe need to\n\nMention: \"VIIRS\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"analyze\", \"summary\": \"Monthly pixel radiance is summed within civilian and military masks to build lit surfaces.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:001620:3:1", "occurrence_id": "9cba123ee735af295614b9d5", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: , 2016). In fact, some studies suggest that during the riots\n\nin Gujarat in 2002, women were victims of most extreme forms of sexual cruelty, including\n\nrape, gang rape, stripping, insertion of objects into their body, and molestation (Hameed\n\net al., 2002). This paper examines how women’s marriage age and postmarital socioeconomic\n\nstatus evolved in Gujarat after the 2002 riots. Even though several studies have examined the\n\nimpact of Hindu-Muslim riots on several social, economic and political outcomes of interest,\n\nwe specifically contribute to the literature by assessing the effect of the riots on women’s\n\nmarital outcomes.\n\n\nTo examine the effects of the Gujarat riots of 2002 on women’s marital outcomes, we use\n\na retrospective state-year level dataset from the fourth round of the National Family Health\n\nSurveys (2015-2016) and a difference-in-differences strategy. Our empirical strategy relies\n\non variation over time in marriages that took place before and after 2002 and the state\nwise variation in the occurrence of riots. We also use the event study approach to observe\n\ndifferential trends in women’s age at marriage between Gujarat and the other Indian states.\n\n\nThe difference-in-differences estimates suggest that age at marriage declined for women\n\n\n2\n\nMention: \"National Family Health\n\nSurveys\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"Retrospective state-year marital histories from the fourth round support the difference-in-differences design.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:001636:10:0", "occurrence_id": "ed563072ec58cbcb162cddcf", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: worker. In the following, we describe the identification of deceased workers and incumbent\n\n\nworkers in the administrative data. We also provide evidence that, when comparing peer groups\n\n\nwith the same pre-death racial composition of employees, peer group characteristics do not\n\n\npredict whether a white or non-white worker dies. In addition, we verify that the death of a\n\n\nnon-white worker, compared to the death of a white worker, leads to a lasting drop in the non\n\nwhite share of the peer group. For these reasons, we can treat the race of the deceased worker\n\n\nas a conditionally exogenous and significant shock to the peer group’s racial composition and\n\n\ncan estimate its effect on incumbent workers’ retention at the firm.\n\n\n**3.1** **Sample** **Construction**\n\n\n**Unexpected** **worker** **deaths.** We identify worker deaths based on the employer notifications\n\n\nin the RAIS data. When employers report contracts that were terminated because the employee\n\n\ndied, they distinguish between deaths due to a work accident, deaths while commuting to work,\n\n\nand all other deaths. We exclude work accident and commuting deaths in order to avoid concerns\n\n\nthat safety conditions at and on the way to work may affect both the likelihood of worker deaths\n\n\nand the retention decisions of workers. Moreover, to rule out spurious death notifications, we\n\n\ndrop deaths of individuals for whom we observe an employment contract at least 30 days the\n\n\ndate of death (less than 3% of all deaths).\n\n\nIn order to identify separations that are likely unexpected for coworkers, we focus on deaths\n\n\nof workers younger than 65 who have a full-time (with at least 30 hours) and permanent job.\n\n\nMoreover, we only include individuals with a minimum tenure of three months at the time of\n\n\ndeath, as a large share of contracts are terminated in the first three months when firms can\n\n\ndismiss workers without cost. We also exploit employer reports on workers\n\nMention: \"RAIS data\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"Employer notifications of contracts terminated by death distinguish accident from other causes.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:001663:5:0", "occurrence_id": "0bac665cc882a7fdd08ff89d", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: Asia from 2000 to 2003, the AICD Database applied the same methodology for Sub-Saharan Africa\nand collected data from 2004 to 2009.\n\n**(b) Have energy subsidy reforms succeeded in restraining energy consumption?**\nTo provide an answer to this question the study uses both indicators of energy prices and related\nconsumption. In the case of gasoline and diesel, road sector consumption of fuels is reported, as\nthe transport sector is one of the most intensive users of such fuels. In the case of electricity power\nconsumption is provided:\n\n **Fossil Fuel Prices** (US$ per liter): Gasoline, diesel and kerosene retail tariff (US$ per liter).\n\n **Electricity Prices** (US$ cent per kWh) – Residential Average Electricity Tariff level (US$ cent per\n\nkWh)\n\n **Road Fuel Consumption** (kt of oil equivalent per capita): Gasoline and Diesel Fuel Consumption (kt\n\nof oil equivalent per capita) by the road sector\n\n **Power Consumption** (kWh per capita) - Electric power consumption measures the production of\n\npower plants and combined heat and power plants less transmission, distribution, and\ntransformation losses and own use by heat and power plants. (kWh per capita)\n\n\n**(c) Have energy subsidy reforms managed to avoid adverse social impacts?**\n\nTo address this final question, evidence from household surveys on the distributional impact of\nsubsidies by income quintile (or deciles, if available) as well as the materiality of energy subsidies,\nreporting for each fuel how much income is spent by each quintile of the population is used in the\ncase studies.\n\n\n **Expenditure of different energy sources** (what proportion of income poor households spend on\n\neach fuel), by quintiles or deciles where available divided by rural/urban areas.\n\n **Welfare impact of removing energy subsidies, by fuels\n\nMention: \"AICD Database\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"It extends the Asian methodology to African countries over a later period.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:001717:29:0", "occurrence_id": "b3126d35dcbce0d8478f7f9b", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: Figure 6: Planned road and rail investments\n\n\nSource: forthcoming World Bank Project Appraisal Document\n\n\nWe create counterfactuals using the transport networks from each country described in Sec\n\ntion 2. We assume a new speed for the new road corridor and reduce border delays in some\n\n\nscenarios. For the rail corridor, we keep the road network as it is and assume a new direct\n\n\ntransport line between Ngaoundere, Yaounde and Douala. New transport times are computed\n\n\nassuming that the previous roads can be used as well as the new rail line, which is more effi\n\ncient. Stops between the main cities are not permitted. The first section between Ngaoundere\n\nand Yaounde is assumed to be 627 km with an average speed of 70km/h. 22 The second section\n\n\nbetween Yaounde and Douala is assumed to be 261 km with an average speed of 70km/h.\n\n\n**4.3.3** **Aggregate Impacts**\n\n\n**Employment impacts** Table 7 reports the change in employment share for all sectors at the\n\n\nnational level from the combined road and rail investments, complemented with universal ac\n\ncess to electricity and lower border delays. The proposed transport investments are expected\n\n\nto have a marginal impact on structural change at the national level for most countries. Rural\n\n\nelectrification tends to increase employment in sectors of tradable goods (agriculture and man\n\nufacturing). Better regional integration through lower transport and border costs will increase\n\n\nmanufacturing employment in Cameroon, and agricultural employment in Chad. Nigeria bene\n\nfits from a better access to its neighbors to specialize slightly more in the services sector. When\n\n\ncombining all interventions, structural changes are marginal in Nigeria but larger for Chad and\n\n\nCameroon. Cameroon specializes more in traded goods, both agricultural and manufacturing\n\n\n22Distance assumptions come from the website rome2rio.com which reports distance per transport mode.\n\n\n28\n\nMention: \"rome2rio.com\""}, {"role": "assistant", "content": "{\"role\": \"supporting\", \"usage_action\": \"source\", \"summary\": \"Distance per transport mode from this website sets the trade cost assumptions.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:001718:18:0", "occurrence_id": "82c5677126920f017d164493", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: Figure 6.b, depicts the partial association between income per capita and the WEF perception of road\nquality during 2008–12. The figure confirms the findings of figure 6.a, that countries with higher income per\ncapita tend to have better road quality. Perceived quality of the road network is the highest in South Africa (and\nabove the international benchmark) for 2008–12—thus, outperforming countries in South America, like Brazil\nand Colombia. Other MICs in the region (for instance, Nigeria and Gabon) clearly underperform for their level\nof income per capita. Among LICs in the region, Guinea appears to have the lowest level of road quality,\nwhereas the quality of roads in Rwanda and Ethiopia is far better than the one predicted by the international\nnorm.\n\n\nRailroad quality also exhibits a direct and positive relationship with income per capita after controlling\nfor demographic and geographic indicators. The perception of railroad quality is the highest in Gabon, closely\nfollowed by South Africa. Countries with lower income per capita (say, Sri Lanka and Morocco) display similar\nlevels of rail quality. Among MICs in the region, the perception of rail quality in Nigeria and Angola is lower\nthan that predicted by the international norm. In the group of LICs in Sub-Saharan Africa, Uganda exhibits the\nlargest distance to the international norm.\n\n\n**Figure 6. Transport Quality and Income per Capita**\n\n\n**a. Share of paved roads** **b. WEF perception of road quality**\n\n\n\n2008 - 2012 Benchmark (average)\n\n\n\n\n\n2008 - 2012 Benchmark (average)\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n|Col1|Col2|\n|---|---|\n|MUS|MUS|\n||BFA
MDG
MLI
MOZ
NER
SEN|\n|CMR
GHA
KEN
TZA|CMR
GHA
KEN
\n\nMention: \"WEF perception of road\nquality\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"analyze\", \"summary\": \"Its survey-based road quality rating is correlated with income per capita.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:001723:20:0", "occurrence_id": "cb2d6319e28bfc429a74c974", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: Lack of innovativeness is also reflected in the small proportion of innovating firms introducing new\ninnovation outputs such as patents (Table 11), although regional innovation leaders present values above\nthe average for the ECA and Africa regions. However, laggards are below international standards. Other\ninnovation outputs such as trademarks or licensing are more important than patents for all the countries\nconsidered.\n\n\nTable 11. Innovation outputs (% of innovating firms)\n\n**Bangladesh** **Pakistan** **India** **Nepal** **SAR average** **ECA** **Africa**\nPatent 8% 2.2% 8% 1.3% 5% 2.5% 6%\nOther than patents 18% 5% 32% 1.7% 14% - 17%\nSource: Author’s elaboration from Enterprise Survey (2014)\n\nTable 12. Links between innovativeness and firm characteristics\n\n**Bangladesh** **India** **Nepal** **Pakistan**\nNo innovators age 18.70 22.54 13.65 22.15\nImitators age 18.42 20.39 18.21 34.24\nradical\n\nMention: \"Enterprise Survey\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"Innovation and patenting behaviour across South Asian countries is drawn from this round.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:001728:4:0", "occurrence_id": "853fd026630f5013d2b110df", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: Table 1: Venezuelan Net Population Displaced Abroad Over the Years\n\n\n2010 2015 2019\n\n\nWorldwide 556,641 695,551 4,326,330\nSouth America 62,240 86,964 3,239,730\nNorth America (US+Canada) 196,910 273,418 371,919\nEurope (Portugal, Spain, Italy) 203,117 224,328 309,170\nCentral America & Mexico 21,260 33,065 166,974\nCarribbean 19,629 21,74 119,333\nOthers 53,485 56,702 119,204\nSouth America\n\n2010 2015 2020\nColombia 43,511 48,714 1,717,352\nPeru 3,504 4,129 1,043,460\nChile 8,095 54,787 475,702\nEcuador 6,120 8,901 415,835\nBrazil 2,844 3,425 261,441\nArgentina 1,236 1,240 217,562\n\n\nSource: Author’s calculation from UN Data\n\n\nThis paper attempts to fill this gap by investigating how integrated the Venezuelan refugees and\nmigrants are in the education, formal labor market and social protection sectors of Brazil 4 and how\ndi↵erent economic and social factors accelerate or hinder the process of integration. By integration,\nthis paper refers to the definition advocated by OECD (2011) that defines integration as a two-way\nprocess of adaptation by migrants\n\nMention: \"UN Data\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"Refugee and migrant stocks by host country are compiled from this portal.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:001729:7:1", "occurrence_id": "bc9189208fbcd789321b4007", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: interest rates via explicit regulation. Specifically,\nwe focus on IRCs in lending and deposit markets, acknowledging that _de jure_ restrictions can\nalso apply to interbank and bond markets.\n\n\nThe formulation and completion of the survey entailed a number of inter-related steps.\nLeveraging existing contacts at central banks and financial supervisory authorities, the initial\noutreach effort targeted the pertinent staff within local regulators and supervisors. However,\ngiven the sometimes-elusive nature of IRCs, with implementing authorities varying from\ncentral banks to different ministries, we also decided to contact the local banking associations,\nas these are in a prime position to provide specific references to the domestic or regional\ninstitutional arrangements. With the aim to cover as many countries as possible, the outreach\neffort included more than 150 jurisdictions.\n\n\nDespite our best efforts, our survey faced several challenges. Not every country responded to\nthe survey. Also, officials from the same country or even the same agency sometimes provided\nconflicting answers. Therefore, we had a second outreach effort to non-respondent local\nauthorities relying on the contacts of World Bank Group financial sector experts, while we also\nfollowed up with the authorities that had provided inconsistent or incomplete responses. In a\nfew countries where we still faced difficulties getting a response from the local authorities, we\nrelied on the answers of World Bank Group financial sector experts. 6 In addition, in an attempt\nto reconcile any inconsistencies, we checked our responses with Ferrari et al. (2018), who\nrecently took stock of lending interest rate caps collecting data from private and public sources;\nwith the 2017 Global Financial Inclusion and Consumer Protection Survey, which included\n\n\n6 These countries are Algeria, Argentina, Bangladesh, China, Ethiopia, Ghana, Kenya, South Africa and the United\nStates.\n\n\n6\n\nMention: \"2017 Global Financial Inclusion and Consumer Protection Survey\""}, {"role": "assistant", "content": "{\"role\": \"supporting\", \"usage_action\": \"validate\", \"summary\": \"Its responses are compared with a separate stocktake of interest rate caps.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:001730:29:0", "occurrence_id": "8a6d399c23d2d75efb1fdc58", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: **Table 1: Children’s anthropometrics prior to the influx of refugees (refugees Vs. non-refugees receiving areas)**\n\n\n\n\n\n\n\n\n\n|Col1|(1)
Refugees
Areas*|(2)
Non-refugees
Areas|Overall|(1) vs. (2)|\n|---|---|---|---|---|\n|**1991**|||||\n|Height-for-age Z-score|-1.986|-2.028|-1.991|0.042|\n||(0.028)|(0.069)|(0.026)|(0.082)|\n|Stunting Prob (HAZ<-2SD)|0.513|0.542|0.516|-0.029|\n||(0.009)|(0.024)|(0.008)|(0.026)|\n|**1992**|||||\n|Height-for-age Z-score|-1.890|-2.017|-1.902|0.127|\n||(0.031)|(0.088)|(0.030)|(0.102)|\n|Stunting Prob (HAZ<-2SD)|0.489|0.529|0.492|-0.041|\n||(0.010)|(0.031)|(0.009)|(0.033)|\n\n\n**Source:** 1991/1992 Tanzania DHS.(*) Kagera, Kigoma\n\nMention: \"Tanzania DHS\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"Stunting probabilities by region are computed from this early round.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:001736:26:1", "occurrence_id": "85c60a4d56a27f3eeb179bad", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: commonly as a reference\n\nfor studies on reserves accumulation. 28 A period in the model refers to a year. I choose a subset of\n\n\nparameter values (summarized in table 2) that can be directly pinned down from the data, and then\n\n\nI choose a second subset of parameter values (summarized in table 3) such that model simulations\n\n\nmatch key aspects of the data.\n\n\nThe risk aversion parameter value ( _σ_ = 2) is standard in quantitative business cycle and sovereign\n\n\ndefault studies. The international risk-free interest rate is set to match the average real interest rate\n\n\nfor US Treasury Bills from 1980 to 2017, which is set to 1 _._ 1% ( _r_ _∗_ = 0 _._ 011). I use spreads from\n\n\nthe EMBI+ to parameterize the lenders’ stochastic discount factor. I assume that a period with\n\n\nhigh risk aversion is one in which the global EMBI+ is one standard deviation above the median\n\n\nover the sample period. With this procedure, I obtain 6 episodes of high risk premium every 20\n\n\n28The time period starts in 1994 because the Mexican central bank independence reform was approved in 1993.\n\n\n24\n\nMention: \"EMBI+\""}, {"role": "assistant", "content": "{\"role\": \"supporting\", \"usage_action\": \"source\", \"summary\": \"Its spreads parameterise the lenders' stochastic discount factor and the risk-aversion state.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:001741:16:0", "occurrence_id": "fe4e0546249da6f47989131f", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: in Table 15, I rely on a first-difference model in which I examine the effect of the future use of\nInternet job search on past labor market outcomes. To do so, I additionally rely on the 2006\nELMPS survey round and follow the same individuals included in my estimation sample (the 2012\nand 2018 panel) that were also surveyed in 2006. Focusing on working aged individuals, I examine\nthe effect of the change in Internet job search between 2018 and 2012 on changes in labor force\nparticipation and employment between 2012 and 2006. The results reported in Table 15 show that\nthe change in Internet job search between 2018 and 2012 is actually associated with lower labor\nforce participation in the pre-period between 2012 and 2006, while my results in Table 6 actually\nshow a positive association. This suggests that individuals who are using the Internet for job search\ndo not initially have better labor market outcomes compared to individuals who are not—if\nanything, they seem to have lower labor force participation rates in the pre-period. Analyzing the\nimpact on employment in Panel B actually shows no effect of the future use of Internet job search\non past changes in employment, suggesting that the results are not driven by pre-existing trends in\nemployment between individuals who rely on Internet job search and those who do not.\n\n\nThe second test consists in utilizing all the available ELMPS survey rounds conducted in Egypt\nsince 1988 (1988, 1998, 2006, 2012 and 2018). Since attrition is problematic and it is impossible\nto follow individuals who remain in the working age category over such a long period of time, I\nrely on sub-district ( _shyakha_ ) level regressions. 7 [^7: The _shyakha_ is the smallest administrative division in Egypt. Egypt is divided into 27 governorates that are further divided into\n_qism_ (the second administrative division) and _shyakha_ (the third administrative division). The number of sub-districts ( _shyakha_ ) is\n1,101.] In these regressions, I use the percent of\nmale/female Internet job searchers\n\nMention: \"ELMPS survey\""}, {"role": "assistant", "content": "{\"role\": \"supporting\", \"usage_action\": \"source\", \"summary\": \"The earlier round lets individuals in the later panel be traced back to past outcomes.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:001749:18:2", "occurrence_id": "01e84e5dff9a7951e5b28958", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: *𝚤** ) −1/𝜃𝜃\n𝑇 **𝑖**\n\n\n\nwith appropriate parameter constraints. Second, these estimates are transformed using a sectoral\n𝑑 **𝚤**\nelasticity of substitution ( 𝜃 𝜃 ):\n\n𝑇 𝑖𝑇 **𝑖** = (𝑑 � 𝚤𝑑 **𝚤** ) −1/𝜃𝜃\nDatabase (WIOD) is used and an experimental data set from the Asian Development Bank (ADB-MRIO).\nTo obtain the estimates of 𝑇 𝑖𝑇 **𝑖** , international and domestic trade data from the World Input-Output\nreaction of demand to prices, and hence a higher responsiveness of import demand to trade frictions.\nThe parameter 𝜃 𝜃 is estimated for each sector in Egger _et al_ . (2018). A higher 𝜃 𝜃 means a more elastic\nreacts less to changes in trade costs.\nGenerally, 𝜃 𝜃 takes on lower\n\nMention: \"Database (WIOD)\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"Its input-output tables are one of two sources used to estimate trade elasticities.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:001751:15:1", "occurrence_id": "231f7d08d9bc439882b0de36", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: \nMost countries with ADL questions are in Europe/Central Asia and Sub-Saharan Africa. As\nexpected, surveys focused on older persons (e.g. CHARLS in China) have questions on ADL.\nWhile not shown in Appendix 1, there is heterogeneity in the ADL questions that are asked\nacross countries with most often questions around physical basic activities such as walking over\n100 meters, standing or sitting.\n\nAppendix 2 includes 36 countries, 53 data sets and 76 data set-years with broad activity\nlimitation questions. The most commonly found broad activity question asks about the person\nbeing limited in daily activities or in learning or in any economic activity due to a health problem\nin the past six months (not shown in Appendix 2). Some countries have several questions to get\nat broad activity limitations, including some recording the number of days the person was unable\nto carry out usual activities.\n\nAppendix 3 has 50 countries, 81 data sets and 113 data set-years with a general disability\nquestion such as “does [Name] have a disability?” Often such questions are followed up with a\nquestion on the type of disability or the impairment the person has.\n\nAppendix 4 has 43 countries, 54 data sets and 75 data set-years that have other types of disability\nquestions such as belonging to the so-called disabled social group for Armenia. 4 In addition,\nsome of the questions found in this list can be mixes of different types of questions such as\nimpairments mixed with chronic health conditions in Tunisia, Bosnia, and Bulgaria. We have\n\n\n4 Disability focused surveys (e.g. Philippines Model functioning Survey) were not covered in this table for other\ndisability questions, but were covered in Tables 1 and 2 and Appendices 1, 2 and 3. Disability focused surveys\ntypically have several types of other disability questions not beyond functional ADL, general and broad activity\nlimitation questions.\n\n3\n\nMention: \"Philippines Model functioning Survey\""}, {"role": "assistant", "content": "{\"role\": \"background\", \"usage_action\": \"inform\", \"summary\": \"It is named as a disability-focused survey excluded from this table but covered elsewhere.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:001760:6:0", "occurrence_id": "c63b86776a94817d8a3480bc", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: _Determinants of empowerment_\n\nA relatively rich research identifies and describes which socio-economic variables tend to have a\n\nstrong association with women’s empowerment and agency. This research shows that women\n\nwho are older, have higher literacy, more children, and live in households of higher\n\nsocioeconomic status are more likely to participate in household decisions (Hameed et al. 2014).\n\nA study in Indonesia found that women’s bargaining power for decisions on use of prenatal care\n\nand delivery is highly influenced by a woman’s access to economic resources. Further, social\n\npower influences whether decisions are made jointly rather than by the husband alone. Women\n\nwho are from higher education or family status than their male spouse were more likely to\n\nexperience couple joint decision-making (Beegle, Frankenberg, and Thomas 2001). As will be\n\ndiscussed in more detail below, the quality of a woman’s relationship is also related to her\n\nparticipation in household decisions and her agency overall (Allendorf 2012). For example, a 2000\n\nstudy in Bangladesh found that the extent to which women negotiated employment depends on\n\nthe level of harmony in their relationships (Kabeer 2001).\n\n\n_Empirical methods to measure agency and the intra-household bargaining models_\n\nEmpowerment is not a new concept but its systematic measurement by researchers and\n\npractitioners is relatively new (World Bank 2005). This recent shift is related to the idea that\n\nempowering the poor is crucial to reduce poverty – since no one has a greater stake in the fight\n\nagainst poverty than the poor themselves. A gold standard for measuring women’s\n\nempowerment is not yet available. The methods to gauge women’s agency, a key component of\n\nempowerment, have been largely inconsistent (Donald et al., 2016). Questions on household\n\ndecision-making and resources allocations, such as the ones of the DHS surveys used in this\n\npaper, are increasingly added to household surveys. However, some issues remain on how to\n\nconstruct a\n\nMention: \"DHS surveys\""}, {"role": "assistant", "content": "{\"role\": \"supporting\", \"usage_action\": \"inform\", \"summary\": \"Its decision-making and resource allocation questions are now common, but construction issues remain.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:001777:3:1", "occurrence_id": "419cb8cdad8440cfba349bf2", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: also increase land productivity generally.\n\n\nThe second empirical regularity has received far less attention. We call it the inverse\n\n\n_plot-size_ productivity relationship (and refer to it as plot-size IR). This relationship, observed\n\n\nin many Sub-Saharan African countries, states that smaller plots are more productive than larger\n\n\nplots, even within a farm household (Ali and Deininger, 2015; Assunção and Braido, 2007;\n\n\nBarrett et al., 2010). Although rarely noted, such a relationship implies that land\n\n\nfragmentation—subdividing already small plots into even smaller units—would heighten\n\n\nproductivity. But more and smaller plots lead to increased travel time (in moving from plot to\n\n\nplot), more wasted space along borders, and fewer options for mechanization, which typically\n\n\nfunctions best on larger plots. For these reasons and others, this finding does not seem credible.\n\n\nA common policy recommendation to improve land productivity is not fragmentation but\n\n\n1 Estimates from PovcalNet ( _iresearch.worldbank.org/PovcalNet_ ), the World Bank data tool for\nestimating extreme poverty, indicate that most of the poor in the rest of the world also live in rural areas.\nFor example, in China essentially all the extreme poor (living on less than US$1.90 a day) are estimated\nto be in rural areas; and in India about 80 percent.\n\n\n2\n\nMention: \"PovcalNet\""}, {"role": "assistant", "content": "{\"role\": \"supporting\", \"usage_action\": \"source\", \"summary\": \"It indicates where most of the world's extreme poor live.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:001774:22:1", "occurrence_id": "2c9bee46b2d9fb0a9d787546", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: Group. 2014. “World Development Indicators.”\n\nhttp://databank.worldbank.org/data/views/variableselection/selectvariables.aspx?source=wo\nrld-development-indicators.\n\n\nYoung, Alwyn. 2012. “The African Growth Miracle.” _National Bureau of Economic Research_\n\n_Working Paper Series_ No. 18490.\n\n\n20\n\nMention: \"World Development Indicators\""}, {"role": "assistant", "content": "{\"role\": \"background\", \"usage_action\": \"inform\", \"summary\": \"A reference list entry pointing to the databank page for these indicators.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:001788:5:0", "occurrence_id": "bccb65fc2af295576632131a", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: ###### Introduction\n\nEven before COVID-19 shut schools, the world was in the middle of a learning crisis that threatened efforts\nto build human capital—the skills and know-how needed for the jobs of the future. More than half of\nchildren (53 percent) in low- and middle-income countries either were out of school or failed to learn to\nread with comprehension by age 10 and so were in learning poverty. 1 [^1: World Bank 2019.] The most recent historical trends\nsuggest that it will take 50 years to halve learning poverty in the developing world. COVID-19 is likely to\nslow that rate by deepening learning gaps and so increasing the number of children in learning poverty in\nmany countries.\n\nTemporary school closures in more than 180 countries have kept nearly 1.6 billion students out of school,\nfurther complicating global efforts to reduce learning poverty. Although most countries have made heroic\nefforts to put remote and remedial learning strategies in place, learning losses are accumulating rapidly.\nA recent survey on national education responses to COVID-19 by the United Nations Children’s Fund\n(UNICEF), the United Nations Educational, Scientific, and Cultural Organization (UNESCO), and the World\nBank shows that while countries and regions have responded in various ways, they have found it difficult\nto reach even half of students.\n\nCOVID-19-related school closures are forcing countries even further off track from achieving their learning\ngoals. Students currently in school stand to lose $10 trillion in labor earnings over their working lives. 2\nThat is one-tenth of global GDP, or half the United States’ annual economic output\n\nMention: \"survey on national education responses to COVID-19\""}, {"role": "assistant", "content": "{\"role\": \"supporting\", \"usage_action\": \"source\", \"summary\": \"Its country responses support the claim that learning losses are accumulating.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:001796:11:2", "occurrence_id": "eb36475327482878730e9fd8", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: > 1 (JPN) 32 (CAN)\nSource: OECD STRI; own calculations\n\n\n5 There is, however, no variation in limitations on duration for these service professionals across sectors for each\ncountry according to the STRI data for the year 2017 (detailed analysis at the sector level is presented in Annex\nTable 3).\n\n\n10\n\nMention: \"the STRI data\""}, {"role": "assistant", "content": "{\"role\": \"supporting\", \"usage_action\": \"validate\", \"summary\": \"It shows no cross-sector variation in duration limits for these professionals.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:001799:34:1", "occurrence_id": "b35eb78c41dc880915c7ce2d", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: reported (out of 7 days) 0.16 0.32 -0.16\n(1.75) (1.81) (0.86)\n\n\nOutcome Variable Average 77.75 48.71 29.04\n\n\nObservations 1,097 1,097 1,097\n\n\nSource: Author calculations from The Hohoe Garment Makers Project Data\n\n\n33\n\nMention: \"The Hohoe Garment Makers Project Data\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"analyze\", \"summary\": \"Outcome averages over 1,097 observations are computed from this project's data.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:001803:6:1", "occurrence_id": "98f4eb790cf7faf4cfa55656", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: well as pre- and posttax/transfer estimations. This coverage, however, comes at the cost of extensive imputations to fill gaps over time in\na country, to extend the data to countries with missing data, and to obtain post-tax/transfer estimates. We recognize\nthis limitation and point out that the World Bank PovcalNet is the unique comprehensive global dataset of nonimputed inequality (and poverty) data. For our purposes in writing this survey paper, the advantages of the SWIID\noutweigh its limitations.\n4 This section analyzes trends in poverty and inequality starting in the 1980s. Longer time series on wealth and\nincome inequality have been collected by Piketty (2014) and are restricted mostly to advanced economies. Piketty\nand Saez (2014) report sustained improvements in wealth and income distribution across Europe and the United\nStates from the 1930s to the 1970s, followed by a worsening of inequality starting in the 1970s to the 1980s. This\nsection captures the rise in inequality in advanced economies starting in the 1980s. Later sections examine several\nchannels that might account for this more recent trend.\n5 Fabrizio et al. (2017) provide an overview of income inequality trends in low-income countries.\n\n3\n\nMention: \"the World Bank PovcalNet\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"It is the only comprehensive global set of non-imputed inequality and poverty estimates.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:001811:24:1", "occurrence_id": "ccad1e030ea31ff78bb2892e", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: \nstandard deviation increase in private sector credit to GDP is 39 percentage points, approximately\n\n\nequal to the growth experienced by Brazil from 1990 to 2020, or double the growth experienced by\n\n\nKenya during the same 30-year period.\n\n\nOur interpretation of these results is that capital controls and limited banking system depth have\n\n\nprevented capital from flowing to viable projects in less financially open and developed economies.\n\nWere this not the case, we would not observe a change in returns as economies open and develop. 22\n\n\nOverall, these results are consistent with the idea that misallocation creates profit opportunities\n\n\nfor private equity investors. As financial systems open and become more competitive, “home run”\n\n\ninvestments are harder to find. Table A11 tests whether the effect of financial openness can be\n\n\nexplained by changes in perceived corruption, which may also have changed during this reform.\n\n\nThe direction of the result in Column (6) of Table 8 is robust to this control.\n\n\nIt is worth relating these findings to what is known about flows of private equity investments\n\n\nacross countries. Lerner et al. (2009) use data from Capital IQ to construct a database of 76,398\n\n\nprivate equity investments made in 1984-2008 across 123 countries. Although they do not measure\n\n\nreturns, they find associations between country characteristics and investment volume as a share\n\n\nof GDP. The authors report that private equity investment flows to countries with higher GDP per\n\n\ncapita and less corruption, although not to markets with less private sector credit to GDP. Although\n\n\ntheir paper examines a different sample of investors with preferences that potentially differ from\n\n\nthe IFC’s, one way to reconcile their results with ours is that the greatest volume of investment\n\n\nneed not necessarily go to markets with the highest returns; indeed, returns could be highest in\n\n\nmarkets with lower private sector credit to GDP precisely because there is less investment in those\n\n\nmarkets.\n\n\n21Table A8 reports results using the IRR as measure of performance. Table A9 reports results\n\nMention: \"data from Capital IQ\""}, {"role": "assistant", "content": "{\"role\": \"background\", \"usage_action\": \"source\", \"summary\": \"A cited study built a database of over seventy-six thousand investments across 123 countries from it.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:001814:27:4", "occurrence_id": "5c1195cfb7c0d3b861c5c10f", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: 9.203\n\n\nThis table shows the long-term effects of the program on a set of variables that result from aggregating groups of durable assets and\nhousehold characteristics. The reweighting strategy employed is the inverse probability weight (DiNardo et al., 1996). In Panel A observations are restricted to households included in 1997 ENCASEH (original households), while in Panel B observations are restricted\nto newly formed households in 2017 (new households) that were identified by searching for members no longer present in their original\n1997 households. The reweighting strategy seeks to reproduce the original sample distribution. Two different target distributions are set\nfollowing the attrition analysis done in _Table 3_ . _Original Distribution_ means the 1997 sample, which corresponds to the original households in the 506 localities. The purpose is to make our results comparable to the vast literature that focuses on this group. _Localities_\n_2017 distribution_ is based on the 334 localities chosen for the sample and assumes that all the original 1997 households in those localities\nwould have been found. The outcomes employed are: (1) _Transportation_, which adds the number of cars and vans; (2) _Entertainment_\n_equipment_, which gathers under entertainment equipment number of TV, radio and sound equipment; (3) _Kitchen supplies_, which sums the\nfollowing appliances: blender, refrigerator, electric grill, gas stove or microwave oven; (4) _Basic services_, which consists of the availability\nof the following services: firm floor, electricity, drainage and water access in the property; (5) _IT_ _items_, which refer to the number of\ncomputers and cellphones; and (6) _IT services_, which sums the home phone, internet and pay-TV; (7) _ln(imp cons)_, is the imputed measure\nof non-durable expenditure on food personal products, and clothing. Data employed comes from\n\nMention: \"1997 ENCASEH\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"analyze\", \"summary\": \"Original households are retained and reweighted by inverse probability to comparability with later years.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:001833:37:2", "occurrence_id": "b579c7dbb8a16857dc38a0d5", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: ** 𝑚 **𝑚** 𝑚 **𝑚** 𝑒𝑒𝑐𝑐,𝑡𝑡�, severance pay for\n\nredundancy dismissals (weeks of salary) �𝑠 **𝑠** 𝑠 **𝑠** 𝑠 **𝑠** 𝑠 **𝑠** 𝑒𝑒𝑐𝑐,𝑡𝑡�, and the share of women in wage\n\n**𝑤** **𝑤**\n\n\n\nindicators of labor market efficiency, we construct a composite index, using factor analysis, consisting of minimum wage (% of value added per worker) �𝑚 **𝑚** 𝑚 **𝑚** 𝑚 **𝑚** 𝑒𝑒𝑐𝑐,𝑡𝑡�, severance pay for\n\nredundancy dismissals (weeks of salary) �𝑠 **𝑠** 𝑠 **𝑠** 𝑠 **𝑠** 𝑠 **𝑠** 𝑒𝑒𝑐𝑐,𝑡𝑡�, and the share of women in wage\n\nemployment in the nonagricultural sector (𝑤 **𝑤** 𝑤 **𝑤** 𝑛𝑛𝑐𝑐,𝑡𝑡) from World Bank databases. The\n\n\n\n**𝑚** **𝑚** **𝑚**\n\nredundancy dismissals (weeks of salary) �𝑠 **𝑠** 𝑠 **𝑠** 𝑠 **𝑠** 𝑠 **𝑠** 𝑒𝑒𝑐𝑐,𝑡𝑡�, and the share of women in wage\n\nconstructed index is shown below.\n\nemployment in the nonagricultural sector (𝑤 **𝑤** 𝑤 **𝑤** 𝑛𝑛𝑐𝑐,𝑡𝑡) from World Bank databases. The\n\n**𝐸** **𝑏** **𝑏** **𝑏** **𝑓** **𝑓** **𝑓** **𝑓** **𝑙** **𝑙**\n\n\n\nconstructed index is shown below.\n\n**𝑤** **𝑤**\n\nMention: \"World Bank databases\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"Female wage employment shares and dismissal cost measures are taken from these compilations.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:001851:21:0", "occurrence_id": "7b91e5e1491c65d2e13a4698", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: component, there is no clear correlation between income and the contribution of health status to relative\n\nproductivity.\n\n\n**Figure 6. Contribution of health to relative productivity in Europe and Central Asia**\n\n\n_Note:_ Productivity figures are from the Europe and Central Asia extension of the Human Capital Index (ECA-HCI).\n\n\n**Table 7 Health component of the Europe and Central Asia extension of the Human Capital Index**\n**(ECA-HCI)**\n\n\n\n_Heavy_\n_episodic_\n_drinkers (%)_\n\n\n\n_Current_\n_smokers_\n\n_(%)_\n\n\n\n_Adult_\n_survival_\n\n_rate_\n\n\n\n_Children under_\n\n_5 not stunted_\n_(%)_\n\n\n\n_Health_\n_component,_\n\n_ECA-HCI_\n\n\n\n_Health_\n_component,_\n\n_HCI_\n\n\n\n_Subregion/country_\n\n\n\n_Obese adult_\n\n_population_\n\n_(%)_\n\n\n\n**Central Asia** **16.6** **11.5** **17.8** **0.859** **88.9** **0.941** **0.937**\n\nKazakhstan 21.3 19.9 24.3 0.845 92.0 0.928 0.937\n\nKyrgyz Republic 15.4 11.1 26.4 0.849 88.2 0.936 0.933\n\nTajikistan 12.6 7.9 18.8 0.871 82.5 0.942 0.930\n\nUzbekistan 15.3 7.9 12.3 0.866 89.2 0.949 0.939\n**Central Europe and Baltic**\n**15.9** **19.3** **27.3** **0.890** - **0.928** **0.933**\n**Countries**\n\nBulgaria 14\n\nMention: \"the Europe and Central Asia extension of the Human Capital Index (ECA-HCI)\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"Its productivity figures and health component underlie the contribution analysis.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:001858:3:0", "occurrence_id": "67882d7bd63af389ccbf8838", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: ###### **1 Introduction**\n\nSatellite-recorded nighttime light data are used extensively as a proxy for economic\n\n\nactivity. However, surprisingly little economic analysis employs data from the Visible\n\nInfrared Imaging Radiometer Suite (VIIRS). 1 These new nighttime light data, with a\n\n\nbetter resolution and a higher frequency than the previous generation of data, have the\n\n\npotential to facilitate our understanding of rapid and spatially heterogeneous economic\n\nchanges, such as those during the COVID-19 pandemic. 2 One reason for the hesitancy\n\n\nto use these data in the economic literature may be the difficulty of converting changes\n\n\nin nighttime light intensity into changes in economic activity. To the best of our\n\n\nknowledge, no properly estimated and widely accepted quarterly elasticity between\n\nVIIRS nighttime lights and economic activity exists to date. 3 In this paper, we attempt\n\n\nto fill this gap.\n\n\nVIIRS nighttime light data are an imprecise measure of man-made lights. Even\n\n\nafter aggregating the data to the country level and to quarterly frequency, substantial\n\n\nstatistical noise remains. It mainly stems from atmospheric conditions like cloud cover\n\n\nthat impact the effective number of observations. For instance, there are only five\n\n\neffective observations at the pixel level on average each month for a median devel\n\noping country. Equally important, missing observations in the summer months and\n\n\noccasional satellite sensor recalibrations contribute to the noise as well.\n\n\nIn this paper, we provide a novel framework to estimate the elasticity between\n\n\nnighttime light intensity and gross domestic product (GDP) at quarterly frequency\n\n\nthat takes measurement errors of nighttime lights explicitly into account. The elas\n\nticity can be identified because countries exhibit varying noise in their nighttime light\n\n\ngrowth. Using information from the average number of effective observations, we pro\n\nvide a regression equation that estimates the elasticity precisely. In emerging markets\n\n\nand developing economies (EMDEs)\n\nMention: \"VIIRS nighttime light data\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"validate\", \"summary\": \"Even aggregated to country quarters it remains an imprecise measure with substantial statistical noise.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:001862:7:0", "occurrence_id": "6a2e473fcb0c45e8965c2f3c", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: expectations around education, marriage, employment, and occupation. Moreover, when it comes to actively\n\nparticipating in community-level decision making, women enjoy very limited agency and they are also less likely to\n\nhold positions of leadership. This can be mainly connected to the widespread belief that men’s opinions matter more\n\nthan women’s, the overwhelming weight of household work and family duties, the strength of the status quo and\n\nthe fear of transgressing gender norms. In addition, there is evidence that elected women officials continue to face\n\ndiscrimination in access to training, information, day-to-day interactions and how they are treated by male\n\ncolleagues (World Bank, 2020).\n\n\n**Ensuring that women entrepreneurs and employees gain from the opportunities presented by economic**\n\n**development must be a priority.** Development of gender-related support interventions necessitates an\n\nunderstanding of the differences between male and female entrepreneurs. This should include the sectors in which\n\nthey operate, location, the experience of social and physical barriers, flexible workplace policies, and whether\n\nperformance gaps exist between male and female entrepreneurial firms, including the drivers behind these gaps.\n\n\nThe aim of the note is to gain a better understanding of the barriers to gender-inclusive Private Sector Development\n\n(PSD) in Myanmar, explore the differential experience female-owned enterprises have in comparison to their male\nowned counterparts, and finally, to provide recommendations for inclusive PSD based on the findings. To achieve\n\nthis, the note uses data from the 2019 Myanmar Gender and Entrepreneurship Survey (MGES) to explore the\n\ndifferential experiences of female-owned micro, small and medium sized enterprises in comparison to their male\n\ncounterparts.\n\n\nTaking the above into account, this note covers and highlights the following issues:\n\n\n - Characteristics of female and male owned enterprises\n\n - Barriers faced by women entrepreneurs\n\n - Determinants of Human Resource Management (HRM) policies\n\n - Impact of HRM policies on business development\n\n - Impact of HRM policies on workplace attitude/employee satisfaction and other areas\n\nMention: \"the 2019 Myanmar Gender and Entrepreneurship Survey\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"Differential experiences of female-owned micro, small and medium enterprises are explored from it.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:001873:32:0", "occurrence_id": "36e4a655b3b8cb40a4e298b5", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: epidemic, during which face-to-face data collection came to a standstill, we used 2019 as\nbenchmark year, implying that any censuses done after 2009 and surveys done after 2014 were\nconsidered up to date.\n\nOur findings are threefold. First price data are typically collected (often at a monthly basis), but\ncensus and survey data are often out of date. Only 14 out of 20 countries are current on their\npopulation census; 9 out of 20 are up to date on their economic census. Only 5 out of the 20\ncountries carried out an establishment survey recently and about half the countries are up to\ndate with respect to their health, labor force and consumption surveys (having been completed\nin 9, 11, and 14 countries respectively). The implication is that in almost half the cases, no or\noutdated microdata are used to produce core statistics including National Accounts and SDG\nreporting.\n\nOur second finding is that only in few instances where microdata has been collected, they are\nmade publicly accessible. Of the 140 potential microdata sets we looked for (7 data categories in\n20 countries) 81 had been collected and as few as 25 were accessible. Remarkably, of these 25\nabout a third are not accessible through the website of the NSO; they can only be downloaded\nfrom international microdata repositories. Our third finding is that recent microdata is scarce in\nMENA. Summary statistics are generally available –as evidenced by the Open Data Inventory\n(ODIN). However, many of these statistics are necessarily based on outdated microdata and\ndecision makers relying on such information would need to consider them with care.\n\nHence, we present a new indicator to complement the ODIN. The new indicator assesses the\ndegree of openness of recent microdata as well as the ease with which microdata users can\naccess this data on NSOs’ websites. Together with the ODIN, it gives a robust picture of data\nopenness in MENA. It is cost effective, takes less\n\nMention: \"Open Data Inventory\""}, {"role": "assistant", "content": "{\"role\": \"supporting\", \"usage_action\": \"source\", \"summary\": \"It evidences that summary statistics are generally available even where recent microdata are scarce.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:001889:24:1", "occurrence_id": "c8a2f8c1d6bd73cc1396a0da", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: interventions improved teachers’ giving attitudes toward parents._\n\n\n**7.4** **Indirect effects on student performance**\n\nTo complete our analysis of the indirect impacts of our interventions, we estimate the treatment\n\neffects on various measures of student performance. We employ four sets of outcome variables. First,\n\nwe look at parents’ satisfaction with their children’s education (column 1). Then, we examine the\n\npercentage of students repeating a grade within each school, using data provided by the ministry of\n\neducation (column 2). Subsequently, we present results for student absenteeism (column 3), an outcome\n\nvariable that is based on our recording of the absence of a randomly selected sample of students at\n\nendline during an unannounced school visit. Finally, we examine student performance in standardized\n\nPortuguese and Math tests that we administered in all schools to students enrolled in grades 3 and 4. 40\n\nWe employ specifications with full controls like in the previous tables. 41\n\n\n38 Figure A5 in the Appendix shows the full distribution of teachers’ giving in the dictator game across treatments.\n39 Similar results are obtained when including block fixed effects, as shown in Table A11 in the Appendix.\n40 In schools offering grade 5, we also administered the tests to grade 5 students. However, since 25 percent of our schools did\nnot offer grade 5, we restrict the analysis to the performance of students in grades 3 and 4.\n41 For the standardized tests, since we have student performance at baseline (even though not for the same students), we also\nestimate difference-in-difference regressions. The results of these estimations provide similar results to the ones presented in\nTable 6, i.e., a null impact of the treatments of student performance in the tests.\n\n\n23\n\nMention: \"the ministry of\n\neducation\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"Grade repetition rates within each school are taken from administrative records.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:001897:32:1", "occurrence_id": "bbbb4b5e9b9447602060ae9e", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: buildings and building materials) as a function of the number of floors of a building.\n\n\nFinally, buildings are supposed to be built for a century which gives us a depreciation rate 𝜌 of 0.01.\nThe interest rate 𝑖 which provides the cost of capital is set at a value of 5%.\n\n\n16 This figure is very close to the increase in the yearly income by inhabitant of the Ile de France compared to the\naverage in France (INSEE).\n17 The net budget of a household must be understood as the income minus transport costs.\n\n\n31\n\nMention: \"INSEE\""}, {"role": "assistant", "content": "{\"role\": \"supporting\", \"usage_action\": \"source\", \"summary\": \"Its figures on per-capita income in the region relative to the national average are cited.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:001908:49:0", "occurrence_id": "55870574541da3b280851497", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: Figure A.1. Did the Governing Coalition Manipulate Elections?\n\n\n\n\n\n_Source:_ Data for the study comes from field reports of the Armed Forces of the Philippines (AFP) and election returns from\nthe Philippines Commission on Elections (COMELEC).\n_Note:_ The figure presents the probability density of coalition candidates’ margin of victory in the 2007 election. Municipalities\nwere grouped into 20 bins of equal width according to the incumbent’s margin of victory. Each scatter dot represents one bin.\nIts horizontal coordinate represents the midpoint of the bin, and its vertical coordinate represents the fraction of municipalities\nfor which the incumbent’s margin of victory was within the bin. Dashed lines are linear fits, separately estimated on both sides\nof the eligibility threshold. Solid lines are nonparametric fits from a local linear regression that uses triangular kernels with a\nbandwidth of 5 percentage points, separately estimated on both sides of the eligibility threshold.\n\n\n47\n\nMention: \"the Philippines Commission on Elections (COMELEC)\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"Official election returns give coalition candidates' margins of victory by municipality.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:001944:10:1", "occurrence_id": "f493583b9d121e440cbf55c1", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: enditures – data**\n\n\nIn the rest of the paper we present new global estimates of out-of-pocket health\nexpenditures for each of the measures listed in Table 1. We present in this section\ndetails of the data we use.\n\n\nOur data are drawn from the 2019 version of the World Bank’s Health Equity and\nFinancial Protection Indicators (HEFPI) database (Wagstaff et al. 2018a; Wagstaff\net al. 2019). In generating the database, we identified potentially suitable surveys\nby searching the above-mentioned microdata catalogs and multi-country survey\ncollections. In some cases, the surveys were not accessible to us. In others, the data\nwere accessible, but the surveys turned out to lack key information. Sometimes the\ndata sets we analyzed were different adaptations of the same survey – for example,\nas mentioned above, Romania’s HBS has been harmonized by Eurostat and the\nWorld Bank’s ECAPOV exercise. We identified 1,948 potentially suitable surveys or\nadaptations thereof from 182 countries. We analyzed and obtained out-of-pocket\nexpenditure estimates for 1,000 of these surveys, covering 154 countries.\n\n\nOur out-of-pocket expenditure estimates vary in how they are computed. In some\ncases, the survey asks only in the consumption or expenditure section about out-of\n\nMention: \"Health Equity and\nFinancial Protection Indicators\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"Its measures, assembled from identified suitable surveys, are the study's data.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:001961:23:0", "occurrence_id": "f458c44f9f9532ba3986b7ca", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: _Source:_ Universal Postal Union database.\n_Note:_ Data are from 2015–17. No data were available for Bangladesh, Kyrgyzstan, and Senegal.\n\nIn particular, the emergence of cross-border e-commerce calls for reexamining the efficiency of customs\nprocesses. Cross-border e-commerce now accounts for 10–15 percent of the volume of global e-commerce,\nand it is expected to grow at twice the rate of domestic e-commerce until 2020. 84 A simplified customs\nprocedure such as prearrival risk assessment and digitizing the process through electronic data exchange\nand payment could all contribute to a more cost-efficient customs process.\n\nGiven the growing flow of low value cross-border shipments, customs authorities face more severe\nchallenges on the long-standing trade-off between foregone revenue and the cost of collection and longer\nclearance times. Many customs authorities around the world have adopted a de minimis threshold—that is,\na “valuation ceiling for goods, including documents and trade samples, below which no duty or tax is\ncharged and clearance procedures, including data requirements, are minimal.” 85 How to set a reasonable de\nminimis threshold has become of special importance. The calculation and collection of customs duties and\ntaxes on low-value shipments disproportionally burden small e-commerce exporters because they are\nunable to streamline these tasks. Research has shown that a reasonable de minimis threshold can be vital\nfor small business firms that depend on cross-border sales. 86\n\nAmong the 21 countries covered under Digital Business Indicators project, Bangladesh, Burkina Faso,\nPakistan, Senegal, and Tunisia do not have a de minimis threshold in place. Thresholds are often set based\non the value of the consignment, ranging from zero up to €1,000 (figure 10). Kenya and Tanzania set a low\nconsignment value threshold\n\nMention: \"Universal Postal Union database\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"Postal indicators for the covered countries are taken from this database.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:001961:23:0", "occurrence_id": "f033205ae49b9ee8a782c30f", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: _Source:_ Universal Postal Union database.\n_Note:_ Data are from 2015–17. No data were available for Bangladesh, Kyrgyzstan, and Senegal.\n\nIn particular, the emergence of cross-border e-commerce calls for reexamining the efficiency of customs\nprocesses. Cross-border e-commerce now accounts for 10–15 percent of the volume of global e-commerce,\nand it is expected to grow at twice the rate of domestic e-commerce until 2020. 84 A simplified customs\nprocedure such as prearrival risk assessment and digitizing the process through electronic data exchange\nand payment could all contribute to a more cost-efficient customs process.\n\nGiven the growing flow of low value cross-border shipments, customs authorities face more severe\nchallenges on the long-standing trade-off between foregone revenue and the cost of collection and longer\nclearance times. Many customs authorities around the world have adopted a de minimis threshold—that is,\na “valuation ceiling for goods, including documents and trade samples, below which no duty or tax is\ncharged and clearance procedures, including data requirements, are minimal.” 85 How to set a reasonable de\nminimis threshold has become of special importance. The calculation and collection of customs duties and\ntaxes on low-value shipments disproportionally burden small e-commerce exporters because they are\nunable to streamline these tasks. Research has shown that a reasonable de minimis threshold can be vital\nfor small business firms that depend on cross-border sales. 86\n\nAmong the 21 countries covered under Digital Business Indicators project, Bangladesh, Burkina Faso,\nPakistan, Senegal, and Tunisia do not have a de minimis threshold in place. Thresholds are often set based\non the value of the consignment, ranging from zero up to €1,000 (figure 10). Kenya and Tanzania set a low\nconsignment value threshold\n\nMention: \"Digital Business Indicators project\""}, {"role": "assistant", "content": "{\"role\": \"supporting\", \"usage_action\": \"source\", \"summary\": \"Its country coverage identifies which economies lack a de minimis threshold.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:001965:4:1", "occurrence_id": "0ed17dfb868c7d885442d0ce", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: undertake due diligence. In the PEP data set, the\n\n\ndefinition of politically exposed person depends on the classifications by intergovernmental bodies\n\n\nsuch as Financial Action Task Force (FATF) or legislation such as the European Union’s Anti-Money\n\n\nLaundering Directive. More importantly, for our purposes, a wide range of information is collected\n\n\nfor each politically exposed person. For example, the data set reports association with specific\n\n\ncompanies, and whether these linkages are established directly, or through family members, close\n\n\nbusiness associates or advisers of each individual PEP. Each politically exposed person is further\n\n\nclassified into four sub-categories based on their primary affiliation with Local Government, State\n\n\n3\n\nMention: \"PEP data set\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"validate\", \"summary\": \"Its definition of politically exposed person follows intergovernmental classifications rather than being fixed.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:001962:32:0", "occurrence_id": "d43126a65ecce4f20e5954c6", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: Figure 4. Financial sector developments\n\nA. Number of EMDE in post-crisis booms\nand credit crunches\n\nNumber of EMDEs\n\n25\n\n\n20\n\n\n15\n\n\n10\n\n\n5\n\n\n0\n\n\n\nB. EMDEs: Bank credit to\nprivate sector\n\n\n\nPercent of GDP\n\n\n70\n\n60\n\n50\n\n40\n\n30\n\n20\n\n10\n\n0\n\n\n\n2000 2007 2016\n\n\n\n\n\n\n\nC. Net capital inflows D. Banks’ profitability\n\n\n\nPercent of GDP Percentage points\n\n2.0 Equity Debt FX volatility (RHS)\n\n\n\nPercent Percent\n\nReturn on equity\n\n\n\n3\n\n\n2\n\n\n1\n\n\n\nReturn on equity\nReturn on assets (RHS)\n\n\n\n25\n\n\n20\n\n\n15\n\n\n10\n\n\n5\n\n\n0\n\n\n\n1.5\n\n\n1.0\n\n\n0.5\n\n\n0.0\n\n\n-0.5\n\n\n\n24\n\n\n18\n\n\n12\n\n\n6\n\n\n0\n\n\n\nE. Bank assets F. EMDE-based banks operating\nin EMDEs\n\n\n\nPercent of GDP\n\n\n120\n100\n80\n60\n40\n20\n0\n\n\n\n\n\n2000 2007 2016\nAdvanced economy 2016 average\n\n\n\nNumber of branches and subsidaries\n\n\n\n600\n\n\n400\n\n\n200\n\n\n0\n\n\n\nWithin region\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\nSource: Institute of International Finance, International Monetary Fund, World Bank.\nNote: EMDEs = Emerging market and developing economies, EAP = East Asia and Pacific, ECA = Europe and\nCentral Asia, LAC = Latin America and the Caribbean, MNA = Middle East and North Africa, SAR = South Asia,\nSSA = Sub-Saharan Africa, and GFC = global financial crisis, 2008/09.\nA. Credit booms (crunches) are episodes when private credit to GDP ratio exceeds (falls below) its long-term trend\nby 1.65 times one standard deviation of a cyclical component obtained with the HP filter. Sample includes about 140\nEMDEs with private sector credit data. Weights are based on nominal GDP measured in U.S. dollars at market\nexchange rates.\nB. Unweighted averages. Based on the private credit by deposit money banks and other financial institutions to\nGDP (%) from the World Bank’s Financial Development and Structure Dataset.\n\nMention: \"Financial Development and Structure Dataset\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"Private credit by banks and other institutions relative to GDP is taken from this dataset.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:001993:20:1", "occurrence_id": "329eb2cd615a168864f54b94", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: Hidalgo and Hausmann (2009).\nD. Exports and imports in percent of GDP.\nE. Government effectiveness survey from the World Bank’s Worldwide Governance indicators, defined as: perceptions of the quality of public\nservices, the quality of the civil service and the degree of its independence from political pressures, the quality of policy formulation and\nimplementation, and the credibility of the government’s commitment to such policies.\nF. Gross fixed capital formation in percent of GDP.\n\n\n1980-90 covariates. Higher initial education, greater economic complexity, institutional quality\n(measured using the WGI government effectiveness index), and lower initial productivity levels\nare consistently associated with a higher probability of switching into a higher-productivity club\n\n\n18\n\nMention: \"Worldwide Governance indicators\""}, {"role": "assistant", "content": "{\"role\": \"supporting\", \"usage_action\": \"source\", \"summary\": \"Its government effectiveness perceptions of public service and civil service quality are used.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:002007:22:1", "occurrence_id": "d32719b9b189b006d647dc4a", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: these efforts. The results\nalso show that high levels of external scrutiny in the form of ratings and Eurobond issuances have a high\nimpact on LICDs’ transparency as a result of the data disclosure and investor relations practices required\nby them. Finally, increasing the numbers of highly skilled staff in debt offices has also been identified as\na key part of improving transparency.\n\n\nIn the absence of reliable and comprehensive data disclosed by the authorities, indirect reporting is\ncurrently integrating and, in some cases, replacing direct reporting channels. Indirect reporting has been\nfound to expand the coverage of debt statistics in most LIDCs, and country-specific comparisons of debt\nstocks from direct sources versus those recorded in the WB-IMF’s DSAs show that deviations therein can\nrepresent up to 30 percent of national GDP, confirming that differences in coverage are a key driver of\nthis gap. Even when direct and indirect reporting coincide in terms of sectoral coverage, discrepancies can\nbe as high as 7 percent of national GDP. This additional mismatch can be attributed to the use of\ndecentralized and non-automated recording processes, data manipulation, and different debt definitions.\n\n\nGiven these challenges, this paper puts forward a call for action to i) improve debt transparency by\nfocusing on those factors that are most likely to promote transparency; (ii) shift the focus of MDBs’\noperations and technical assistance from indirect to direct reporting; (iii) introduce a core of enforceable\n\nMention: \"WB-IMF’s DSAs\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"validate\", \"summary\": \"Debt stocks recorded here deviate from direct sources by up to thirty percent of GDP, revealing coverage gaps.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:002016:12:5", "occurrence_id": "15a03bde0ec719ce1ace98cb", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: .8 percentage points higher. In our sample the standard deviation of cumulative sales is\n0.193, so one standard deviation increase in cumulative sales would be associated with a 0.7\npercentage point (=0.193*0.038) increase in ROE. Finally, regressions 7-9 in Table 3 suggest that\nthere are no statistically significant short-term differences in cost-to-income ratios a few years\n\n\n20 We control for lagged ROA in the specifications except where the dependent variable was ROA, ROE or NIM.\n21 All bank-level variables come from the Bankscope (1995-2014) and Bank Focus Orbis (2015-2017) databases and\nall macro variables come from the Global Financial Development Database.\n\n\n11\n\nMention: \"Global Financial Development Database\""}, {"role": "assistant", "content": "{\"role\": \"supporting\", \"usage_action\": \"source\", \"summary\": \"All macroeconomic variables in the bank panel are drawn from this compilation.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:002025:26:1", "occurrence_id": "16145f7e028f59ed55d8baf4", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: s_**, multiplied by the elasticity of substitution of imports between the\nsources **_σM,k_**, using the Armington elasticity for the sector as in the GTAP Data Base, (ii)\nimport-augmenting technical change, _amsk_ **_k,r,s_**, that lowers the effective price of a good in\nthe destination market, and (iii) the import penetration as captured by the change in\ncomposite imports of subsector commodity _k_, _qimk_ **_k,s_** . Note that the substitution effect for\na particular flow _(k,r,s)_ increases in divergence of import tariff for good _k_ from regions _r_\nto _s_, from the weighted-average tariff of _s_ . Since a higher weight means lower divergence,\nthis effect decreases in import-shares of region _r_ in the total imports by region _s_ of the good\n_k_ .\n\n\n**For all sectors k in SECT, regions r and s in REG:**\n\n\n**_qxskk,r,s = -amskk,r,s + qimkk,s -σM,k * [pmskk,r,s - amskk,r,s - pimkk,s] …………… (1)_**\n\n\nGlobal transport margins are treated in the same manner as in the standard GTAP model,\nwith the quantity of international trade, transport and insurance services required being a\nfixed proportion of the volume of goods shipped. Technical change in this sector is\nrepresented with the variable atmfsdkk **_,r,s_** and is obtained by adding up the changes at\ndifferent levels, which are directly translated from the aggregate changes in the\ncorresponding variables. Trade and transport services\n\nMention: \"the GTAP Data Base\""}, {"role": "assistant", "content": "{\"role\": \"supporting\", \"usage_action\": \"source\", \"summary\": \"Its sectoral Armington elasticities set the substitution between import sources.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:002040:64:2", "occurrence_id": "0d3d7ca08e02e4bc00383415", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: prices (in US dollars). For identification of equation (2),\nwe use diplomatic exchange between Egypt and the countries of destination of Egyptian migrants at\ntime of migration. It is a dummy variable equal zero if there is no evidence of diplomatic exchange\nneither in Egypt, nor in the country of destination and is equal one if there is evidence of diplomatic\nexchange either in Egypt or in the country of destination at the level of charg´e d’affaires, minister,\nambassador or other. For identification of equation (3), we use the number of active armed conflicts\nthat is both country and year specific from the Uppsala Conflict Data Project (UCDP). Equation (4)\nestimates the effect of illegality on the logarithm of hourly wages, unconditional on return migration.\nThe predicted logarithm of hourly wages for non-migrants, illegal migrants and legal migrants are\nreported in the last row.\n\n\n63\n\nMention: \"Uppsala Conflict Data Project\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"analyze\", \"summary\": \"Country-year counts of active armed conflicts serve as the instrument for identification.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:002044:3:0", "occurrence_id": "219af0fa5635c8d1950f97a1", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: #### **1 Introduction**\n\nThe increase in gasoline prices stemming from the oil crisis overshadowed the\n\n\nUnited States presidential debate of October 1980. Ronald Reagan and then-President\n\n\nJimmy Carter were going head to head in the election. Carter’s loss that year coin\n\ncided with a peak in oil prices. Other modern US presidential incumbents - for\n\n\nexample, Presidents Ford and George H.W. Bush - also lost their reelection bids fol\n\nlowing oil price spikes. This anecdotal evidence points to a broader question about\n\n\nthe role of exogenous shocks in determining electoral outcomes.\n\n\nOur paper is the first effort to systematically examine the effect of oil price shocks\n\n\non the reelection probability of political incumbents in oil-importing countries. We\n\n\nuse a novel dataset of 207 national elections in 50 mostly oil-importing democracies,\n\n\nwhich crucially also includes polling data in the run-up to elections. The polling data\n\n\nallow us to explore the effect of exogenous shocks not only on the election outcome,\n\n\nbut also on voting intentions in the months leading up to the vote. Depending on the\n\n\npolitical system, the dataset includes elections of the chief executive in parliamentary\n\n\nor presidential systems. As large oil imports leave a country vulnerable to changes\n\n\nin _international_ crude oil prices, we rely on these prices as an exogenous source of\n\n\n_country-specific_ variation in terms of trade. Specifically, we create a measure of ’oil\n\n\nprice shock’ by interacting the fluctuations in international oil prices (over which\n\n\nindividual countries do not have explicit control) with the country-specific intensity\n\n\nof oil imports relative to GDP.\n\n\nAn oil price shock one year prior to an election is found to significantly reduce\n\n\nthe likelihood of reelection for the incumbent party. Specifically, a 1% increase in\n\n\nour oil shock measure decreases the likelihood of incumbent re-election by nearly six\n\n\npercentage points. Furthermore, novel polling data confirm that these shocks operate\n\n\nby reducing the popularity of the sitting government. We show that both\n\nMention: \"dataset of 207 national elections\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"It covers fifty mostly oil-importing democracies and includes pre-election polling.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:002048:40:0", "occurrence_id": "771490ca1abd14706269404f", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: Table 5: Data to be calibrated\n\n\nFrequency of lagged shipments in bin 0 1 2 3-5 6-10 11-100 100+\nShare of total 2016 shipments 0.189 0.051 0.038 0.084 0.089 0.374 0.176\nInspections per 100 shipments 14 6.7 6.4 6.0 5.6 5.7 6.0\nMean no. of lagged shipments 0 1 2 3.8 7.6 26.9 205\nTotal inspections per 100 shipments 7.3\n\nTable notes: Author calculations using Serbian customs data from 2016.\n\n\nmade up entirely of observations with exactly zero, one, or two lagged shipments, respectively.\n\n\nIn the last four bins, we average over _ofk_ triplets that have varying levels of lagged shipment\n\n\nfrequencies. The mean for each bin is reported in row 3 of Table 5.\n\n\n**Parameterization**\n\n\nIn order to emphasize the role of ambiguity, we shut down by assumption other possible\n\n\nsources of cross-bin variation that might otherwise affect search behavior and/or compliance.\n\n\nWe restrict the optimism parameter to be equal across bins, _αl_ = _α_, _∀l_ . Likewise the firm’s\n\n\nloss parameter, _L_, is assumed\n\nMention: \"Serbian customs data\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"analyze\", \"summary\": \"Inspections per hundred shipments are calculated from these records.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:002062:9:1", "occurrence_id": "d0338b5b49b2c4c53273fbe4", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: Our expected dowry variable is a sig\n\nnificant predictor of the actual dowry paid at the time of marriage. Using data on individuals whose\n\n\nyear of birth and year of marriage fall within our data, we run an ordinary least-squares (OLS)\n\n\nregression of the actual dowry paid at the time of marriage on the expected dowry in the year of\n\n\nbirth (using our definition). Table A.3 shows that the “first stage” relationship between our con\n\nstructed expected dowry measure and actual dowry that the household pays, including state fixed\n\neffects, year-of-birth fixed effects, caste fixed effects and their interactions, is highly significant. 23\n\n\nFigure A.4 shows the scatter plot overlaid with the linear prediction plot without any controls.\n\n\nMoreover, the correlation between expected and actual dowry is positive and significant for all four\n\n\nof our caste categories.\n\n\nRecall bias in dowry data: Like most survey data, one may be concerned about the recall bias\n\n\nin the reported dowry variable, especially when the year of marriage is too far back in time. To\n\n\nexamine the extent of the recall error, we utilize data from the 1999 round of REDS and compare\n\n\naverage dowry paid by year of marriage for years that are available in both rounds. Note that the\n\n\nquestion about dowry was asked differently in both rounds. Nonetheless, Figure A.5 shows that,\n\n\nfor the sample period of our savings analysis (1986-2007), the two rounds report similar dowry\n\n\namounts. Thus, recall bias is unlikely to be a significant issue for our regression estimates. Given\n\n\n20The same issue prevents us from using district-level variation—the average number of marriages in a\ndistrict-caste-year cell is just four\n\nMention: \"1999 round of REDS\""}, {"role": "assistant", "content": "{\"role\": \"supporting\", \"usage_action\": \"validate\", \"summary\": \"Dowry reported by year of marriage is compared across rounds to gauge recall error.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:002073:48:0", "occurrence_id": "1f742e43d48506c5b28e3f2d", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: Figure S3.2: Teenage parenthood by age of migration\n\n\n\n\n\n\n\n\n\n\n\n\n\n_a) Female, 19 years old at census_ _b) Female, 24 years old at census_\n\n\n\n\n\n\n\n_c)_ _Female, 30 years old at census_\n\n\n\n\n\n\n\n\n\n\n\n\n\n_d)_ _Male, 19 years old at census_ _e) Male, 24 years old at census_\n\n\nNotes: Markers indicate mean of teenage pregnancies, bars indicate 95% confidence interval. Red\nhorizontal line is the estimated teenage birth rate for non-migrating population of same age.\n\n\nSource: School data come from the 1997–2009 waves of the Brazilian School Census; official\npopulation estimates from the Brazilian Census Bureau; births by age of conception from Brazilian\nVital Statistics.\n\n\n\n13\n\nMention: \"Brazilian School Census\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"Its waves supply the school data behind the teenage birth rate estimates.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:002073:48:0", "occurrence_id": "520b7ef0572c4bd16e4769e5", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: Figure S3.2: Teenage parenthood by age of migration\n\n\n\n\n\n\n\n\n\n\n\n\n\n_a) Female, 19 years old at census_ _b) Female, 24 years old at census_\n\n\n\n\n\n\n\n_c)_ _Female, 30 years old at census_\n\n\n\n\n\n\n\n\n\n\n\n\n\n_d)_ _Male, 19 years old at census_ _e) Male, 24 years old at census_\n\n\nNotes: Markers indicate mean of teenage pregnancies, bars indicate 95% confidence interval. Red\nhorizontal line is the estimated teenage birth rate for non-migrating population of same age.\n\n\nSource: School data come from the 1997–2009 waves of the Brazilian School Census; official\npopulation estimates from the Brazilian Census Bureau; births by age of conception from Brazilian\nVital Statistics.\n\n\n\n13\n\nMention: \"Brazilian\nVital Statistics\""}, {"role": "assistant", "content": "{\"role\": \"supporting\", \"usage_action\": \"source\", \"summary\": \"Births by age at conception are taken from these civil registration records.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:002079:4:0", "occurrence_id": "7ab3e89d1e25b4c200ee5b60", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: and whether it is perceived in the same way by both parties. Joint decision making has been found to\n\n\ncorrelate negatively with IPV in several country studies, including Ebrahim and Atteraya (2019),\n\n\nFriedemann-Sánchez and Lovatón (2012), Gage (2005), Hindin and Adair (2002) and Svec and Andic\n\n\n(2018). This literature primarily focuses on the wife’s perception of the process of decision making and\n\n\nhow egalitarian she thinks this process is. While one analysis included both the husband’s and wife’s\n\n\nresponses (Zegenhagen et al. 2019), we go beyond this and include covariates that reflect not only their\n\n\nresponses, but whether or not they give the same responses. This allows us to explore the direction of\n\n\ndisagreement and its asymmetric effect on IPV.\n\n\nA separate body of interdisciplinary research offers a theoretical explanation for why joint decision making\n\n\nmay be associated with lower IPV. In the management, political science and conflict resolution literatures,\n\n\njoint decision making is highlighted as a tool for diffusing responsibility and reducing decisional conflict by\n\n\nsharing risk. For example, in her typology of political blame management strategies, McGraw (1991)\n\n\nfeatures ‘horizontal diffusion of responsibility’, whereby political leaders avoid conflict in the face of a\n\n\ndecision gone awry by arguing that their decision was a joint product of a group of individuals. Thompson\n\n\n(1980) discusses the blame-mitigation strategy of emphasizing ‘collective responsibility’. Shared decision\n\n\nmaking between doctors and patients is also highlighted as a tool for reducing decisional conflict—and\n\n\nhence, malpractice lawsuits—in the medical literature (Hoffmann et al. 2014, Kremer et al. 2007).\n\n\nOur paper builds on existing work by examining the relationship between joint decision making and\n\n\nphysical, sexual and emotional IPV across 12 Sub-Saharan African countries, using nationally\n\n\nrepresentative Demographic and Health Surveys (DHS) for 31,243 couples. We find\n\nMention: \"Demographic and Health Surveys (DHS)\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"analyze\", \"summary\": \"Thirty-one thousand couples are used to relate joint decision making to physical, sexual and emotional violence.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:002115:15:0", "occurrence_id": "05cc18a61a39aa2d3fbd9372", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: **Figure 2 Financial performance of SOEs in energy-rich economies, 2012–18**\n\n**a.** **EBITDA** **b.** **Adjusted EBITDA**\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n**c.** **Capital expenditures** **d.** **Operating expenditures**\n\n\n\n\n\n\n\n\n\n\n\n_Source_ : World Bank Infrastructure SOEs Database and authors’ calculations.\n_Note_ : EBITDA: Earnings before interest, taxes, depreciation, and amortization. FSOE: Fully owned state-owned\nenterprise. PPSOE: partially privatized state-owned enterprise.\n\nFigure 3 shows the evolution of fiscal support for PPSOEs and FSOEs in energy-rich countries. The\naverage FSOE has received more operations subsidies as percent of assets than the average\nPPSOEs since 2013 (panel a.). Operational subsidies over assets increased sharply in 2012–14 for\nall SOEs, reaching almost 90 percent of average assets for the mean SOE, followed by a slight\ndecrease after 2014. In the case of overall fiscal injections, there is significant volatility in the\nperiod of analysis, particularly for PPSOEs, with the mean fiscal injections to average assets for\nall SOEs ranging between 2 and 6 (panel b.).\n\n\n14\n\nMention: \"World Bank Infrastructure SOEs Database\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"Earnings, capital and operating expenditure of state-owned infrastructure enterprises are drawn from it.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:002121:6:1", "occurrence_id": "b415930771ecc6bef9795bb1", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: , they find that growth was driven by static structural\n\nchange and within-sector productivity growth. However, productivity growth was low in the sub\nregion over the period of analysis.\n\n\nde Vries _et al_ . (2015) analyze structural change in Africa and its implications for productivity\n\ngrowth during the past 50 years. According to this paper, during the early post-independence\n\n\n3 DHS are nationally representative surveys designed to collect detailed information on child mortality, health, and\nfertility, as well as on households’ durables and quality of dwellings. In addition, DHS data include information on\ngender, age, location, education, employment status, and occupation of women and their partners between the ages of\n15 and 59.\n\n5\n\nMention: \"3 DHS\""}, {"role": "assistant", "content": "{\"role\": \"background\", \"usage_action\": \"inform\", \"summary\": \"Described as nationally representative surveys collecting mortality, health, fertility and dwelling information.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:002121:6:1", "occurrence_id": "f4f33c9abea8a7cad7ff1a9d", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: , they find that growth was driven by static structural\n\nchange and within-sector productivity growth. However, productivity growth was low in the sub\nregion over the period of analysis.\n\n\nde Vries _et al_ . (2015) analyze structural change in Africa and its implications for productivity\n\ngrowth during the past 50 years. According to this paper, during the early post-independence\n\n\n3 DHS are nationally representative surveys designed to collect detailed information on child mortality, health, and\nfertility, as well as on households’ durables and quality of dwellings. In addition, DHS data include information on\ngender, age, location, education, employment status, and occupation of women and their partners between the ages of\n15 and 59.\n\n5\n\nMention: \"DHS data\""}, {"role": "assistant", "content": "{\"role\": \"supporting\", \"usage_action\": \"inform\", \"summary\": \"It adds gender, age, location, education and occupation details for women and their partners.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:002129:47:2", "occurrence_id": "dae233ef4d2153cf4cbcd0ab", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: 01 0.10 0.00 0.00 1.00 3237\n\n\nHH head is literate ERIVaS 0.08 0.28 0.00 0.00 1.00 577\nEACI 2017 0.20 0.40 0.00 0.00 1.00 3237\n***\n\n\n_Notes:_ To ensure comparability of the variables, the EACI 2017 sample is limited to pure stand plots.\n\nThe stars below the sample mean values of the two surveys denotes the statistical significance\nof the difference between the two means: _∗_ p _<_ 0.1; _∗∗_ p _<_ 0.05; _∗∗∗_ p _<_ 0.01\n\n\n46\n\nMention: \"EACI 2017\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"analyze\", \"summary\": \"Plot-level variables are restricted to pure stands so they are comparable with the other source.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:002131:3:0", "occurrence_id": "d2d29d7aa89cebe0a0018d86", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: **Introduction**\n\n\nEconomists explain the closure of firms during recessions with Schumpeter’s (1934) creative\n\ndestruction theory, where during downturns small and less efficient firms are the ones to exit the\n\nmarket. In times of extreme economic distress, however, firms in every country are reeling from\n\nthe inability to do business as usual. To make things worse, many sectors see collapsed demand\n\nand economic uncertainty stretching months, if not years. In the current pandemic, governments\n\nrightly focus on dealing with the health aspects first, and only then on the recovery of the economy\n\nonce the immediate danger of the pandemic is over.\n\n\nIn the meantime, businesses are rapidly running out of cash. In the United States, half of\n\nsmall firms – those with fewer than 500 employees – have cash reserves for less than a month, and\n\nanother quarter of businesses may run out of cash in two months. For service industries, the period\n\nto illiquidity is even shorter. Restaurants, for example, have less than a month of cash in hand\n\n(Didier et al., 2020).\n\n\nThis breathing period is extended with government programs already in place to support\n\nworker retention through subsidizing jobs, freezing interest payments on loans, and extending new\n\nbank credit. This extension differs across industries – it helps labor-intensive sectors more, and\n\nfirms with established lines of credit benefit more as well. Still, other payments – like rent and cost\n\nof materials – are weighing on businesses. Exporters are unable to ship goods due to disrupted\n\ntransport links. Even when transport is possible, new trade restrictions may apply or demand has\n\nsimply collapsed.\n\n\nNew analysis on 12 high-income and middle-income economies across Africa, Central Asia,\n\nEurope, Latin America, and the Middle East reflects similar patterns. The analysis uses a sample\n\nof 6,345 firms from the World Bank’s Enterprises Surveys in Colombia, Greece, Italy, Jordan,\n\nKazakhstan, Kenya, Morocco, Peru, Portugal, the\n\nMention: \"the World Bank’s Enterprises Surveys\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"A sample of 6,345 firms across many countries supplies the analysis.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:002160:9:0", "occurrence_id": "6311ee5868be72cfc07fa3fa", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: 7\n\n\nThis trend-check exercise is detailed further in section 3.1 on dropped data points. Section\n\n\n3.2 discussed data points which are included in both the 2018 and 2019 HEFPI versions but change\n\n\nin value due to changes in their underlying source or our indicator definitions, or because of coding\n\n\ncorrections. Section 3.3 introduces the data points we newly added to the HEFPI database in its 2019\n\n\nversion. Finally, section 3.4 gives an overview of the subnational surveys included on the health\n\n\nequity side of HEFPI.\n\n\n3.1. Dropped data points\n\n\nFor the 2019 HEFPI database, we quality-checked all points from the 2018 database and all\n\n\nnewly obtained points for the following eight health equity indicators: Inpatient care use, 4+\n\n\nantenatal care visits, skilled birth attendance, full child immunization, formal health care provider\n\n\nvisits for children with acute respiratory infections, receipt of oral rehydration salts among children\n\n\nwith diarrhea, adult inpatient care use, mammograms, and pap smears.\n\n\nThe quality check consisted in reviewing each point in a country’s time-series for the\n\n\nrespective indicator via visual inspection of trend charts. For outlying points that we computed from\n\n\nmicrodata we reviewed, and if necessary corrected our code. 3 If the data came from publications or if\n\n\nwe found our coding to be correct, we re-checked if the survey’s raw data indeed allowed us to\n\n\nconstruct the indicator in line with or sufficiently similarly to the HEFPI indicator definitions 4 [^4: See Tables 1-3 in Wagstaff et al. (2018) for detailed HEFPI indicator definitions.] - and\n\n\ndropped the point if we found this to not be possible. If definitions were sufficiently similar, we\n\n\n3 Changes in indicator values between the 2018 and 2019 HEFPI versions due to such coding corrections or for\nother reasons are discussed further in section 3.2.3 below.\n4 See Tables 1-3 in Wagstaff et\n\nMention: \"HEFPI database\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"curate\", \"summary\": \"New data points and subnational health equity surveys are documented for this version.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:002178:5:2", "occurrence_id": "ba30dad8e16df0e3b393d2a0", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: incidence analysis to comprehensively assess the impact of the fiscal system**\n**on poverty and inequality in Albania, in order to inform the dialogue around fiscal reform with an**\n**equity lens.** It also benchmarks Albania to other countries in which a similar methodology has been applied.\nIn particular, the analysis employs the Commitment to Equity Methodology (Lustig and Higgins, 2017),\nalready applied in many countries around the world and across regions, to explore: a) How much income\nredistribution and poverty reduction is achieved in Albania through the fiscal system (taxes, subsidies and\nsocial spending), b) Who bears the burden of taxes and receives the benefits?; c) How equalizing and propoor are particular fiscal interventions, and how equitable is the use of education and health services?, and\nd) What is the expected impact of changes in the size and progressivity of a particular tax (i.e. the personal\nincome tax) on poverty and inequality outcomes.\n\n**The analysis relies on the 2015 Household Budget Survey collected by INSTAT, together with**\n**macroeconomic and fiscal data from the national income accounts in Albania** . The analysis does not\nincorporate behavioral or general equilibrium effects. Moreover, using an input-output matrix it captures\nthe indirect effects of excise taxes on intermediate goods, since these can be important as they are passed\nthrough to prices of all other goods. Given the available data, the analysis incorporates the fiscal\ncomponents that capture around 70 percent of fiscal revenues, in particular direct taxes (personal income\ntax and social security contributions) and indirect taxes (household-paid VAT and excises). On the spending\nside, it captures social spending (education, health and social protection), which amounts to 45 percent of\n\n\n4\n\nMention: \"2015 Household Budget Survey\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"Combined with national accounts data to assess how income tax progressivity affects poverty and inequality.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:002189:10:0", "occurrence_id": "ccf15a45c1e9f348722ea128", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: The survey is nationally representative of the formal private sector. It is built based on\n\n\na stratified random sampling frame designed by the WBES team. Three variables are used\n\n\nto construct the strata: firm size, sector, and geographic area within a country. Under the\n\n\nWBES sampling framework, firms are divided into three categories according to their size:\n\n\nsmall, medium-sized, and large. Small firms are those with 5-19 full-time employees; medium\n\nsized firms have 20-99 full-time employees; and the large ones have more than 99 full-time\n\n\nemployees. The industries are classified according to the ISIC Revision 3.1 classification at\n\n\n2-digits. The regions within a country are defined by the WBES team. The database also\n\n\nincludes sampling weights that can be used to mimic nationally representative samples in\n\n\nthe empirics.\n\n\nThe WBES collects data on a broad range of variables related to firm production, perfor\n\nmance, and the business environment in which firms operate. It has information on variables\n\n\nrelated to production such as sales, capital, labor, materials, investment, exports, and man\n\nager’s education, among others. Due to the lack of information on prices at the firm-level,\n\n\nwe use the consumer price index from the World Bank’s World Development Indicators to\n\n\ndeflate sales, capital, materials, and investment, thus transforming nominal values into 2010\n\ndollar values. Firms’ labor is equal to the number of permanent employees that work for the\n\n\nfirm. The survey collects data on the percentage of firms’ sales that are exported. Last, a\n\n\nfirm’s managerial capability is measured by the number of years of experience of the man\n\nager. The novelty of the WBES is that it also collects information on technology adoption\n\n\nat the firm-level. Thus, at every wave, firms are asked whether they use a business email to\n\n\ncommunicate with clients and suppliers and whether they have a business website in\n\nMention: \"World Development Indicators\""}, {"role": "assistant", "content": "{\"role\": \"supporting\", \"usage_action\": \"curate\", \"summary\": \"Its consumer price index deflates sales, capital, materials and investment to constant dollars.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:002197:11:0", "occurrence_id": "4b147973d7b026a36bae584f", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: managerial, and business environment measures. Within the WBES, the Green Economy\n\n\nmodule is rolled out by the World Bank Group, jointly with the EBRD-EIB.\n\n\n_Generic_ _and_ _Energy-centric_ _Management_ _Scores_ . General management scores are calculated\n\n\nusing 11 questions from the management practice module. These questions map to eight\n\n\nquestions from the U.S. Management and Organizational Practices Survey (U.S. Census\n\n\nBureau, 2015). They cover four categories of practices: target-setting, monitoring, incentives,\n\n\nand operations (see Table A1). Firms’ responses to questions on management practices are\n\n\naggregated into a single management score following Bloom et al. (2019a) in two steps.\n\n\n_First_, the responses to each of the management practice questions are normalized on a 0-1\n\n\nscale: the response associated with the most structure is normalized to one, and the one\n\n\nassociated with the least structured is normalized to zero. _Second_, overall management\n\n\nscore is calculated as the unweighted average of the individual question scores as in Bloom\n\n\net al. (2012c) in computing the average based on the z-scores of individual questions. We\n\n\nuse these scores to compute descriptive statistics. About 2% of the firms with non-missing\n\n\nentries report a zero average score, while the average for all firms is 0.48 (standard deviation\n\n\nof 0.21). For regressions, we take the z-scores of individual questions, and compute the\n\n\nunweighted average. We then once again take the z-score to obtain a composite management\n\n\nscore. General management score also separates the overall management index into four sub\n\nindices to separately assess the importance of monitoring, incentives, targets and operations\n\n\npractices.\n\n\nEnergy management scores use questions from the Green Economy Module of the WBES\n\n\nthat relate to monitoring, target setting, and relative emphasis on energy efficiency. Ques\n\ntions and scoring scales are\n\nMention: \"U.S. Management and Organizational Practices Survey\""}, {"role": "assistant", "content": "{\"role\": \"supporting\", \"usage_action\": \"source\", \"summary\": \"Eight of its questions map to the management practice module used for scoring.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:002236:7:0", "occurrence_id": "174159a27592007971a37e0f", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: #### **2 Data**\n\n###### **2.1 Lockdown data**\n\nLockdown is a binary variable where one indicates the month the following measures were\n\n\nimposed by trading partners of the Philippines: workplace closure, the closure of public\n\n\ntransport, stay at home requirements, restrictions on internal movement, and international\n\n\ntravel controls. This definition of lockdowns has been adopted from Majune (2020). Data for\n\n\nthese indicators is from the Oxford COVID-19 Government Response Tracker (Hale et al.,\n\n\n2020).\n\n\nTo explain the pattern of lockdown measures, we display the trend of the lockdown\n\n\nStringency Index for the Philippines and neighboring countries (Thailand, Malaysia, China,\n\n\nIndonesia, and Vietnam) between January 1, 2020, and December 31, 2020, in Figure 1.\n\n\nThe index is constructed by re-scaling the maximum ordinal values of nine indicators (one\n\n\nhealth measure and eight closures and containment policies) to range between 0 and 100.\n\n\nThe scores are then averaged to get a composite index for over 180 countries. A score of 0\n\n\nindicates no restrictions while 100 signals severe implementation of lockdown policies in a\n\n\ncountry (Hale et al., 2020).\n\n\nThe first lockdown measure in the Philippines was on January 31, 2020, when arrivals\n\n\nof people from some regions were banned. This was followed by the closure of the border,\n\n\nworkplaces, public transport, and imposition of stay-at-home requirements and restrictions\n\n\non internal movement on March 15, 2020, as reflected by a sudden jump in the index, from\n\n\n34 to 75. The index was 100 on March 22, 2020, indicating maximum implementation of\n\n\nall containment measures. However, it dropped significantly, on May 29, 2020, when work\n\nplace and public transport closure, stay at home requirements and restrictions on internal\n\n\nmovement were temporarily suspended. The easing of international travel controls started\n\n\non July 7, 2020. The Philippines had the joint least index\n\nMention: \"Oxford COVID-19 Government Response Tracker\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"Its stringency index and lockdown indicators describe the measures adopted.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:002278:9:0", "occurrence_id": "fd41fd46347857119d18c8c9", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: markets, destroyed infrastructure, and an absence of state-provided electricity and piped water\nuntil 2006 (International Crisis Group, 2003).\n\nThree years after the last peace agreement, only about half of those who had been forcibly\ndisplaced returned home. While many former combatants had entered reintegration programs,\ndemobilized army officers and former security personnel continued to stage protests, some\nviolent, throughout the years (Amnesty International, 2007). By the end of 2006, approximately\n9% of Liberians still resided in other countries such as Guinea, Sierra Leone, Côte d’Ivoire,\nGhana and Nigeria (Amnesty International, 2008).\n\nViolence against women, including rape and IPV, was pervasive in post-conflict Liberia, as\nreported in the DHS conducted five years after the war. In a 2007 survey, over one-third of\nwomen in Liberia reported ever having experienced physical violence by a partner, and 11%\nreported partner sexual violence (Liberia Institute of Statistics, 2008). Just under half of all\nwomen (49%) reported having experienced some kind of violence (physical, sexual or\nemotional) from a partner. Sixty percent of women believed that a husband is justified in beating\nhis wife for at least one reason. Almost half of women surveyed (45%) indicated that they\nexperienced some kind of physical violence from the age of 15, and one-third of women\nexperienced this abuse in the past 12 months. During this time, other incidents of violent crime\nsuch as armed robbery and murder increased as well (Human Rights Watch, 2008).\n\nThe Human Development Index (HDI) provides a rare insight into Liberia’s development pre-,\nduring, and post-conflict. The scale aggregates information about lifespan, education and gross\ndomestic product (GDP) to create a global ranking of countries (Anand & Sen, 1994). In 1970,\nLiberia scored in the lowest quartile of development. The country’s progress\n\nMention: \"DHS\""}, {"role": "assistant", "content": "{\"role\": \"supporting\", \"usage_action\": \"source\", \"summary\": \"Its post-war round reports the prevalence of physical violence against women by a partner.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:002278:9:0", "occurrence_id": "104871a0c5456ee3dcf05515", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: markets, destroyed infrastructure, and an absence of state-provided electricity and piped water\nuntil 2006 (International Crisis Group, 2003).\n\nThree years after the last peace agreement, only about half of those who had been forcibly\ndisplaced returned home. While many former combatants had entered reintegration programs,\ndemobilized army officers and former security personnel continued to stage protests, some\nviolent, throughout the years (Amnesty International, 2007). By the end of 2006, approximately\n9% of Liberians still resided in other countries such as Guinea, Sierra Leone, Côte d’Ivoire,\nGhana and Nigeria (Amnesty International, 2008).\n\nViolence against women, including rape and IPV, was pervasive in post-conflict Liberia, as\nreported in the DHS conducted five years after the war. In a 2007 survey, over one-third of\nwomen in Liberia reported ever having experienced physical violence by a partner, and 11%\nreported partner sexual violence (Liberia Institute of Statistics, 2008). Just under half of all\nwomen (49%) reported having experienced some kind of violence (physical, sexual or\nemotional) from a partner. Sixty percent of women believed that a husband is justified in beating\nhis wife for at least one reason. Almost half of women surveyed (45%) indicated that they\nexperienced some kind of physical violence from the age of 15, and one-third of women\nexperienced this abuse in the past 12 months. During this time, other incidents of violent crime\nsuch as armed robbery and murder increased as well (Human Rights Watch, 2008).\n\nThe Human Development Index (HDI) provides a rare insight into Liberia’s development pre-,\nduring, and post-conflict. The scale aggregates information about lifespan, education and gross\ndomestic product (GDP) to create a global ranking of countries (Anand & Sen, 1994). In 1970,\nLiberia scored in the lowest quartile of development. The country’s progress\n\nMention: \"Human Development Index\""}, {"role": "assistant", "content": "{\"role\": \"supporting\", \"usage_action\": \"source\", \"summary\": \"Its aggregate of lifespan, education and living standards gives insight into development across the conflict.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:002316:16:0", "occurrence_id": "832ccf80d2eccdbc0cb31570", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: Figure 5: State-level change in electricity and fuel prices: Mexico\n\n\n(a) Growth in electricity prices (%)\n\n\n(b) Growth in fuel prices (%)\n\n\nNote: Electricity prices are weighted by the tariff that correspond to\neach user using data from the EAIM. Fuel prices are calculated as a\nweighted average of the prices of coal, petroleum coke, diesel and\nnatural gas using 3-digits NAICS consumption as weights.\n_Source:_ Authors’ calculations with data from SENER.\n\n\n14\n\nMention: \"data from the EAIM\""}, {"role": "assistant", "content": "{\"role\": \"supporting\", \"usage_action\": \"analyze\", \"summary\": \"Tariff categories from it weight the electricity price growth by user type.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:002330:4:0", "occurrence_id": "4b619b03f9b622b991dbcae8", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: primary channel through which protection has been ratcheted up around the world. We refer to\n\nsuch accords as Intellectual-Property-Related PTAs, or IPAs.\n\n\nThe TRIPS Agreement has been studied empirically in broad terms, with papers asking\n\nwhether its adoption by members has affected such economic outcomes as trade and foreign\n\ndirect investment (FDI). The role of PTAs that feature strong IPRs standards has attracted much\n\nless attention, however. These agreements, which have steadily proliferated since the mid-1990s,\n\nare a potentially significant determinant of trade and investment patterns and innovation\n\nactivities. As such, they deserve systematic study, which we undertake in this paper. Specifically,\n\nwe build on an existing working paper (Maskus and Ridley, 2020), which studied the impact of\n\nmembership in IPAs, where one partner is the US, the EU, or EFTA, on the composition of\n\naggregate and bilateral trade, controlling for compliance with TRIPS standards. Here we delve\n\ndeeper by using specific aspects of such agreements, as measured by the World Bank’s database\n\non the depth of trade agreements (Hofmann, et al, 2017).\n\n\nThe relationship between intellectual property standards and trade is theoretically\n\nambiguous and depends on context. Most important, patents and copyrights are different from\n\nimport barriers. A cut in import tariffs is a reduction in trade costs, implying generally higher\n\ntrade. Lower trade barriers expose domestic firms to competition, typically reducing market\n\npower and markups. Intellectual property rights, however, create temporary monopolies in the\n\nuse, including trade, of technologies and goods. These exclusive rights permit their owners to\n\ndecide where, when, and how they will produce, export, license, and sell protected products and\n\ntechnologies.\n\n\nA small number of studies have estimated the trade effects of TRIPS, using broad\n\nmeasures. Thus, Ivus (2010) found that a group of developing countries (those that were not\n\nBritish or French colonies) that were obligated by membership\n\nMention: \"database\n\non the depth of trade agreements\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"Specific aspects of agreements are measured from this compilation.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:002331:13:1", "occurrence_id": "5870dda66e56a29b104e28dc", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: \nlower values of our concentration measures can be interpreted as greater extent of export diversification. The Herfindahl\n\n\nindex is computed as follows:\n\n\n\n\n- \n\n\n𝐻�� ~~�~~ 𝑥 � �\n\n\n\n\n\n\n\n∑�� 𝑥�\n\n\n\n\n𝑥 �� � 𝑥��\n\n\n\nwhere _x_ represents the amount of exports, the subscript 𝑖 stands for a specific product (or market) and 𝑛 is the total\n\n\nnumber of products (or markets). When a single export product (market) produces all the revenues, _H_ =1, as opposed\n\n\nto _H_ =0 when a large variety of products compose the revenues (Haddad et al. 2010; Lederman and Maloney 2012;\n\n\nCadot et al. 2013). Higher (lower) values of the Herfindahl index, _H_, imply lower (higher) degree of export\n\n\ndiversification. We use COMTRADE data on exports by product at a 4-digit disaggregated level from the SITC Revision\n\n\n1.0 to compute Herfindahl indices of export product concentration. Bilateral data from COMTRADE are also used to\n\n\ncompute Herfindahl indices of export market concentration.\n\n\n_Table 1_ displays the evolution over time of the Herfindahl indices of export product and market concentration\n\n\nin the periods 1990-94 and 2010-14. In the period under analysis, the region’s Herfindahl Index for export product\n\n\nconcentration declined from 0.41 in 1990-94 to 0.3 in 2010-14 —thus, signaling an improvement in terms of trade\n\n\ndiversification\n\nMention: \"COMTRADE data on exports by product\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"analyze\", \"summary\": \"Four-digit product export values are used to compute concentration indices.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:002331:13:1", "occurrence_id": "ea4aa6ba0629981f7f85277f", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: \nlower values of our concentration measures can be interpreted as greater extent of export diversification. The Herfindahl\n\n\nindex is computed as follows:\n\n\n\n\n- \n\n\n𝐻�� ~~�~~ 𝑥 � �\n\n\n\n\n\n\n\n∑�� 𝑥�\n\n\n\n\n𝑥 �� � 𝑥��\n\n\n\nwhere _x_ represents the amount of exports, the subscript 𝑖 stands for a specific product (or market) and 𝑛 is the total\n\n\nnumber of products (or markets). When a single export product (market) produces all the revenues, _H_ =1, as opposed\n\n\nto _H_ =0 when a large variety of products compose the revenues (Haddad et al. 2010; Lederman and Maloney 2012;\n\n\nCadot et al. 2013). Higher (lower) values of the Herfindahl index, _H_, imply lower (higher) degree of export\n\n\ndiversification. We use COMTRADE data on exports by product at a 4-digit disaggregated level from the SITC Revision\n\n\n1.0 to compute Herfindahl indices of export product concentration. Bilateral data from COMTRADE are also used to\n\n\ncompute Herfindahl indices of export market concentration.\n\n\n_Table 1_ displays the evolution over time of the Herfindahl indices of export product and market concentration\n\n\nin the periods 1990-94 and 2010-14. In the period under analysis, the region’s Herfindahl Index for export product\n\n\nconcentration declined from 0.41 in 1990-94 to 0.3 in 2010-14 —thus, signaling an improvement in terms of trade\n\n\ndiversification\n\nMention: \"Bilateral data from COMTRADE\""}, {"role": "assistant", "content": "{\"role\": \"supporting\", \"usage_action\": \"analyze\", \"summary\": \"Partner-country flows give the market concentration index.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:002337:43:0", "occurrence_id": "6b84fcde266521b40212bb04", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: Figure 1: China’s Growing Role in the World and the U.S.\n\n\n\n(a) China’s Share of World Totals\n\n\n\n(b) China’s Share of U.S. Trade\n\n\n\n\n\n\n\n\n\n\n\n_Notes:_ Panel (a) shows China’s share of Non-U.S. World GDP (dashed) and World Exports (solid). Panel\n(b) shows China’s share in U.S. exports (dashed) and imports (solid). Data source is UN Comtrade.\n\n\nFigure 2: China’s Aggregate Import Share and Duties\n\n\n\n\n\n_Notes:_ Tariffs are defined at the SITC level and calculated as the log of 1 + total duties over the total FOB\nvalue of imports. The dashed lines are the median tariff across goods and the 25 th and 75 th percentiles. The\nsolid line is the log import share of China over the total of U.S. imports from all countries.\n\n\n41\n\nMention: \"UN Comtrade\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"World export shares and China's trade shares are computed from this database.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:002350:6:0", "occurrence_id": "24dc2774ff2f1b79461879a7", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: relatively low in developing countries, and total gasoline consumption is still far behind that in\n\nthe United States (Figure 3), the upward trend in these countries is substantial.\n\n\n**Figure 2: New Passenger Car Registrations for Selected Countries**\n\n\n_Notes: Figure 2 shows the new passenger car registrations_ _and changes from 2005 to 2017 using_\n_[data from the International Organization of Motor Vehicle Manufacturers (www.oica.net). Axis](http://www.oica.net/)_\n_on the right corresponds to China’s new passenger car registrations._\n\n\n**Figure 3: Fuel Consumption by Country**\n\n\n**Panel (a) Gasoline Consumption by Country**\n\n\n5\n\nMention: \"the International Organization of Motor Vehicle Manufacturers\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"New passenger car registrations by country are taken from this association.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:002351:43:0", "occurrence_id": "cac771dba6289bde34c0cb20", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: **Figure A.1. Drivers of females being out of the labor force (OLF) - Women over age 25**\n(Marginal Effects on the probability of female inactivity)\n\n\nSource: Author’s calculations using HCP Enquête National sur l’emploi, 2001-2018. Controls include: 5 age categories,\nnumber of kids under 10 years old in the household, a 4-categories education variable (omitted category is ”No\neducation”), education level of head of household, a dummy that equals one if women were never married, the number of\ninactive women in the household and its square. Marginal effects evaluated at the mean of the covariates in the estimation\nsample. Sample restricted to women between 15-65 years old.\n\n\n42\n\nMention: \"HCP Enquête National sur l’emploi\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"analyze\", \"summary\": \"Marginal effects on female inactivity are estimated with age, children and education controls.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:002369:48:0", "occurrence_id": "4e916a191ed0a6f37d5f4ef2", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: Figure A6: Predicted mobility around transit stations in countries not covered by Google trends.\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n47\n\nMention: \"Google trends\""}, {"role": "assistant", "content": "{\"role\": \"supporting\", \"usage_action\": \"validate\", \"summary\": \"Countries it does not cover must be identified separately, bounding the analysis's reach.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:002378:25:0", "occurrence_id": "7799d9bf4007a6b9c6da9697", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: behavioral responses to taxation (e.g., Blundell and MaCurdy, 1999), we assume that\nincome effects are negligible (so that _ξz_ _u_ = _ξ_ _z_ _c_ and _ξ_ _h_ _u_ = _ξ_ _h_ _c_ ).27\n\nAfter briefly discussing what the baseline results imply about the drivers of income\n\ninequality, our main analysis concerns performing the inversion from labor supply deci\nsions to primitives under different assumptions on the relevant elasticities, highlighting\n\nhow deviations from the baseline estimates change our inference about the determinants\n\nof income inequality. We show that (1) larger differences between the income and hours\n\nelasticities with respect to the tax rate (i.e., larger effort elasticities) and (2) larger income\n\neffects will both lead us to infer that preference heterogeneity is increasingly important\n\nin driving income differences between rich and poor. We also discuss briefly at the end of\n\nthis section how our findings change if allow for heterogeneity in the elasticity schedules\n\n(roughly in line with the findings of Gruber and Saez, 2002) and how we can account for\n\nlabor market frictions using survey data on actual and preferred hours.\n\n###### **5.1 Data on Incomes and Hours Worked**\n\n\nWe will use data on incomes and hours worked from the American Time Use Survey\n\n(ATUS), which is a\n\nMention: \"American Time Use Survey\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"It supplies incomes and actual and preferred hours worked.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:002384:10:0", "occurrence_id": "bdbea644ca43dbdf82b359ce", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: **Step 3. Tabulate summary statistics of individuals and dummy variables by nationality and state.**\n\n\nThe share and number of foreign workers are computed by main nationality and state, and by month from\nMarch 2017 through February 2018. We also take an annual average distribution.\n\n\n**Step 4. Make adjustments to the remittance statistics and compare the results obtained from**\n**remittance data analysis with the official numbers reported by MOHA** .\n\n\nBased on the remittance analysis, we make additional adjustments to estimate the total number of foreign\nworkers in Malaysia. As earlier in World Bank (2020), we recognize that not all foreign workers use MSPs\nto remit their earnings back home, and thus assume that the remittance data represent 77 percent of the\nforeign worker population, based on the World Bank Greenback 2.0 surveys of foreign workers in Johor,\nwhich finds that about 77 percent of foreign workers use MSPs to transfer money (World Bank, 2017).\nThen, the final estimated foreign worker population is compared with MOHA’s figures on work permit\nholders, using annual averages, to find the estimated number of irregular workers between March 2017\nand February 2018.\n\n\n**Step 5. Robustness check to provide a lower-bound estimate of the number of foreign workers.**\n\n\nAs a robustness check of our initial estimations, we took the share of foreign workers by nationality in\neach state from the MOHA data, and then applied these shares to the total number of foreign workers at\nthe state level we obtained from the remittance data (the figure prior to adjusting using the 77 percent\nremitter proportion in Step 4). After recalibrating the monthly numbers of foreign worker population by\nnationality, we calculated the differences in the number of foreign workers in each state between our\nresults and the MOHA data. When the differences are negative (that is, the number of foreign workers in\nthe remittance data set is smaller than in the MOHA\n\nMention: \"World Bank Greenback 2.0 surveys\""}, {"role": "assistant", "content": "{\"role\": \"supporting\", \"usage_action\": \"analyze\", \"summary\": \"Its finding that 77 percent of foreign workers remit through formal providers sets the scaling factor.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:002384:10:0", "occurrence_id": "a0179eb113875a4e3c2dfe19", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: **Step 3. Tabulate summary statistics of individuals and dummy variables by nationality and state.**\n\n\nThe share and number of foreign workers are computed by main nationality and state, and by month from\nMarch 2017 through February 2018. We also take an annual average distribution.\n\n\n**Step 4. Make adjustments to the remittance statistics and compare the results obtained from**\n**remittance data analysis with the official numbers reported by MOHA** .\n\n\nBased on the remittance analysis, we make additional adjustments to estimate the total number of foreign\nworkers in Malaysia. As earlier in World Bank (2020), we recognize that not all foreign workers use MSPs\nto remit their earnings back home, and thus assume that the remittance data represent 77 percent of the\nforeign worker population, based on the World Bank Greenback 2.0 surveys of foreign workers in Johor,\nwhich finds that about 77 percent of foreign workers use MSPs to transfer money (World Bank, 2017).\nThen, the final estimated foreign worker population is compared with MOHA’s figures on work permit\nholders, using annual averages, to find the estimated number of irregular workers between March 2017\nand February 2018.\n\n\n**Step 5. Robustness check to provide a lower-bound estimate of the number of foreign workers.**\n\n\nAs a robustness check of our initial estimations, we took the share of foreign workers by nationality in\neach state from the MOHA data, and then applied these shares to the total number of foreign workers at\nthe state level we obtained from the remittance data (the figure prior to adjusting using the 77 percent\nremitter proportion in Step 4). After recalibrating the monthly numbers of foreign worker population by\nnationality, we calculated the differences in the number of foreign workers in each state between our\nresults and the MOHA data. When the differences are negative (that is, the number of foreign workers in\nthe remittance data set is smaller than in the MOHA\n\nMention: \"MOHA data\""}, {"role": "assistant", "content": "{\"role\": \"supporting\", \"usage_action\": \"analyze\", \"summary\": \"Shares of foreign workers by nationality per state are applied to the remittance totals.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:002385:17:2", "occurrence_id": "5b188160eb3a22b343d87637", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: \naxis) assessments. The dotted lines in the figure represent test scores that are one standard deviation\n\n\nabove and below the average scores. Each dot in the figure represents a school. The color of the\n\n\ndots represents the poverty rates of the parishes (the smallest administrative territorial\n\n\ndisaggregation) where schools are located. The blue dots represent the schools located in areas\n\n\nwith the highest poverty rates, and the black dots represent the schools located in areas with the\n\nlowest poverty rates. 7\n\n\nFigure 4 illustrates that schools with the worst-performing teachers also have the worst\n\nperforming students (bottom left panel of the chart). While this relationship does not necessarily\n\n\nimply a causality, it contributes to identifying the worst-performing institutions, presumably those\n\n\n7 Poverty is measured by the (census-based) Unsatisfied Basic Needs Index produced in 2010 by Ecuador’s National\nOffice of Census and Statistics.\n\n\n16\n\nMention: \"Unsatisfied Basic Needs Index\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"This census-based index is the measure of poverty in the analysis.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:002426:58:0", "occurrence_id": "be1ce2457ed19e6b5dafc16b", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: Figure A1: Monthly Income by Education, 2018 Household Survey\n\nMention: \"2018 Household Survey\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"Monthly income by education level is tabulated from this survey.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:002448:35:2", "occurrence_id": "beae1f1a174d2d67cf42c661", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: br>01mar2020
01apr2020
01may2020
(g) Actual reduction in bookings vs reduction Google search index: U.S.A|-50
-40
-30
-20
-10
0
% Reduction in Google search index
-100
-80
-60
-40
-20
0
% Reduction in actual bookings
01mar2020
01apr2020
01may2020
(g) Actual reduction in bookings vs reduction Google search index: U.S.A|\n\n\n\nActual bookings Google serch index\n\n\nNote: The graphs in this figure compare actual reductions in restaurant bookings versus reductions in the Google\nsearch index for “restaurant” for the seven countries where these data are available. The bookings data come from\n[OpenTable, https://www.opentable.com/state-of-industry](https://www.opentable.com/state-of-industry) .\n\nFigure B.1: Comparison of actual reductions in restaurant bookings versus reductions in Google search\nindex for “restaurant”\n\n\n34\n\nMention: \"OpenTable\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"analyze\", \"summary\": \"Restaurant bookings are compared with search index declines in seven countries.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:002454:13:0", "occurrence_id": "896af8e17a9fd06cb8da4cf8", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: **3.3** **Patterns within countries**\n\nHow are gender gaps shaped by urbanization? Though we lack panel data or repeated crosssections to explore trends over time, we can compare gender gaps between urban and rural areas.\nOwn land has a central role in rural areas, as the main place to live and produce, but is less relevant\nin towns and cities where most jobs are outside of agriculture and housing can be rented. In urban\nareas, housing and residential land play a larger role than agricultural land, but even though city\ndwellers tend to earn more than their rural compatriots, they are often less likely to own a home\n(Pendall et al 2016 for the United States; Eurostat 2015 for European Union countries; Sato et al\n2011 for China). This reflects partly that land is relatively scarce in urban areas, leading to highpriced real estate, but also better access to financial services, as an alternative means to store\nwealth. Because of this, some caution must be exercised in comparing ownership of land and\nhousing property across rural and urban areas.\n\nFigure 5 plots gender gaps in property ownership by country, separately for rural and urban\nareas. Gender gaps in sole ownership are almost always larger in rural than in urban areas. This\npattern holds for the most part, though less pronounced, also for gender gaps in sole and joint\nownership, though there are some exceptions. This, however, does _not_ mean that women are more\nlikely to own property if they live in urban areas. It rather reflects that urban men are much _less_\nlikely to own property than their rural counterparts.\n\nTo further investigate distributional patterns, we estimate gender gaps by quintile, using the\nDHS household-level wealth index. As shown in Figure 6, gender gaps in sole property ownership\nare in most countries larger for the poorest than for the richest quintile, though there are some\ncountries where the opposite pattern holds (Burundi, Jordan,\n\nMention: \"DHS household-level wealth index\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"analyze\", \"summary\": \"Its quintiles are used to examine how property ownership gaps vary by wealth.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:002461:0:0", "occurrence_id": "d03aa00677fc7087ed3dc2d8", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: # WPS 4140\n\n## **Corporate Governance and Regulation:** **Can There Be Too Much of a Good Thing?**\n\n∗\n\n**Valentina G. Bruno and Stijn Claessens**\n\n\n**Abstract**\n\nFor a large number of companies from different countries, we analyze how company\ncorporate governance practices and country regulatory regimes interact in terms of\ncompany valuation. We confirm that company corporate governance practices play a\ncrucial role in efficient company functioning and shareholder protection, and\nconsequently positively impact valuation. We find little valuation impact from corporate\ngovernance measures at the country level, and evidence of possible over-regulation.\nCorporate governance appears more valuable for large companies and those that rely\nmore heavily on external financing, consistent with the hypothesis that the main role of\ncorporate governance is to protect external financiers.\n\nKeywords: Corporate governance practices, Regulatory regimes, Company valuation\n\nJEL Classifications: G34\n\nWorld Bank Policy Research Working Paper 4140, March 2007\n\n_The Policy Research Working Paper Series disseminates the findings of work in progress to encourage the_\n_exchange of ideas about development issues. An objective of the series is to get the findings out quickly, even if_\n_the presentations are less than fully polished. The papers carry the names of the authors and should be cited_\n_accordingly. The findings, interpretations, and conclusions expressed in this paper are entirely those of the_\n_authors. They do not necessarily represent the view of the World Bank, its Executive Directors, or the countries_\n_they represent. Policy Research Working Papers are available online at http://econ.worldbank.org._\n\n______________________________\n\n\n\n∗\n\n\n\nWe thank the Institutional Shareholder Services (ISS) for providing us with data on companies’\ncorporate governance practices, Vidhi Chhaochharia, Luc La\n\nMention: \"Institutional Shareholder Services (ISS)\""}, {"role": "assistant", "content": "{\"role\": \"supporting\", \"usage_action\": \"source\", \"summary\": \"It supplied the corporate governance practice data the paper is built on.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:002478:20:0", "occurrence_id": "49933bfdb32d5bedc699c3d4", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: movements Mexico, Brazil and Colombia. 8,9 Although cointegration is sometimes given\n\n\nthe economic interpretation of capturing “long run” relations, fundamentally it is a\n\n\nstatistical relationship existing among non-stationary series. In our case, both relative\n\n\nsector sizes and the real exchange rate can plausibly be posited as I(1) and they always\n\n\nappear to be so in the analysis. Changing aggregate skill levels postulated in section 2\n\n\nsuggest no reason to assume the wages ex ante to be I(0) and even if they were, a slow\n\n\nadjustment process could lead to apparent non-stationary behavior within the sample\n\nanalyzed. 10\n\n\nWe then use recursive cointegration estimation techniques to explore the stability\n\n\nof the cointegration space over time and we apply LR-test to test hypotheses on the\n\n\ncoefficients of the cointegration vectors in order to provide empirical evidence to test the\n\n\nvarious predictions of the model and to extract some conclusions about labor market\n\n\nrigidities and the source of appreciations in the three countries.\n\n\n**3.1 Data**\n\n\nWe use quarterly data for Mexico, Brazil and Colombia on the log-transformed\n\n\nreal exchange rate, _p_, the wage ratio of formal over self-employed workers, _WT/WN_, and\n\n\nthe ratio of the absolute size of formal over the self-employed sector, _nT/nN_ . Real\n\nexchange rates where taken from IFS, all labor market data were derived from national\n\n\nlabor force surveys ( _Pesquisa Mensual do Empreg_ - for Brazil, _Encuesta Nacional de_\n\n\n_Empleo Urbano_ for Mexico and _Encuesta Nacional de Hogares_, Colombia). The work\n\n\nforce was defined as only the active male population. Because we are interested in\n\n\ninformal workers and not educated workers opening consulting firms, all workers with\n\n\nmore than 12 years of education were\n\nMention: \"IFS\""}, {"role": "assistant", "content": "{\"role\": \"supporting\", \"usage_action\": \"source\", \"summary\": \"Real exchange rates are taken from this financial statistics compilation.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:002480:9:1", "occurrence_id": "9bb2f66c7fb4e907601146fa", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: sector to include up to seven\nforms of private enterprises: four types of registered domestic private enterprises, as well\nas household firms, cooperatives and foreign invested enterprises. Official statistics also\nrefer to the “private economy” ( _kinh te tu nhan_ ), which includes only sole proprietorship\ncompanies, while limited liability and shareholding companies are presented separately\nunder the vaguely-titled “mixed economy” ( _kinh te hon hop_ ) category.9 Official statistics\non private companies are also very difficult to obtain and flawed by methodological\ninconsistencies.10\n\n\n11. Reports on the private sector, in turn, have not always distinguished between\nformal companies and household enterprises, sometimes referring to both as formal\n\n\n6 The legality of private enterprises was further strengthened by the Constitution in 1992, which recognized the right of\nfreedom of business in various economic sectors, including the right to equal treatment among all economic sectors.\n7 Household enterprises were previously covered in a separate piece of legislation (Decree 66). Note that even though\nthey are now included in the 1999 Enterprise Law, they are still subject to different regulations than formally registered\nenterprises. Household enterprises are now considered as “quasi-formal” private enterprises. They benefit from simple\nregistration procedures but are restricted in certain business operations, such as the right to trade, scope of operation\nand land use rights. These restrictions are put in place to encourage household enterprises to become formal business\nentities. Household enterprises, however, do continue to enjoy significantly lower taxes as they do not pay VAT taxes\nand are in a better position to negotiate lower taxes with local officials.\n8 Also included is the newest form: a variation on the limited liability company that allows for single ownership unlike\nthe original form that still is defined to include multiple owners.\n9 Webster and Taussig (1999), p. 13.\n10 The GSO’s methods for calculating private sector statistics have varied across recent years. Methodologies appear to\nvary across provinces, too\n\nMention: \"Official statistics\non private companies\""}, {"role": "assistant", "content": "{\"role\": \"supporting\", \"usage_action\": \"validate\", \"summary\": \"They are hard to obtain and affected by methodological inconsistencies.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:002480:9:1", "occurrence_id": "9b088c29c45790d6aeeae843", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: sector to include up to seven\nforms of private enterprises: four types of registered domestic private enterprises, as well\nas household firms, cooperatives and foreign invested enterprises. Official statistics also\nrefer to the “private economy” ( _kinh te tu nhan_ ), which includes only sole proprietorship\ncompanies, while limited liability and shareholding companies are presented separately\nunder the vaguely-titled “mixed economy” ( _kinh te hon hop_ ) category.9 Official statistics\non private companies are also very difficult to obtain and flawed by methodological\ninconsistencies.10\n\n\n11. Reports on the private sector, in turn, have not always distinguished between\nformal companies and household enterprises, sometimes referring to both as formal\n\n\n6 The legality of private enterprises was further strengthened by the Constitution in 1992, which recognized the right of\nfreedom of business in various economic sectors, including the right to equal treatment among all economic sectors.\n7 Household enterprises were previously covered in a separate piece of legislation (Decree 66). Note that even though\nthey are now included in the 1999 Enterprise Law, they are still subject to different regulations than formally registered\nenterprises. Household enterprises are now considered as “quasi-formal” private enterprises. They benefit from simple\nregistration procedures but are restricted in certain business operations, such as the right to trade, scope of operation\nand land use rights. These restrictions are put in place to encourage household enterprises to become formal business\nentities. Household enterprises, however, do continue to enjoy significantly lower taxes as they do not pay VAT taxes\nand are in a better position to negotiate lower taxes with local officials.\n8 Also included is the newest form: a variation on the limited liability company that allows for single ownership unlike\nthe original form that still is defined to include multiple owners.\n9 Webster and Taussig (1999), p. 13.\n10 The GSO’s methods for calculating private sector statistics have varied across recent years. Methodologies appear to\nvary across provinces, too\n\nMention: \"private sector statistics\""}, {"role": "assistant", "content": "{\"role\": \"supporting\", \"usage_action\": \"validate\", \"summary\": \"Calculation methods have varied across years and provinces.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:002508:23:1", "occurrence_id": "b4b19b0c571327818b7d0d5f", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: \n7 Low income and middle income countries are those which are classified as such by the World Bank in the\nWorld Development Report, 2000/01 (Washington, DC), p. 334. Low income includes countries with 1999\nGNP per capita $756 or less; middle-income includes countries with 1999 GNP per capita of $756 to\n$9,265.\n\n8 In line with other cross-national studies of poverty, 1980 was selected as a cutoff point because the\npoverty data prior to that year are far less comprehensive. See, for example, Martin Ravallion and Shaohua\nChen, “What Can New Survey Data Tell Us About Recent Changes in Distribution and Poverty,” World\nBank Economic Review 11:2 (May 1997): 357-382; and Richard Adams, Jr., Economic Growth, Inequality\nand Poverty: Findings from a New Data Set, World Bank Research Working Paper 2972, Washington, DC,\nFebruary 2003.\n\n9 For the purposes of this study, OECD (Europe) includes 21 countries: Austria, Belgium, Czech Republic,\nDenmark, Finland, France, Germany, Greece, Hungary, Ireland, Italy, Luxemburg, Netherlands, Norway,\nPoland, Portugal, Slovak Republic, Spain, Sweden, Switzerland and United Kingdom.\n\n10 The International Monetary Fund (IMF) records annual flow in international remittances in its\npublication, Balance of Payments Statistics Yearbook (Washington, DC).\n\n11 A recent IMF study estimated that informal transfers of remittance monies currently amount to $10\nbillion per annum. See Mohammed el-Qorchi, Samuel Maimbo and John Wilson, “The Hawala Informal\nFunds Transfer System: An Economic and Regulatory Analysis,” unpublished paper, International\nMonetary Fund, Washington, DC, August 2002, p. 64.\n\n12 For a full list of these 157 developing countries, see World Bank, World Development Report\n\nMention: \"Balance of Payments Statistics Yearbook\""}, {"role": "assistant", "content": "{\"role\": \"supporting\", \"usage_action\": \"source\", \"summary\": \"It records annual international remittance flows.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:002513:25:1", "occurrence_id": "260a9f6d256d215d834e3ea0", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: staff, or that prevailing salaries for highly qualified civil servants are\nhigh enough. The point is rather that donors should not unduly distort the market for\nskilled labor. The resource injection from high donor-paid salaries potentially has a\npositive net impact on development, despite the adverse impact on the functioning of\ngovernment. However, those same benefits could be obtained, without the negative\nconsequences, from using the funds to increase the salaries of underpaid civil servants, or\nthrough general budget support. Budget support targeted for increasing salaries of senior\nand technical staff—particularly where the use of merit systems increases the\n\n\n28 Bureaucratic quality has been linked to growth in several cross-country studies, including Evans and\nRauch (1999) and Keefer and Knack (1997), who measure bureaucratic quality using ICRG data.\n\n\n24\n\nMention: \"ICRG data\""}, {"role": "assistant", "content": "{\"role\": \"background\", \"usage_action\": \"source\", \"summary\": \"Cited cross-country studies measure bureaucratic quality with it.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:002528:19:6", "occurrence_id": "0702c9a3bcc11dba95b91b16", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: ,9
31,7
22,0
23,8
38,7|58,3
39,3
29,9
20,1
20,1
34,4|\n\n\n\n_Source:_ Author’s calculations based on PNAD 1981-2001.\n\n\n20\n\n\n\nnone or less\nthan 1\n\nMention: \"PNAD 1981-2001\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"analyze\", \"summary\": \"Distributional shares by education are computed from this series of household surveys.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:002538:13:3", "occurrence_id": "08f25baa8f0e7aec85557bc8", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: 11.5 14.6\nNet domestic assets of RBI 12.0 7.0 6.6 6.0 4.8 4.2 2.5 -2.2\nNet public debt 63.8 53.8 55.2 56.5 60.8 65.6 70.2 77.6\nSource: Reserve Bank of India, Monthly Bulletins\n\n\n36 The definition of net public debt also includes some other terms on RBI’s balance sheet, as shown in Table 5, which\nwe ignore here for simplicity.\n37 Strictly speaking, this holds approximately because net foreign assets and net domestic assets are both expressed as\nshares of GDP.\n38 Another way of making this point is to say that genuine assets can be created only by saving, not borrowing. To\nquote Flood and Jeanne (2000) “…reserves are expensive window dressing…by accumulating them the government\nbehaves as an insolvent household that would try to impress creditors by financing large cash balances with credit card\ndebt”.\n39 That is, RBI was exchanging an appreciating asset (rupee government securities) for a depreciating one (dollars) with\na lower nominal\n\nMention: \"Monthly Bulletins\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"Its published series supply the debt and financial aggregates.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:002544:34:1", "occurrence_id": "af707a239f6fcf997aa31707", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: ATO 20 483 613 51 1,167\nGUERRERO 59 105 643 447 76 1,330\nHIDALGO 44 143 488 489 91 1,255\nJALISCO 42 289 388 797 108 1,624\nMICHOACAN 69 399 384 558 95 1,505\nMORELOS 15 48 420 927 64 1,474\nNAYARIT 6 14 441 679 81 1,221\nNUEVO LEON 6 411 939 104 1,460\nOAXACA 34 448 709 516 64 1,771\nPUEBLA 20 401 432 473 96 1,422\nQUERETARO 18 52 504 500 138 1,212\nQUINTANA ROO 5 45 385 809 85 1,329\nSAN LUIS POTOSI 35 444 464 497 90 1,530\nSINALOA 20 16 415 643 103 1,197\nSONORA 2 412 345 773 477 2,009\nTABASCO 20 409 544 484 71 1,528\nTAMAULIPAS 12 394 787 73 1,266\nTLAXCALA 6 533 604 79 1,222\nVERACRUZ 45 800 1,867 2,083 66 4,861\nYUCATAN 10 400 409 830 74 1,723\nZACATECAS 11 484 517 98 1,110\nTotal 638 5123 15742 27277 4429 53,209\nSource: Primary Education Assessment Survey, second round SEP, 1997\n\n\n35\n\nMention: \"Primary Education Assessment Survey\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"State-level school and student counts are tabulated from this round.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:002552:10:0", "occurrence_id": "c11b70a5d45cdc93840b52a7", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: We also construct a variable XCONST that is the average for the years 1990-99 of\n\n\nthe Polity IV sub-index on executive constraints. XCONST measures the extent of\n\n\ninstitutionalized constraints on the decision-making powers of chief executives.\n\n\nXCONST ranges from 0 to 10 with a higher score indicating less _de facto_ operational\n\n\nindependence (and more accountability) of the country’s chief executive. XCONST\n\n\ncaptures the extent to which the political system enables minorities or non-elites to\n\n\ninfluence political elites in regular ways.\n\n\nNext, we construct a variable COALITION that takes a value of one if the\n\n\ngovernment of the country is a coalition government, and zero otherwise. The variable\n\n\nCOALITION is averaged for the years 1975-97 and is based on data collected by the\n\n\nWorld Bank. For more details on this database, see Beck et al. (2001). Unfortunately, we\n\n\ndo not have cross-country data on political campaign contributions from interest groups,\n\n\nunlike Kroszner and Strahan (2001) in their study of state-level deposit insurance limits\n\n\nin the United States. Therefore, we cannot control for the effect that money contributions\n\n\nmay have on the voting patterns of politicians.\n\n\nSecond, we control for structural differences within the banking industry. Private\n\n\ninterest theory emphasizes how different interest groups can provide funds and votes to\n\n\npoliticians who, in turn, control the regulatory decision to raise the coverage level of\n\n\ndeposit insurance. Private interest theory thus predicts that support for high coverage\n\n\nlevels is more likely in countries with greater political influence of risky banks relative to\n\n\nthat of safe banks. Public interest theory, on the other hand, would imply that support for\n\n\nhigh deposit insurance coverage is less likely in countries where the share of risky banks\n\n\nis large because the social costs of deposit insurance are directly related to the size of the\n\n\n10\n\nMention: \"Polity IV\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"analyze\", \"summary\": \"Its executive constraints sub-index is averaged across the decade.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:002559:25:0", "occurrence_id": "661e70478f7e63ebe2fedc72", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: focused on whether the Indian industrial strategy, which involved extensive use of industrial\n\n\nlicensing and tariff and non-tariff barriers, led Indian manufacturing to perform poorly\n\n\nrelative to other countries in particular those in East Asia (Bhagwati and Desai 1970, and\n\n\nBhagwati and Srinivasan 1975). 8 [^8: Between 1960 and 1995, manufacturing as a share of GDP grew from 9 percent to 24\npercent of GDP in Indonesia, 8 percent to 26 percent in Malaysia and 12.5 percent to 28\npercent in Thailand. In contrast, manufacturing output in India constituted 13 percent of GDP\nin 1960 but grew to only 18 percent of GDP by 1995. Source: World Development.\nIndicators.] Nationwide policies, however, have limited scope to explain\n\n\nthe marked cross-state variation in manufacturing performance that we observe in Figure 4.\n\n\nTo understand these patterns we need to focus on state specific policies and\n\n\nconditions. We examine three examples of research on how 1 st advantage factors and the\n\n\ninterplay between 1 st advantage and 2 nd advantage factors determine the pattern of\n\n\nmanufacturing growth in India. These examples illustrate how the framework we have\n\n\ndeveloped can be used build up a microeconomic evidence base on what matters.\n\n\n_Example [1]: 1_ _st_ _advantage: labor regulation and registered manufacturing_\n\n\nLabor regulations have been identified as an important element of the investment climate in\n\n\nIndia (Stern, 2001; Dollar, Iarossi and Mengitsae, 2001, Sachs et al, 1999). Besley and\n\n\nBurgess (2002) examine whether labor regulation is an important source of 1 st advantage\n\n\nwhich could help explain differences in manufacturing performance across Indian states. To\n\n\ndo this they exploit two key facts: (i) labor regulations only apply to firms in the registered\n\n\nmanufacturing sector, and (ii) the Indian constitution empowers state governments to amend\n\n\ncentral legislation. The\n\nMention: \"World Development.\nIndicators\""}, {"role": "assistant", "content": "{\"role\": \"supporting\", \"usage_action\": \"source\", \"summary\": \"Manufacturing output as a share of GDP is drawn from this compilation.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:002564:30:1", "occurrence_id": "e8a336368a828ee31824fb1e", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: country\n\nlevel characteristics used in Table IX with one change. I substitute capital control regulations\n\n\nwith the level of foreign direct investment, FDI, taken from the IMF’s Balance of Payment\n\n\nStatistics and YEARS_LIBER which is the number of years since the official date of\n\n\n30\n\nMention: \"the IMF’s Balance of Payment\n\n\nStatistics\""}, {"role": "assistant", "content": "{\"role\": \"supporting\", \"usage_action\": \"source\", \"summary\": \"Foreign direct investment levels substitute for capital control regulations.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:002568:5:0", "occurrence_id": "04c7108a60cb4e8659686f30", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: To construct a water-resource indicator, we draw on two sources of information.\n\n\nThe first is an estimated geographic distribution of excess demand for water resources\n\n\n(surface and sub-surface) in Vörösmarty, et al. (2000). We use GIS to compute the total\n\n\npopulation residing in excess-demand areas identified by this research. The second\n\n\ninformation source is a database of deaths and injuries from floods maintained by the\n\n\nCentre for Research on the Epidemiology of Disasters (CRED, Université Catholique de\n\n\nLouvain). For each of the Bank's partner countries, we calculate the sum of deaths and\n\n\ninjuries for all recorded floods since 1960. In constructing an indicator for flood damage,\n\n\nwe weight deaths to injuries in the ratio 50:1. Using equal weights, we combine our\n\n\nindicators for demand pressure and floods into a composite indicator of water-related\n\n\nproblems. 4\n\n\nWe derive our indicator for environmental policy and institutional problems from\n\n\ntwo sources. The first is the World Bank's Country Policy and Institutional Assessment\n\n\n(CPIA) database, which rates environmental policies and institutions on a numerical scale\n\n\nof 1 (the lowest) to 6. For this exercise, we reverse the scaling (1 becomes the highest)\n\n\nand normalize the ratings so that countries with the greatest problems score 100. To\n\n\nproxy the scale of the problems confronted by environmental institutions, we compute the\n\n\nmean value of our five thematic indicators (global emissions, pollution, natural resource\n\n\ndegradation, biodiversity threats, water-related problems). 5,6 To assure equal weighting\n\n\n4 Our index of demand pressure also provides a useful proxy for economic damage from drought\nconditions. We are indebted to our colleagues in the Bank’s Middle East / North Africa region for this\nobservation.\n5 While the CPIA ratings provide useful information for comparing institutional needs, they are not\nsufficient for judging investment priorities because they\n\nMention: \"Country Policy and Institutional Assessment\n\n\n(CPIA) database\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"analyze\", \"summary\": \"Environmental policies and institutions are rated on a reversed one-to-six scale.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:002586:8:1", "occurrence_id": "9f9a703aa951a54b66ed5e71", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: |---|---|\n||||**Farebox**|**Farebox**|**Farebox**|**Farebox**|**Farebox**|**Farebox**|**Farebox**|||||||||||||||||||||||||||\n|||||||||||||||||||||||||||||||||||||\n|||||||||||||||||||||||||||||||||||||\n|||||||||||||||||||||||||||||||||||||\n|||||||||||||||||||||||||||||||||||||\n|||||||||||||||||||||||||||||||||||||\n|||||||||||||||||||||||||||||||||||||\n|||||||||||||||||||||||||||||||||||||\n\n\n\n**_Source: Frontier Economics calculations based on SRA data_**\n\n\nIt is clear that the maximum incentive payments available represent a\n\n\nrelatively small proportion of\n\nMention: \"SRA data\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"analyze\", \"summary\": \"Incentive payments are compared against these returns.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:002572:5:0", "occurrence_id": "b3cfa98cca59b2bac816588d", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: donors have in many countries (including Uganda) supported the establishment of institutions to deal\n\n\nspecifically with issues of corruption. However, little is known about the extent to which such institutions\n\n\nhave been effective or the extent to which increased levels of accountability would help improve their\n\n\neffectiveness, as would be suggested by a number of recent studies that have pointed to an important role\n\n\nof the mass media to put policy making on a more informed basis (Stromberg 2001, Besley and Burgess\n\n\n2002) and demands to bring in new actors such as NGOs and to foster transparency and open debate as a\n\n\nmeans to expose corrupt practices (Merhotra 2002, Goetz and Jenkins 2002, Ebrahim 2003).\n\n\nUganda provides an interesting case to study this issue. Despite high levels of economic growth since the\n\n\nearly 1990s, the country has ranked continuously in the bottom part of Transparency International’s\n\ncorruption perception index. 1 [^1: While the expansion in the number of countries in the corruption perception index compiled by Transparency International makes a consistent\nassessment more difficult, Uganda ranked as 43 rd out of 51 countries in 1996 (the first year when the country was included), 74 th of 85 in 1998,] Low levels of transparency and accountability have been identified as\n\n\npotential obstacles to continued progress in reducing poverty (Francis and James 2003). The goal of\n\n\nreducing corruption features prominently in the country’s development strategy and an Inspector General\n\n\nof Government (IGG) and a Ministry of Ethics and Integrity have been set up to help put this into\n\n\npractice. In addition, the Leadership Code Act of 2002 provides for minimum standards of behavior and\n\n\nconduct by leaders serving in public offices (including government departments and statutory bodies) and\n\n\nfor an enforcement mechanism through the IGG’s office. It requires leaders to declare there incomes,\n\n\nassets and liabilities at the time of assumption of office and thereafter every two years (Republic of\n\n\nUganda,\n\nMention: \"Transparency International’s\n\ncorruption perception index\""}, {"role": "assistant", "content": "{\"role\": \"supporting\", \"usage_action\": \"source\", \"summary\": \"The country's persistent low ranking motivates the case study.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:002596:50:0", "occurrence_id": "620e6b2e0bdba0800222e789", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: Coffee productivity has seemingly not increased substantially in the Dominican Republic despite\nyears of efforts to shift to higher yielding varieties, and a slow shakeout of smaller-scale\nproducers (figure III.1). Average yields in the Dominican Republic are below other coffeeproducing countries in the region and appear to be trending downward. 52 These trends do not\nportend well for the competitiveness of the Dominican coffee sector. Low productivity is\ncompounded by increasing costs of production, particularly labor costs and high financing costs.\n\n**Figure III.1 Coffee yields, Dominican Republic and various countries, 1970-2002**\n\n\n1800\n\n\n1600\n\n\n1400\n\n\n1200\n\n\n\n1000\n\n\n800\n\n\n600\n\n\n400\n\n\n200\n\n\n0\n\n\n\n\n\n\n\n**Year**\n\n\nSource: FAO Statistical Database\n\nSeveral representative budgets were examined in an effort to measure the costs of coffee\nproduction. Estimated costs range from US$45-85 per hundredweight 53, depending on\ntechnology use and yields. As noted above, these estimates are subject to a number of caveats,\nbut compare favorably to estimates from other sources in other countries in the region (table\nIII.11). Low yields, high production costs and poor quality beans are the main constraints to the\ncompetitiveness of the Dominican coffee sector.\n\n\n52 A recent diagnostic carried out for FEDECARES indicates that average yields of its 3,500 members are\nabout 80lbs/tarea. (or 550kg/ha).\n53 A recent study carried out for COCOCAFE (see Mercedes, 2002), indicates higher costs of production\nthan returns from coffee sales for low, medium and high technified coffee producers, although high\ntechnified producers have a lower cost of production per qq and receive a higher price per qq.\n\n\n51\n\nMention: \"FAO Statistical Database\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"Coffee producer prices over three decades are plotted from this database.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:002616:15:0", "occurrence_id": "ca42cb9869c200417d83e67b", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: Student 2000 Bgrd Sixth 45,676 3,189\nStudent 2001 Bgrd Third 48,903 3,268\nStudent 2001 Bgrd & Test Fifth 46,718 3,221\nStudent 2002 Bgrd Fourth 48,451 3,205\nStudent 2002 Bgrd & Test Sixth 46,365 3,165\nStudent 1992-2002 Drop First-Sixth 583,876 82,520\nTeacher 1998 Bgrd 23,357 3,562\nTeacher 2001 Bgrd 22,917 3,437\nTeacher 2002 Bgrd 20,634 3,373\nSource: SEP data.\n\n**Table 4. Secondary School Databases**\n\n**Respondent** **Year** **Type** **Grade** **Obs** **Schools**\nPrincipal 2000 Bgrd 1,406 1,403\nPrincipal 2001 Bgrd 1,184 1,181\nPrincipal 2002 Bgrd 860 860\nStudent 2000 Test Seventh 39,562 1,189\nStudent 2001 Bgrd & Test Eighth 39,562 1,189\nStudent 2002 Bgrd Eighth 53,919 1,982\nStudent 2002 Bgrd & Test Ninth 53,202 1,980\nSource: SEP data.\n\n\nInformation on student test scores came from _Estándares\n\nMention: \"SEP data\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"Teacher record counts by year and grade are drawn from this ministry source.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:002674:27:1", "occurrence_id": "33227634f76f5a3eec25f9fa", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: in 1985 (OECD\n1987:44). Low pensions were raised considerably, especially pensions to farmers, while\ncoverage of pension rights was also extended to returning immigrants with no record of\ncontributions to social security programs. Another source of increased government spending was\nsupport to loss-making public corporations. The combined deficit of these entities rose from 2 to\n5.5 percent of GNP between 1979 and 1985. In addition, many private sector firms were unable\nto meet the competitive challenge of European firms that followed the dismantling of tariffs\n(Giannitsis 1993). Many of these firms were declared “problematic” and relied on financial\nsupport from state-controlled banks for their continuing survival.\n\n\nThe effect of these policies was a massive increase in the public sector borrowing\nrequirement that reached 17.7 percent of GNP by 1985. The level of general government debt\nrose from 39 percent of GDP in 1980 to 73 percent in 1985. 14\n\n\nExternal debt grew from 16 percent of total debt in 1980 to 31 percent in 1985. Most of\nthe external debt was of a long-term nature, mostly syndicated loans from international banks,\nwith little exposure to interest rate and refinancing risk. However, being denominated in foreign\ncurrency, it was exposed to foreign currency risk and suffered from the periodic devaluations of\n\n14 Data from the 1987 OECD survey show that on a net basis the general government debt rose from 27\npercent of GNP in 1979 to 63 percent in 1985. Adding the debt of public corporations brought the total to 85\npercent of GNP, which was one of the highest ratios in the OECD area. Particularly disquieting was the speed at\nwhich the total public debt had grown, having soared in relation to GNP by nearly 55 percentage points between\n1979 and 1985.\n\n\n25\n\nMention: \"the 1987 OECD survey\""}, {"role": "assistant", "content": "{\"role\": \"supporting\", \"usage_action\": \"source\", \"summary\": \"It records general government net debt rising from 27 to 63 percent of GNP.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:002673:33:0", "occurrence_id": "d8ad2360f5fee4db880578b2", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: estate values could more than compensate for the loss of stamp duties due to a substantial\nreduction in rates. Only in those scenarios that are shaded would the black economy tax effect\nbe less than total stamp tax collections.\n\n\nWithin this broad range of scenarios, it is possible to assess which parameter values are\nthe more plausible by relating these computations to other estimates of the percentage of GDP in\nthe “black” economy. One can work backward through the basic equations to compute the total\nvalue of black GDP driven by underdeclaration in real estate. The share of stamp duties in GDP\nis roughly 0.5 percent. 39 [^39: See Indian Public Finance Statistics 2001-2002, Table 1.2] If the velocity of black money is 5, underdeclaration is 40 percent, and\nthe stamp tax rate is 10 percent 40 [^40: The weighted average stamp tax rate for the sixteen major states is 9.7 percent as of 2001.], then the implied black economy share of GDP from real estate\nis about 17 percent. Recent estimates show about 23 percent of GDP is in the black economy in\nIndia. 41 [^41: See Friedrich Schneider (2002), “Size and Measurement of the Informal Economy in 110 Countries Around the\nWorld”, paper presented at the Workshop of the Australian Tax Centre, ANU, Canberra, Australia, July 17, 2002.] Earlier work by Acharya et al. (1986) on the black economy suggests a figure of about\n18 to 21 percent for 1980-1981. 42 [^42: See Shankar Acharya et al. (1986), _Aspects of the Black Economy in India_, National Institute of Public Finance\nand Policy (New Delhi, India).] Together these figures strongly suggest that the parameter\nvalues we have chosen are not outside the bounds of plausibility.\n\n**E. Stamp Duty Rates\n\nMention: \"Indian Public Finance Statistics\""}, {"role": "assistant", "content": "{\"role\": \"supporting\", \"usage_action\": \"source\", \"summary\": \"Table 1.2 supplies the stamp duty share of GDP.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:002709:10:1", "occurrence_id": "e102a7d29d0e184e5b3ed05b", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: one might have expected a positive\nrelation between the level of mandated labor protection and income across countries (i.e.\nlabor protection is a normal good), the relationship is in fact weakly negative across our\nsample of countries.\n\n\n\n**Table 1 The synthetic indicators of the stringency of employment protection for**\n**regular and temporary employment**\nCountry (by region) Overall Rank Regular Rank Temporary Rank\nemployment employment employment\n\n\n\nindex\n\n\n\nRank Temporary\n\n\n\nRank\n\n\n\nemployment\n\n\n\nindex\n\n\n\nRank Regular\nemployment\nprotection index\n\n\n\n_Sub-Saharan Africa (SAS)_\nBotswana 0.20 24 0.40 44 0 1\nCameroon 0.67 75 0.67 80 0.67 60\nCote d'Ivoire 0.53 55 0.22 12 0.83 70\nEthiopia 0.57 63 0.40 44 0.75 63\nGhana 0.18 17 0.35 31 0 1\n\n\n11 In order to check the quality of our index, we compare it to the new indicator derived by the\nOECD (2004). The comparison can be made for 15 industrial and transition countries: Canada, Czech\nRepublic, France, Germany, Hungary, Italy, Mexico, Poland, Portugal, Slovak Republic, Spain, Sweden,\nTurkey, United Kingdom, and United States. The correlation between our weighted index for overall\nemployment regulation with the relevant overall OECD index is statistically significant at 1 per cent level\n(correlation coefficient= 0.82).\n\n\n10\n\nMention: \"overall OECD index\""}, {"role": "assistant", "content": "{\"role\": \"supporting\", \"usage_action\": \"validate\", \"summary\": \"The weighted employment regulation index correlates 0.82 with it.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:002713:31:1", "occurrence_id": "972111822c5766cf0b56d074", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: .5 percent of income is spent on water services. The overall budget share is\nrelatively constant across consumption quintiles, although richer households spend less on cooking fuels\nand more on telecommunications. Only a tiny fraction of the poorest households have access to\ntelephones, but those that do so spend as much as 5 percent of their income on the service. Such\nbreakdowns, however useful for designing tariff structures to ensure affordability, are seldom available.\n\nvi Brook and Smith (2001).\nvii See Jalan and Ravaillon, 2001; Jayasuriya and Wodon, 2003; Leipziger et al., 2003; World Bank, 2004;\n\nand references cited therein.\nviii Except where otherwise specified, the sources for the data in this section are as follows:\n\nUSAID Demographic and Health Surveys (1997–2001, depending on the country) available at\n\nhttp://www.measuredhs.com/: access to electricity services, proxy of water service quality, proxy\nof sanitation service quality;\nWorld Bank’s _World Development Indicators_ (1997-2001, depending on the country): technical\n\nquality of electricy services, access to water services, sanitation services, to telecom services, and\ntechnical quality of transport services;\nWorld Economic Forum (2003): perceived quality of water services, perceived quality of electricity\n\nservices, of sanitation services, of ICT services, and of transport services.\nInternational Telecommunication Union: technical quality of telecoms services, access to telecom\n\nservices;\nAngel (2000): quality of housing;\nRoberts (2003): access to transport services.\nix Urban housing alone is worth more than twice that, but problems of double counting make it difficult to\n\nestimate the value of infrastructure stock, including housing (Angel, 2000, p. 288).\n\n\n32\n\nMention: \"USAID Demographic and Health Surveys\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"Access to electricity and water service proxies are read from these rounds.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:002714:41:1", "occurrence_id": "41771592423ff3337d3b63f4", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: **\n\nFrom Section:\n\n\n1: Size of government\n\n\nBased on: Price Waterhouse, Individual Taxes: A\nWorldwide Summary (various issues)\n\n\n\n**Scale** **Description** **Years** **Source**\n\n\n\n% Total trade union membership, in percent of the total labor 1945- **A Database of Labor-Market Indicators Across**\n\nforce. Includes workers of both sexes in the public and the 2000 **Countries**\n\n\n\nTotal trade union membership, in percent of the total labor\nforce. Includes workers of both sexes in the public and the\nprivate sectors. In some countries, the union membership\nmay include unemployed and retired workers who pay their\ndues. Based on the number of active contributors declared\nby the trade unions themselves and on labor force\nestimates. When declared membership is larger than the\nlabor force, a 100 percent membership rate is reported.\n\n\n\n19452000\n(5 year)\n\n\n\nAvailability of part-time and fixed-term contracts\n\n\nWorking time requirements, including mandatory minimum\ndaily rest, maximum number of hours in a normal workweek,\npremium for overtime work, restrictions on weekly holiday,\nmandatory payment for nonworking days, (which includes\ndays of annual leave with pay and paid time off for\nholidays), and minimum wage legislation. The constitutional\nprinciples dealing with the minimum conditions of\nemployment are also coded.\n\n\n\nSurvey\nconducted\nin 1997,\nupdated\nto 2003\n\n\n\nM. Rama and R. Artecona, The World Bank, 2002.\n\n\n**Doing Business, The World Bank**\nsee Botero, Djankov, La Porta, Lopez-de-Silanes, and\nShleifer, \"The Regulation of Labor\", Working Paper 9756,\nNational Bureau of Economic Research, June 2003\nBased on: NATLEX database (International Labour\nOrganization); Constitutions, available online on the U.S.\nLaw Library of Congress website; International\nEncyclopaedia for Labour Law and Industrial Relations,\nand Social Security Programs Throughout the World\n\nMention: \"Database of Labor-Market Indicators\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"Trade union membership as a share of the labour force is taken from this compilation.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:002720:21:0", "occurrence_id": "050a31a3c242ed0c2cf46430", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: construction process. A check against the well-known Penn World Tables data (see\n\n\nwww.nber.org) for a range of countries suggests that physical capital/output ratios were\n\n\ngenerally rising quite rapidly in the 1970-1990 period for which the capital accumulation\n\n\ndata are available. The fact that the growth rates of K/Q and Edn/Q are generally lower\n\n\nthan their growth relative to the labor input does, however, give reason for caution about\n\n\ncommon assumptions, such as Hicks-Neutral technical change in all sectors used by\n\n\nHarrigan (1997) and Kee (2001).\n\n\nDespite the evidence from many different types of empirical studies on the\n\n\npotential role of Rybczynski effects, the coincidence of high rates of accumulation of\n\n\nphysical and human capital over the period, and the rapid shift of developing countries\n\n\ninto exports of manufactures and services, is clearly not definitive evidence of causation.\n\n\nHowever, it is strongly suggestive, and needs to be examined in conjunction with changes\n\n\nin trade policy and in technology.\n\n\n**Protection Policies**\n\n\nProtection policy is frequently advocated as a means to promote industrial development.\n\n\nIt can certainly do this for import competing activities, such as production of consumer\n\n\ngoods. However, this production pattern locks producers into small, and typically slow\n\n\ngrowing, markets for their output. Further, it introduces a major discontinuity. Under a\n\n\nprotectionist policy regime, an exporter must not only have sufficient comparative\n\n\nadvantage to be able to compete in world markets, but must have sufficient advantage to\n\n\nbe able to compete _despite_ the cost increases resulting from protection levied on its\n\n\nintermediate inputs, and the adverse effects of real exchange rate devaluation on its costs\n\n\nfor factors and nontraded goods.\n\n\nDeveloping countries have increasingly come to recognize the adverse impacts of\n\n\nprotection on their export performance. and begun to adjust their policies towards more\n\n\nopen trade regimes. The most profound and far-reaching manifestation of developing\n\n\ncountries’ interest in greater participation in trade is evident\n\nMention: \"Penn World Tables data\""}, {"role": "assistant", "content": "{\"role\": \"supporting\", \"usage_action\": \"validate\", \"summary\": \"Capital-output ratios from the constructed series are checked against it.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:002728:45:5", "occurrence_id": "9b472bb50b9fc5f2be415110", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: up> elasticity faced by Large for good i.\n\nδ: Small’s discount factor of time.\nτ T : The threat level of the tariff used by Large if Small stops cooperating.\ne˜ B [e B ]: Equilibrium e S under PTAs without [with] a CET.\nT : Total amount of numeraire transfer from Large to Small.\n\n\n\nA.5 Data Sources and De fi nitions of Variables\n\n\n\n∆t: Change in the bound advalorem MFN tariff rates between the pre- Uruguay Round and post-UR\nperiods for the HS 8-digit product i. Source: WTO.\nI any0 [I evy0 ]: Indicator variable equal to 1, if good i is imported at a duty-free preferential rate by EU\nunder any [all] of its PTAs in 1994. It excludes PTAs involving a common external tariff. Sources:\nEurostat’s COMEXT (trade fl ows) and UNCTAD’s TRAINS (preferential tariff rates).\nI any [I pos ]: Indicator equal to 1, if good i is imported by the EU under any of its PTAs at either\na duty-free or positive preferential tariff rate [a positive preferential rate only] in 1994\n\nMention: \"COMEXT\""}, {"role": "assistant", "content": "{\"role\": \"supporting\", \"usage_action\": \"source\", \"summary\": \"It provides the trade flows in the preferential tariff indicators.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:002728:45:5", "occurrence_id": "5dcd68d0edd3377159fea7cc", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: up> elasticity faced by Large for good i.\n\nδ: Small’s discount factor of time.\nτ T : The threat level of the tariff used by Large if Small stops cooperating.\ne˜ B [e B ]: Equilibrium e S under PTAs without [with] a CET.\nT : Total amount of numeraire transfer from Large to Small.\n\n\n\nA.5 Data Sources and De fi nitions of Variables\n\n\n\n∆t: Change in the bound advalorem MFN tariff rates between the pre- Uruguay Round and post-UR\nperiods for the HS 8-digit product i. Source: WTO.\nI any0 [I evy0 ]: Indicator variable equal to 1, if good i is imported at a duty-free preferential rate by EU\nunder any [all] of its PTAs in 1994. It excludes PTAs involving a common external tariff. Sources:\nEurostat’s COMEXT (trade fl ows) and UNCTAD’s TRAINS (preferential tariff rates).\nI any [I pos ]: Indicator equal to 1, if good i is imported by the EU under any of its PTAs at either\na duty-free or positive preferential tariff rate [a positive preferential rate only] in 1994\n\nMention: \"TRAINS\""}, {"role": "assistant", "content": "{\"role\": \"supporting\", \"usage_action\": \"source\", \"summary\": \"It provides the preferential tariff rates in the same indicators.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:002706:7:1", "occurrence_id": "354b39019ff46ffd37c79b0f", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: br>31.2
33.1
29.9
29.3|\n|Source: Encuesta de Hogares por Muestro|Source: Encuesta de Hogares por Muestro|Source: Encuesta de Hogares por Muestro|Source: Encuesta de Hogares por Muestro|Source: Encuesta de Hogares por Muestro|\n\n\n\nFigure 2: Shares of employment for Informal Sector, Employees and Self-employed: 1992-2002\n\n\n80\n\n\n70\n\n\n60\n\n\n\n50\n\n\n40\n\n\n30\n\n\n20\n\n\n10\n\n\n0\n\n\n\n\n\n\n\n1992 1995 1996 1997 1998 1999 2000 2001 2002\n\n\n7\n\nMention: \"Encuesta de Hogares por Muestro\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"Its household series underlie the tabulated shares across the sample years.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:002762:54:0", "occurrence_id": "c98364678f84b9f29745d35a", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: raw materials shares than that obtained using data for a single year. Although the input\n\noutput matrices used do not cover our sample period, 1981-1991, we believe that input\n\noutput relationships are relatively stable over these two decades. Matrix _A_ has 22 rows\n\n\nand 17 columns corresponding to the Colombian national accounts classification of\n\n\nindustries. The number of rows exceeds the number of columns because some raw\n\n\nmaterials used in manufacturing originate in the primary sector. Note that by\n\n\n\n22\n\n\n\n22\n## ∑ aij =\n\n_i_ = 1\n\n\n\nconstruction∑ _aij_ = 1\n\n\n\n_i_ = 1\n\n\n\n_aij_ = 1. Hence, our domestic raw materials price indexes are weighted\n\n\n\naverages of producer price indexes: for each manufacturing industry _j_ = 1, …, 17 and\n\n\n\n22\n\n\n\n22\n## time t, the domestic raw materials price index is defined as p RMjt = ∑\n\n\n## p RMjt = ∑ aij pit . To perform\n\n\n\n=\n## ∑\n\n_i_ = 1\n\n\n\n_i_ = 1\n\n\n\nthis calculation we aggregate 29 manufacturing producer price indexes at the 3-digit ISIC\n\n\nrevision 2 into 17 producer price indexes at the broader Colombian national accounts\n\n\nclassification. We use production weights for the period 1975-1989 to aggregate these\n\n\nprice indexes. For the primary sectors included in the calculations we use wholesale price\n\n\nindexes.\n\n\nThe construction of exports price indexes is more involved because the series\n\n\navailable from Banco de la República (Colombia’s central bank) starts only in 1990. For the\n\n\nperiod 1975-1990, we construct export price indexes using detailed trade data from the\n\n\nDirección de Impuestos y Aduanas Nacionales (DIAN). Export transactions in 1975-1990\n\n\nare recorded at an 8-digit Colombian trade classification (NABANDINA) based on the\n\n\nBrussels Tariff Nomenclature. For each NABANDINA and year, we compute export prices\n\n\nin pesos per unit of weight by dividing the value\n\nMention: \"Dirección de Impuestos y Aduanas Nacionales\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"Eight-digit export transactions are used to build export price indexes.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:002763:16:0", "occurrence_id": "ea34d9f3b5eb98a4d9ca8b7d", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: Together, Beijing and Shanghai hold a large share of innovative industries in the country\n\n\naccording to the figures in Table 9, whether in terms of firm numbers or employee numbers.\n\n\nHowever, the innovative sectors are still small in the overall urban economy in Beijing and\n\n\nShanghai. For example, employment in the high- and new-tech enterprises amounts to about 4%\n\n\nof the total employment in Beijing and less than 1% in Shanghai. 7 [^7: However, according to a more extensive definition of high-tech industries which not limited within high-tech\nindustrial parks, the gross output value of high-tech industries in both Beijing and Shanghai has hold a large share in\ntotal industrial output, over 20%, in both cities in 2002 (See Beijing and Shanghai Statistic Yearbook 2003).] The disparities between\n\n\nBeijing and Shanghai in knowledge intensive business services and creative content providers\n\n\nseem even larger. The employment in the selected categories together adds up to nearly 10% of\n\n\nthe total employment in Beijing, much higher than that of the nation as a whole (3.3%), while\n\n\nthis figure is less than 4% for Shanghai, only a little higher than the national level.\n\n\n**Innovative industries in Beijing**\n\n\nBeijing has unique advantages as the national capital in the development of innovative\n\n\nindustries.\n\n\n_National R&D center for high-tech development_\n\n\nBeijing has an abundance of academic think-tanks, universities, research institutes and\n\n\nresearch and development (R&D) centers. More than 50 universities and colleges and over 200\n\n\nresearch bodies are located in the capital, helping to spawn the largest number of high-tech\n\n\nenterprises in China, and some of the nation’s top high-tech companies such as Lenovo and\n\n\nFounder. Table 10 compares the R&D investment in Beijing and Shanghai in 2000. The large\n\n\nnumber of state-owned higher education and R&D institutes received the lion’s share of\n\n\ngovernment funded R&D investment.\n\n\n**Table 10: The R&D Investment in Beijing and Shanghai\n\nMention: \"Beijing and Shanghai Statistic Yearbook 2003\""}, {"role": "assistant", "content": "{\"role\": \"supporting\", \"usage_action\": \"source\", \"summary\": \"It reports high-tech industries exceeding a fifth of industrial output.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:002796:8:0", "occurrence_id": "62dbd5978343c1dd9d075307", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: 31.7 percent). The incidence is also signi fi cantly greater for more highly educated workers,\n\n\nand for professionals relative to technical and clerical staff.\n\n\nTable 1: Employer sponsored training in 1998-99\n\n|Immigrant category|% of recent immigrants in the
category receiving training|% of Canadian-born in the
category receiving training|\n|---|---|---|\n|All|47.7|56.3|\n|With no post-secondary education|34.5|50.6|\n|With post-secondary education|55.4|61.9|\n|Non-permanent workers|31.7|43.2|\n|Permanent workers|49.2|57.7|\n|Professionals|63.8|69.4|\n|Technical/trades|44.6|53.2|\n|Clerical/administrative|50.3|55.7|\n\n\n\nSource: Workplace and Employee Survey, 1998-99. Sample size: 23,540.\n\n\nFor simplicity, the costs and bene fi ts from training are assumed to have the following\n\n\nstructure. Let c - 0 denote the exogenously given and constant cost of training each\n\n\nimmigrant, which is incurred in stage 1. Training involves imparting fi rm-speci fi c knowledge\n\n\nto a worker while currently employed (on the job training). Without loss of generality we\n\n\nassume that the efficiency unit of each immigrant in stage 1 equals unity. Let γ - 1 denote\n\n\nthe efficiency unit of a trained worker in stage 2 to his stage 1 employer. 3 Let\n\nMention: \"Workplace and Employee Survey\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"Training incidence by occupational group is tabulated from 23,540 respondents.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:002798:10:0", "occurrence_id": "9028a2cc466d9cefc4bdef33", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: Table 7 provides information on the importance of intra-industry trade in Central America based\n\non the adjusted Grubel-Loyed intra-industry trade index. 5 [^5: _AIIT_ = _i_ _i_] This index can take values between 0\n\n\n(no intra-industry trade) to 1 (all trade is intra-industry). There appears to be some importance of\n\n\nintra-industry trade within Central America, however, with the exception of Costa Rica (0.3)\n\n\nthere is virtually no evidence of intra-industry trade with the United States. For El Salvador and\n\n\nGuatemala intra-industry trade appears to be quite high with Mexico and Brazil.\n\n\n**Table 7. Intra-industry Trade**\n\n\nSource: Own calculation based on trade data from UN COMTRADE for the year 2001. A 5 digit level of\ndisaggregation is used for this exercise.\n\n\n**3.3. Business Cycle Synchronization and Trade**\n\n\nEmpirical evidence on trade integration and business cycle synchronization is somewhat mixed.\n\n\nWhile Frankel and Rose (1998), Choe (2001), Calderon, Chong and Stein (2002) and Calderon\n\n\n(2003) find that a higher trade intensity tends to increase business cycle synchronization, Shin\n\n\nand Wang (2003) find that increasing trade itself does not necessarily lead to more synchronized\n\n\nbusiness cycles, evidence for East Asia suggests that only the expansion of intra-industry trade\n\n\nhad such an effect. However, Garnier (2003) find only weak or no relations between intra\n\nindustry trade and business cycle synchronization for 16 industrialized countries and conclude\n\n\nthat intra-industry trade at most only partially explains business cycle transmission; the low\n\n\n\n_n_\n\n\n\n( _X_ _i_ + _M_ _i_ )\n\n\n\n_n_ _n_\n## ∑ ( X i + M i ) − ∑\n\n\n## ∑ ( X i + M i ) − ∑ X i −\n\n= _i_ _<\n\nMention: \"UN COMTRADE\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"analyze\", \"summary\": \"Five-digit trade flows give the intra-industry trade indices.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:002811:10:0", "occurrence_id": "dd47e66690545332670b65e2", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: series (land, buildings, etc.) we applied estimated depreciation rates from Harris et al.\n(1994). 18 [^18: The assumed annual depreciation rate for buildings is 3.3 percent, for machinery 10 percent, and for vehicles\nand other fixed assets 20 percent. For land, we assumed no depreciation. These rates are very similar to estimates\npresented in Goeltom (1995).]\n\nSince the data contain no information on physical quantities of inputs used or output\nproduced by plants, we are forced to start with nominal values instead. These are deflated\nusing a set of 192 wholesale price indices for manufactured commodities, published by the\nIndonesian Statistical Office. The commodity indices are mapped to the 5-digit ISIC\nclassification using a concordance table provided by the Statistical Office. These detailed 5digit ISIC level deflators are applied to plant output and material inputs. Figures on\ninvestment and capital are deflated as follows. For buildings, we use a wholesale price index\n(WPI) published in the Statistical Yearbook of Indonesia, and for machinery and vehicles the\naverage of the WPIs for 5-digit sectors producing machinery and vehicles, respectively. For\nother assets, we employ the economy-wide WPI. Unfortunately, the Indonesian Statistical\nOffice does not publish a wholesale price index for energy, so we were constrained to use a\nCPI specific to energy instead.\n\nThe production function is assumed to be Cobb-Douglas and is estimated using the\nsemiparametric procedure suggested by Levinsohn and Petrin (2003). 19 [^19: The estimation was implemented in Stata 8 using the program described in Levinsohn et al. (2003). In 29 out of] As a proxy for\nunobserved productivity shocks that may influence the input decision of the plant, we\nemploy the amount of electricity consumed by each plant. The data contain information on\nelectricity consumption net of own production and sales to other plants, expressed in\nphysical quantities (kWh) which rules out measurement errors related to deflation. Our\nproductivity\n\nMention: \"Statistical Yearbook of Indonesia\""}, {"role": "assistant", "content": "{\"role\": \"supporting\", \"usage_action\": \"curate\", \"summary\": \"Its wholesale price index deflates buildings and machinery investment.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:002820:30:0", "occurrence_id": "e651206c5fb702801b31c141", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: Appendix Table: _Main finance questions in recent LSMS surveys_\n\n\n_Country_\n\n\n_Date of the survey_\n\n\n_Sample size_\n\n\n**_Loan or credit-related questions_**\n\nDid you borrow in the past 12 months? ***** ***** ***** ***** ***** ***** ***** ***** ***** ***** ***** ***** ***** ***** ***** ***** ***** ***** ***** ***** *****\n\n\nSources of the credit? ***** ***** ***** ***** ***** ***** ***** ***** ***** ***** ***** ***** ***** ***** ***** ***** ***** ***** ***** ***** ***** *****\nMain reason for borrowing? ***** ***** ***** ***** ***** ***** ***** ***** ***** ***** ***** ***** ***** ***** ***** *****\n\nHow much did you borrow? ***** ***** **\n\nMention: \"LSMS surveys\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"curate\", \"summary\": \"Their finance modules are compared to harmonise borrowing questions.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:002788:9:1", "occurrence_id": "f70fcd87b8c1676e5f4dbcf5", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: nominal wages for differences in price levels\n\n\nacross urban and rural areas and states, and for temporal changes in price levels between\n\n\n1993 and 1999, using the indexes developed by Deaton and Tarozzi (2000). Thus, all\n\n\nwages in the paper are expressed in terms of the 1999 average of India’s rural prices.\n\n\nWorkers engaged in salaried occupations were asked about the type of enterprise\n\nwhere they carried out their main work activity. In the 50 th round, all salaried workers\n\n\nwere asked to choose from three categories: public, private, or semipublic, and we\n\n\n4 These cross-sectional surveys use a two-stage stratified sampling design, and are representative of the\nnational, state, and so-called “NSS region” level. The first-stage sampling units (FSUs) are census villages\nin the rural areas, and the NSS Urban Frame Survey (UFS) are blocks in the urban areas. The second stage\nunits are the households in both urban and rural sectors. For more information on the survey and sample\ndesign see, e.g., NSSO, Ministry of Planning (1994, 2000).\n5 In the 50th round, the sector of employment – public or private – is defined only for those engaged in\nregular salaried/wage work (in all industrial activities), while in the 55 th round, it is defined for those who\nare employed in non-agricultural activities. In both rounds, wages are defined for everyone who reported\nbeing employed. In order to maintain consistency and comparability across the two rounds, the\nclassification of the sector of employment was defined only for those with regular salaried/wage\nemployment in non-agricultural industries. We also excluded casual workers in public works as well as\nindividuals who were sick or did not work for other reasons.\n\n10\n\nMention: \"NSS Urban Frame Survey\""}, {"role": "assistant", "content": "{\"role\": \"supporting\", \"usage_action\": \"curate\", \"summary\": \"Its blocks serve as first-stage sampling units in urban areas.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:002828:32:0", "occurrence_id": "0310f7609f9050cba63288d1", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: **Source:** Authors’ elaboration based on INDEC.\n\n\n\n31\n\nMention: \"INDEC\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"The tabulated statistics are elaborated from this statistical institute.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:002859:37:3", "occurrence_id": "89ae43a194d8e27ce95c7faa", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: (.00)|37.22
(.00)|25.33
(.00)|24.74
(.01)|\n\n\n\nNote:\n1. - 0.01 significance level, ** 0.05 significance level, *** 0.10 significance level, and insignificant otherwise\n2. EDU2-2: Inputs: orthogonalized public spending on education per capita, teachers per pupil\nOutputs: gross primary and secondary enrollments\nEDU2-2n: same inputs as EDU2-2, outputs: net primary and secondary enrollment\nEDU3-2: literacy of adult is added to EDU2-2 as input\nEDU3-2n: literacy of adult is added to EDU2-2n as input\nEDU3-3: literacy of youth is added to EDU3-2 as output\nEDU3-3bl: same inputs as in EDU3-2,\n\noutputs: average years of school, first level complete, and second level complete (Barro-Lee education indicators)\nHEA2-2: Inputs: orthogonalized public spending on health per capita, literacy of adult\nOutputs: life expectancy at birth, and immunization DPT\nHEA3-2: orthogonalized private spending on health per capita is added to HEA2-2 as input\nHEA3-2m: Immunization Measles is in place of DPT in HEA3-2 as output\nHEA3-3: Immunization Measles is added to HEA3-2 as output\n\n\n36\n\nMention: \"Barro-Lee education indicators\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"Average years of schooling and completion levels are taken as outputs.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:002874:31:3", "occurrence_id": "55307db657599748b51e2a10", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: World Development Indicators.\nGDP\n\nCredit via banks Average domestic credit provided by banking sector (% of GDP) in the pre-crisis period. Source: World\nto GDP Development Indicators.\n\n\n\nAverage domestic credit provided by banking sector (% of GDP) in the pre-crisis period. Source: World\nDevelopment Indicators.\n\n\n\nInflation Average inflation in the pre-crisis period. Source: World Development Indicators.\n\nGDP per capita Average GDP per capita in 1995 US $ in the pre-crisis period. Source: World Development Indicators.\n\n\n32\n\nMention: \"World Development Indicators\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"Pre-crisis domestic credit provided by banks as a share of GDP is taken from it.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:002909:17:0", "occurrence_id": "0589f2c560e941b1a0c68f1c", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: ### 3 Empirical Results\n\nI exemplify the use of the method by estimating the responses of quantities consumed and\n\n\nagricultural wage income in rural Mexico. The case of Mexico is, in principle, a good case\n\n\nstudy because of the importance of the agricultural sector. Mexico is also close to the United\n\n\nStates, and thus WTO reforms are likely to reach rural producers.\n\n\nIn Mexico, a good source of data is the Household Income and Expenditure National\n\n\nSurveys, ENIGH (Encuesta Nacional de Ingresos y Gastos de los Hogares). During the\n\n\n1990s, the data were collected every other year; I use data from the 1994, 1996, 1998, and\n\n\n2000 rounds. The surveys are representative of the population at the National level, and\n\n\ncover rural and urban areas. Since I am focusing on the impacts of price reforms on wage\n\n\nagricultural income, I use the rural modules only. Table 1 reports some summary statistics.\n\n\nI begin with sample sizes and number of clusters c. The ENIGH is carried out at different\n\n\nweeks in different districts. To make the assumption of common prices in a given cluster\n\n\nc reasonable, I define them as district-week pairs. There are between 3306 and 5007 rural\n\n\nhouseholds in the samples. There are 1095 clusters in the pooled sample, approximately 275\n\n\nin each ENIGH round. The number of households interviewed in each “cluster” is typically\n\n\nlarger than in other surveys, with at least 20 households in each of them.\n\n\nOn the consumption side, expenditure data include food and non-food items. Since\n\n\nquantities are only reported for foodstuff, I estimate the model for the following six goods:\n\n\ncorn, wheat, dairy, oils & fats, meat, and fruits & vegetables. These goods are aggregates\n\n\nof differentiated goods within each category. For instance, corn includes own-consumption,\n\n\ncorn grain, and finely grinded corn; meat includes different types of beef, poultry and pork\n\nMention: \"Household Income and Expenditure National\n\n\nSurveys\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"It is the good source of data reaching rural producers.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:002909:17:0", "occurrence_id": "bb05d07f9ea494481c884fba", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: ### 3 Empirical Results\n\nI exemplify the use of the method by estimating the responses of quantities consumed and\n\n\nagricultural wage income in rural Mexico. The case of Mexico is, in principle, a good case\n\n\nstudy because of the importance of the agricultural sector. Mexico is also close to the United\n\n\nStates, and thus WTO reforms are likely to reach rural producers.\n\n\nIn Mexico, a good source of data is the Household Income and Expenditure National\n\n\nSurveys, ENIGH (Encuesta Nacional de Ingresos y Gastos de los Hogares). During the\n\n\n1990s, the data were collected every other year; I use data from the 1994, 1996, 1998, and\n\n\n2000 rounds. The surveys are representative of the population at the National level, and\n\n\ncover rural and urban areas. Since I am focusing on the impacts of price reforms on wage\n\n\nagricultural income, I use the rural modules only. Table 1 reports some summary statistics.\n\n\nI begin with sample sizes and number of clusters c. The ENIGH is carried out at different\n\n\nweeks in different districts. To make the assumption of common prices in a given cluster\n\n\nc reasonable, I define them as district-week pairs. There are between 3306 and 5007 rural\n\n\nhouseholds in the samples. There are 1095 clusters in the pooled sample, approximately 275\n\n\nin each ENIGH round. The number of households interviewed in each “cluster” is typically\n\n\nlarger than in other surveys, with at least 20 households in each of them.\n\n\nOn the consumption side, expenditure data include food and non-food items. Since\n\n\nquantities are only reported for foodstuff, I estimate the model for the following six goods:\n\n\ncorn, wheat, dairy, oils & fats, meat, and fruits & vegetables. These goods are aggregates\n\n\nof differentiated goods within each category. For instance, corn includes own-consumption,\n\n\ncorn grain, and finely grinded corn; meat includes different types of beef, poultry and pork\n\nMention: \"ENIGH\""}, {"role": "assistant", "content": "{\"role\": \"supporting\", \"usage_action\": \"validate\", \"summary\": \"Collection in different weeks across districts complicates the common price assumption.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:002955:4:1", "occurrence_id": "d0c6e2aeefc2ef738b2bae30", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: fell, as did GIS coverage. By 1998 nearly half the urban\n\n\npopulation lacked insurance coverage. A variety of reforms have been introduced, including the\n\n\n4 Figures on coverage are from China’s National Health Survey (NHS), undertaken by the Ministry of Health (MOH) in 1993,\n1998 and 2003. The figures for 1993 and 1998 are published in Gao et al. (2002). The urban insurance figures for 2003 are taken\nfrom “Health Services Utilization and Urban Health Insurance Reform in China”, a presentation by Ling Xu of China’s MOH in\nDecember 2004 at an MOH seminar on the 2003 NHS. The rural figures for 2003 are from “Main Findings from the 3rd NHS\nSurvey”, available online at www.moh.gov.cn, accessed on April 21st, 2005.\n\nMention: \"the 3rd NHS\nSurvey\""}, {"role": "assistant", "content": "{\"role\": \"supporting\", \"usage_action\": \"source\", \"summary\": \"Its main findings give the rural health figures for that year.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:002969:16:1", "occurrence_id": "d39f41384067808879353941", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: if the country has controls\n\n\non cross-border financial credits. Second, we control for restrictions on on-shore foreign\n\n\ncurrency lending by including a dummy for the countries where such restrictions are in place.\n\n\nData for both variables come from the IMF _Annual Report on Exchange Arrangements and_\n\n\n12 Ideally, we would have liked to control as well for the share of non-financial FDI from the home to the host\ncountry, however, this information was missing for many of the countries in our sample.\n\n\n16\n\nMention: \"IMF _Annual Report on Exchange Arrangements\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"It supplies both the restriction dummies and the arrangement variables.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:002988:29:1", "occurrence_id": "7593ac3e81d410889a591c43", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: |Unit
|U.S. Patent & Trademark Office
|\n|Patepo
|Total patents
granted by the
EPO by year
for each
country
|Unit
|European Patent Office
|\n|Royal
|Royalties and
license fees,
payments
|Current U.S. dollars
|-World Development Indicators through
World Bank electronic databases
|\n|Rdexp|R&D
expenditure|Constant U.S. dollars|-UNESCO:printed and electronic
versions of Statistical Yearbook.|\n\n\n\n7 Red Iberoamericana de Indicadores de Ciencia y Tecnología\n\n\n\n29\n\nMention: \"World Bank electronic databases\""}, {"role": "assistant", "content": "{\"role\": \"supporting\", \"usage_action\": \"source\", \"summary\": \"The indicators are accessed through these portals.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:003004:3:1", "occurrence_id": "c812f88ee2b47641e3b6d352", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: ||||\n|||||||\n|||||||\n|||~~Taiwan, Ch~~|
~~ ina~~|~~Japan~~
||\n|||
Korea|Hong Ko
|ng, China||\n||||~~Singapore~~|||\n|||||||\n\n\n0 10,000 20,000 30,000 40,000 50,000\n\nGDP per capita ($US)\n\n\n\n\n\n\n\n\n\n\n- Data refer to 2001 the latest year for which complete data are available. The predicted figures are from a regression of the\nnatural logarithm of total health expenditure (expressed as a share of GDP) on the natural logarithm of GDP per capita. Data are\nfrom the 2005 World Health Report annexes in the cases of Japan, Korea and Singapore. The per capita income data for Hong\nKong (China) and Taiwan (China) are from the World Bank’s World Development Indicators. Data on health spending are from\nhttp://www.hwfb.gov.hk/statistics/download/dha/en/table1.pdf in the case of Hong Kong (China) and from\nhttp://www.doh.gov.tw/ufile/doc/200411_Statistic%20of%20Expenditure%20for%20Health,%201991-2003.pdf in the case of\nTaiwan (China).\n\nMention: \"2005 World Health Report annexes\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"Health expenditure as a share of output is taken from its annexes for three economies.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:003004:3:1", "occurrence_id": "e45d982b98b0a7db080fe3b9", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: ||||\n|||||||\n|||||||\n|||~~Taiwan, Ch~~|
~~ ina~~|~~Japan~~
||\n|||
Korea|Hong Ko
|ng, China||\n||||~~Singapore~~|||\n|||||||\n\n\n0 10,000 20,000 30,000 40,000 50,000\n\nGDP per capita ($US)\n\n\n\n\n\n\n\n\n\n\n- Data refer to 2001 the latest year for which complete data are available. The predicted figures are from a regression of the\nnatural logarithm of total health expenditure (expressed as a share of GDP) on the natural logarithm of GDP per capita. Data are\nfrom the 2005 World Health Report annexes in the cases of Japan, Korea and Singapore. The per capita income data for Hong\nKong (China) and Taiwan (China) are from the World Bank’s World Development Indicators. Data on health spending are from\nhttp://www.hwfb.gov.hk/statistics/download/dha/en/table1.pdf in the case of Hong Kong (China) and from\nhttp://www.doh.gov.tw/ufile/doc/200411_Statistic%20of%20Expenditure%20for%20Health,%201991-2003.pdf in the case of\nTaiwan (China).\n\nMention: \"World Development Indicators\""}, {"role": "assistant", "content": "{\"role\": \"supporting\", \"usage_action\": \"source\", \"summary\": \"It supplies per-capita income for the remaining two economies.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:003023:1:0", "occurrence_id": "44272f4c27163a3aba03b835", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: **Abstract**\n\n\nStandards and technical regulations are an increasingly prominent part of\nthe international trade policy debate. In particular, there has been\nconsiderable discussion of whether standards and regulations affect trade\ncosts and export prospects for developing countries. In this paper, we\nexamine how meeting foreign standards affects firms’ export performance,\nreflected in export propensity and market diversification. The analysis\ndraws on the World Bank Technical Barriers to Trade Survey database of\n619 firms in 17 developing countries. Our results indicate that standards\nand technical regulations in developed countries do affect firms' propensity\nto export in developing countries. In particular, testing procedures and\nlengthy inspection procedures by importers reduce exports by 9% and 3%,\nrespectively. Furthermore, in our model, the difference in standards across\nforeign countries causes diseconomy of scale for firms and affects decisions\nabout whether to enter export markets. The empirical analysis presented\nhere implies that standards impede exporters' market entry, reducing the\nlikelihood of exporting to more than three markets by 7%. In addition, we\nfind that firms that outsource components are more challenged by\ncompliance with multiple standards than those that do not outsource..\n\n\n2\n\nMention: \"the World Bank Technical Barriers to Trade Survey database\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"Six hundred nineteen firms across seventeen developing countries are analysed for export effects.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:003061:19:0", "occurrence_id": "00f1fe698923651d59b758e9", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: Management and Natural Resource Management (in Table 4, **Honesty** also strengthens Waste\n\n\nPollution regulation). This may explain the insignificance of some of the **Honesty** results in\n\n\nTable 2. Environmental lobbying, as captured by **ENGOs**, affects environmental policies\n\n\naddressing Air Pollution, Waste Pollution, and Ecosystem Management in a positive and\n\n\nstrongly significant fashion (consistent with the Table 2 results). **%Urban** is (negative)\n\n\nsignificant only for Waste Pollution regulation in Table 3.\n\n\n**V.** **CONCLUSION**\n\n\nAs developing countries undergo or consider some form of decentralization of government\n\n\nresponsibilities, concerns arise regarding the environmental impacts of decentralized policy\n\n\nmaking. However, empirical research underpinning the associated difficult policy decisions in\n\n\ndeveloping countries is severely lacking in this policy area.\n\n\nThis paper seeks to evaluate the empirical effects of environmental federalism across\n\n\ndeveloping countries. We develop a simple theory of environmental policy formation in\n\n\ncentralized and decentralized systems, where worker-, capital- and environmental lobby groups\n\n\ncompete for the favors of a semi-benevolent government. The prediction that emerges is that a\n\n\ndecentralized government regime yields weaker environmental policy than a centralized\n\n\ninstitutional design. This is due to a greater aggregate incentive for worker- and capital-owner\n\n\nlobbying for less stringent environmental policy under a decentralized system. Using a novel and\n\n\nunique World Bank dataset, we find empirical support for this prediction. This holds especially\n\n\nfor air pollution policies. Moreover, we also find that the effect of federalism is conditional on\n\n\nthe degree of trade openness. In particular, the negative effect of environmental federalism falls\n\n\nas the degree of trade openness rises. We believe this is the first cross-country evidence of a\n\n\nnegative effect of federal institutional designs in developing countries.\n\n\n19\n\nMention: \"World Bank dataset\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"This novel compilation supports the prediction about lobbying under decentralisation.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:003064:2:0", "occurrence_id": "c94e22f9b5b1ed19272f4b03", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: consistency between the micro data and the CGE results; however, by combining the two,\n\n\nit maps aggregate results from the CGE to the detailed information available in the\n\n\nhousehold survey and provides a much more nuanced and useful analysis of poverty\n\n\nimpact. This approach also allows decomposing the total effect on poverty into an\n\n\naggregate income growth component and a redistribution component.\n\n\nA useful insight from this analysis is that even if the total impact on poverty is not\n\n\ntoo large, its dispersion across households – due to their heterogeneity of factor\n\n\nendowments, inputs use, commodity production, and consumption preferences – is\n\n\nsignificant and this should help in designing compensatory policies. Additionally, our\n\n\ngrowth and redistribution decomposition shows that, at least in the short to medium run,\n\n\nredistribution can be as important as growth.\n\n\nThe paper is structured as follows: section 2 presents the CGE model, the micro\n\n\nmodule and the relevant data. The first part of section 3 describes the general equilibrium\n\n\nresults of the trade policy shocks, and the second part the poverty implications. The final\n\n\nsection presents some conclusions.\n\n###### **2 Measuring the effects of trade reforms on poverty: linking a** **CGE model to household surveys**\n\n\nThis section describes the main features of the CGE model and household survey\n\n\nmicro-simulation module.\n\n\n**_The Nicaragua general equilibrium model and its data_**\n\n\nA 2000 Social Accounting Matrix (SAM) represents the initial benchmark\n\n\nequilibrium for the CGE model. This SAM, which includes 39 sectors, 39 commodities, 3\n\n\nfactors (skilled and unskilled labor and one composite capital), an aggregate household\n\n\naccount, and other accounts (government, savings and investment, and the Rest of the\n\n\nWorld), has been assembled from various sources incorporating data from the 2000\n\n\nInput-Output Table and the 2001 Living Standards Measurement Survey (LSMS). As\n\n\n3\n\nMention: \"2001 Living Standards Measurement Survey\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"Household welfare data are combined with the input-output table.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:003078:9:1", "occurrence_id": "ddddf07961123d9085cd43e1", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: definitions of survey income are very\n\n\ndifferent, and the more countries we include, the more different they become. A huge\n\n\neffort, conducted by Luxembourg Income Study, has gone into standardization of\n\n\nnational definitions. A similar project is underway at the World Bank using Living\n\n\nStandards Measurement Surveys (LSMS). Yet the standardization covers only a small\n\n\nportion of all countries and surveys. The main differences arise in the treatment of self\n\nemployed income (what are business expenditures for the self-employed?), valuation of\n\n16 Disposable household income retrieved from surveys in West European nations amounts to about 60\npercent of GDI. A bulk of that difference is explained by health and education consumption. Publiclyfinanced health and education as share of GDI is much less in poor countries.\n\n17 On the additional pitfalls caused by the use of averages from national accounts and distributions from\nhousehold surveys, see Ravallion (2000), Deaton and Dreze (2002), and Deaton (2003).\n\n\n10\n\nMention: \"Living\n\n\nStandards Measurement Surveys\""}, {"role": "assistant", "content": "{\"role\": \"supporting\", \"usage_action\": \"analyze\", \"summary\": \"A standardisation project uses them to harmonise national definitions.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:003080:8:1", "occurrence_id": "fb43296a78ebe90eeac88689", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: .445 0.196 0.115 0.328 0.147 0.088\n1992 0.456 0.209 0.128 0.325 0.150 0.093\n1993 0.466 0.215 0.130 0.326 0.151 0.093\n1995 0.380 0.164 0.095 0.277 0.117 0.070\n1996 0.378 0.167 0.101 0.273 0.122 0.075\n1997 0.370 0.162 0.096 0.273 0.116 0.071\n1998 0.363 0.156 0.091 0.251 0.110 0.066\n1999 0.375 0.161 0.094 0.256 0.112 0.067\n2001 0.375 0.166 0.100 0.258 0.113 0.069\n2002 0.365 0.156 0.090 0.245 0.102 0.060\n2003 0.373 0.163 0.097 0.249 0.106 0.064\n2004 0.345 0.145 0.083 0.222 0.093 0.054\n\n\nNotes: 1 - Rocha (1993) regional poverty lines. See Appendix 2 for details. 2 - The \"administrative poverty\nline\" is set as R$100 per person per month, in September 2004 values.\n\nSource: Authors' calculations from the PNADs.\n\n\nBehind the overall decline, poverty dynamics in Brazil over the last two decades have been\n\nmarked by considerable volatility, which largely reflected macroeconomic instability.\n\nUnsurprisingly, therefore, the volatility was more pronounced in the unstable decade of the\n\n1980s, with a sharp increase during the 1981-83 recession, and a substantial decline during the\n\nrecovery that took place between 1984 and 1986. All three measures are at their minimum in\n\n\n16 See Foster, Greer and Thorbecke (1984).\n17 The Thai (Indonesian) poverty incidence is calculated with respect\n\nMention: \"the PNADs\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"analyze\", \"summary\": \"Poverty line dynamics over two decades are calculated from them.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:003089:7:1", "occurrence_id": "a8b6b229d3f10436d9c166d5", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: ,840 320,274\n\nMax 34,102,743 106,596 8,348,993\n\nAverage 22,295,590 63,303 5,593,792\n\nTotal Independent 66,886,770 189,908 16,781,376\n\n% of Market 8% 8% 8%\n\nSource: HFSA raw data.\n\n\n13. The MPFs sponsored by financial institutions typically outsource asset\nmanagement and administration to other specialized companies within the same financial\ngroup. The other MPFs usually outsource these services as well, sometimes to the same\ncompanies, although there are MPFs sponsored by employers that manage their assets\ninternally. When asset management is outsourced, the asset management company\ntypically charges much lower fees to MPFs outside the financial group. There is a marked\nsegmentation in terms of fees that has not translated into increased switching by members\nfrom high fee funds to low fee funds. As noted below, this is due in part to the lack of\nreadily comparable information on returns and fees until recently.\n\n14. Finally, arrangements for revenue collection have remained deficient. Individual\nMPFs deal with many employers, including thousands of small and medium enterprises.\nAs a result, the industry has been considering the creation of a single company specialized\nin revenue collection, and owned by all the MPFs.\n\n\n**III. PERFORMANCE OF THE SECOND PILLAR:** **GROWTH**\n\n\n15. Membership in the second pillar grew rapidly in the first years of operation, as\nshown in Figure 1. The initial jump in membership reflected the high rate of voluntary\nswitching of younger workers which had already rights under the old system, especially\nworkers under 40 years of age. In the following years, membership was expected to\nincrease at lower but steady rates, in line with the flow of new entrants to the labor force.\n\nMention: \"HFSA raw data\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"Assets and market shares of independent sponsors are tabulated from it.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:003095:5:1", "occurrence_id": "ef5e8939be436f1f22bdba06", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: not use factual information to measure\n\n\ndifferences in institutions and regulations across countries.\n\n\nRecently, the World Bank started to publish results from their Doing Business project (World\n\n\nBank 2004). The Doing Business database provides objective measures of business\n\n\nregulations and their enforcement. The Doing Business indicators are comparable across\n\n\neconomies and indicate the regulatory costs of business. They allow us to obtain information\n\n\non regulatory outcomes, such as time and money spent on bureaucratic procedures, and thus\n\n\nto investigate the efficiency of the government institutions in place. By focusing on evidence\n\n\n6\n\nMention: \"Doing Business database\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"It provides objective measures of business regulation and its enforcement.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:003104:17:1", "occurrence_id": "63a58178d6f2b62df692e516", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: composed of 304\nestablishments included for the first time in that year, and 254 from the old sample not all of\nwhich are to be followed in subsequent years.\n\n\n**7.1.** **Capital**\n\nTo construct the establishment capital stock series, we follow a methodology close to Black and\nLynch (1997). The 1988 Census reports information on the capital stock. We use machinery\ncapital. We avoid overestimation of the amount of depreciation by calculating an average\ndepreciation rate by industrial sector and year. The resulting depreciation rate is then used for all\nfirms within each sector yearly. We further exclude the value of assets sold in our measure of\ncapital, assuming assets have been totally depreciated at that point. Thus, the equation for\nestimating the capital stock for years later than 1988 is:\n\n###### K jit = K jit − 1 + I jit −δ it K jit − 1 (22)\n\nwith\n\n\n18\n\nMention: \"The 1988 Census\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"Machinery capital stock reported here anchors the establishment capital series.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:003116:7:0", "occurrence_id": "d3867953ec5f053dc0d8985a", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: to the same municipal areas (“villages”). The paper uses the 1998 wave because this is\n\n\nthe only year for which detailed information on household migration (previous migration\n\n\nspells and area of birth of actual household members) was asked in the EHPM. Such\n\n\ninformation will be useful in the construction of instrumental variables for the analysis\n\n\nthat follows. The 1998 wave contains a total of 11,953 households belonging to 111\n\n\n“villages” in the country, with all regions nearly equally represented (3,740 households\n\n\nfrom the Metropolitan region, 2,903 from the Western region, 2,780 from the Central\n\n\nregion, and 2,952 from the Eastern region).\n\n\nA panel structure would be ideal to help solve the potential selection problem by\n\n\nincluding households’ fixed effects and, in this way, exploit the variability of remittances\n\n\nwithin a household across time. Unfortunately, this is not possible as each survey does\n\n\nnot follow the same group of households. The data are also incomplete in that, for the\n\n\nsender, only the number of migrant family members is known (the question refers to the\n\n\n“number of members from this household living abroad”).\n\n\nConcerning remittances, the survey questions include whether the household\n\n\nreceives transfers from abroad, as well as their amount and the frequency. Information on\n\n\nthe items (food, housing, health, education, savings) the family decides to spend money\n\n\non, from the amount remitted, is also available. However, as pointed out by Cox-Edwards\n\n\nand Ureta (2003), it is easy to doubt the reliability of such information, as people tend to\n\n\npool remittances and earned income when expenditure decisions are made. Recall bias\n\n\nalso may be an important source of measurement error in such questions.\n\n\n8\n\nMention: \"the EHPM\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"Its migration history and place of birth items support the instrumental variables.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:003121:21:4", "occurrence_id": "6afe5f54365492fe817ace72", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: 84
76
72
82
90
91
78
89
64
73
83
79
73
75
62
64
74
66
71
66
92
83
83
83
76
77
91
87
20
25
81
78
61
49
81
70
21
42
63
56|\n||All above products|8,097
19,626|242|48.2
55.5|
|69
71|\n|0 to 9|All goods|16,803
35,378|211|100
100|
|55
55|\n\n\nSource: Derived from the UN COMTRADE database as reported by the EU.\n\n\nThe composition of exports of top-twenty performers in terms of technology content and\nnatural resource intensity also points to significant realignment in Turkish export offer. The share\n\nMention: \"the UN COMTRADE database\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"Export composition for the top performers is derived from it as reported by the EU.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:003125:56:0", "occurrence_id": "83951a3e0908a1b1507570f7", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: _Flat Returns_\n\n\nWhile skill supply increased, has is kept up with demand? If demand is outpacing supply,\none would expect to see the wage gap between workers with skills and without skills to\nincrease. Figure 24.A (all wage workers) and Figure 24.B (monthly wage workers only)\nsuggest that, first, more education is associated with higher wages at any point in time;\nand, second, real monthly wages trended upward until 1996, fell during the crisis, and\nremained roughly constant since, especially for secondary or higher education levels.\nWage data from the national Socio-Economic Surveys (SES) from 1986 to 2002 for wage\nworkers confirms this pattern, although the actual wage time series differ somewhat\n(Figure 24.C).\n\n\nCombining wages and education, it is possible to estimate returns to education over time\nusing Mincer regressions. In its most basic form, log hourly wages are regressed on\neducation, controlling for age, aged squared, gender, province and urbanization. 21 [^21: The calculation yields, under certain conditions, private returns. Social returns would require\nincorporating the public costs of providing education net of any external effects (through endogenous\ngrowth other channels) of education (Psacharopoulos 1995). The analysis makes no attempt at measuring\nthese effects, implicitly assuming that they have not changed differentially across skill levels over time.] Figure\n24.D shows the coefficients on education levels from a series of such cross-sectional\nregressions for wage workers. Education is divided into six attainment levels (less than\nprimary, primary, lower secondary, upper secondary, vocational and university) and the\nreturns are estimated relative to workers with less than primary education, the omitted\ncategory. The returns relative to less than primary education are flat over time and there\nis no trend towards higher wage differentials across skill levels. If anything, there is a\nsmall downward shift of returns to university post crisis.\n\n\nA robustness check is to restrict the sample to workers on a monthly\n\nMention: \"national Socio-Economic Surveys\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"Wages of wage workers over this period confirm the education pattern.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:003136:6:2", "occurrence_id": "2466f36786a14d624d9954c4", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: .4 3.9 2.5 5.4 4.8 0.9\n% with university education 3.2 4.6 0.7 5.4 5.2 0.7\n\n\nNo of. Uncensored observations 2011 1293 718 878 270 453\n_Note: standard deviations (STD) are not reported for dummy variables._\n_Source: Author's calculation based on EDAMS 1996._\n\n\nWages are the sum of cash earnings. Monthly wages 6 are obtained by dividing reported\n\n\nmonthly wages by imputed monthly hours. The average monthly earning is USD 288 with\n\nmales earning proportionally more on average (USD 354 vs. USD 169 for females). %.\n\n\nPublic sector monthly wages are on average higher by USD 26.9 relative to wages in the\n\nprivate formal sector.\n\n\nForty-three percent of workers are employed in the public sector, 14 percent in the private\n\n\nformal sector, and 22 percent in the informal sector. Males make up 64.3 percent of overall\n\nwage earners. More than 75 percent of male workers are married and more than 58 percent\n\n\nwork in the public sector. In contrast, 74 percent of female workers are unmarried and only\n\n\n6 Daily wages are converted in monthly figures by multiplying with 26 days. Similarly weekly wages are\nconverted to monthly wages by multiplying with 4.2 weeks.\n\nMention: \"EDAMS 1996\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"analyze\", \"summary\": \"Monthly wages are constructed from cash earnings reported here.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:003151:18:0", "occurrence_id": "b9cd1b712d4ce9a56791581a", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: good match. All financial institutions are required by law to obtain information about a borrower\n\n\nfrom the CIB before granting or renewing a loan. This provision was introduced in the effort to\n\n\nreduce non-performing loans in the banking system.\n\n\nWhile the CIB has a long and positive track record, several shortcomings of the existing\n\n\nsystem should be noted. First, the system is still limited by the lack of computization. Second,\n\n\nbanks effectively only obtain current information about existing borrowers, but no historic\n\n\ninformation, i.e. information about past payment performance. One can imagine defaulting\n\n\nborrower paying up to one institution before taking out new loans with another institution – the\n\n\nCIB reports do not seem to be able to capture such behavior. Third, only financial institutions\n\n\nparticipate in the information sharing agreement, other non-financial institutions such as utility\n\n\ncompanies, which are a source of valuable credit information about customers in other countries\n\n\nare excluded. Most importantly, however, the CIB has a stability focus – credit information\n\n\nsharing has the objective to prevent future loan losses, which is an important and valid aspect of\n\n\ncredit information sharing. As important, however, is the function of credit information sharing\n\n\nin enhancing competitiveness and access to credit by allowing borrowers to create “reputation\n\n\ncollateral”, i.e. allow them to use their track record as reference in future loan applications. The\n\n\nlack of historical information limits such a role of the CIB. More importantly, the threshold of\n\n\n50,000 BDT (800 USD) excludes the class of borrowers that around the world rely most on\n\n\nreputation collateral – small and opaque enterprises. While technical problems are certainly\n\n\nrecognized, a move towards including all borrowers irrespective of the size of their loans should\n\n\nbe envisioned in the medium-term. Another important step would be to link the existing CIB for\n\n\nbanks and financial institutions to the credit registry to be created for MFIs. Finally, there does\n\n\nnot seem any reason to prevent private credit information sharing, i.e. to\n\nMention: \"CIB reports\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"validate\", \"summary\": \"Sequential defaulting across institutions is not captured by these reports.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:003151:18:0", "occurrence_id": "d69e22bdb234e1ff041fd0af", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: good match. All financial institutions are required by law to obtain information about a borrower\n\n\nfrom the CIB before granting or renewing a loan. This provision was introduced in the effort to\n\n\nreduce non-performing loans in the banking system.\n\n\nWhile the CIB has a long and positive track record, several shortcomings of the existing\n\n\nsystem should be noted. First, the system is still limited by the lack of computization. Second,\n\n\nbanks effectively only obtain current information about existing borrowers, but no historic\n\n\ninformation, i.e. information about past payment performance. One can imagine defaulting\n\n\nborrower paying up to one institution before taking out new loans with another institution – the\n\n\nCIB reports do not seem to be able to capture such behavior. Third, only financial institutions\n\n\nparticipate in the information sharing agreement, other non-financial institutions such as utility\n\n\ncompanies, which are a source of valuable credit information about customers in other countries\n\n\nare excluded. Most importantly, however, the CIB has a stability focus – credit information\n\n\nsharing has the objective to prevent future loan losses, which is an important and valid aspect of\n\n\ncredit information sharing. As important, however, is the function of credit information sharing\n\n\nin enhancing competitiveness and access to credit by allowing borrowers to create “reputation\n\n\ncollateral”, i.e. allow them to use their track record as reference in future loan applications. The\n\n\nlack of historical information limits such a role of the CIB. More importantly, the threshold of\n\n\n50,000 BDT (800 USD) excludes the class of borrowers that around the world rely most on\n\n\nreputation collateral – small and opaque enterprises. While technical problems are certainly\n\n\nrecognized, a move towards including all borrowers irrespective of the size of their loans should\n\n\nbe envisioned in the medium-term. Another important step would be to link the existing CIB for\n\n\nbanks and financial institutions to the credit registry to be created for MFIs. Finally, there does\n\n\nnot seem any reason to prevent private credit information sharing, i.e. to\n\nMention: \"credit registry\""}, {"role": "assistant", "content": "{\"role\": \"supporting\", \"usage_action\": \"inform\", \"summary\": \"A planned registry for microfinance institutions would be linked to the existing system.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:003170:2:1", "occurrence_id": "c65c86510bca8f1dc332e683", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: \n4 A recent survey of central banks in 40 countries reveals that most countries (90 percent of the sample to be exact)\ncollect remittance statistics from commercial banks, while less than 40 percent gather information from money\ntransfer companies and post offices (De Luna Martinez, 2005). Therefore, balance of payment statistics tend to\nbetter reflect the portion of remittances that is transferred through banks.\n\n\n2\n\nMention: \"survey of central banks\""}, {"role": "assistant", "content": "{\"role\": \"supporting\", \"usage_action\": \"source\", \"summary\": \"It found ninety percent of forty countries compile remittance statistics.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:003176:35:0", "occurrence_id": "b485327f51de5ed9742f6dcf", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: **Figure 3**\n\n\n\n**Domestic Stock Market Development**\n\n\n\nThis figure shows the evolution of domestic stock market capitalization over GDP and value traded domestically over\nGDP. The series are averages across countries. The data for G-7 countries are averages for Canada, France, Germany,\nItaly, Japan, United Kingdom, and United States. The data for East Asian countries are averages for Hong Kong,\nIndonesia, Korea, Malaysia, Philippines, Taiwan, and Thailand. The data for Latin American countries are averages\nfor Argentina, Brazil, Chile, Colombia, Mexico, Peru, and Venezuela.\n\n\n\n**Market Capitalization / GDP**\n\n\n160%\n\n\n140%\n\n\n120%\n\n\n100%\n\n\n80%\n\n\n60%\n\n\n40%\n\n\n20%\n\n\n0%\n\n\n**Value Traded Domestically / GDP**\n\n\n120%\n\n\n100%\n\n\n80%\n\n\n60%\n\n\n40%\n\n\n20%\n\n\n0%\n\n\nLatin American Countries G-7 Countries East Asian Countries\n\n\nSource: S&P Stock Markets Factbook, World Bank\n\n\n35\n\nMention: \"S&P Stock Markets Factbook\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"Market capitalisation shares by country group are taken from this factbook.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:003208:10:0", "occurrence_id": "37dca0fd56c1e85983a7d87b", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: and a systematic sampling rule used to select the households to be interviewed. We\n\n\nadministered a screening questionnaire to determine whether the household contained a\n\n\nperson between the ages of 18 and 65 who was employed and commuted regularly to his\n\n\nor her place of work. We also required respondents to have at least an 8 th grade\n\n\neducation, in order to understand the risk information provided in the survey, and to have\n\n\nresided in Delhi for at least three months. The questionnaire was administered to 1,200\n\n\nrespondents during October – December of 2005, following two pretests involving 601\n\n\nhouseholds.\n\n\n**IV. Sample Characteristics and Responses**\n\n\n**A. Individual Characteristics of the Respondents**\n\n\nDescriptive statistics of the sample respondents are displayed in table 2. The top\n\n\npanel of table 2 reports information about demographic and socioeconomic\n\n\ncharacteristics of the sample. Briefly, we note that the average age of the respondent is 35\n\n\nand that 95% of the respondents are male. The high proportion of males reflects the fact\n\n\nthat only 15% of women in Delhi work outside the home (National Sample Survey,\n\n\n2005). About 48% of respondents have a high school diploma or vocational degree, and\n\n\n28% a bachelor’s degree or better. Mean household income is Rs. 135,000 a year, or\n\n\napproximately $15,350 in purchasing power parity terms. Mean earnings (personal\n\n\nincome) are approximately $10,250 in PPP terms.\n\n\nAs shown in the table, we place our respondents in three income groups,\n\n\ndepending on personal income. Individuals earning less than Rs. 8,000 a month constitute\n\n\nour low-income group, which accounts for 44% of the sample. Individuals with monthly\n\n\n8 Pretests of the questionnaire revealed that changes in the bids on the payment card did not have a\n\n\n - 10\n\nMention: \"National Sample Survey\""}, {"role": "assistant", "content": "{\"role\": \"supporting\", \"usage_action\": \"source\", \"summary\": \"It reports that only fifteen percent of women in the city work outside the home.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:003233:13:0", "occurrence_id": "9ec6edf6aa2e4b1217e205f6", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: spread during the earlier outbreaks in DRC and West Africa. Control measures cur‐\nrently in use aim at reducing the spread of the disease through burning infected coffee\ntrees on site, delaying replanting at least by one to two seasons, and restricting move‐\nment of infected material and soil.\n\nThe wilt disease, which was first confirmed in Uganda in 1993, has been moni‐\ntored through field reports and numerous scientific surveys. The disease was the sub‐\nject of a workshop (hosted by the Government of Uganda in July 1997), attended by 60\nparticipants from most East and Central Africa coffee producing countries (Sewaya\n1999, p. 37). The workshop’s resolutions were: (i) immediate action should be taken to\ncontain the disease; (ii) a project proposal should be presented to the ICO and EU for\nfunding; and (iii) Uganda and DRC should take the lead in the investigations. In terms\nof research, however, it appears that no immediate progress was made. A few years\nlater, for example, Lutakome (2001, p. 66) noted that “Research work will be intensified\nto develop a resistant coffee cultivar. Epidemiological study results on the disease will\nalso be made available to farmers.”\n\nThe latest UCDA survey confirmed that all robusta‐producing districts have\nbeen affected by the disease. In some cases entire coffee fields have been destroyed. Al‐\nthough precise estimates on the impact of the disease are not available, one can gauge\nthe effects of the disease based on the 2003 review study which estimated that of the to‐\ntal of 240,000 hectares in all 21 robusta‐growing (traditional) districts, 122,400 hectares\nhave been infected (equivalent to about 136 million robusta trees), representing a 51\npercent cumulative infection rate (UCDA, _2003/04 Annual Report_, p. 29). There is consid‐\nerable variation among districts\n\nMention: \"UCDA survey\""}, {"role": "assistant", "content": "{\"role\": \"supporting\", \"usage_action\": \"source\", \"summary\": \"It confirmed the disease had reached all robusta-producing districts.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:003241:20:1", "occurrence_id": "14ab591033d1eca02a52a27a", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: hat consumption as a share of total expenditure (%)|Col2|Col3|Col4|\n|---|---|---|---|\n|**Income Categories**
**All**
**Male Head**
**Female Head**
**Households**|**Income Categories**
**All**
**Male Head**
**Female Head**
**Households**|**Income Categories**
**All**
**Male Head**
**Female Head**
**Households**|**Income Categories**
**All**
**Male Head**
**Female Head**
**Households**|\n|All
poorest
2nd quartile
3rd quartile
richest|9.5
3.5
7.5
12.2
14.7|10.9
4.4
8.9
13.3
15.9|4.7
1.1
3.5
8.2
8.1|\n\n\n\n_Source: Authors' calculation based on EDAM 1996_\n\n\n**_5.5. Impact on income distribution_**\n\n**_Income inequality as measured by the Gini index rose slightly across all three scenarios which_**\n**_tentatively show that the devaluation exercise will not exacerbate inequality._** Again this appears\n\nMention: \"EDAM 1996\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"analyze\", \"summary\": \"Income distribution and Gini changes are calculated from this round.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:003281:10:1", "occurrence_id": "ae5a2a0157d1f36ce91d650d", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: in Malawi using 1997-98 household data\n\n\n(National Economic Council, National Statistical Office, Government of Malawi and\n\n\nInternational Food Policy Research Institute 2001). This model is also documented in Mukherjee\n\n\nand Benson (2003). This model is also similar to the model used in Chapter 2 of this volume to\n\n\nassess determinants of poverty. Our main extension is in the use of biomass as a determinant of\n\n\nwelfare.\n\n\nIn our reduced form model, the variable of interest on the right hand side is amount of biomass\n\n\nper hectare in the community. We postulate that household welfare and biomass stock have a\n\n\nnonlinear relationship. As biomass increases, welfare does not linearly increase but increases at a\n\n\n11\n\nMention: \"1997-98 household data\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"Poverty analysis in the country is conducted on these household observations.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:003308:24:1", "occurrence_id": "5f428b246f0d3da44d1b8703", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: \nCotton (Seed) 3.3 1.3 -- 2.7 2.1 1.9 3.3 0.6 3.3\nCoffee (Green) 0.4 -- -- 0.9 0.8 -- -- 1.0 -Citrus 12.4 20.1 15.4 22.0 17.0 34.7 18.3 17.8 8.2\nPulses 0.8 1.1 1.6 0.7 0.8 1.9 2.7 0.6 1.4\nVegetables 16.5 17.2 25.6 17.9 14.9 27.1 26.7 12.9 19.2\nSoybeans 1.6 2.5 0.0 2.6 2.5 2.6 3.3 0.8 1.7\nSource: Caballero (2005)--calculations based on FAO’s AGROSTAT.\n\n\nLabor productivity in Argentina’s agricultural sector is the highest in the region and\nway above the average for LAC countries. Labor productivity is compared across the LAC\nregion in Figure 7.1. Argentina and Uruguay, both land-abundant countries, have the\nhighest labor productivity, with a labor productivity of US$ 9,461 and US$ 7,807,\nrespectively, which is far more than double the LAC average of US$ 3,368. The high\nagricultural labor productivity in Argentina are mainly due to factors other than public\nexpenditure in the sector, which are only $136 per worker and\n\nMention: \"FAO’s AGROSTAT\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"Agricultural labour productivity comparisons are calculated from it.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:003329:2:0", "occurrence_id": "62115677aed896b268008a1d", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: 2\n\n\nand more on investment items -- like education and housing. Households receiving\n\n\nremittances also have a higher likelihood of investing in entrepreneurial activities.\n\n\nThis paper proceeds in five sections. Section 1 defines official international\n\n\nremittances and presents the new data set of 115 developing countries. Section 2 uses\n\n\nthis macro-level data set to estimate an econometric model to identity the determinants of\n\n\nremittances within the developing world. Moving to the level of the household, Section 3\n\n\nexamines how the receipt of international remittances affects the welfare and poverty\n\n\nstatus of households in various developing countries. Section 4 then analyzes how\n\n\nhouseholds consume and invest their remittance earnings, and the impact of these\n\n\nremittance expenditures on entrepreneurial activities and economic development. Section\n\n\n5 summarizes the findings and highlights areas for future work.\n\n\n1. Official International Remittances; Data Set of 115 Developing Countries\n\n\nIt should be stressed at the outset that a variety of data problems make it difficult\n\n\nto accurately examine the impact of international remittances on the developing world.\n\n\nThese data problems relate to the way in which information on international remittances\n\n\nis collected and compiled. While the International Monetary Fund (IMF) publishes\n\n\nannual records of the amount of “worker remittances” received by developing countries\n\n\nin its _Balance of Payments Statistics Yearbook_, these IMF data rely entirely on the\n\n\nreporting conventions of the central banks of some 185 developing countries. In other\n\n\nwords, while the central banks of many developing countries may receive remittances\n\n\nfrom their citizens working abroad, and correctly record these income flows as “worker\n\n\nremittances,” the central banks in other countries may report such remittance flows under\n\n\nanother line item in the balance of payments. In short, there is no reliable and consistent\n\n\nrule for enforcing the way that developing countries report “worker remittances” in their\n\n\nbalance of payments. This means that some countries which produce large numbers of\n\n\ninternational migrants – like the Philippines and the Russian Federation – report receiving\n\n\nlittle or no “worker remittances” because they (probably) record these remittance flows\n\nunder another category in their\n\nMention: \"data set of 115 developing countries\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"The new compilation defines remittances and identifies their determinants.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:003340:8:0", "occurrence_id": "63d8f7257fe085f683602edf", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: environment matter, but there is less agreement as to whether absolute differences or differences\n\n\nvis-à-vis competitors are important. Galindo, Micco, and Serra (2003) argue that absolute legal,\n\n\nregulatory and institutional differences across countries can increase entry costs and reduce the\n\n\nparticipation of banks in foreign countries. Using bilateral foreign banking data for 176\n\n\ncountries, the authors find results that support their hypotheses. In other words, they find that\n\n\nforeign bank penetration is higher between countries that have similar legal origins, banking\n\n\nregulations, and institutional set ups. On the other hand, Claessens and Van Horen (2006) argue\n\n\nthat what is important in driving foreign bank participation is not the difference between the\n\n\ninstitutional environment in the host and source country, but rather the difference taking into\n\n\naccount the institutional quality of the competitors from other source countries. Using data for\n\n\nmost banks in all developing countries, the authors find that absolute levels of institutional\n\n\ndifferences between the host and source countries do not matter once they control for the relative\n\n\nadvantage the source country has compared to its competitors from other countries operating in\n\n\nthe same host.\n\n\nTo summarize, there is substantial evidence that factors such as market opportunities,\n\n\nregulatory barriers in the host countries along with economic, cultural and institutional\n\n\nsimilarities between home and host economies influence the decision of banks to operate\n\n\noverseas. Contrary to the wealth of evidence on these factors, the role that crises can play in\n\n\nbringing about foreign bank participation has only been discussed anecdotally. For example, in\n\n\ndiscussing the rise in foreign bank participation in Argentina, Brazil and Mexico, Peek and\n\n\nRosengren (2000) mention the Tequila Crisis in Mexico and Argentina and the 1999 Brazilian\n\n\ncrises as catalytic events. Moreno and Villar (2006) also point to the experience of Mexico in\n\n\nstating that foreign bank entry might be stimulated by the need for countries to recapitalize their\n\n\nbanking systems in the aftermath of crises. Similarly, Tschoegl (2003) discusses the importance\n\n\nof\n\nMention: \"bilateral foreign banking data for 176\n\n\ncountries\""}, {"role": "assistant", "content": "{\"role\": \"supporting\", \"usage_action\": \"source\", \"summary\": \"A cited study uses these bilateral data to test entry cost hypotheses.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:003343:10:0", "occurrence_id": "a8f9fa6d270e9730d71e3ddf", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: take place between countries without bilateral aid flows. Moreover, we also expect to find a non\nzero correlation between the two error terms in the statistical model in a way that is consistent\n\n\nwith the truncation of potential outcomes. Alternatively, when investment decisions are not\n\nsubject to agency selection – that is, when firms optimize over Ω ( _st_ ) -- we expect no correlation\n\n\nbetween the error terms of the statistical model and any observed correspondence between\n\ninvestment flows and aid flows is attributed to coincidence.\n\n\n**5.** **Data Description**\n\n\n5.1. AIJ Investments\n\n\nOur dichotomous measure of AIJ investment is taken from data on AIJ projects reported to the\n\nUNFCCC and compiled by the SBSTA. As of February 2002, the UNFCCC reported on 156\n\n\nprojects. Among these, we include in our sample the 147 projects in which a letter of intent was\n\nsigned with the host country. The projects began between 1992 and 2001 and were distributed\n\namong 22 investor countries and 42 host countries (table 1). 16 [^16: The Bonn Decision, taken in 1995, gave rise to several new national programs. However, the Decision also\nbrought several established programs into the common AIJ framework. Consequently, some projects under the\nDutch, Norwegian, Swedish and US programs were negotiated prior to the Bonn decision.] For our initial analysis we focus on\n\nthe 65 unique investor-host partnerships that evolved over the study period; that is, for our\n\n\npreferred model we define an investment event as the joint agreement by an investor country and\n\na host country to participate in any number of AIJ projects. We do so for two reasons.\n\n\nFirst, this approach is more in keeping with descriptive studies that suggest agency\n\npreferences, sometimes tied to national policy objectives, were influential in screening outcomes.\n\n\nThe related point of interest then is whether the agency approval hurdle is cleared for any given\n\npotential partnership, rather than how frequently it is cleared. Second\n\nMention: \"the\n\nUNFCCC\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"Project reports compiled here give the joint implementation investment count.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:003365:13:0", "occurrence_id": "5831c59952c80d219f51ae7c", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: 13\n\n\nTo assess this question, the following system and its analog for long-run financial\n\n\nsector development are estimated:\n\n\n(3) _Security of property rights_ ( _1975_ ) = _β1_ + _β2ln(initial financial sector) i_ +\n\n\n_β3(_ **political/institutional variable** _) i_ + **Xi ′β4** + _εi_\n\n\n(4) _Growth of the financial sector i_ ( _1975-2000_ ) = _α1_ + _α2ln(initial financial sector) i_ +\n\n\n_α3(_ **predicted security of property rights)** + **Xi ′a4** + _μi_\n\n\nThese regressions simply ask whether the component of secure property rights that can be\n\n\nexplained by politics or political institutions is a significant determinant of financial sector\n\n\ndevelopment.\n\n\n**Data**\n\nThe regressions below require data on financial sector development and the political\n\n\ncharacteristics of countries. For the first, estimates below rely on _private credit_, total credit\n\n\nextended to the private sector by banks and other financial institutions. This variable is the\n\n\npreferred measure of financial sector development in Beck, et al. (2001) and is taken from\n\n\nthe Financial Structures Database of the World Bank (see Beck, Demirgüç-Kunt and Levine\n\n\n2000). Beck, et al. (2001) describe this as the preferred measure of financial sector\n\n\ndevelopment.\n\n\nFour different measures of political institutions or competition are evaluated here.\n\n\nAll are taken from the _Database of Political Institutions_ (Beck, et al. 2001), running from 1975 –\n\n\n2000. In contrast to the measures used in much of the literature, those here are all objective\n\n\nand easily replicable by others. The _checks_ indicator is an objective counterpart to a\n\n\nsubjective measure often used\n\nMention: \"Financial Structures Database\""}, {"role": "assistant", "content": "{\"role\": \"supporting\", \"usage_action\": \"source\", \"summary\": \"Its bank size measure is the preferred indicator of financial development.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:003368:55:0", "occurrence_id": "8070fe35399268880d41b236", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: Variable Definition Source\n\n\nOther Percentage of new investment over the last year coming from other sources Investment Climate Survey\n\nShare of borrowing in foreign\ncurrency Percentage share of total borrowing (loans, accounts payable) that is denominated in foreign currency? Investment Climate Survey\n\n\nNecessity of collateral Did the financing require collateral or a deposit? Yes (1) No (0) Investment Climate Survey\n\n**_Historical Instruments_**\n\n\n\nLa Porta, Lopez-de-Silanes, Shleifer and\nVishny (1999)\n\n\nLa Porta, Lopez-de-Silanes, Shleifer and\nVishny (1999)\n\n\nLa Porta, Lopez-de-Silanes, Shleifer and\nVishny (1999)\n\n\nLa Porta, Lopez-de-Silanes, Shleifer and\nVishny (1999)\n\n\nAlesina et al. (2003)\n\n\nLa Porta, Lopez-de-Silanes, Shleifer and\nVishny (1999)\n\n\n\nEnglish Common Law\n\n\n\nEnglish Common Law is a dummy variable that takes the value 1 for Common Law Countries and 0 for\nCivil Law and Socialist Law Countries\n\n\n\nCatholic Dummy Variables that takes the value 1 if the dominant religious group in the country are Catholics\n\n\nMuslim Dummy Variables that takes the value 1 if the dominant religious group in the country are Muslims\n\n\nProtest Dummy Variables that takes the value 1 if the dominant religious group in the country are Protestants\n\n\n\nEthnic Fractionalization\n\n\n\nEthnic Fractionalization is the probability that two randomly selected individuals in a country do not\nbelong to the same ethnic group\n\n\n\nLatitude Latitude is the absolute value of the latitude of the country scaled between zero and one.\n\n\n\n56\n\nMention: \"Investment Climate Survey\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"It defines the share of new investment from other sources and foreign-currency borrowing.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:003389:9:1", "occurrence_id": "42959d46cdf4d6964e308b31", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: ||||||\n|||||||||\n|||||||||\n|||||||||\n|||||||||\n|||||||||\n\n\n\nage\n\n\n\ngirls\n\n\n\nFigure 2 - Distribution of children according to school attendance and current work status, by age\nand gender.\nSource: Own calculations based on World Bank, Fortaleza Survey 2003.\nNote: There is one other category—attending school only—which is not plotted.\n\n\nFigure 2 highlights that, after the age of 16, there is an increasing share of teenagers who, though\n\n\nnot having a job, drop out of school. By the age of 18, almost half of the teenagers is neither in\n\n\nschool nor at work. These figures cast some doubt on the relevance of child labor as the driving\n\n\nforce pulling teenagers out of school in urban Brazil.\n\n\n9\n\nMention: \"Fortaleza Survey\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"analyze\", \"summary\": \"Attendance and work status by age and gender are tabulated from it.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:003417:18:0", "occurrence_id": "8dd8ae1ea9c5301a4b3dd81b", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: Expectedly, the following 16 countries are included in our comparison sample of\n\n\ndeveloping economies for the variables from the PolityIV database (i.e., when the institutional\n\n\nvariables are executive constraints or responsible government): Benin, Chile, Ghana, Hungary,\n\n\nIran, Jordan, Kenya, Mali, Mexico, Nicaragua, Pakistan, Rwanda, Senegal, Syria, Tunisia, and\n\n\nUganda. 6 [^6: In the case of executive constraints, Brazil is in, but Hungary is out.] We use 32 countries for the ICRG-data-based regressions (i.e., when the institutional\n\n\nvariables are the control of corruption 7 [^7: The list of countries when the institution is measured as the rule of law is similar but not identical, and is\navailable upon request.] ): Bangladesh, Bolivia, Cameroon, Colombia, El Salvador,\n\n\nGhana, Guatemala, Haiti, Honduras, Hong Kong, India, Indonesia, Kenya, Mali, Mexico, Niger,\n\n\nPakistan, Panama, Papua New Guinea, Paraguay, Philippines, Sierra Leone, Sudan, Syrian Arab\n\n\nRepublic, Thailand, Togo, Trinidad and Tobago, Turkey, Uganda, Venezuela, Zambia, Zimbabwe.\n\n\nTable 2 reports standard descriptive statistics for these variables across the relevant\n\n\nsamples of countries.\n\n\nTable 3 reports our cross country regression results. These regressions incorporate year\n\n\nfixed effects to absorb global macro factors. Because of expected serial correlations for\n\n\nobservations within the same country, the standard errors are estimated based on country\n\n\nclustering.\n\n\nThe institutional measures of good government that capture the strength of constraints on\n\n\nexecutive power are statistically significant positive determinants of FDI. In contrast, the two\n\n\nvariables related to general government quality (i.e., control of corruption and the rule of law) are\n\n\nnot associated with significantly more FDI. These results show that conditional on government\n\n\ntract record and general development levels, limits on executive power indeed attracts FDI, yet\n\n\nmany other aspects of general government\n\nMention: \"the PolityIV database\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"Its executive constraints and responsible government variables define the comparison sample.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:003433:23:1", "occurrence_id": "15f2fdaada845ace88f7892e", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: by design, focuses on medium and large firms with\nover 100 employees, and larger firms tend on average to train more than small ones. The\nBEEPS and ICS surveys, by contrast, tend to include a higher proportion of smaller\nfirms. To compare the incidence of training in Russia to that of OECD and selected\ncomparator developing countries, we adopt a common weighting scheme based\n(arbitrarily) on the size distribution of firms in the India ICS survey. 15 The weighted\nincidence of formal in-service training is calculated for the pooled LME and SE samples\nfrom Russia, and for 16 other comparator countries: 6 from the OECD, 3 from East Asia,\n2 from South Asia, 2 from Latin America, and 3 from Eastern Europe. 16\n\nFigure 10 shows estimates of training incidence in OECD countries and in four regions,\nand separately for the 17 countries used to calculate regional averages. The selected\n\n14 Olga Lazareva, Irina Denisova, and Serguey Tsukhlo (2006), “Hiring or Retraining: Russian Firms’\nExperience”, HSE Working paper WP3/2006/11, 2006.\n15 The size distribution of micro (15 or fewer workers), small (16-100 workers), medium (101-250 workers)\nand large firms (over 250 workers) in India is 40, 44, 7 and 8 percent; the corresponding size distribution\nfor the pooled LME and SE surveys in Russia are 12, 16, 29 and 43 percent\n16 The 17 countries clustered by region include Germany, Greece, Ireland, Portugal, South Korea and Spain\n(OECD), China, Malaysia and Thailand (East Asia), India and Sri Lanka (South Asia), Brazil and Chile\n(Latin America), Bulgaria, Lithuania, Serbia and Russia (Eastern Europe).\n\n\n24\n\nMention: \"ICS surveys\""}, {"role": "assistant", "content": "{\"role\": \"supporting\", \"usage_action\": \"source\", \"summary\": \"Their samples include more small firms than the alternative survey.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:003433:23:1", "occurrence_id": "3dedd72252e4342ab06b27b2", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: by design, focuses on medium and large firms with\nover 100 employees, and larger firms tend on average to train more than small ones. The\nBEEPS and ICS surveys, by contrast, tend to include a higher proportion of smaller\nfirms. To compare the incidence of training in Russia to that of OECD and selected\ncomparator developing countries, we adopt a common weighting scheme based\n(arbitrarily) on the size distribution of firms in the India ICS survey. 15 The weighted\nincidence of formal in-service training is calculated for the pooled LME and SE samples\nfrom Russia, and for 16 other comparator countries: 6 from the OECD, 3 from East Asia,\n2 from South Asia, 2 from Latin America, and 3 from Eastern Europe. 16\n\nFigure 10 shows estimates of training incidence in OECD countries and in four regions,\nand separately for the 17 countries used to calculate regional averages. The selected\n\n14 Olga Lazareva, Irina Denisova, and Serguey Tsukhlo (2006), “Hiring or Retraining: Russian Firms’\nExperience”, HSE Working paper WP3/2006/11, 2006.\n15 The size distribution of micro (15 or fewer workers), small (16-100 workers), medium (101-250 workers)\nand large firms (over 250 workers) in India is 40, 44, 7 and 8 percent; the corresponding size distribution\nfor the pooled LME and SE surveys in Russia are 12, 16, 29 and 43 percent\n16 The 17 countries clustered by region include Germany, Greece, Ireland, Portugal, South Korea and Spain\n(OECD), China, Malaysia and Thailand (East Asia), India and Sri Lanka (South Asia), Brazil and Chile\n(Latin America), Bulgaria, Lithuania, Serbia and Russia (Eastern Europe).\n\n\n24\n\nMention: \"India ICS survey\""}, {"role": "assistant", "content": "{\"role\": \"supporting\", \"usage_action\": \"curate\", \"summary\": \"Its firm size distribution supplies the common weighting scheme.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:003441:11:0", "occurrence_id": "200909dd745f20e4459a7b50", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: the change in monthly profits from one quarter to the next was less than -90 percent or\n\ngreater than 962 percent, corresponding to the 1 st and 99 th percentiles of the distribution\n\n\nof changes in profits. The estimated nominal return on the treatment is 5.9 percent per\n\n\nmonth after this trimming.\n\n\nInflation in Sri Lanka was low over the period studied, with point-to-point\n\n\ninflation of 4.0 percent between March 2005 and March 2006. The second row of Table 2\n\n\nexamines the treatment effect on real profits, where the monthly Sri Lanka Consumers’\n\nPrice Index was used to deflate nominal profits. 6 [^6: Source: Sri Lanka Department of Census and Statistics,\nhttp://www.statistics.gov.lk/price/slcpi/slcpi_monthly.htm [accessed February 17, 2007].\n7 Recall that none of the firms had paid non-family workers in the baseline, and less than 5 percent of firms\nhad non-family workers at any time during the panel survey.] After trimming based on extreme\n\n\nchanges in profits, we see that the real monthly increase in profits was 5.7 percent of the\n\n\ntreatment amount.\n\n\n_Impact on Labor Hours_\n\n\nThis treatment effect represents the increase in real monthly profits from our\n\n\ntreatment. The treatment increased capital stock. However, labor hours may have also\n\n\nhave been affected if firm owners adjusted their own labor hours, or if the resulting rise\n\n\nin profits caused owners to substitute towards leisure. We therefore empirically\n\n\ninvestigate the impact of the treatment on labor hours by estimating equation (1), using\n\nown labor hours and family worker labor hours as the dependent variables. 7 The\n\n\ntreatment is found to have a positive and significant impact on own labor hours: a 10,000\n\n\nrupee treatment increases own weekly hours by 3.4 hours (t\n\nMention: \"Sri Lanka Consumers’\n\nPrice Index\""}, {"role": "assistant", "content": "{\"role\": \"supporting\", \"usage_action\": \"curate\", \"summary\": \"Monthly movements in this index deflate nominal profits.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:003444:38:1", "occurrence_id": "2afb2493dba64bf31958d4e9", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: 923.86 61019.07\n\n_Investment_ 1980-1999 0.50 26462.34\nBefore (1980-1991) 1265.90 11323.9\nAfter (1992-1999) -1830.70 39024.2\n\n_Average Tariffs_ 1980-1999 100.27 50.11\nBefore (1980-1991) 153.13 25.04\nAfter (1992-1999) 65.09 25.83\n\n_Average Non-Tariff Barriers_ 1980-1999 66..88 21.99\nBefore (1980-1991) 85.35 14.52\nAfter (1992-1999) 56.44 19.44\n\n_Output Share of Delicensed Industries_ 1980-1999 53.50 45.20\nBefore (1980-1991) 28.01 38.55\nAfter (1992-1999) 87.35 27.83\n\n_Share of Export>Import Industries_ 1991 0.55 0.48\n\nNotes:\n1) Output and Net Value Added are deflated by WPI obtained from Reserve Bank of India Database on Indian Economy at\nhttp://www.rbi.org.in/. Base year for WPI is 1981.\n2) Development expenditures are deflated by the GDP deflator.\n3) Number of workers includes direct and contracted employment.\n\n\n38\n\nMention: \"Reserve Bank of India Database on Indian Economy\""}, {"role": "assistant", "content": "{\"role\": \"supporting\", \"usage_action\": \"curate\", \"summary\": \"Its wholesale price series with that base year deflates output and value added.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:003465:72:0", "occurrence_id": "5a02f372f02d531f0f32ce15", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: _Source: Customs Adviser to the TTFSE Project and Authors’ Calculation. (2002_\n\n_survey one month period)_\n\n\n**3.** **USA Land Borders**\n\n|Border Post|State of Entry|Baseline|Average|95th Percentile|\n|---|---|---|---|---|\n|Ambassador bridge
Blaine Crossing
Blue Water
Peace Bridge
World Trade|Michigan
Washington
Michigan
New York
Texas|5.7
8.1
11.1
8.3
12.2|8.8
17.3
34.2
21.5
31.2|13.9
35.6.3
80.3
83.4
54.9|\n\n\n\n_Time in minutes_\n_Source: DOT (2002 survey). Office of Freight Management ._\n\n\n\n73\n\nMention: \"DOT (2002 survey)\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"Transport times by corridor are compiled from this freight survey.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:003469:12:0", "occurrence_id": "fd586ba0ae87dc26e2f3ee16", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: continuously augment the stock of knowledge and ensure a sufficient flow of innovations\n\n\n(see Table 3).\n\n\n**Table 3 – R & D Expenditures and Sectoral Distribution in 2004**\n\n\n\n\n\n\n\n|Country|Share of R&D by Sector|Col3|Col4|GERD as percent of
GDP|\n|---|---|---|---|---|\n|Country|Industry|Higher Education|Government|Government|\n|Finland
Japan
Korea
United States
EU-25
China|70.1
75.2
76.7
70.1
63.3
66.8|19.8
13.4
9.9
13.6
22.1
10.2|9.5
9.5
12.1
12.2
13.4
23.0|3.51
3.13
2.85
2.68
1.81
1.23|\n\n\nSource: OECD Science, Technology and Industry Outlook 2006.\n\n\nGovernments have tended to shoulder more of the financing burden for basic\n\n\nresearch in universities and research institutes which adds to the pool of scientific\n\n\nknowledge 29 [^29: Some of the key research underlying innovation by Pharmaceutical industry in the U.S. was done in\npublic labs or with government fundings.] although they do support downstream and applied research by corporations\n\n\nas well. In the majority of cases, resources from the public sector (including for\n\n\nuniversity based research) account for between 20 and 40 percent of spending on R&D\n\n\n(Table 3). The balance comes from the private sector\n\nMention: \"OECD Science, Technology and Industry Outlook 2006\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"Research financing shares by source are reported in this outlook.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:003477:36:0", "occurrence_id": "b3bd0ce73205c7dfc2e802a7", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: **Table A2: Descriptives for Self-Employment Activities (cont)**\n\n2004 2005\nPanel F: Future Work Preferences\n\nRemain in MEP Project 71% 90%\nFind wage employment 10% 8%\nStart another self-employment activity 19% 2%\n\nPanel G: Project Sustainability\n\nDefinitely sustainable 82% 80%\nProbably sustainable 16% 16%\nProbably not sustainable 0% 2%\nDefinitely not sustainable 0% 2%\nNo Knowledge 2% 0%\n\nPanel H: Income Sustainability\n\nDefinitely sustainable 77% 66%\nProbably sustainable 18% 25%\nProbably not sustainable 1% 8%\nDefinitely not sustainable 1% 2%\nNo Knowledge 3% 0%\n\nSource: Author's calculations based on MEP sample (2004, 2005). Table reports descriptive\nstatistics in the baseline period for different project characteristics. For example, the first number\nin Panel F means that 71% of the MEP beneficiaries in 2004 report that if they could choose in the\nfuture they would remain in MEP.\n\n\n**Table A4: Descriptives for Project Rentability**\n\n\n\nNegative Low/medium High\nRentability Rentability Rentability\n\n(1) (2) (3)\nShare Females 0.8 0.5 0.7\nAv. Years Schooling 8.5 8.0 8.5\nAge 39.1 40.1 38.5\nShare of HH Heads 0.8 0.7 0.6\nNumber of Children in the HH 2.0 2.0 1.9\nSize\n\nMention: \"MEP sample (2004, 2005)\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"analyze\", \"summary\": \"Baseline project characteristics and sustainability perceptions are tabulated from these rounds.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:003497:16:0", "occurrence_id": "9a75d4cfde8e0d57f4352a18", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: important aspect of the runoff regime to simulate correctly. A genetic mutation algorithm\n\n\n(Frontline Systems Inc. 2003) was used to optimize the parameters. This approach enables\n\n\nthe whole of the ‘solution space’ to be searched and generally allows solutions to be obtained\n\n\nmore rapidly than alternative optimization methods. The AWCmult parameters were\n\n\nconstrained to lie within a range 0.1m to 5.0m depending on the likely rooting depth of\n\n\nvegetation within the specified land use class (Table 3).\n\n\nUsing a dedicated computer, parameter calibration took approximately 15 seconds per grid\n\n\ncell. Thus the total time for calibrating parameters for all cells in Africa was three days. A\n\n\ncomparison between average annual runoff generated using WatBal and the UNH runoff\n\n\ndata, at the scale of ‘food production units’ (of which there are 97 in Africa) shows a\n\n\nreasonable fit (Figure 8).\n\n\n**_2.4_** **_Runoff simulation_**\n\n\nWhen the model was calibrated it was run to estimate runoff, on a monthly time step, for all\n\n\ngrid cells for the period 1961–1990. The cell data were then converted to runoff in each\n\n\ndistrict. The percentage of each district’s area in each associated grid cell was determined\n\n\nusing a blank global 0.5 x 0.5 degree grid and geoprocessing tools in ArcView. This enabled\n\n\nthe weighted average runoff produced by the grid cells contributing to runoff within any\n\n\ngiven district to be determined. For example, at any given time step, all districts in the same\n\n\ngrid cell will have the same runoff. However, if a district was divided across a number of grid\n\n\ncells (as illustrated in Figure 9), runoff for that district was calculated based on the percentage\n\n\narea of the district in each of the grid cells.\n\n\n**_2.5 Flow simulation_**\n\n\nThe flow routing model uses the STN-30p drainage network (Section 2.2.3\n\nMention: \"UNH runoff\n\n\ndata\""}, {"role": "assistant", "content": "{\"role\": \"supporting\", \"usage_action\": \"validate\", \"summary\": \"Modelled runoff is compared with these data at food production unit scale.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:003514:10:0", "occurrence_id": "f0d53c3b304590c0fde11df1", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: assumption in turn implies that the next three months would be spring, the three months after that\n\n\nwould be summer, and August, September and October would be fall (in the north). The choice\n\n\nof these particular seasonal definitions is motivated by the fact that they provided the best fit\n\n\nwith the data and that they reflected the mid-point for key rainy seasons in the sample. We\n\n\nadjusted for the fact that seasons in the southern hemisphere occur at exactly opposite months of\n\n\nthe year from northern hemisphere seasons.\n\n\nSoil data were obtained from FAO (2003). The FAO data provide information about the major\n\n\nand minor soils in each location. Data concerning the hydrology were obtained from the\n\n\nUniversity of Colorado (IWMI & University of Colorado 2003). Using a hydrological model for\n\n\nAfrica, the hydrology team calculated flow and runoff for each district in the surveyed countries.\n\n\n**4. Results**\n\n\nTable 2 summarizes the crop choice categories in the African analysis. The most popular crop\n\n\nchoice in the sample is maize. This crop is capable of growing across a range of climates because\n\n\nthere are a number of varieties of maize grown in Africa. The second most popular crop portfolio\n\n\nis maize-groundnut. We hyphenate crop combinations throughout the paper. Cowpea-sorghum,\n\n\nsorghum and millet-groundnut are also popular choices. While growing maize alone is the most\n\n\npopular choice in Zambia and Ghana, farmers in Cameroon prefer to grow maize-groundnut.\n\n\nDrought tolerant crops were the revealed preference of farmers in Burkina Faso, Niger and\n\n\nSenegal (sorghum, cowpea, or cowpea-sorghum). In Egypt and South Africa, as expected, the\n\n\npopular choices are maize and wheat. South African farmers also selected a variety of other crops\n\n\n(which did not belong to any of the other revealed categories). Farmers in Zambia and Zimbabwe\n\n\nindicated a preference for maize and maize-groundnut.\n\n\nIn Table 3, we examine the determinants of crop\n\nMention: \"FAO data\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"Major and minor soil types by location are taken from this source.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:003529:29:2", "occurrence_id": "d9b7be2c6f6bc6bdc044fbe2", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: domestic appliances,\ncleaning accessories, personal health products, recreation. Non Eligible: Alcoholic drinks and tobacco, cost of housing,\nelectricity and fuels, other services related to housing, health care, public transport, private transport, education.\n\n\nTable 7: Effect of SARE on Consumer Prices\n\n\n\n.\n\n\n\nThe two columns on the right compare changes across eligible vs non-eligible industries\nusing specification 3. 20 Banco de Mexico only reports prices for 46 cities, 29 of which had\n\nimplemented SARE during our sample period. We report results using both: only SARE\n\nmunicipalities and using all cities which includes non-SARE cities as controls. The results\n\nin the four specifications show that SARE had _no_ significant effect on prices.\n\n\n20We classified 8 industries as eligible for SARE and the remaining 8 as non-eligible, making them as\n\ncompatible as possible with our previous definition. Table 7 lists our classification.\n\n\n28\n\nMention: \"Banco de Mexico\""}, {"role": "assistant", "content": "{\"role\": \"supporting\", \"usage_action\": \"validate\", \"summary\": \"Its price coverage is limited to forty-six cities, restricting the comparison.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:003535:20:0", "occurrence_id": "284c357266462d4325cd92cd", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: The evidence thus far suggests that while there is a significantly positive partial\n\n\ncorrelation between disbursements on IDA lending and debt service paid to IDA, we do\n\n\nnot think that this correlation should be interpreted as evidence of defensive lending.\n\n\nThere is however a further possibility for defensive lending: it is possible that defensive\n\n\nlending is not done overtly, by increasing disbursements beyond what is prescribed by\n\n\nthe PBA formula to countries with incipient debt servicing difficulties. Rather it could be\n\ndone more covertly through manipulation of the variables driving PBA allocations. 23 In\n\n\nparticular, it is possible that defensive lending is accomplished by giving better-than\n\nwarranted CPIA scores to countries with incipient debt servicing difficulties. This would\n\n\nresult in higher-than-warranted commitments and eventual disbursements to the country,\n\n\nbut yet would not evidence itself as a significant partial correlation between\n\n\ndisbursements and debt service after controlling for policy performance.\n\n\nA simple way to test for this possibility is to examine whether measures of\n\n\ncountry indebtedness have predictive power for IDA country performance ratings after\n\n\ncontrolling for other measures of policy performance. We do this in Table 4, where we\n\n\nuse data from the Worldwide Governance Indicators project (Kaufmann, Kraay, and\n\n\nMastruzzi (2006)) as alternative measures of policy performance. We consider two of\n\n\nthe six measures from this dataset, Rule of Law, and Government Effectiveness, as\n\n\nones that correspond most closely to what the IDA country performance ratings are\n\nmeasuring. 24 Although these indicators have the advantage of covering all IDA\n\n\nborrowers, they have a more limited time dimension and are available only 1996, 1998,\n\n\n2000, and annually since 2002. We then report results of pooled and fixed-effects\n\n\nregressions in this shorter panel, including in turn the stock of IDA debt and the flow of\n\n\nIDA debt service as proxies for incipient debt servicing difficulties that might be met with\n\n\nthis interaction to be statistically significant, possibly because we consider a\n\nMention: \"the Worldwide Governance Indicators project\""}, {"role": "assistant", "content": "{\"role\": \"supporting\", \"usage_action\": \"analyze\", \"summary\": \"Its measures serve as alternative policy performance controls.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:003537:10:0", "occurrence_id": "8675131dea9f137db53e87e2", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: deregulation process, followed by de novo branching. Table A1 presents the deregulation dates. 1 [^1: We have data for 50 states and the District of Columbia. Consistent with the literature on branch deregulation, we\ndrop Delaware and South Dakota because the structure of their banking systems were heavily affected by laws that\nmade them centers for the credit card industry, and because South Dakota lacks some financial and banking data.]\n\n\nTwelve states deregulated before the start of our sample period in 1976. Arkansas, Iowa and\n\n\nMinnesota were the last states to deregulate, only after the passage of the Riegle-Neal Act in 1994.\n\n\n**1.2. Income distribution data**\n\n\nInformation on the distribution of income is from the March Supplement of the Current\n\n\nPopulation Survey (CPS), which is a survey of about 60,000 households across the states of the\n\n\nU.S. The CPS provides information on total personal income, income from wages, proprietor\n\n\nincome, as well as detailed demographic information. The CPS is not a true panel; it is\n\n\ncross-sectional survey that is repeated each year. The CPS does not trace individuals through time,\n\n\nbut rather replaces 50% of the sample each year, so that each household is included for two\n\n\nconsecutive years. Each individual is assigned a sample weight corresponding to his or her\n\n\nrepresentativeness in the sample, which we use in our analyses.\n\n\nWe measure the distribution of income for each state and year over the period 1976-2005\n\n\nin four ways. First, the natural logarithm of the Gini coefficient of income distribution is derived\n\n\nfrom the Lorenz curve (Gini), where larger values imply greater income inequality. Our second\n\n\nmeasure of income distribution is the coefficient of variation of income, i.e. the variance of\n\n\nincome divided by the mean (Variance). Third, we use the difference between the natural\n\n\nlogarithm of incomes of those at the 90 th percentile and those at the 10 th\n\nMention: \"Current\n\n\nPopulation Survey\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"Its March supplement of roughly sixty thousand households supplies the income distribution.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:003550:24:0", "occurrence_id": "50b900f2736726a4a695065f", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: 2) _IMPikt_ = λ 0 + λ 1 _GOVit_ + λ 2 _TPit_ + λ 3 _INFit_ + λ 4 _TotDemand_ _t_ +γ ' _X_ _it_ + _u_ 2\n\n\n**4.1 Description of variables and data sources**\n\n\nWe use US and EU imports of clothing products classified at the heading level (4 digit) of HS\n\nchapters 61-63. Trade data are obtained from the USITC website and the EU COMEXT\n\n\ndatabase. Data on the quality of governance are obtained from the Worldwide Governance\n\n\nIndicators (2006). As the six indicators contained in that dataset are highly correlated, including\n\n\nthem separately inevitably leads to problems of multicollinearity. Following Francois and\n\n\nManchin (2007) we use principal component analysis and retain one vector which accounts for\n\n\n80% of the total observed variance. All elements of the vector are positive, making\n\n\ninterpretation of the vector’s coefficient in the regression simple. An increase in any of the\n\n\nmeasured dimensions of government quality increases our aggregate measure and hence the\n\n\neffect on the propensity to export a given clothing product to a given market is qualitatively\n\n\nsimilar for all the contained indicators. In general, the quality of governance is better in\n\n\ncountries with higher per capita income. In order to isolate the relative quality of governance\n\n\n(per capita income is an explanatory variable in our gravity model), we regress this vector of\n\n\ngovernance on the log of per capita income and include the residuals as an independent variable\n\n\nin the regression.\n\n\nWe also use principal component analysis for indicators of infrastructure availability (main\n\n\ntelephone lines, internet users per 1000 inhabitants, road density (relative to both inhabitants\n\n\nand country size)) to deal with the collinearity of the individual variables. The retained vector is\n\n\nagain regressed on the log of per capita income and residuals are then used in the regression\n\n\nequation. We use the simple average of import\n\nMention: \"EU COMEXT\n\n\ndatabase\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"Textile trade at four-digit heading level is obtained from it.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:003550:24:0", "occurrence_id": "ddb1536dd9f09c80cfad6e94", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: 2) _IMPikt_ = λ 0 + λ 1 _GOVit_ + λ 2 _TPit_ + λ 3 _INFit_ + λ 4 _TotDemand_ _t_ +γ ' _X_ _it_ + _u_ 2\n\n\n**4.1 Description of variables and data sources**\n\n\nWe use US and EU imports of clothing products classified at the heading level (4 digit) of HS\n\nchapters 61-63. Trade data are obtained from the USITC website and the EU COMEXT\n\n\ndatabase. Data on the quality of governance are obtained from the Worldwide Governance\n\n\nIndicators (2006). As the six indicators contained in that dataset are highly correlated, including\n\n\nthem separately inevitably leads to problems of multicollinearity. Following Francois and\n\n\nManchin (2007) we use principal component analysis and retain one vector which accounts for\n\n\n80% of the total observed variance. All elements of the vector are positive, making\n\n\ninterpretation of the vector’s coefficient in the regression simple. An increase in any of the\n\n\nmeasured dimensions of government quality increases our aggregate measure and hence the\n\n\neffect on the propensity to export a given clothing product to a given market is qualitatively\n\n\nsimilar for all the contained indicators. In general, the quality of governance is better in\n\n\ncountries with higher per capita income. In order to isolate the relative quality of governance\n\n\n(per capita income is an explanatory variable in our gravity model), we regress this vector of\n\n\ngovernance on the log of per capita income and include the residuals as an independent variable\n\n\nin the regression.\n\n\nWe also use principal component analysis for indicators of infrastructure availability (main\n\n\ntelephone lines, internet users per 1000 inhabitants, road density (relative to both inhabitants\n\n\nand country size)) to deal with the collinearity of the individual variables. The retained vector is\n\n\nagain regressed on the log of per capita income and residuals are then used in the regression\n\n\nequation. We use the simple average of import\n\nMention: \"Worldwide Governance\n\n\nIndicators\""}, {"role": "assistant", "content": "{\"role\": \"supporting\", \"usage_action\": \"analyze\", \"summary\": \"Its highly correlated composite indicators are used as governance controls.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:003573:35:0", "occurrence_id": "32d4a971fa35f3528247568a", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: **Figure 1**\n\n\n\n\n\nSource: ALSMS05\n\n\n**Figure 2**\n\n\n\n\n\nSource: ALSMS05\n\n\n**Figure 3**\n\n\n\n\n\n\n\nSource: ALSMS05\n\n\n - 34\n\nMention: \"ALSMS05\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"All three figures are drawn from this household survey round.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:003578:16:0", "occurrence_id": "ca9c821438ebb216b6564a1f", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: 14\n\n##### **_Social health insurance status_**\n\n\nWe define our SHI dummy _SHIit_ as taking a value of one if in country _i_ at time _t_\n\n\nearmarked payroll taxes for health care were collected from formal-sector workers and there was\n\n\na SHI agency in place. The required information was obtained mainly from the _Health Systems in_\n\n\n_Transition_ ( _HiT)_ document series published by the European Observatory on Health Systems and\n\n\nPolicies, a partnership between the European Office of the World Health Organization (WHO)\n\n\nand governmental, national and international agencies. World Bank reports and consultations\n\n\nwith its staff working in the ECA region were also used in order to obtain data on countries for\n\n\nwhich HiTs have not yet been published, and to double-check the information assembled through\n\n\nthe HiTs. 19\n\n\nOur derivation of the SHI status indicator is shown in Table 1. Our strict definition means\n\n\nthat we end up classifying as non-SHI some country-year combinations that are often—we\n\n\nbelieve, erroneously—classified as SHI (such as Latvia and Poland). Furthermore, we classify\n\n\nRomania as SHI only after 1998; despite the fact that payroll taxes were used somewhat before\n\n\nthen, it was not until 1998 that SHI was fully set up with a SHI agency and with payroll\n\n\ncontributions making up the majority of health care revenues. We explore the sensitivity of our\n\n\nresults to not classifying these as SHI countries, by re-running our models with the three of them\n\n\nclassified as SHI for the years indicated in Table 1.\n\n\n19 Our classification is consistent with the evidence presented in Langenbrunner et al. (in press) which came to our\nattention after the empirical work for the paper hade been completed.\n\nMention: \"HiTs\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"validate\", \"summary\": \"Their information is double-checked against other sources for missing cases.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:003607:2:0", "occurrence_id": "305814d81efc5cece54a3f1d", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: ##### **Help or Hindrance?** **The Impact of Harmonized Standards on African Exports**\n\nWitold Czubala, Ben Shepherd and John S. Wilson *, †\n\nThe World Bank\n\n1818 H St. NW\nWashington D.C. 20433\n\n\n**Keywords:** International trade; Technical barriers to trade; Product standards; Economic\ndevelopment; Textiles and clothing.\n\n\n**JEL Codes:** F13; F15.\n\n\n- The first author is with the Bank of America, and second a Consultant and third author a Lead Economist in the\nDevelopment Research Group—Trade, The World Bank. This work is part of a broader project on trade facilitation\nand development supported through a Trust Fund of the U.K. Department for International Development.\nCompilation of the World Bank EU Standards Database (EUSDB) was supported by a Trust Fund of the U.S.\nAgency for International Development. Sincere thanks to the following for their superb assistance in assembling the\nWorld Bank EUSDB: Jérôme Beaufils, Teresa Bianchi, Françoise Blarez, Anne-Claire Hoyaux, Mark-André\nSaucier-Nadeau, and Mark Troger. We are also grateful to a number of World Bank colleagues for their comments\nand suggestions: Enrique Aldaz-Carroll, Silja Baller, Paul Brenton, and Bernard Hoekman, as well as participants at\na World Bank workshop on Trade Costs on April 30, 2007. Comments to: bshepherd@worldbank.org\n(corresponding author), jswilson@worldbank.org, or witold.czubala@gmail.com.\n\n- The findings, interpretations, and conclusions expressed in this paper are entirely those of the authors. They do not\nnecessarily represent\n\nMention: \"World Bank EU Standards Database\""}, {"role": "assistant", "content": "{\"role\": \"supporting\", \"usage_action\": \"inform\", \"summary\": \"Its compilation was financed by a development trust fund.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:003611:12:0", "occurrence_id": "05ab575ba304256f6e292328", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: Madrasah teachers). The samples were drawn in two stages. 91 clusters 1 were selected at\n\n\nthe first stage as a subsample of the 361 clusters included in the Bangladesh\n\n\nDemographic and Health Survey (BDHS) of 2004. The second sampling stage selected\n\n\none adult from each household. Opinion leaders were selected from among those who\n\n\nwere resident in and around the cluster, having knowledge of and influences on the\n\n\npeople of the cluster. On average 49 adults and 5-6 opinion leaders were interviewed in\n\n\neach cluster. Out of the 49 adults interviewed in a cluster, roughly 16 were married\n\n\nwomen age 15-25, 16 married women age 45-59 and 17 married men age 25-50.\n\n\nInterviews were conducted in April-May 2006.\n\n\nWe have two estimation samples: older women (1431 initial observations) and\n\n\nyounger women (1543 initial observations). Explanatory variables are missing for some\n\n\nobservations, which cause a drop in sample sizes for the final/effective analyses samples.\n\n\nOur final samples thus are: older women (1408 observations) and younger women (1534\n\n\nobservations). Sample drops of these magnitudes do not seem to be cause for concern\n\n\nregarding the representativeness of the estimation samples. The means for the analyses\n\n\nsamples are reported in Table 2.\n\n\n[Table 2 about here]\n\n\nIn analyzing the difference in patterns between the two cohorts of women in the\n\n\nsample, we capture intergenerational change. Of course, it is entirely possible that the\n\n\ndifference could well be a function of age and life-cycle and not of cohort. That being so,\n\n\nwe believe that once we control for a number of demographic characteristics, we do\n\n\ncapture the effect of change over time.\n\n\n1 A cluster is a census defined village that corresponds roughly to a mouza village in rural areas and a\ncensus block (part of a mohollah) in an urban area.\n\n\n11\n\nMention: \"Bangladesh\n\n\nDemographic and Health Survey\""}, {"role": "assistant", "content": "{\"role\": \"supporting\", \"usage_action\": \"source\", \"summary\": \"Its cluster frame supplies the first-stage sample for the follow-up survey.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:003617:20:2", "occurrence_id": "68043a14994e31aa5f08ab55", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: _Source_: Briceño and Klytchnikova (2006)
_Note_: Data are the most recent available for 2000–04.|_Source_: Briceño and Klytchnikova (2006)
_Note_: Data are the most recent available for 2000–04.|_Source_: Briceño and Klytchnikova (2006)
_Note_: Data are the most recent available for 2000–04.|\n\n\n_How bad is the affordability problem?_\n\n\nThe access gap is only part of the problem. There is also an affordability issue.\nInfrastructure practitioners rely on rules of thumb to get a sense of the affordability\nproblem in any sector. One such rule of thumb (developed by the World Health\nOrganization) is that households should not need to spend more than 5% of their income\non their water and sanitations need—3.5 for water alone. In the case of electricity, there\nis no such formal ‘rule of thumb’ but many also assume that 4-6% is a maximum to\nspend on energy. Overall, the more general informal rule is the one that suggests that\npoor households should not have to spend more than 15% of their income on\ninfrastructure services.\n\n\nArmed with these rules of thumbs, it should be easy to get a sense of the extent of the\naffordability problem across the world. It is however impossible, because there is no\nsystematic formal monitoring of this crucial issue. There are however a number of recent\nbooks which have documented quite carefully the problem within Africa, Eastern Europe,\n\n\n22. In the Demographic and Health Survey data, the poorer and richer are defined based on an asset index used as a proxy\nof the welfare level. In the Living Standard Measurement Survey data, households are ranked by total per capita\nexpenditure.\n\n\n18\n\nMention: \"Demographic and Health Survey data\""}, {"role": "assistant", "content": "{\"role\": \"supporting\", \"usage_action\": \"analyze\", \"summary\": \"Wealth groups are defined from an asset index in these data.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:003617:20:2", "occurrence_id": "8fcff9841d2807f683fc2772", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: _Source_: Briceño and Klytchnikova (2006)
_Note_: Data are the most recent available for 2000–04.|_Source_: Briceño and Klytchnikova (2006)
_Note_: Data are the most recent available for 2000–04.|_Source_: Briceño and Klytchnikova (2006)
_Note_: Data are the most recent available for 2000–04.|\n\n\n_How bad is the affordability problem?_\n\n\nThe access gap is only part of the problem. There is also an affordability issue.\nInfrastructure practitioners rely on rules of thumb to get a sense of the affordability\nproblem in any sector. One such rule of thumb (developed by the World Health\nOrganization) is that households should not need to spend more than 5% of their income\non their water and sanitations need—3.5 for water alone. In the case of electricity, there\nis no such formal ‘rule of thumb’ but many also assume that 4-6% is a maximum to\nspend on energy. Overall, the more general informal rule is the one that suggests that\npoor households should not have to spend more than 15% of their income on\ninfrastructure services.\n\n\nArmed with these rules of thumbs, it should be easy to get a sense of the extent of the\naffordability problem across the world. It is however impossible, because there is no\nsystematic formal monitoring of this crucial issue. There are however a number of recent\nbooks which have documented quite carefully the problem within Africa, Eastern Europe,\n\n\n22. In the Demographic and Health Survey data, the poorer and richer are defined based on an asset index used as a proxy\nof the welfare level. In the Living Standard Measurement Survey data, households are ranked by total per capita\nexpenditure.\n\n\n18\n\nMention: \"Living Standard Measurement Survey data\""}, {"role": "assistant", "content": "{\"role\": \"supporting\", \"usage_action\": \"analyze\", \"summary\": \"Households here are ranked by per-capita total expenditure instead.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:003618:27:23", "occurrence_id": "da30e98ad1118f1547385c31", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text:
(Millions of kilogram)
(7
|05
9)|(6|1)
|(58)|\n|||||||||||||||\n|||||||||||||||\n|||||||||||||||\n|||||||||||||||\n|||||||||||||||\n|||||||||||||||\n|||||||||||||||\n|||||||||||||||\n|||||||||||||||\n|||||||||||||||\n\n\n\nSource: _WITS COMTRADE_ database.\n\nMention: \"_WITS COMTRADE_ database\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"The tabulated trade flows are drawn from this database.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:003626:12:1", "occurrence_id": "21ca8e37ee6fceb3d54ad0d3", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: population\n\n\napproaching 50 million people. The sampling process then consisted of three stages.\n\n\nFirst, a stratified random sample of 75 census tracts was selected. Second, interviewers\n\n\ncarried out a door-to-door listing within each census tract in order to determine which\n\n\nhouseholds had a Nikkei member. Third, the survey questionnaire was then administered\n\n\nto households identified as Nikkei. We now describe the details of each step.\n\n\n4 Population numbers from the 2000 Census are taken from\nhttp://www.ibge.gov.br/english/estatistica/populacao/censo2000/ [accessed February 8, 2007].\n\n\n - - 11\n\nMention: \"the 2000 Census\""}, {"role": "assistant", "content": "{\"role\": \"supporting\", \"usage_action\": \"source\", \"summary\": \"Population counts used to scale the estimates are taken from this enumeration.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:003630:18:1", "occurrence_id": "a5f00fca99cbdcce6a05c2f6", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: 7: Internet Hosts per 10,000 Inhabitants in 2003\n\n\n300\n\n\n\n250\n\n\n200\n\n\n150\n\n\n100\n\n\n50\n\n\n0\n\n\n\n\n\n\n\n\n\n\n\n\n|276.3|Col2|Col3|Col4|\n|---|---|---|---|\n|276.3||||\n|||||\n|||||\n|||90.0|90.0|\n|||||\n|||||\n|0.82
13.91
18.55
0.39
1.010.98
5.9||||\n\n\n\nSource: Authors’ calculation based on International Telecommunication Union (2004) data\n\n\nImprovement in information technology services is as equally important as development\nof physical infrastructure. Biggs et al. (2000) examines the case in Nepal where service is\npoor and hinders business activities. For example, phone lines usually do not work well\noutside of the cities. Services are not available all day, and when available, voice quality\nis often poor (Biggs et al., 2000). Continued efforts to deregulate telecommunications,\nopen markets to competition and investment, and expand financing for infrastructure\n\n\n17\n\nMention: \"International Telecommunication Union (2004)\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"Indicators of information technology services are calculated from this source.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:003666:7:0", "occurrence_id": "19f3b0fb0acc7165184e742c", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: - 6 \n\nIn the 3G mobile telecommunications experiences in European countries, for instance, the\n\n\nnumber of bidding firms per license ranges from 0.75 to 2.6. In the United Kingdom, five\n\n\nlicenses were auctioned among 13 bidders. On the other hand, there was no competition in\n\n\nthe Austrian and Swiss cases, meaning that the number of bidders was eventually the same as\n\n\nthe number of licenses to be issued (Klemperer, 2002; van Damme, 2002). NOA (2007)\n\n\nindicates that half of the past U.K. PFI projects attracted at most two or three bids. Similarly,\n\n\nin the railway concession cases in Argentina and Brazil during the 1990s, two to four firms\n\n\nparticipated in the bidding process. Particularly, the freight train contracts, which may be less\n\n\nprofitable from the private sector point of view, attracted only one or two bidders.\n\n\nHow many bidders are required for sufficient competition? Gupta (2002) shows that the\n\n\nhighway construction market (in Florida) becomes competitive with about six to eight\n\nbidders. 3 [^3: It means that the marginal impact of one more bidder on the equilibrium bid is not statistically significant\nwhen the number of participants exceeds eight.] As per Iimi (2006), large-scale official development projects—mostly in the\n\n\ninfrastructure sector—require eight firms to minimize the contract prices. In the U.S.\n\n\noffshore oil lease market, a similar level of bidder participation seems necessary for\n\n\ncompetition purposes (Brannman _et al_ ., 1987).\n\n\nDeveloping countries may have an even more limited competition in PPP infrastructure\n\n\nauctions. The PPI Database shows that about 60 percent of PPP infrastructure transactions in\n\ndeveloping countries involved one to three bidders (Figure 1). 4 [^4: The database covers only transactions of which total investment commitments exceed US$ 1 million.] About 15 percent of contracts\n\n\nattracted only one bidder even under the competitive bidding circumstances. The degree of\n\n\ncompetition varies\n\nMention: \"PPI Database\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"It shows most infrastructure transactions involved only a few bidders.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:003668:9:0", "occurrence_id": "7ceda4788ca405e6d4627d70", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: move to the location of the consumer (or vice versa). As the conventional definition of\n\n\ntrade – where a product crosses the frontier – would miss out on the latter type of\n\n\ninternational transactions, the WTO has defined trade to span four modes of supply:\n\n\n - _Mode 1 – Cross-border_ : services supplied from the territory of one country into\nthe territory of another.\n\n - _Mode 2 – Consumption abroad_ : services supplied in the territory of a country to\nthe consumers of another.\n\n - _Mode 3 – Commercial presence_ : services supplied through any type of business\nor professional establishment of one country in the territory of another (i.e., FDI).\n\n - _Mode 4 – Presence of natural persons_ : services supplied by nationals of a\ncountry in the territory of another.\n\n \n\nData on services trade are notoriously weak. The primary source is the balance of\n\n\npayments, where measured flows correspond mainly to modes 1 and 2. IMF data reveal\n\nthat service imports roughly tripled over the decade from 1994 to 2004. 11 For the 178\n\n\ncountries for which the IMF reports data the median value of imports of services in 1994\n\n\nwas some US$550 million. As of 2004, this had increased to US$1.5 billion. For the\n\n\nworld’s largest services trader, the US, total reported imports rose from almost US$200\n\n\nbillion to US$340 billion.\n\n\nNotwithstanding this growth in the absolute value of services trade, world service\n\n\nimports as a percentage of GDP rose slightly from 11 percent in 1994 to 12 percent of\n\n\nGDP in 2004 (Table 1). This masks declines in the services share in developing\n\n\ncountries. The rising importance of service imports in the aggregate stems mainly from\n\n\nincreases within the most developed countries (from 8 percent to 12.7 percent), driven by\n\n\nstrong growth in producer and business services imports (whose ratio to GDP rose from\n\n\n3.3 percent to 6.7 percent\n\nMention: \"IMF data\""}, {"role": "assistant", "content": "{\"role\": \"supporting\", \"usage_action\": \"source\", \"summary\": \"Its balance of payments records show service imports roughly tripling over the decade.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:003679:9:1", "occurrence_id": "9c504495fbbc336a2cde85d0", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: 2007\n\n\n\n**Private investment fell despite rising growth.** The private sector found serious\n\n\nimpediments to investing in the poor transportation network, the declining quality of\n\neducation and the high cost of inputs, particularly electricity. 9 Between 2000 and 2004,\n\n\nprivate investment - deterred by political instability and systemic uncertainties - did not\n\n\nrespond to higher growth (Figure 4 and Figure 5), and private sector credit fell by 40 percent\n\n\nas a share of GDP.\n\n\n7 In recent years, foreign investments have grown from a small base (from 2005 to 2006, net FDI inflows\nhave reached $2 billion, growing to 14 percent of the overall private investment), but are still too small to\nmatter, and many investment approvals have not translated into actual flows.\n8 There is evidence that busts in the real estate tend to be longer-lived than in other asset markets, and tend\nto be associated with more severe downturns in overall economic activity. For example, in industrial\ncountries, the evidence for housing market busts suggests they have an average duration of 4-5 years\ncompared to 2-3 years for equity market busts (World Bank, 2006a).\n9 Based on the competitiveness ranking of the World Economic Forum on basic infrastructure, the\nPhilippines placed 89th out of 102 countries surveyed.\n\n\n10\n\nMention: \"the World Economic Forum\""}, {"role": "assistant", "content": "{\"role\": \"supporting\", \"usage_action\": \"source\", \"summary\": \"Its infrastructure competitiveness ranking places the country eighty-ninth of one hundred two.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:003696:17:0", "occurrence_id": "8428f0c3701bb84515fe096e", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: and I omit any analysis of farm employment and rural labor markets. Moreover, and\n\n\npartly for this reason, I restrict the analysis to the impact of changes in the prices of\n\n\nagro-manufactures exports, leaving aside the impacts of changes in the export prices of\n\n\nagricultural commodities. 9\n\n\nTable 1 reports the main trends in three variables of interest: the employment status of\n\n\nthe individual, monthly wages, and the level of the price of agro-industrial exports. In the\n\n\nTable, I report data on all workers in all sectors. 10 The sample is restricted to include all\n\n\n“employed” workers, leaving aside the self-employed. Sample sizes of employed, unemployed\n\n\nand inactive individuals of working age are reported as well.\n\n\nThe average wage of unskilled workers (primary education) increased until 1995 and\n\n\ndeclined afterwards to reach, in 1999, a level comparable to that in 1992. The wages of\n\n\nsemi-skilled workers (secondary education) increased until 1996, and then stabilized. In\n\n\n1999, average wages declined, but were still higher than in 1992. The wages of skilled\n\n\nworkers (college education) fluctuated more: they increased until 1995, declined in 1996,\n\n\nand then recovered again until 1998. In 1999, wages are higher than in 1992, indicating\n\n\npositive growth during the period.\n\n\nThe Argentine Statistical Institute provides data on the international prices of Argentine\n\n\nexports of agro-manufactured goods, which include dairy product, beef, oils and fats, and\n\n\nfood-processing goods. These export prices show an increasing trend (with fluctuations)\n\n\nfrom 1992 to 1997, and a decline in more recent years. 11\n\n\nIn the EPH survey, there are three employment categories: employed, unemployed and\n\n\ninactive. The employment categories are defined on a weekly basis—this type of reporting is\n\n\n15\n\nMention: \"EPH survey\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"Its three employment categories define the measured activity statuses.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:003714:24:0", "occurrence_id": "5b87d49f1d9452156831bb16", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: **Figure 1: Estimated male and female hazards of ever—migration, Albania 2005 LSMS**\n\n\n\n22\n\nMention: \"LSMS\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"analyze\", \"summary\": \"Male and female migration hazards are estimated from this round.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:003726:5:3", "occurrence_id": "c88566cfc4a3ac28688b2a34", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: eychelles
0.1
2.3
Côte d'Ivoire
-0.3
2.0
Zimbabwe
-5.5
-2.6
Average
1.8
2.3
|\n|Source:World Bank World Development Indicators database.
1The cut-off point of 4 percent is based primarily on the performance during 2000-06. Somalia is not included for lack of data. At the World
Bank, Djibouti is classified as part of Middle East and not part of Sub-Saharan Africa.
*Data for Liberia was available only for 1999-2006.|Source:World Bank World Development Indicators database.
1The cut-off point of 4 percent is based primarily on the performance during 2000-06. Somalia is not included for lack of data. At the World
Bank, Djibouti is classified as part of Middle East and not part of Sub-Saharan Africa.
*Data for Liberia was available only for 1999-2006.|\n\n\n**_B._** **_Performance by different types of countries_**\n\nNonetheless, the range of growth among individual countries can vary widely, anywhere\nfrom −5.5 percent to a high of 23.1 percent. Alternative taxonomies of countries are often\nnecessary to characterize the growth story better. Table 2 presents the growth\nperformance for frequently used country groups for the 1980s, the 1990s\n\nMention: \"World Bank World Development Indicators database\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"Growth comparisons over this window are drawn from this database.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:003733:66:0", "occurrence_id": "612eba80221bdbae3fe16979", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: **Table A.2**\n**Evidence on Educational Attainment of Migrants**\n\n**from the China Urban Labor Survey (2001)**\n\n\nSource Community\nAll Provinces 4 RCRE Provinces\n\nEducation\nElementary or Less 0.247 0.220\n\nSome Middle School 0.086 0.096\n\nMiddle School 0.485 0.501\n\nSome High School 0.039 0.045\n\nHigh School 0.120 0.120\n\nSome Post Secondary 0.009 0.011\n\nCollege 0.010 0.012\n\nNumber of Observations 2,463 481\n\n*Source: China Urban Labor Survey (see discussion on note of Table 1).\n\n\n65\n\nMention: \"China Urban Labor Survey\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"Educational attainment of migrants by source community is tabulated from it.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:003758:12:1", "occurrence_id": "d8cc054a97ce9bcd5306ebf6", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: 624
4,953
4,840
899
366
502
674
835
257
1,652
5,185
5,480
881
756
894
750
761
298
1,721
6,060
5,950
959
816
722
675
650
246
1,729
5,795
6,180
815
698
892
746
639
327
2,002
6,118
6,330
749
663
860
805
520
386
2,163
6,146
5,660
924
848
931
866
579
533
2,455
7,136
6,140
743
922
863
864
660
599
2,764
7,413
6,496|\n\n\nSource: COMTRADE database.\nNote: Excludes intra-EU trade. Arabian Peninsula include: Bahrain, Kuwait, Oman, Qatar, Saudi Arabia. United Arab Emirates and\nYemen.\n\n\n\nThe impact of avian flu on international trade flows is more evident by examining\n\n\nthe evolution of the exports of major exporters. Table 3 shows the rapid shifting in\n\n\noverall exports of unprepared poultry from HPAI affected countries to\n\nMention: \"COMTRADE database\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"Regional trade values excluding intra-community flows are drawn from it.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:003764:7:0", "occurrence_id": "d426284cb9f4b2d01ca08cc7", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: regulatory measures. We control for these factors using private credit to GDP ratio (from\n\n\nDjankov et al 2007) and number of procedures required to start a business, number of\n\n\nprocedures required to enforce a contract and an index of the difficulty of hiring labor\n\n\n(from World Bank’s Doing Business project, 2004).\n\n\nRegression results with these controls are reported in columns 1 and 2 of Table 2.\n\n\nEnglish common law continues to show a positive and significant effect on the dependent\n\n\nvariable. Private credit to GDP and all the Doing Business indicators show a significant\n\n\nrelationship with the dependent variable in the expected direction.\n\n\nNext, we control for the index of creditor rights from Djankov et al 2007 and\n\n\nmeasures of institutional quality as perceived by the firms (from WBES) which include:\n\n\nthe level of confidence in the legal system for upholding contract and property rights in a\n\n\ndispute ( _Property rights_ ), efficiency of courts in enforcing their decisions in business\n\n\ndisputes ( _Enforcement_ ), quality of power supply ( _Power_ ), and the severity of business\n\n\nregulations, high interest rates and labor regulations as obstacles for the firm’s operations.\n\n\nEach of the obstacles is ranked by firms on a 1-4 scale with a higher value indicating a\n\n\nmore severe obstacle. _Property rights_, _Enforcement_ and _Power_ take values 1-6 with a\n\n\nhigher value implying better quality. The motivation for the firm-level measures is to\n\n\ncapture possible heterogeneity in their enforcement and how they affect firms.\n\n\nRegression results in columns 3 and 4 of Table 2 show that controlling for the\n\n\nvariables discussed above does not change our main results much. Most of the firm-level\n\n\nmeasures show significant effects on government helpfulness in the expected direction:\n\n\nbetter quality of institutions and less severe obstacle implies a more helpful government.\n\n\n5\n\nMention: \"World Bank’s Doing Business project\""}, {"role": "assistant", "content": "{\"role\": \"supporting\", \"usage_action\": \"source\", \"summary\": \"Its procedure counts and hiring difficulty index enter as controls.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:003778:2:0", "occurrence_id": "3b7d69d1bea55542b589ee98", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: ### **Making Poor Haitians Count**\n\n**Poverty in Rural and Urban Haiti**\n**Based on the First Household Survey for Haiti**\n\n##### By **Dorte Verner** World Bank 1\n\n\n1 I am very grateful to Nadim Khouri for inviting me to join the Haiti Rural Development Team, Michael\nJustesen for excellent and invaluable research assistance, and the Haiti Rural Development Team for\nanswering many questions. Moreover I am especially grateful to Willy Egset for data information and other\nsupport with the household data set. Without the help of all these people this paper would not have existed.\nThe findings, interpretations, and conclusions expressed in this paper are entirely those of the author.\n\nMention: \"Household Survey for Haiti\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"The first such survey measures rural and urban poverty in the country.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:003781:20:0", "occurrence_id": "33802826d2c690b76a3c8629", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: Moreover, the intensive use of land has caused a large soil erosion problem for\nfarmers. Sixty-six percent of extreme poor farmers and 46 percent of the 20 percent\nrichest farmers reported that soil erosion is a severe problem on their land in 2001. Poor\nfarmers have little access to productivity enhancing plant nutrients and therefore see soil\nerosion as a more severe problem than rich farmers. Moreover, lack of titles or land\nownership is another problem faced by poor farmers. Of the 20 percent poorest farmers\n81 percent have a title or own their land compared to 92 percent of the 20 percent richest\nfarmers (Table 7). Data reveal little difference in travel time to plots between rich and\npoor farmers (Table 8).\n\n\nTable 6: Reporting on Soil Erosion in Haiti, 2001 (percent)\n\nQuintile\n1 (poorest) 2 3 4 5 (richest)\nYes, important 65.5 65.82 63.92 62.9 45.63\nYes, minor 7.82 7.47 8.73 6.47 7.32\nNo problem 26.67 26.71 27.34 31.63 47.05\n\n_Source:_ Own calculations based on HLCS 2001.\n\n\nTable 7: Legal Title or Deed to Home and Land, 2001 (percent)\nQuintile\n1 (poorest) 2 3 4 5 (richest)\n\nMention: \"HLCS 2001\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"analyze\", \"summary\": \"Perceptions of problems and land title ownership are tabulated by quintile.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:003782:12:0", "occurrence_id": "0b186d4e46cfaec8fb5fcc9c", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: their θ s are higher than those of firms with higher variable trade costs, even though both types of\n\n\nfirms serve the same market. Thus, once we allow private characteristics of individual firms to\n\n\ngenerate variation in variable and fixed trade costs, lowering trade costs also increases the export\n\n\nintensity of individual firms.\n\n\n**3. Data**\n\n\nThe empirical part of this study uses the firm-level World Bank Investment Climate Survey (ICS)\n\n\ndata from the manufacturing sectors of seven Sub-Saharan African countries: Benin, Ethiopia, Kenya,\n\n\nMadagascar, Senegal, Tanzania, and Uganda. 9 [^9: The World Bank ICS has been renamed as the World Bank Enterprise Survey. Visit [www.enterprisesurvey.org](http://www.enterprisesurvey.org/) for more\ninformation.] These seven countries were chosen on the basis of\n\n\navailability of detailed information on firm-level export destinations in ICS. The ICS data are\n\n\ncollected to prepare Investment Climate Assessments (ICAs), diagnostic reports intended to serve as\n\n\nthe basis for policy reforms that will help improve these countries’ business environments with the\n\n\nsupport of the World Bank. 10 [^10: ICA reports for Sub-Saharan African countries are available from the World Bank Africa Regional Program on\n[Enterprise Development (RPED) website http://www.worldbank.org/rped).](http://www.worldbank.org/rped)] The data are collected through firm surveys that include a common set\n\n\nof questions for all countries surveyed, supplemented by country-specific questions to help each\n\n\ncountry assess its investment climate. The sample is selected by a stratified random sampling method\n\n\ncontrolling for size, sub-sector, and geographic distribution, based on the company registration\n\n\nrecords or manufacturing census information available from the government. More than 80 countries\n\n\nhave been surveyed since the program started in 2002. The sample size varies, ranging from about\n\n\n100 firms for some\n\nMention: \"World Bank Investment Climate Survey\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"Manufacturing firms in seven countries supply the export intensity measures.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:003788:14:0", "occurrence_id": "5c50289aa6c7a06498fd964b", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: - 13 \n\nThe extent to which the service quality of infrastructure has improved varies from country to\n\n\ncountry. Figures 13 to 15 show the difference between the 2002 and 2005 BEEPS results for\n\n\neach country. Obviously, more advanced countries tend to have experienced relatively\n\n\n\n20\n\n\n10\n\n\n0\n\n\n-10\n\n\n-20\n\n\n-30\n\n\n-40\n\n\n-50\n\n\n\n\n\n\n\n20\n\n\n10\n\n\n0\n\n\n-10\n\n\n-20\n\n\n-30\n\n\n-40\n\n\n-50\n\n\n\n\n|because they already achieved t
her improvement. Armenia, Geo
the best performing countries in
ange in electricity. Interestingly
consistent with each other with
development strategy and priori
3. Quality Improvements in Electricity in E
(16|Col2|Col3|Col4|Col5|Col6|Col7|Col8|h
r
,
i
t
0)|\n|---|---|---|---|---|---|---|---|---|\n||||||||||\n||||||||||\n||||||||||\n||||||||||\n||||||||||\n||||||||||\n||||||||||\n|Azerbaijan
Uzbekistan
Kyrgyz
Moldova
Georgia
Ukraine
Kazakhstan
Romania
Macedonia
Armenia
Slovakia
Russia
Estonia
Czech
Poland
Croatia
Slovenia
Hungary
Lithuania<\n\nMention: \"BEEPS\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"analyze\", \"summary\": \"Differences between these two rounds show how perceptions changed by country.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:003810:8:0", "occurrence_id": "42bf98f5305943cecaad1e86", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: through each district in the surveyed countries. Data on elevation at the centroid of each\n\n\ndistrict were obtained from the United States Geological Survey (USGS 2004). The\n\n\nUSGS data are derived from a global digital elevation model with a horizontal grid\n\n\nspacing of 30 arc seconds (approximately one kilometer).\n\n###### **4. Empirical Results**\n\n\nAfrica contains a wide range of agricultural ecological zones across the continent. Due to\n\n\nits diverse ecological zones, farmers are expected to rely on different farm types, crops,\n\n\nlivestock, inputs, and outputs depending upon the characteristics of the farm location.\n\n\nTable 1 describes how farmers chose different farm types in the sample. Livestock was\n\n\nchosen in about 65 percent of the total farms. Irrigated farms account for about 25 percent\n\n\nof farmers. Across the sample, the proportion of each of the five distinct farm types is:\n\n\ncrop-only rainfed farms (28 percent), crop-only irrigated farms (10 percent), mixed\n\n\nrainfed farms (42 percent), mixed irrigated farms (14 percent), and livestock-only farms\n\n\n(6 percent).\n\n\nWe examine whether the choice of these farm types is sensitive to climate. We begin by\n\n\nexamining a cross section of farmers who face different climate conditions. We\n\n\nhypothesize that farm type choice is influenced by climate. Table 2 shows the results\n\n\nfrom a multinomial logit regression of the five farm types against a set of independent\n\n\nvariables which include climate variables in quadratic form, soil variables, household\n\n\ncharacteristics, water flow, pasture, and output prices. The choice of livestock-only is\n\n\nomitted as the base case. Several control variables are significant. When the farm has\n\n\nelectricity, farmers favor livestock-only farms over other choices. This may be because\n\n\nelectricity is needed for milk production and for storage of livestock products or it may\n\n\nbe because electricity is correlated with other missing variables that favor livestock.\n\n\nWhen Lithosol soils are dominant in a district, farmers tend\n\nMention: \"global digital elevation model\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"Terrain restrictions derive from this one-kilometre grid.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:003827:7:1", "occurrence_id": "14197495a23653bc401814aa", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: ) to an absolute poverty measure.\n\n\nWe begin by presenting our new cross-country data set on poverty lines in developing countries.\n\n###### **3. National poverty lines across developing countries**\n\n\nThe set of national poverty lines collected by RDV covered 33 countries (both developed\n\n\nand developing) and drew on specialized, country-specific, mostly academic, studies of poverty\n\nspanning 1980-90. Clearly, this data set is now rather old. 13\n\n\nSince RDV, there has been considerable expansion in research and analysis on poverty in\n\n\ndeveloping countries through the World Bank’s country-level _Poverty Assessments_ (PA’s),\n\n\nwhich have now been done for many developing countries (though there were very few PA’s\n\n\navailable in 1990). These are core reports within the Bank’s program of analytic work at country\n\n\nlevel; each report describes the extent of poverty and its causes in that country. The Bank’s PA\n\n\n12 Ravallion and Lokshin (2007) provide survey-based evidence for one of the poorest countries,\nMalawi, indicating that relative deprivation is not a welfare concern to the bulk of the population, though\nthey do find that it matters to better off groups in urban areas. For a theoretical analysis in a model\ncombining risk sharing with positional goods see Ravallion (2008a).\n13 The only prior update was done by Ravallion (1998), who tested the effect of including a number\nof new observations for Africa (which was clearly under-represented in the Ravallion et al., 1991, data\nset). The main result of the earlier study by RDV on the relationship between poverty lines and mean\nconsumption was found to be quite robust to including these extra observations.\n\n\n6\n\nMention: \"Ravallion et al., 1991, data\nset\""}, {"role": "assistant", "content": "{\"role\": \"supporting\", \"usage_action\": \"validate\", \"summary\": \"New African observations address its under-representation.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:003836:1:0", "occurrence_id": "e9fe21ced81e04bf1c4f0b6d", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: Policy Research Working Paper 4629\n\n### **Abstract**\n\n\nThe Addis Ababa Integrated Housing Development\nProgram aims to tackle the housing shortage and\nunemployment that prevail in Addis Ababa by deploying\nand supporting small and medium scale enterprises to\nconstruct low-cost housing using technologies novel for\nEthiopia. The motivation for such support is predicated\non the view that small firms create more jobs per unit\nof investment by virtue of being more labor intensive\nand that the jobs so created are concentrated among the\nlow-skilled and hence the poor. To assess whether the\nprogram has succeeded in biasing technology adoption\nin favor of labor and thereby contributed to poverty\nreduction, the impact of the program on technology\n\n\n\nusage, labor intensity, and earnings is investigated using\na unique matched workers-firms dataset, the Addis\nAbaba Construction Enterprise Survey. The data are\nrepresentative of all registered construction firms in\nAddis and were collected specifically for the purpose of\nanalyzing the impact of the program. The authors find\nthat program firms do not adopt different technologies\nand are not more labor intensive than non-program\nfirms. There is an earnings premium for program\nparticipants, who tend to be relatively well-educated,\nwhich is heterogeneous and highest for those at the\nbottom of the earnings distribution.\n\n\n\nThis paper—a product of the Poverty Reduction and Economic Management Department, Africa Region—is part of a\nlarger effort in the department to support evidence based policy making. Policy Research Working Papers are also posted\non the Web at http://econ.worldbank.org. The author may be contacted at cruggeriladerchi@worldbank.org.\n\n\n_The Policy Research Working Paper Series disseminates the findings of work in progress to encourage the exchange of ideas about development_\n_issues. An objective of the series is to get the findings out quickly, even if the presentations are less than fully polished. The papers carry the_\n_names of the authors and should be cited accordingly. The findings, interpretations, and conclusions expressed\n\nMention: \"Addis\nAbaba Construction Enterprise Survey\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"A matched worker-firm dataset representative of registered construction firms.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:003846:9:1", "occurrence_id": "94678cfdbe378461c2e64b4d", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: 3.1 3.7 2.4 2.7\nNicaragua -0.1 2.1 2.8 5.4 1.4 2.6\nPeru 1.1 2.2 2.2 3.0 1.7 2.1\nAverage 1.4 2.1 2.4 4.1 1.9 2.8\n\n- Excludes the 1980s to compute the average growth rate.\n** Data from 1980-1993 are missing.\nFCT. Projections of growth under a continuous trend of reform scenario.\nFDC. Projections of growth under a dramatic change reform scenario.\nFCT1. Projections of growth resulting from merging FCT1 and average growth over 1961-2006.\nFDC. Projections of growth resulting from merging FDC and average growth over 1961-2006.\nSources: Own calculation using data from WDI and Loayza et al. (2005).\n\nA second reason of why past growth rates in per capita consumption are a poor proxy for\nexpected growth rates in the Latin American context is because of the potential role\nplayed by the reforms implement by the region in 1990s. Comparing the situation in the\nearly 2000s and early 1990s, Latin American countries have better macroeconomic\nframeworks, are more open to trade, have more developed financial sectors, and in\nvirtually all countries public spending in education has increased. All these elements are\nusually considered in the growth literature as growth enhancers. Moreover, per capita\nconsumption growth in\n\nMention: \"data from WDI\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"analyze\", \"summary\": \"Growth projections merge these series with an alternative estimator.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:003877:9:0", "occurrence_id": "d4d9de8a6b172ce64abfc95f", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: ##### Ro = ( 1 +δ n )( 1 +δ s ) Re = ( 1 +δ n )( 1 +δ s )( 1 +δ p ), (3)\n\nthat is, a combination of natural barriers, selection, and policy-induced wage\ndiscrimination. We will return to the subject of selection in detail below. It turns out that\nthe effect of this assumption on the estimates is closely related to the assumption of the\n##### independence of φ fh ( x ′ i ) and φ ff ( x ′ i ) .\n\n\n2.3 _Data_\n\nWe estimate equation (2) using unusually rich and standardized collection of individual\nlevel data sets on wage-earners compiled by the World Bank 7 [^7: The sources for all data are given in the appendix. The basic database is also described in Montenegro and Hirn\n(2008).] plus the US Census Public\nUse Microdata Sample (PUMS) five percent file.\n\nA series of steps brings us from the raw collection of data sets to the estimation sample.\nFirst, we remove all self-employed people and unpaid family workers from the data,\nleaving only wage-earners. This has the advantage of increasing the comparability and\naccuracy of the earnings measures, but has the disadvantage of eliminating a large portion\n(though not all) of the informal sector from the sample—especially many agriculturists in\nthe poorest countries. Second, we remove all people aged 14 or less and all people aged\n66 or greater, as well as all people reporting zero wage earnings. Third, we remove data\nfrom twelve transition countries because many of these countries were undergoing\nextraordinary instability of prices, wages, and currencies at the time the survey was\nadministered. Rather than picking and choosing among them we just eliminated the\ntransition countries as a block. 8 Fourth, we randomly delete US-born US-residents from\nthe PUMS to reduce the size of that group from about 6.\n\nMention: \"US Census Public\nUse Microdata Sample\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"Its five percent file is added to the basic database for estimation.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:003898:29:0", "occurrence_id": "dc158f4b85de4ef2c9db61f9", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: |Col1|2000|Col3|2004|Col5|\n|---|---|---|---|---|\n||**RMB/capita**|**percent**|** RMB/capita**|** Percent**|\n|**County-to-Township Transfers**|**58**||**84**||\n|**Disposable Fiscal Resources**|**119**|**119**|**119**|**119**|\n|Total Extra-budgetary Income|55||53||\n|Total Self-raised Income (incl._tiliu_)|37|37|10|10|\n|_Tongchou_ (township levy)|20|20|0|0|\n|_Tiliu_(village accumulation)|14|14|0|0|\n|Other|4|4|10|10|\n|**Total Fiscal Revenues**|**211**||**182**||\n\n\nSource: fieldwork survey.\n\n\n**3.3. The Village**\n\n\nVillages figure prominently in the NSC as the basic unit of the xiaokang society in the\n\n\ncountryside. In 2005, China had a total of 640,139 administrative villages (China Statistical\n\n\nYearbook 2007). 30 [^30: The number of village committees has declined by about 11.5 percent in the five-year period from 1999 to] A typical “administrative village” 31 [^31: The traditional term “administrative village” is used here, since the formal term “village committee” has a] ( _cun_ ) generally has a population of\n\n\n1,000 to several thousand people, but can be as small as only a few hundred or as large as\n\n\n10,000 people. The average village in our sample survey of 100 had a population of\n\nMention: \"China Statistical\n\n\nYearbook 2007\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"It counts the administrative villages at that date.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:003900:35:2", "occurrence_id": "1ef815c40579193f7a193dad", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: Denmark**~~|
~~**Denmark**~~|\n||||||||\n\n\n15000 17000 19000 21000 23000 25000 27000\n\n\nGDP per capita\n\n\nFigure A2: Plotting vehicle stock fuel use (per 100 km) against income per capita (IEA\n\n\nand OECD data).\n\n\n\n15\n\n\n13\n\n\n11\n\n\n9\n\n\n7\n\n\n5\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n10000 15000 20000 25000 30000\n\n\n**Disposable income (USDppp per capita)**\n\n\nFigure A3: Fuel use of new car sales plotted against income per capita.\n\n\n\n34\n\nMention: \"IEA\n\n\nand OECD data\""}, {"role": "assistant", "content": "{\"role\": \"supporting\", \"usage_action\": \"source\", \"summary\": \"Vehicle stock, fuel use and income are plotted from these sources.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:003920:26:0", "occurrence_id": "d335d0b0b01ae6028ea89c16", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: **Table 1.** DHS Surveys and Mother/Birth Numbers\n\n|Country|Year(s) of Study|Total Mothers Observed|Total Births Observed|\n|---|---|---|---|\n|Armenia
Bangladesh
Benin
Bolivia
Brazil
Burkina Faso
Burundi
Cambodia
Cameroon
Central African Republic
Chad
Colombia
Comoros
Congo (Brazzaville)
Dominican Republic
Ecuador
Egypt
Ethiopia
Gabon
Ghana
Guatemala
Guinea
Haiti
Honduras
India
Indonesia
Ivory Coast
Kazakhstan
Kenya
Kyrgyzstan
Lesotho
Liberia
Madagascar
Malawi
Mali
Mexico
Moldova
Morocco
Mozambique
Namibia
Nepal
Nicaragua
Nigeria
Niger
Pakistan
Paraguay
Peru
Philippines
Rwanda
Senegal
South Africa
Sri Lanka
Sudan
Tanzania
Thailand
Togo
Trindad & Tobago
Tunisia
Turkey
Uganda
Uzbekistan
Vietnam
Yemen
\n\nMention: \"DHS Surveys\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"Mothers and births observed by country and study year are listed from these surveys.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:003924:31:2", "occurrence_id": "e88e16d11131cac64474b7e8", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: 64.5\nBonds 32.3 15.3 6.6\nUnits of investment funds 2.0 2.6 0.6\nOthers 0.4 2.4 0.4\n**Claims on the Foreign Sector** 4.8 9.0 4.1\nUnits of mutual funds and shares 3.8 6.6 3.1\nDebt 0.9 2.1 0.5\nTime deposits 0.1 0.2 0.5\n**Others** 5.9 7.0 4.3\n**Total assets (LCU million)** 2,693.6 41,044.8 2,311.8\nSource: SBS.\n\n\n50 See, for example, Shah (1997), Vittas (1997, 1998), Queisser (1999), Srinivas and Yermo (1999),\nSrinivas, Whitehouse and Yermo (2000), and Olivares (2005).\n51 In Peru, the legal framework refers to a minimum rate guarantee that is\n\nMention: \"SBS\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"Bank asset and concentration figures are drawn from this banking survey.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:003941:22:0", "occurrence_id": "bb27c96a6cc8d13aea1171c5", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: ### **Figure 1: Labor force participation by race and** **immigration status. Males.**\n\n\n\n0\n\n\n-0.01\n\n\n-0.02\n\n\n-0.03\n\n\n-0.04\n\n\n-0.05\n\n\n-0.06\n\n\n-0.07\n\n\n-0.08\n\n\n-0.09\n\n\n0.06\n\n\n0.04\n\n\n0.02\n\n\n0\n\n\n-0.02\n\n\n-0.04\n\n\n-0.06\n\n\n-0.08\n\n\n-0.1\n\n\n-0.12\n\n\n\nWhites\n\nout\n\n\n\nBlacks in Blacks\n\nout\n\n\n\nAsians in Asians\n\nout\n\n\n\nHispanics\n\nin\n\n\n\nHispanics\n\nout\n\n\n### **Figure 2: Labor force participation by race and** **immigration status. Females.**\n\n\n\nWhites\n\nout\n\n\n\nBlacks in Blacks\n\nout\n\n\n\nAsians in Asians\n\nout\n\n\n\nHispanics\n\nin\n\n\n\nHispanics\n\nout\n\n\n\nData from the 2000 Census IPUMS data (5% sample), population aged 25-65. The figures display the\nmarginal coefficients and their 95% confidence intervals on interaction terms for racial groups and foreign\nborn status (“in” for natives, “out” for foreign born) in probit regressions with labor force participation as\nthe dependent variable. “White natives” is the omitted dummy. The regression results are further detailed in\ntable 2, columns 1 (males) and 5 (females).\n\n\n21\n\nMention: \"IPUMS data\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"analyze\", \"summary\": \"Marginal coefficients on migration flows are estimated on this five percent sample.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:003966:17:0", "occurrence_id": "5169c9f5f9460532feed478f", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: and political data from the World Bank’s _Database of Political Institutions_ (DPI). The fiscal variables\n\n\nmeasure total spending (excluding interest payments), total tax revenues, and fiscal deficits of central\n\ngovernments. 20\n\n\nWe measure coalition governments in three different ways using data from the DPI, given the\n\n\nfinding that coefficient estimates are sensitive to the way coalitions are defined (Perotti and\n\n\nKontoupoulos, 2002). The simplest measure is that of an indicator variable which equals 1 if the party of\n\n\nthe executive leader in a country does not control a majority in all lawmaking houses, which we label\n\n“DIVIDED”. 21 The second measure is the probability (which lies between 0 and 1) that two legislators\n\n\nchosen at random from among parties that form the government will belong to two different parties,\n\n\nwhich is the variable labeled “GOVFRAC” in the DPI. The third measure is the number of political\n\n\nparties forming the government, similar to the measure used by Perotti and Kontoupoulos (2002), which\n\n\nwe calculate by simply counting the number of parties listed as government parties in the DPI—\n\n\n“NUMBER OF PARTIES”.\n\nWe compile available data for more than 70 countries over the period 1970 – 2006. 22 We specify\n\n\nthe time interval over which the variables are measured, _t_, as a decade. We calculate decadal averages for\n\n\neach country in our sample, for the 1970s (1970-1979), 1980s (1980-1989), 1990s (1990-1999), and\n\n\n2000s (2000-2006), using non-missing values within a decade. We analyze the correlation of political\n\n\nparty composition of government with fiscal policy over this country-decade sample. However, there is a\n\n\nlot of missing fiscal data, with observations on\n\nMention: \"data from the DPI\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"Coalition governments are defined in three ways from this dataset.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:004030:18:0", "occurrence_id": "d0a214123fef6ae939e6c2e2", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: #### **Figure 1**\n\nThe figure is a partial scatter plot showing the relationship between _Reform_ and _Democracy_ on average over the sample period, and controlling for GDP per\ncapita and regional fixed effects. The Y axis plots the residuals from the linear regression of _Reform_ on the control variables while the X axis contains residuals\nfrom a similar regression using _Democracy_ . Both these regressions are run over average values of all the variables taken over the sample period (2003-2008).\nAbbreviations of country names follow World Development Indicators, World Bank.\n\n\n17\n\nMention: \"World Development Indicators\""}, {"role": "assistant", "content": "{\"role\": \"supporting\", \"usage_action\": \"source\", \"summary\": \"Country name abbreviations follow this compilation.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:004036:8:0", "occurrence_id": "6ab3b9f58cf24eb1a07a130a", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: **_2.2. AMADEUS Database_**\n\n\nFor the estimation of firm productivity, the analysis uses data from the May 2006 edition\n\n\nof the AMADEUS database, a comprehensive, pan-European commercial database compiled by\n\n\nBureau van Dijk. For each firm, AMADEUS provides accounting data in standardized financial\n\n\nformat for 24 balance sheet items, 25 profit and loss account items, 26 financial ratios, and\n\n\nadditional information including trade description and activity codes. The database includes up\n\n\nto ten years of information per firm through 2004, although coverage varies by country.\n\n\nAMADEUS is created by collecting standardized data received from 50 vendors across Europe,\n\nwhere the local source for these data is generally the office of the Registrar of Companies. 5 [^5: Further details about the AMADEUS database can be found on the product page of Bureau van Dijk’s website:\nhttp://www.bvdep.com/en/AMADEUS.html.]\n\n\nThe accounts for each firm are transformed into a universal format to allow for\n\n\ncomparison across countries. All accounting data is converted into U.S. dollars using period\n\n\naverage exchange rates, based on monthly series from the International Monetary Fund, nearest\n\n\nto the end date of each respective financial account. Nominal values are deflated using country\n\nlevel GDP deflators to express values in 2001 US dollars. In addition, all firms are categorized\n\n\nby industry according to NACE Rev.1., and for the analysis, industry dummy variables are coded\n\n\nbased on the 4-digit activity code following NACE Rev.1 that AMADEUS assigns to each firm.\n\n\n**_2.3. Sample Selection_**\n\n\nThe econometric analysis of firm-level TFP growth and changes in the business\n\n\nenvironment uses a first-differenced equation in firm characteristics with two-year changes and\n\n\nrequires a panel of manufacturing firms from the AMADEUS database with complete\n\n\ninformation on production function variables for the years 2001 through 2004, the period that\n\n\ncorrespond to the 2002 and 2005 rounds of the BEEPS. Specifically, output, labor, material\n\n\ninputs, and capital\n\nMention: \"AMADEUS database\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"Firm-level productivity is estimated from this pan-European edition.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:004039:9:1", "occurrence_id": "d1860422121ad7eb4da750d2", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: avallion et al.,\n\n1991). AB then argued that the value of _k_ could also be based on national poverty lines above\n\nthose found in the poorest countries, by studying how those lines vary with man consumption in\n\nthe original data base of poverty lines used by Ravallion et al. (1991) to set the “$1-a-day” line.\n\nBy visual inspection of the Ravallion et al. (1991) data set on national poverty lines at 1985 PPP,\n\nAtkinson and Bourguignon set _k_ =0.37. Subsequently, Chen and Ravallion (2001) found that\n\n_k_ =1/3 gave a better fit with the Ravallion et al. (1991) data set at 1993 PPP.\n\nHowever, the AB line fails the WRA in that it has an elasticity of unity for all countries\n\nwith _M i_ - _Z_ - / _k_ . This is surely implausible. The idea that distribution-neutral growth has no\n\nimpact on the extent of poverty in new middle-income countries such as China would surely be\n\nvery hard to accept (not least, we would conjecture, in China). The violation of the WEA stems\n\nfrom the seemingly implausible assumption that the cost of social inclusion is directly\n\n\n8\n\nMention: \"Ravallion et al. (1991) data set\""}, {"role": "assistant", "content": "{\"role\": \"supporting\", \"usage_action\": \"source\", \"summary\": \"Its national poverty lines at that purchasing power basis informed the daily line.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:004064:4:0", "occurrence_id": "9cf005836abcafc054ef7dfa", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: performances. In a context of increasing pressure of globalization, _ICA_ surveys can be seen as\nan instrument for identifying key obstacles to firms’ productivity and competitiveness. They\ncan be used as a support to policy reforms for an increased economic growth.\n\n\nDrawing on the World Bank firm-surveys, this paper analyzes the relationship between\ninvestment climate and firm-level productivity for a large number of developing countries (22\namong which 5 MENA economies) and eight manufacturing industries. We first propose\ndifferent measures of firms’ productive performances, such as Labor Productivity ( _LP_ ), Total\nFactor Productivity ( _TFP_ ), and Technical Efficiency ( _TE_ ) using a production frontier\napproach. These indicators are compared to each others as well as across countries, in order to\nposition MENA manufacturing amongst a wide range of firms from other regions. We reveal\nthat enterprises in MENA perform in average poorly, compared to other countries of the\nsample. The exception is _Morocco_, whose various measures of firms’ productive performance\nalways rank close to the one of the most productive firms in the sample. An originality of our\napproach has also been to generate a few composite indicators of investment climate using\nPrincipal Component Analysis ( _PCA_ ), which summarizes well the key dimensions of the\ninvestment climate. This has allowed as well tackling the problem of multicolinearity when\nexplaining firm productive performances with a wide range of correlated _IC_ variables. We\ndefine four dimensions of the investment climate: the Quality of Infrastructure ( _Infra_ ), the\nBusiness-Government Relations ( _Gov_ ), the Human Capacity ( _H_ ), and the Financing\nConstraints ( _Fin_ ). We use, as well, city or region-sector averages to reduce the endogeneity\nproblem underlying the investment climate ( _IC_ ) variables. The analysis finally shows that\ninvestment climate matters for firms’ productive performances. This has been done by\nestimating an efficiency\n\nMention: \"the World Bank firm-surveys\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"Investment climate and productivity are linked using these firm data.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:004049:3:0", "occurrence_id": "a61f59336cf0d02b9bedb1ce", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: **I.** **INTRODUCTION**\n\n\nCompetition is the single most important factor to contain pubic procurement costs and\n\n\nperhaps discourage collusive bidding behavior and corrupt practices. However, many\n\n\ninfrastructure projects seem to continue faced with considerable difficulties to intensify\n\n\ncompetition in the procurement process (Estache and Iimi, 2008a). This may be partly\n\n\nunavoidable because infrastructure projects are normally extremely valuable and highly\n\ncustomized. 1 However, there are still several simple measures that could potentially extend\n\n\nmarket competition but sometimes have not been exploited carefully.\n\n\nThe current paper revisits the problem of endogenous participation in auctions and the\n\n\ndivision into procurement lots in the water supply and sewage industry. In this sector, it is\n\n\nalways of particular concern that the observed degree of competition has been limited. In the\n\n\npublic-private partnership (PPP) context, less than five multinational water enterprises may\n\nhave been dominant over the world (Foster, 2005). 2 [^2: According to the Private Participation in Infrastructure (PPI) database, the top 10 percent largest firms—\ndefined by the number of transactions that each company obtained—were awarded about half of total\ninfrastructure PPP contracts. In the water industry, especially, a multinational French water service operator,\nVeolia Environnement (former Vivendi Environnement, or Compagnie Générale des Eaux), was alone awarded] Even in the traditional public\n\n\nprocurement context, the degree of competition is in general limited (Estache and Iimi,\n\n\n2008a).\n\n\nThere is a tradeoff between competition in auctions and size of contracts. Not many firms can\n\n\napply for highly valuable contracts, because of financial and experiential constraints. Highly\n\n\nspecific works (which are normally valuable as well) would also limit competition. On the\n\n\nother hand, infrastructure projects are normally expected to exhibit economies of scale and\n\n\npossibly economies of scope in preparation and implementation. Therefore, larger lot works\n\n\ncould be procured at relatively low costs per unit, though fewer applicants may participate.\n\n\n1 Estache and Iimi (\n\nMention: \"Private Participation in Infrastructure (PPI) database\""}, {"role": "assistant", "content": "{\"role\": \"supporting\", \"usage_action\": \"source\", \"summary\": \"It shows the ten percent largest firms winning most transactions.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:004076:9:0", "occurrence_id": "c4e50ebf3a32010134abd6bc", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: quintile of wealth to which the household belongs, and the leave-out take-up rate in the primary\n\n\nsampling unit where the household lives.\n\n\nThe index of wealth is estimated using factor analysis because we do not have household\n\n\nincome or expenditure data in the DHS. The variables used for the factor analysis are allowed to\n\n\ndiffer between countries depending on the data available in each survey so as to maximize the\n\n\ninformation used. In practice, the variables used include housing variables, variables on the\n\n\naccess to various types of provision for basic infrastructure services (there is a slight issue of\n\n\nendogeneity here, since we are modeling take-up of utility services, but it is minor given the\n\n\nmany other variables included in the index), and variables on a range of assets owned.\n\n\nThe regressions on take-up of service are estimated only on the samples of households\n\n\nwho live in neighborhoods where there is access, and the estimation follows a simple probit\n\n\nprocedure. The regressions are not presented here, as there are many of them, but they are rather\n\n\nstraightforward. The leave-out access rate is meant to capture the general conditions of the\n\n\nneighborhood (including factors such as the average distance from the water pipes or electic\n\n\nlines), while the wealth index quintiles are used to deal with the affordability issue.\n\n\nOnce the regressions have been estimated, we simulate what the access rate would be if\n\n\nall households living in areas where there is access would be lifted in terms of wealth from\n\n\nwherever they are in the distribution of wealth to the top wealth quintile. That is, we simulate\n\n\nwhat the take-up rate would be for all households living in primary sampling units where there is\n\n\naccess based on what the behavior of the households would be if they were in the top quintile,\n\n\nwhich corresponds implicitly to an assumption of no affordability problem, since the households\n\n\nin the top quintile should be able to afford the cost of piped water and electricity services. When\n\n\naggregating the results for\n\nMention: \"DHS\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"Lacking income data here, wealth is built by factor analysis instead.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:004077:16:1", "occurrence_id": "da4d96f20045b857e550ac18", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: which consists of disbursements of\nloans made on concessional terms (net of repayments of principal) and grants by official agencies of the\nmembers of the Development Assistance Committee (DAC), by multilateral institutions, and by non-DAC\ncountries to promote economic development and welfare in countries and territories in the DAC list of\nODA recipients. Data source for the variable is World Development Indicators, World Bank.\n\n\n15\n\nMention: \"World Development Indicators\""}, {"role": "assistant", "content": "{\"role\": \"supporting\", \"usage_action\": \"source\", \"summary\": \"Growth and welfare for aid-recipient countries come from this compilation.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:004103:9:0", "occurrence_id": "42c4d8b2632b6280d7e8f094", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: 8\n\n\nThe module provides detailed information on migration histories of all current and former\n\n\nhousehold members, as well as information on the household migration networks abroad. Lastly,\n\n\nthe survey supplies community-level data, which include information on prices, access to\n\n\nservices and infrastructure in the locality.\n\n\nOur sample of interest is 9,565 individuals in the working age category of [15-64] in\n\n2005, excluding return migrants that have been in Albania less than 12 months. 5 The ALSMS05\n\n\ncollected data on _initial_ and _2005_ employment outcomes according to the three digit codes from\n\n\nthe 1988 International Standard Classification of Occupations (ISCO). The three digit codes can\n\nbe classified under 10 major occupational groups 6, which can be collapsed into 5 distinct\n\n\ncategories. These categories are namely (i) agricultural (major group 6), (ii) low-skilled blue\n\n\ncollar (major groups 8 and 9), (iii) high-skilled blue collar (major group 7), (iv) low-skilled white\n\n\ncollar (major groups 4 and 5), and (v) high-skilled white collar (major groups 1, 2 and 3)\n\noccupations. 7 Although agricultural occupations are traditionally included as part of the high\n\n\nskilled blue collar category under the ISCO definition, we found it appropriate to create a unique\n\n\ncategory for them, as agriculture still remains the principal source of employment in Albania.\n\n\n_3.1. Occupational Ranking_\n\n\nAs our objective is to test the hypothesis of upward occupational mobility that is induced\n\n\nby past migration experience, it is essential to first rank occupational groups in a reasonable and\n\n\nsystematic manner. Following Sicherman and Galor (1990), we rank occupational groups\n\n\naccording to the average level of human capital necessary to be employed in each of them. The\n\n\n5 In our sample, there were\n\nMention: \"ALSMS05\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"Initial and current employment outcomes are coded at three digits here.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:004108:16:0", "occurrence_id": "547147e6291b3fb0828895b3", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: PAYING THE PRICE FOR UNRELIABLE POWER SUPPLIES:\nGENERATION OF ELECTRICITY BY PRIVATE FIRMS IN AFRICA\n\n\nshare of own generation. The share of manufacturing in GNI was positively associated with the degree of\nown generation. 17 [^17: The estimated coefficients reflect correlations, not causalities. Further analysis of the estimated relationship is\nimpeded by the simultaneity of the choice of own-generation and the explanatory variables.]\n\n\nThe World Bank’s enterprise surveys offer clues to why firms elect to generate their own power.\nBecause deficiencies in the provision of public power impede business operations, firms install their own\ngenerating equipment to protect themselves against power outages. 18 [^18: Statistics from the Enterprise Surveys on power outages and the adoption of own-generation appear in appendix 1,\ntables 2a to 2f.]\n\n\nPower outages have a significant effect on business operations. Firms that experienced few power\noutages (fewer than 30 days per annum) tended to declare that electricity was not an obstacle or was only\na minor obstacle for the operation and growth of their businesses. On the other hand, firms that suffered\nfrequent outages (more than 60 days per annum) tended to believe that electricity was a major or very\nsevere obstacle for the operation and growth of their businesses.\n\n\nFrequent power outages result in significant losses for enterprises in terms of forgone sales and\ndamaged equipment. Firms experiencing frequent power outages (more than 60 days per year) lose 10–12\npercent of their sales (figure 17). This is about twice as high as the figure for firms that have few outages\n(less than 15 days per year). Equipment damage traceable to power outages is about twice as high for\nfirms that suffer frequent outages as for firms that suffer few outages (1 percent of sales compared to 0.5\npercent of sales) (figure 18).\n\n\n\n**Figure 17 Sales lost owing to power outages**\n\n\nPercent\n\n\n**14.00**\n\n\n**12.00*\n\nMention: \"enterprise surveys\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"analyze\", \"summary\": \"They explain why firms choose to generate their own power.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:004132:8:0", "occurrence_id": "a682321747b84a813e667d2e", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: **Figure 1: Entrepreneurship around the world**\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\nSource: 2008 World Bank Group Entrepreneurship Survey.\n\n\nIn addition to these indicators, the 2008 _WBGES_ provides enough historical data to\n\n\nestablish the trends in the number of new and total businesses in 100 countries during the\n\n\neight year-period 2000 to 2008. In this regard, it is interesting to note that developing\n\n\ncountries have a higher trend in both the number of total and new businesses, with some\n\n\nof the countries doubling their numbers during the period, whereas industrialized\n\n\ncountries show little variation during the same period (Figure 2). Interestingly, the\n\n\nmajority of the surveyed countries with a negative business growth were those that\n\n\nsuffered a war, civil unrest or remarkable political instability during the eight-year\n\nperiod. 2\n\n\n2 Such as Lebanon, Bosnia and Herzegovina and Haiti.\n\n\n7\n\nMention: \"2008 World Bank Group Entrepreneurship Survey\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"Global new-business counts and their historical trend come from this edition.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:004158:13:0", "occurrence_id": "be540511398aae77c6077710", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: _3.2. Economic Impact Estimation Methodology: Social Accounting Matrix_\n\nVarious methods can be used to estimate higher-order effect of disasters based on\n\ndamages and/or losses data, including input-output (IO) table, social accounting matrix\n\n(SAM), and computable general equilibrium (CGE) model. 15 [^15: A summary and discussion of methodologies on impact estimation can be seen in a companion paper,\n“Critical Review of Methodologies on Disaster Impact Estimation.”] Since the cases for\n\nglobal aggregate include a large group of countries in different years, the data\n\navailability of method becomes one of the key issues for the selection of methodology.\n\nSAM is employed in this study because of its data availability of construction and the\n\n\n\nfamiliarity of use in international development community 16 [^16: Please see Appendix 1 for detailed description of SAM, and a companion paper, ‘Impact Estimation\nMethodology: Case Studies.’]\n\n\n\n.\n\n\n\nSocial accounting matrix (SAM) has been utilized to examine the higher-order\n\neffects across different socio-economic agents, activities, and factors. Notable studies\n\nusing a SAM or one of its variants include Cole (1995, 1998, and 2004) among others.\n\nLike IO models, the SAM approach has rigid coefficients and tends to provide upper\n\nbounds of impact estimates. On the other hand, the SAM framework with certain\n\ndisaggregation, as well as extended IO model and CGE model, can derive the\n\ndistributional impacts of a disaster in order to evaluate equity considerations for public\n\npolicies against disasters. In this paper, SAMs were constructed in an aggregated\n\n\n\nDue to the\n\n\n\nversion for each country and each decade, based on the World Bank data.\n\n\n\n17\n\n\n\nlarge number of SAMs that needed to be constructed, and in order to maintain the\n\nconsistency of the structure and features among them, the SAMs were constructed in the\n\nmost aggregated way—one sector (one value) for each principal account (see the Figure\n\n3-1). This simple structure is also\n\nMention: \"World Bank data\""}, {"role": "assistant", "content": "{\"role\": \"supporting\", \"usage_action\": \"source\", \"summary\": \"The aggregate matrices for each country and decade are built from these data.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:004175:8:0", "occurrence_id": "20877fd835c0a0dc14eb7b2e", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: Figure 2 shows the relative difference in the number of savings accounts in\n\n\nmunicipalities with Azteca, vs. municipalities without Azteca. Data on savings accounts\n\n\ncomes from the Mexican bank supervisory body, the Comisión Nacional Bancaria y de\n\n\nValores (CNBV). There is a clear rapid growth in savings accounts in municipalities with\n\nAzteca after December 2002 8 [^8: Unfortunately, we cannot perform the same regression analysis for loans since we do not have date on loans\npre- and post-Azteca opening at the municipality level.] . These effects are also significant in a regression framework\n\nthat controls for municipality-specific time trends 9 [^9: Available from the authors upon request.] .\n\n\nThus, the opening of Banco Azteca had a non-trivial impact on availability of\n\n\nfinancial services in municipalities where the branches were present. More details on the\n\n\nbank opening are available in the Appendix.\n\n\n**II. Identification Strategy**\n\n\nIn order to identify the effect of Banco Azteca opening on economic activity, we\n\n\nexploit the cross-municipality and cross-time variation in Azteca branches. As discussed\n\n\nabove, Banco Azteca opened in October 2002, only in the municipalities that had pre-exiting\n\n\nGrupo Elektra stores. This allows us to estimate the following difference-in-difference\n\n\nregression, which compares municipalities with and without Banco Azteca before and after\n\n\nAzteca opening:\n\n_yict_ _c_ _t_ - _Aztecact_ - _Z_ _ict_ _ict_,\n\n\nwhere _i_ denotes individuals, _c_ denotes municipalities, and _t_ denotes quarters. ß is a set of\n\n\nmunicipality fixed effects, γ is a set of quarter fixed effects and Z is a matrix of individual\n\n\ncontrol variables. Our main variable of interest is the _Azteca_ dummy, which is the interaction\n\n\nbetween a post third quarter of 2002 dummy and a dummy that equals one for municipalities\n\n\nthat had at least one Azteca branch in the fourth quarter of 2002\n\nMention: \"Mexican bank supervisory body\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"Savings account counts by municipality come from this supervisor.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:004187:17:1", "occurrence_id": "40f21e4e0a0a61ec120286d5", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: 5 62 104 206\n\n\n\nGreenfield project 971 589 376 226 2162\nConcession 103 10 594 241 948\nDivestiture 478 203 65 26 772\nTotal 1587 807 1097 597 4088\n\n\n\nSource: PPI database.\n\n8 A private sponsor builds a new facility largely at its own risk, transfers ownership to the government, leases\nthe facility from the government and operates it at its own risk up to the expiry of the lease.\n\n\n\n9 A private sponsor builds a new facility at its own risk, operates the facility at its own risk, and then transfers\nthe facility to the government at the end of the contract period. The private sponsor may or may not have the\nownership of the assets during the contract period.\n\n10 A private sponsor builds a new facility at its own risk, then owns and operates the facility at its own risk.\n\n11 A private sponsor builds a new facility in a liberalized market in which the government provides no revenue\nguarantees. The private developer assumes construction, operating, and market risk for the project.\n\n12 Electricity utilities or governments rent mobile power plants from private sponsors for periods ranging from 1\nyear to 15 years. A private sponsor places a new facility at its own risk, owns and operates the facility at its own\nrisk during the contract period.\n\nMention: \"PPI database\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"Transaction counts by sponsor type and region are tabulated from it.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:004196:32:1", "occurrence_id": "2ef10367ebbf3075955f430c", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: GIEK from NOK 50b1n to 11Obin. In addition, its financial institution \"Eksportfinans\"
will lend banks NOK 50bln over the next two years to be used for medium to long-term export credits.|\n|||\n|**Pakistan**|11/18/2008:
**Plan**: The Central Bank will provide 100% refinancing to banks against export finance provided by them to
exporters under Part I of the Export Finance Scheme (EFS). Earlier, the State Bank was providing export
finance to the banks up to 70 percent. Export finance already provided by banks under Part I of EFS from
own sources at the ratio of 30 percent and outstanding as on Oct. 31, 2008 will also be refinanced by the
State Bank for the remaining period of individual loans|\n||
06/12/2009 **Announcement:** The IFC, Habib Bank Limited (HBL) and Citibank (Citi) announced that their
joint execution of a structured trade finance deal to support the import of equipment for a new power
generation plant**in Pakistan**. IFC and Citi worked together to structure a deal with coverage of up to Ђ73
million (PKR 8 Billion) to a Pakistani power company. HBL, Pakistan’s largest privately owned bank,
established the original letter of credit, which was confirmed by Citi utilizing IFC’s Global Trade Finance
program for 50% risk coverage.
|\n|||\n|**Poland**|Source: Berne Union, Compiled in May 2009
**Action:**Poland’s Export Credit Insurance Corporation (**KUKE Poland**), a joint-\n\nMention: \"Berne Union\""}, {"role": "assistant", "content": "{\"role\": \"supporting\", \"usage_action\": \"source\", \"summary\": \"Export credit and guarantee arrangements are compiled from this association.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:004153:14:1", "occurrence_id": "e39c232296759709329a79b1", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: It is also currently the main contributor to GDP (Table\nA-5, Panel 3). The analysis of the latest household survey (EICV 2) showed that poverty has\nfallen the most during the previous years in households that depend on agriculture. The low use\nof modern inputs (such as fertilizers and improved seeds), the lack of extension services as well\nas poor water management, however, hamper the development of the agriculture sector. The poor\ncondition of the necessary infrastructure in addition limits the extent of growth and\ntransformation in the sector.\n\nThis scenario assumes that additional donor financing will be spent on agriculture, investing and\nraising growth in its capital stock, again accompanied by increased growth in real recurrent\nexpenditure (operations and maintenance). A possible example for such an investment would be\nthe World Bank project on land husbandry, water harvesting and irrigation that is currently under\npreparation. The larger agricultural capital stock has a positive impact on productivity growth in\nthe agricultural sector. MDG and education indicators may improve due to indirect effects via\nhigher household incomes. However, in the model there is no direct effect on MDGs and\neducational indicators from spending on agriculture (as opposed to spending on infrastructure).\n\nThe simulation outcome in terms of macroeconomic effects is very similar to that of AID-INF,\nexcept for an even stronger bias of government spending on investment at the expense of\ngovernment consumption (Table 5). Annual GDP growth averages 6.5 percent, with the\nagriculture sector consequently growing faster than in the previous scenarios, whereas growth\nrates of the industry and services sector are between those of AID-HD and AID-INF (Table A-5).\n\nThe development of the MDG and education indicators is less positive than in AID-INF and AIDHD, but nevertheless more positive than in the baseline. The poverty headcount declines to 32\npercent in 2020 similar to AID-INF (Table 6), highlighting the indirect positive impact of\n\n\n11\n\nMention: \"EICV 2\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"analyze\", \"summary\": \"Poverty fell most among agriculture-dependent households in this round.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:004201:6:0", "occurrence_id": "43621d514e34fb2b65579d9b", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: (34) and Bulgaria (14). The track I projects are located in Germany, Hungary, Romania, New Zealand,\nFrance and Ukraine. 10 [^10: The data come for the UNFCCC website and the UNEP Risoe CDM pipeline.]\n\n\nThe number of JI projects is dwarfed by those in the CDM pipeline, which in June 2009 contained 4,417\nprojects. The disparity in the numbers between JI and CDM projects is partially attributable to the fact\nthat the CDM enjoyed a “prompt start” authorized by the Conference of the Parties (COP) to the\nUNFCCC which allowed the registration of projects starting in 2001. This means that the CDM’s Certified\nEmissions Reductions (CERs) obtained during the period between 2000 and 2008 can be used to assist in\nachieving compliance during the first commitment period. JI on the other hand can only generate\nEmission Reduction Units (ERUs) during the first commitment period, namely between 2008 and 2012.\nWhile the CDM is managed or administered on the international level by a governance structure that is\nlargely independent from host country performance, administrative capacities and GHG accounting\nframeworks, JI depends on emission limitation targets, allocation of AAUs, registries and the functioning\nof almost all other elements of the infrastructure of the Kyoto Protocol. Carbon credits generated by JI\nare nothing but AAUs in disguise, authorized for private trade, but generated by the host country which\nconverts AAUs into ERUs based on the evidence of verified emission reductions. As a result JI is\nenvironmentally more robust than the CDM, but institutionally more vulnerable. It is also highly\ndependent on the functioning of domestic institutions: in order to participate in JI, countries have to\nfulfill a number of accounting requirements and compliance has to continue throughout the\nimplementation of a JI project. Countries have to elaborate project approval procedures and be able to\naccount for ERUs as part of their AAUs. Participation in JI also depends on political will. Until June 2009\nthe Russian Federation has not approved a single JI\n\nMention: \"the UNEP Risoe CDM pipeline\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"It counts the clean development mechanism projects in the pipeline.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:004203:6:1", "occurrence_id": "9d6b44c6e9bb69a5e9dccd31", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: world.\n\nAccording to the International Labour Organization (2002), 246 million children and\nteenagers between 5 and 17 years old are engaged in child labor around the world.\nFurthermore, 75.0% of those children work for their own family activities. Asia, Africa and\nLatin America are the continents with the most the child labor in the world. Asia has the\nhighest number of children in terms of volume but Africa is the leader relative to the total size\nof the work force.\n\nIn Brazil, data from PNAD (IBGE, 2007) has shown that from a 44.7 million population\nbetween 5 and 17 years old, 10.8% (4.8 million) are directly involved in child labor. The\nworst region of Brazil regarding this subject is the Northeast, with 13.4% of the 5-17 year old\npopulation working; Southeast holds the lowest average (7.9%). These statistics represent a\npositive evolution over the last 4 years (see Figure 3 below).\n\n\n5\n\nMention: \"data from PNAD\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"Its figures give the working share of children aged five to seventeen.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:004224:26:1", "occurrence_id": "fb98f916b2835fd91dccbc18", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: >1.0
5.0
2.0
1.0
10.0
1.0
1.0|\n|**Total**|179
70|1 - 15|3.0|\n\n\n(*) See Footnote in Table A-1.\n\n\n**Table A - 6 : Bureaucratic Red Tape on Imports:**\n**Number of Man-days per Year Spent in Resolving Problems**\n\n**with Customs and Tax Administration**\n\n\n\n\n\n\n\n\n\n\n\n|Country|2008 Survey|Col3|Col4|2001 Survey|\n|---|---|---|---|---|\n|**Country**|**% of total**
**respondents**|**Range(*)**
**(days)**|**Average(*)**
**(days)**|**Average (days)**|\n|**Egypt**
**Jordan**
**Lebanon**
**Morocco**
**Saudi Arabia**
**Syria**
**Tunisia**
**UAE**
**Yemen**|84.6
46.8
88.5
81.8
89.5
96.2
57.7
75
92.6|25 - 60
25 - 42
20 - 50
20 - 56
14 - 24
20 - 42
18 -\n\nMention: \"2008 Survey\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"Days lost resolving customs and tax problems are reported in this round.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:004224:26:1", "occurrence_id": "56ddf9e9caad569e49ec6477", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: >1.0
5.0
2.0
1.0
10.0
1.0
1.0|\n|**Total**|179
70|1 - 15|3.0|\n\n\n(*) See Footnote in Table A-1.\n\n\n**Table A - 6 : Bureaucratic Red Tape on Imports:**\n**Number of Man-days per Year Spent in Resolving Problems**\n\n**with Customs and Tax Administration**\n\n\n\n\n\n\n\n\n\n\n\n|Country|2008 Survey|Col3|Col4|2001 Survey|\n|---|---|---|---|---|\n|**Country**|**% of total**
**respondents**|**Range(*)**
**(days)**|**Average(*)**
**(days)**|**Average (days)**|\n|**Egypt**
**Jordan**
**Lebanon**
**Morocco**
**Saudi Arabia**
**Syria**
**Tunisia**
**UAE**
**Yemen**|84.6
46.8
88.5
81.8
89.5
96.2
57.7
75
92.6|25 - 60
25 - 42
20 - 50
20 - 56
14 - 24
20 - 42
18 -\n\nMention: \"2001 Survey\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"The earlier round of the same constraint question.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:004269:27:1", "occurrence_id": "2fbbf6bc88f6eab1674e92a9", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: some elements of _x_ are binary. Robust z-stat in parentheses.\nOmitted dummies are no education, female, single and catholic. The type of housing materials\n(soft roof and house, mixed or hard roof and house) serves as a proxy for wealth. The indicator\nfor mobility takes the value 1 if the individual goes more than once a year outside the country.\nThe sample size decreases when age dummies are included since at very old age nobody is HIV\npositive.\n_Source_ : MRC General Population Cohort 1989/90 (round 1).\n\n\n\n26\n\nMention: \"MRC General Population Cohort\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"The first round of this cohort gives age-specific infection prevalence.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:004275:36:1", "occurrence_id": "123081e294846030819f149b", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: (-0.75) (0.57) (2.64) (-1.02)\n6-7 years later 0.152* 0.162* -0.003 0.102* 0.166** -0.717\n(2.32) (2.47) (-0.08) (2.30) (2.63) (-0.32)\n8-10 years later 0.306*** 0.331*** 0.116* 0.069 0.215** 3.157\n(3.74) (4.01) (2.31) (1.23) (2.72) (1.26)\n11 + years later 0.301** 0.319** 0.04 0.146* 0.279** -5.773\n(3.02) (3.18) (0.65) (2.14) (2.90) (-1.76)\n\nSample size 6253 6253 6253 5822 6252 5150\n\nSource: Linked ICS-ENIA panel data\nNote: (1) The regression model included indicator variables for location in the capital region,\nfirm size, and 12 year dummy variables.\n(2) ***, ** and * denote statistical significance at the 1, 5 and 10 percent level\n\n\n\n35\n\nMention: \"ICS-ENIA panel data\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"analyze\", \"summary\": \"Firms are linked across rounds for the capital-region and size regressions.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:004286:43:0", "occurrence_id": "284e961e6bcd30daf3101ac2", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: **ANNEX**\n\n**Annex Figure I: Map of Treated and Control Districts**\n\n\nNotes: The lighter regions represent lower poverty levels, and darker regions represent higher poverty\nlevels.\nSource: Author’s calculations using national poverty estimates\n\n\n42\n\nMention: \"national poverty estimates\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"analyze\", \"summary\": \"Subnational rates are shaded on the map from these estimates.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:004294:11:2", "occurrence_id": "0e4ff6b0c929ad1ee4cc6f86", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: KOR
BRA
IND
CHN
V.A. per Worker (Korea=100)- product 371
0
50
100
150
200
1980
1985
1990
1995
2000
2005
KOR
BRA
IND
CHN
V.A. per Worker (Current '000 US$/worker) - product 371
Product: Iron and steel
Source: UNIDO Industrial Statistics Database, Rev. 2 and 3|\n||0
100
200
300
400
1980
1985
1990
1995
2000
2005
KOR
BRA
IND
CHN
V.A. per Worker (Korea=100)- product 322
0
10
20
30
40
1980
1985
1990
1995
2000
2005
KOR
BRA
IND
CHN
V.A. per Worker (Current '000 US$/worker) - product 322
Product: Wearing apparel, except footwear
Source: UNIDO Industrial Statistics Database, Rev. 2 and 3||0
20
40
60
80
100
1980
1985
1990
1995
2000
2005
KOR
BRA<\n\nMention: \"UNIDO Industrial Statistics Database\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"Value added per worker by product across these decades comes from it.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:004310:12:0", "occurrence_id": "568c6157c97618822edea76e", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: shock pushes households’ utility below this level, they enter poverty. Conversely, if they are\nlifted above this level of utility, they are no longer in poverty.\n\n\nThe framework of Hertel et al (2004, 2009b), and that which this paper adopts, uses the\nAIDADS system to represent consumer preferences. This choice is based on AIDADS’ strength in\ncapturing food expenditure patterns across the income spectrum (Verma et al, 2009), and for its\nability to perform well out of sample when compared to other demand systems (see Cranfield et\nal, 2002, 2003) 8 [^8: Please see Appendix C for details of AIDADS formulation and parameterization.] . Reflecting its suitability for poverty analysis is that AIDADS devotes two‐thirds\nof its parameters to characterizing consumer behavior at very low levels of income. Estimation\nof this demand system is undertaken using the 80 country, per capita consumption data set\noffered by Version 6.1 of the GTAP database, also following Hertel et al (2004). For each\ncommodity, we have estimates of subsistence quantities of consumption, from which we may\ninfer (for average prices), budget shares at the subsistence level of income.\n\n\nThe poverty line in Tanzania is set to match the observed national poverty headcount\nratio reported by the World Bank (2006) and this in turn dictates the poverty level of utility in\nthe initial equilibrium. So, in the wake of a change in climate, commodity prices and wages will\nadjust, household incomes will change, as will the consumption profile of households at the\npoverty line, thereby resulting in new utility level. If household utility rises above the poverty\nlevel of utility, then it is lifted out of poverty. Conversely, if the household utility level falls below\nthe poverty utility threshold, then it has become impoverished.\n\n\nEquations (2) to (4) describe how the model can then be used to predict the change in\nthe national poverty rate – the percentage of the population\n\nMention: \"GTAP database\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"Per-capita consumption for eighty countries in this version drives the demand system.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:004337:26:0", "occurrence_id": "a0618719f4c4264c6933d841", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: **Annex 1: The Sensitivity of Central Government Revenues and Expenditures to the**\n**Business Cycle** **15** [^15: We are thankful to Catalina Delgado and Conrado Garcia for excellent research assistance provided for\nthis section.]\n\nBased on monthly data for the period from January 1997 to January 2008 16 [^16: The data sample selection has been determined by data constraints because consistent information on\nrelevant budget aggregates is not available for a long enough time series. The source is the National\nTreasury and IPEA data (www.ipea.gov.br)] the sensitivity\nof federal revenues and expenditures to the business cycle is assessed through the\nestimation of closed-form elasticities using the following specification:\n\n\n\n\n\n\n### Re vBKi a 0 12 a 1 j log Re\n\nRe _vi_ _t_ _j_ 1 Re _v_\n\n\n### vBKi a 0 12 a 1 j log Re vBKi\n\n_vi_ _t_ _j_ 1 Re _vi_\n\n\n\n_vi_\n\n\n\n_i_\n\n\n\n Re _vi_ \n\n _BK_ \n Re _vi_ _t_\n\n\n\n_j_ 0 2 _j_ _IPI_ _iBK_ _t_ _j_\n\n\n\n Re\n\nlog \n\n\n\n_BK_\n_i_ _t_\n\n\n\n_j_ log _i_\n\n \n\n\n\n Re _vi_ \n\nMention: \"IPEA data\""}, {"role": "assistant", "content": "{\"role\": \"supporting\", \"usage_action\": \"source\", \"summary\": \"Budget aggregates from this institute support the cyclicality assessment.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:004391:25:1", "occurrence_id": "000f52298dbad0607bc62d3a", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: >Wall of dwelling (% with
cement / CI sheet)
Roof of dwelling (% with
cement / CI sheet)
Safe latrine use (%)
Electricity connection (%)
TV ownership (%)
Phone ownership (%)|4280
5281
35.2
40.3
37.7
55.2
76.4
89.9
52.0
69.3
31.2
44.2
15.8
26.5
1.5
12.2|3222
4653
33.6
43.3
21.4
39.5
68.1
84.2
35.2
55.6
14.6
25.4
3.6
10.1
0.1
1.5|2623
3919
31.6
42.5
17.4
33.9
64.5
81.6
29.4
50.0
10.0
20.2
1.8
6.7
0.0
0.9|\n|_Source_: HIES 2000, 2005
|_Source_: HIES 2000, 2005
|_Source_: HIES 2000, 2005
|_\n\nMention: \"HIES\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"Two rounds support the household characteristics tabulated.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:004405:20:2", "occurrence_id": "74d6eb388537a1a63ae7f5f6", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: u>**\n\n\n\n**Real** **annual**\n**sales growth,**\n**%**\n\n\n\n**Type of firm**\n\n\n\n**Return** **on**\n**Equity, %**\n\n\n\n**EBIT to interest**\n**expenses, x**\n\n\n\n**Current to total**\n**liabilities, %**\n\n\n\n**Total debt to**\n**common equity,**\n**%**\n\n\n\n**Total liabilities**\n**to Equity, %**\n\n\n\n**Paid-in to total**\n**capital, %**\n\n\n\n**Type of firm**\n\n\n\n**Retained**\n**earnings to**\n**equity, %**\n\n\n\nPrivate 33.5 4.4 27.7 84.1 74.5 36.1\nFormer SOE 37.0 6.0 27.1 90.3 104.2 30.1\n\nSource: Coface; World Bank staff analysis\n\nSince most privatizations occurred in the consumer staples industry, the comparison could be\ninfluenced by industry particulars. Moreover, former SOEs\n\nMention: \"Coface\""}, {"role": "assistant", "content": "{\"role\": \"supporting\", \"usage_action\": \"source\", \"summary\": \"Firm performance by ownership type is drawn from this insurer's data.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:004439:4:1", "occurrence_id": "54def8521a8df277db7c1196", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: were $46 (Figure Two).\n\n\n5 Kenny, 2009.\n6 This for a two-lane road between 6-8 meters wide with a bituminous surface, for countries where we have\nfour or more estimates based on individual project data Data from the ROCKs database\nhttp://www.worldbank.org/transport/roads/rd_tools/rocks_main.htm\n7 The results suggest that an increase in the CPI (reflecting reduced corruption) from Pakistan’s score to\nGhana’s would be associated with a drop in Pakistan’s road construction prices of around 20 percent. The\nequation is Cost = 51.9 – 5.9*(CPI), with the constant and CPI entering at one percent, R=0.23, N=28.\nIncluding GDP per capita reduces the coefficient on CPI to 4.5 and the significance to ten percent (GDP per\ncapita does not enter significantly). For a range of World Bank financed infrastructure goods and works\ncontracts, Kenny and Musatova (2009) find that aid dependency and weak institutions lead to fewer bidders\nand a higher risk of price escalations.\n\n3\n\nMention: \"the ROCKs database\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"Project-level road cost estimates are pooled in this database.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:004442:3:1", "occurrence_id": "50fe413de96e770038b8f850", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: dynamic model of the welfare\neffects of real exchange rate undervaluation and to assess the desirability of reserve\naccumulation and real exchange rate undervaluation as a second-best instrument to\ninternalize such learning-by-doing externalities. 5\n\nOur setup is based on the notion that reserve accumulation and undervaluation\nsolve a targeting problem: In a first-best world with a full set of instruments, government would like to subsidize investment to induce agents to internalize their learningby-doing externalities. However, if policymakers face difficulties in targeting productive investment opportunities, an alternative mechanism is needed. By lending to for\n\n1China, for example, was sitting atop of USD 2.4 trillion of official foreign reserves by early 2010\n\n- a whopping 49% of its GDP, and experienced growth of more than 9% on average over the past\ndecade (data from the People’s Bank of China). Its performance on both measures was followed\nclosely by other Asian tiger economies such as Taiwan and South Korea.\n\n2See e.g. Aizenman and Marion (2003), Durdu et al. (2009), Mendoza et al. (2009) or Carroll\nand Jeanne (2009) for proponents of this view.\n\n3This is discussed e.g. in Jeanne and Ranci`ere (2009). However, see Carroll and Jeanne (2009)\nfor a more positive assessment.\n\n4Mercantilism was a widespread view among economic thinkers in Europe during the period of\n1500 - 1750 and is still a frequent argument in the public discourse among non-economists.\n5For the purposes of this paper, we equate the term “reserve accumulation” to “real exchange\nrate undervaluation,” since reserve accumulation in our model of closed capital accounts requires\nthat more tradable goods are exported, which makes tradable goods in the domestic economy scarcer\nand depreciates the real exchange rate.\n\n\n2\n\nMention: \"the People’s Bank of China\""}, {"role": "assistant", "content": "{\"role\": \"supporting\", \"usage_action\": \"source\", \"summary\": \"Credit relative to output and growth over the decade come from this central bank.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:004455:20:0", "occurrence_id": "dd52f00e024901bc6f4671f0", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: OECD) (OECD 2003: Table 2.1a; OECD 2007: Table 6.1a). That poses interesting questions\nabout what caused the “shift” of the student score distribution. While extension of compulsory\ncomprehensive education can explain higher performance for low-achievers who were mostly in\nvocational tracks, it is more complicated to explain higher performance of top-achievers. The\nquestion is whether the introduction of lower secondary schools could have an impact on\nstudents in former general secondary schools and what was in the reform that increased scores so\nsignificantly.\n\n\nFigure 4: Change in reading literacy distribution between PISA 2000 and 2006\n\n\nFigure 5: Change in reading literacy distribution between PISA 2003 and 2006\n\n\n\n\n\n\n\nEstimates of score change for students in different tracks\n\nResults for differences-in-differences propensity score matching estimates of the effect of\nabolishing tracking system for 15-year-olds are presented in Tables 3, 4 and 5. Table 3 contains\nestimates of factual and counterfactual mean scores for all students in PISA 2000, 2003 and\n2006. In addition, results for students in vocational and non-vocational tracks are presented.\nFactual scores were weighted by survey weights provided in the official PISA datasets.\nCounterfactual scores were constructed using matching methods with survey weights taken into\naccount in the manner described above.\n\n\n18\n\nMention: \"PISA datasets\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"analyze\", \"summary\": \"Official survey weights from these datasets weight the factual and counterfactual scores.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:004482:22:0", "occurrence_id": "5900549b46bef65e4aa394b0", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: yields biased estimates. 23 In the estimation, we instrument for the lagged growth rate, ∆ _xciht−_ 1,\n\n\nwith the second lag of the log level of exports, _ln_ ( _xciht−_ 2) if _xciht−_ 2 _>_ 1 and a value of zero if the\n\nsecond lag of the level of exports is less than 1. 24\n\n\nBy utilizing 6-digit HS product fixed effects in (5) we control for changes in production costs or\n\n\ntechnology that imply that a particular good _h_ will have a growth rate for exports that is higher\n\n\nor lower than average. Note that commodities with very high average growth rates also tend to be\n\n\nthose most likely to be targeted for antidumping measures. As in equations (2) and (3) we use year\n\n\ndummies to control for all aggregate variation in China and country _i_ over time.\n\n\nFor estimating equation (5), we calculate annual export growth of China’s exports to 38 different\n\n\ncountries _i_ listed in table 1, excluding the U.S., EU and India.\n\n\n**5.2** **Instrumental** **variables** **estimates** **of** **trade** **deflection** **and** **trade** **depres-**\n\n\n**sion**\n\n\nTable 10 presents our estimates of trade deflection and trade depression from a panel of Chinese\n\n\nexports to 38 countries. Our finding of a chilling effect of U.S. antidumping duties from the difference\n\nin-difference equation (2) discussed in section 4.1 appears to be robust across models. Although we\n\n\nfind no evidence of chilling in specification (14) which regresses the growth of the volume of Chinese\n\n\ntrade on\n\nMention: \"panel of Chinese\n\n\nexports\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"analyze\", \"summary\": \"Deflection and depression across thirty-eight destinations are estimated on this panel.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:004491:17:0", "occurrence_id": "e08060f201ba99a985d7a137", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: potential new trade barriers to other complementary databases (e.g., on trade flows) to\n\n\ndetermine how economically important any given policy action would be.\n\n\nSuch an approach was also adopted by a new initiative launched in June 2009\n\n\ncalled the _Global Trade Alert_ . 16 The Global Trade Alert (GTA) was designed to go\n\n\nbeyond the trade remedy data provided in the Global Antidumping Database to catalogue\n\n\nand detail dozens of other types of trade and trade-related measures – e.g., changes in\n\n\ntariffs, import licensing, government procurement, imposition of subsidies, and changes\n\n\nin technical and sanitary or phytosanitary standards among others. Many interpreted the\n\n\nGTA’s contributions throughout the global economic crisis as being intended to ‘name\n\n\nand shame’ government policymakers by raising the public profile of trade policy\n\n\nactions. Perhaps government officials would think twice about how they structured new\n\n\npolicy initiatives if they were concerned that the GTA would flag their policies with a red\n\n\ntriangle that indicated ‘the measure has been implemented and almost certainly\n\n\ndiscriminates against foreign commercial interests.’ Nevertheless, the publicity around\n\n\nthe GTA has resulted in critics of its own. Some focused on the utility of the information\n\n\nbeing provided for understanding the scale of the spread of protectionism taking hold\n\n\nduring the global crisis, given the lack of comparable pre-crisis data available to use as a\n\n\nbenchmark. Others argued that the GTA was overstating the incidence of protectionism\n\n\nwhich could provide fodder and cover for other policymakers interested in increasing\n\n\n16 For a discussion see Evenett (2009). According to the Global Trade Alert website, it is coordinated by the\n\n\nCentre for Economic Policy Research (London), and its funders include The World Bank, UK’s Trade\n\n\nPolicy Unit (combining the Department for International Development and the Department for Business,\n\n\nInnovation and Skills), the German Marshall Fund of the United States, Canada’s Centre for International\n\n\nGovernance Innovation, and Canada’s International Development Research\n\nMention: \"Global Antidumping Database\""}, {"role": "assistant", "content": "{\"role\": \"supporting\", \"usage_action\": \"validate\", \"summary\": \"The newer monitoring system was designed to go beyond this remedy dataset.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:004506:16:0", "occurrence_id": "e50f8faf8a45a2d70cd57327", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: 14\n\n\n**Figure 7. Latin America and East Asia: Gross Domestic Savings (1970-2008)**\n\n(Percent of GDP)\n\n\n\n\n\n_Note: East Asia is the un-weighted average of Hong Kong, Singapore, South Korea, Taiwan,_\n_Indonesia, Thailand and Malaysia, while LAC covers the whole Latin American and Caribbean_\n_region._\n_Source: World Development Indicators (2010)._\n\n\n**Figure 8. Latin American Capital Markets Reform Implementation (1990-2002)**\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n_Note: Percentage of Latin American countries having implemented reforms._\n_Source: De la Torre and Schmukler (2007)._\n\nMention: \"World Development Indicators (2010)\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"Regional comparisons and reform series are drawn from this edition.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:004512:2:0", "occurrence_id": "66f28dd2db22f26434926495", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: ### **Deals versus Rules:** **Policy Implementation Uncertainty and Why Firms Hate It**\n\n##### Mary Hallward-Driemeier Gita Khun-Jush Lant Pritchett *\n\n**Key words:** Uncertainty, Corruption, Enterprise Surveys, Doing Business, Policy\nImplementation\n**JEL codes:** H32, O17, D81, J23, K2\n\n\n- We would like to thank the NBER for support via the Africa Project. We would like to thank Bill\nBattaile, Asli Demirguc-Kunt, Ahmed Galal, Ricardo Hausmann, Marialisa Motta, Stephen O’Connell, Rita\nRamalho, James Robinson, Dani Rodrik, Luis Serven, Andrei Shleifer, Sylvia Solf and David Weil for\nconversations that were, perhaps unbeknownst to them, helpful and to Dan Willey for motivation on this\ntopic **.** Mamadou Bady Balde provided the materials on Rwanda. The views expressed here do not\nnecessarily represent the views of the World Bank or its Executive Directors. Corresponding author: Mary\nHallward-Driemeier, mhallward@worldbank.org.\n\nMention: \"Enterprise Surveys\""}, {"role": "assistant", "content": "{\"role\": \"supporting\", \"usage_action\": \"inform\", \"summary\": \"Listed among the paper's key words as a data source.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:004524:39:30", "occurrence_id": "0f239ac7e0241777a2e9a26a", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: br>0.91
_0.85_
_0.85_
_0.85_|\n|JPN|JPN|JPN|JPN|JPN|JPN|JPN|JPN|JPN|JPN|\n|CAN|CAN|CAN|CAN|CAN|CAN|CAN|CAN|CAN|CAN|\n|USA|USA|USA|USA|USA|USA|USA|USA|USA|USA|\n|EU15|EU15|EU15|EU15|EU15|EU15|EU15|EU15|EU15|EU15|\n|OEUR|OEUR|OEUR|OEUR|OEUR|OEUR|OEUR|OEUR|OEUR|OEUR|\n|RUS|RUS|RUS|RUS|RUS|RUS|RUS|RUS|RUS|RUS|\n\n\n\nSource: Authors' calculations via COMTRADE and GTAP6 Databases\nNotes: PR is the average of each exporter’s unit value divided by the world average export unit value from 2000 to 2004. BIPR equals PR divided by the\n2001 weighted average import price for each importing region. Italicized values ( _0.85_ ) have been truncated for purposes of incorporation into the model,\nfor which this represents trigger point for the P-SSM.\n\n\n38\n\nMention: \"COMTRADE\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"analyze\", \"summary\": \"Unit values underlying the price ratios are computed from this database.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:004524:39:30", "occurrence_id": "a8e32b2dc44b56855b9d16ca", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: br>0.91
_0.85_
_0.85_
_0.85_|\n|JPN|JPN|JPN|JPN|JPN|JPN|JPN|JPN|JPN|JPN|\n|CAN|CAN|CAN|CAN|CAN|CAN|CAN|CAN|CAN|CAN|\n|USA|USA|USA|USA|USA|USA|USA|USA|USA|USA|\n|EU15|EU15|EU15|EU15|EU15|EU15|EU15|EU15|EU15|EU15|\n|OEUR|OEUR|OEUR|OEUR|OEUR|OEUR|OEUR|OEUR|OEUR|OEUR|\n|RUS|RUS|RUS|RUS|RUS|RUS|RUS|RUS|RUS|RUS|\n\n\n\nSource: Authors' calculations via COMTRADE and GTAP6 Databases\nNotes: PR is the average of each exporter’s unit value divided by the world average export unit value from 2000 to 2004. BIPR equals PR divided by the\n2001 weighted average import price for each importing region. Italicized values ( _0.85_ ) have been truncated for purposes of incorporation into the model,\nfor which this represents trigger point for the P-SSM.\n\n\n38\n\nMention: \"GTAP6 Databases\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"analyze\", \"summary\": \"The companion database used in the same computations.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:004536:3:2", "occurrence_id": "6e0309a17c2b935b893b4fba", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: in all sectors.\n5 Information is missing for various reasons. A sizeable fraction of the respondents refuse, forget or fail to answer\nsome questions. In other cases, even well-trained interviewers may neglect to ask some questions. Sometimes\nrespondents just say they do not have the information available to them or they do not know the answer to the\nquestion. Some questions are simply not applicable to some respondents (see Allison, 2001). All of these cases may\nbe applicable to IC data.\n6 The number of observations available in the complete case decreases as we consider more and more investment\nclimate variables. If we consider all the variables included in the survey, the complete case due to missing cells is\n\n2\n\nMention: \"IC data\""}, {"role": "assistant", "content": "{\"role\": \"supporting\", \"usage_action\": \"validate\", \"summary\": \"Several methodological caveats may apply to this survey's respondents.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:004549:15:1", "occurrence_id": "f68d5b63a9618a07a0e56042", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: sup> For the Chinese EAF producer, the tax is equal to only 4 percent (compared to 3\npercent for U.S. firms using EAF). For Brazilian producers, this rate is much lower than their\nChinese counterparts at 11 percent (BOF) and 2 percent (EAF). Notably, this means that\nBrazilian EAF steel producers would be taxed by a lower amount than their U.S. counterparts\naccording to OECD carbon footprint estimates.\n\n\nImposing differentiated border taxes on imported steel does satisfy some of the policy\nconstraints. It likely would result in support from domestic firms (Constraint 1a). It also would\nprovide incentives for foreign firms to use the less intensive carbon technique (Constraints 2). It\nwould plausibly be consistent with WTO national treatment rules (individual domestic and\nforeign firms are both charged according to their carbon emissions). And since the U.S. therefore\nmight win a WTO dispute, foreign firms may be loath to ask their government for a formal\ncomplaint at the dispute body.\n\n\nThe real problem rests with Constraint 4. Unfortunately, one cannot look at the steel coil\nand know if it is produced by one technique or the other. 21 [^21: There are certain steel types that currently cannot be produced economically using EAF processes (e.g. exterior grade\nauto steel) because of the impurities present in recycled steel. For many other products, including flat rolled coil used\nin many situations, EAF and BOF processes could both be used. Moreover, the range of items where EAF produced\nsteel is used has expanded dramatically in recent years; a few decades ago, minimills produced only for the low-end\nlong product market such as rebar.] One cannot perform tests on the steel\nitself since the CO2 is not contained in the steel but instead is emitted in the production process.\nSimilar problems occur for requiring importers to buy emission permits as envisioned under\nvarious U.S. legislative proposals. Without cooperation by the Chinese and Brazilian\n\nMention: \"OECD carbon footprint estimates\""}, {"role": "assistant", "content": "{\"role\": \"supporting\", \"usage_action\": \"source\", \"summary\": \"Their estimates imply a lower tax burden for the comparison producers.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:004553:7:1", "occurrence_id": "c0a766936395c4024c86cf63", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: (2) and defined above.\n\n_D_ and _α0i_ denote time effects and bank-level fixed effects, respectively. As in most papers, our\n\n\nestimations impose the restrictions of symmetry and degree one homogeneity in the price of\n\ninputs. 6\n\n\nWe compute the H-statistic and the Lerner index using bank-level balance sheet and\n\n\nincome statement data from Bankscope for the period 1994-2008. The sample for MENA\n\n\nincludes data on 250 commercial and Islamic banks, operating in 12 MENA countries, namely:\n\n\nAlgeria, Bahrain, Egypt, Jordan, Kuwait, Lebanon, Morocco, Oman, Qatar, Saudi Arabia,\n\n\nTunisia, and United Arab Emirates. Table 1 shows the number of banks and observations for\n\n\neach country in our sample.\n\n\nWe compare competition in MENA to that in other regions using similar Bankscope data\n\n\nfor 3,785 banks operating in 122 countries across 6 regions. Table 2 lists the countries included\n\n\nin each region and reports the number of banks and observations that go into the calculations of\n\n\nthe H-statistic and the Lerner index for each region.\n\n\n**3.** **Empirical results on the non-structural measures of competition**\n\n\n3.a. H- Statistic\n\n\nTable 3 shows H-statistics for individual countries in MENA over two periods: 1994-2001 and\n\n\n2002-2008. Also, this table reports p-values for tests of whether H is equal to 0 and the market\n\n\ncan be best characterized as a monopoly or H is equal to 1 and the market operates under perfect\n\n\ncompetition.\n\n\n6 However, the results do not change if we drop these constraints.\n\n\n6\n\nMention: \"data on 250 commercial and Islamic banks\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"The regional sample covers a quarter thousand banks across twelve countries.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:004553:7:1", "occurrence_id": "00add28ccbb9845349a047bd", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: (2) and defined above.\n\n_D_ and _α0i_ denote time effects and bank-level fixed effects, respectively. As in most papers, our\n\n\nestimations impose the restrictions of symmetry and degree one homogeneity in the price of\n\ninputs. 6\n\n\nWe compute the H-statistic and the Lerner index using bank-level balance sheet and\n\n\nincome statement data from Bankscope for the period 1994-2008. The sample for MENA\n\n\nincludes data on 250 commercial and Islamic banks, operating in 12 MENA countries, namely:\n\n\nAlgeria, Bahrain, Egypt, Jordan, Kuwait, Lebanon, Morocco, Oman, Qatar, Saudi Arabia,\n\n\nTunisia, and United Arab Emirates. Table 1 shows the number of banks and observations for\n\n\neach country in our sample.\n\n\nWe compare competition in MENA to that in other regions using similar Bankscope data\n\n\nfor 3,785 banks operating in 122 countries across 6 regions. Table 2 lists the countries included\n\n\nin each region and reports the number of banks and observations that go into the calculations of\n\n\nthe H-statistic and the Lerner index for each region.\n\n\n**3.** **Empirical results on the non-structural measures of competition**\n\n\n3.a. H- Statistic\n\n\nTable 3 shows H-statistics for individual countries in MENA over two periods: 1994-2001 and\n\n\n2002-2008. Also, this table reports p-values for tests of whether H is equal to 0 and the market\n\n\ncan be best characterized as a monopoly or H is equal to 1 and the market operates under perfect\n\n\ncompetition.\n\n\n6 However, the results do not change if we drop these constraints.\n\n\n6\n\nMention: \"Bankscope data\""}, {"role": "assistant", "content": "{\"role\": \"supporting\", \"usage_action\": \"source\", \"summary\": \"The comparator covers thousands of banks across 122 countries.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:004564:13:0", "occurrence_id": "be989a4bcf53aa81272a389a", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: Note that, if the normalized citation curves intersect we may still be able to establish a\n\n\nrobust ordering in terms of average influence by imposing declining marginal influence. By a\n\n\nsimilar argument, the corresponding second-order dominance condition for this case is that\n\n_GA_ ( _c_ ) _GB_ ( _c_ ) for all _c_, with strict inequality for some _c_ . If this holds then one can conclude that\n\n\nthe publication record of A has greater average influence per publication for any influence\n\n\nfunction satisfying both our core and extra assumptions.\n\n\n**Empirical examples**\n\n\nWe illustrate these ideas using comparisons of the economics publications records of\n\n\nselected universities and the World Bank.\n\n\nWe rely on Google Scholar for citation counts. Compared to other bibliographic\n\n\ndatabases, Google Scholar casts a broad net, including citations by books, working papers,\n\n\nconference proceedings, open-access journals, new and less well-established journals. Google\n\n\nScholar is also more “global” in its reach, as it includes research outputs from everywhere in the\n\n\nworld and all languages. Google Scholar is also timelier than the bibliographic databases.\n\n\nNo time limit was set for the data on citations, since all are old institutions; in practice the\n\n\nrecords we use date back to 1964, but only five percent of them are before 1980. We searched in\n\n\nSCOPUS for articles where any author was affiliated with one of the institutions we consider;\n\n\nmultiple records are therefore possible in the dataset where collaboration has taken place across\n\n\ntwo or more of the institutions. Only articles in the discipline “Economics, Econometrics and\n\n\nFinance” were included in our analysis. Google Scholar citation data were then obtained for each\n\n\narticle in our database.\n\n\nTable 1 gives the summary statistics on citations for Berkeley, Harvard, London School\n\n\nof Economics (LSE), Oxford, Princeton and Yale, plus the World Bank. The _h_ -index ranking is\n\n\nHarvard (\n\nMention: \"Google Scholar citation data\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"Citation counts are obtained for each article in the bibliometric database.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:004593:29:1", "occurrence_id": "d249e17870f2b8cb755e94f0", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: with the ease of starting or closing a business;\n\n - Trade Freedom: Rises as the levels of tariff and nontariff barriers are reduced;\n\n - Fiscal Freedom: Increases as marginal tax rates on personal and corporate income and\n\ntotal taxes as a fraction of GDP fall;\n\n - Freedom from Government: Rises as the importance of state-owned enterprises and\n\ngovernment expenditure as a share of GDP are reduced;\n\n - Monetary Freedom: Rises as inflation rates fall and as the imposition of price controls are\n\nreduced;\n\n - Investment Freedom: Rises with quality of investment climate for both foreign and\n\ndomestic investors;\n\n - Financial Freedom: Rises as regulations on banking and other financial institutions are\n\neased;\n\n - Property Rights: Rises with legislation and enforcement that protect individual property;\n\n - Freedom from Corruption: Rises with the country’s score on Transparency International’s\n\nCorruption Perception Index.\n\n\n28\n\nMention: \"Transparency International’s\n\nCorruption Perception Index\""}, {"role": "assistant", "content": "{\"role\": \"supporting\", \"usage_action\": \"source\", \"summary\": \"The freedom from corruption dimension rises with this score.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:004604:8:0", "occurrence_id": "7ae8ee82d52ac098d42a7d32", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: to crime. 8 [^8: We have also tried specifications including the share of losses of sales due to power outage and the\naverage level of schooling of firm employees. The results including these additional controls are similar.\nHowever, several countries do not have these measures. To preserve as many SADC countries as possible\nin our sample, we opted to report the results without including them.] The country level controls, _Z_, include logged GDP per capita, the ICRG index\n\n\nof government efficiency, the firing costs in years of salary, and the interest spread (as a\n\n\nmeasure of banking competitiveness). All the country-level variables come from the\n\n\nWorld Development Indicators data base of the World Bank. Since the regressions are at\n\n\nthe firm level, while we have country-level explanatory variables, to avoid exaggerating\n\n\nestimation precision, we cluster the standard errors at the country level (Moulton 1986).\n\n\nTable 3 reports the results.\n\n\nThe most important finding is that foreign ownership has a strong and significant\n\n\nrelationship with both sales growth and TFP. Increasing foreign ownership by 10\n\n\npercentage points would increase sales growth by 1.2 percentage points, and TFP by 1.8\n\n\npercentage points—effects that are non-trivial. To put this in perspective, Table A1 in\n\n\nthe appendix provides the comparison of SADC with the East Asia and Pacific region\n\n\n(consisting of China, Indonesia, Malaysia, and Thailand, EAP hereafter) and all non\nSADC countries with similar income level as SADCs. 9 [^9: That is, with income less than 4600 U.S. dollars of 2000, the level of South Africa.] Foreign ownership is\n\n\nsignificantly higher in SADC (17.5 percent) than in EAP (13.5 percent) and the similar\n\nincome sample (10.8 percent). In light of the positive effect of foreign ownership and\n\n\nSADC's advantage in this measure, foreign ownership has reduced the disadvantage of\n\n\nSADC toward other regions\n\nMention: \"World Development Indicators data base\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"All country-level regressors including the competition measure come from it.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:004607:6:0", "occurrence_id": "b2cfee5e63b7a222f3e310de", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: Information instruments have diverse forms, including reports of measured pollution,\n\n\nenvironmental accident reports, and environmental performance ratings. In the US, for example,\n\n\nthe Toxic Release Inventory (TRI) discloses toxic chemical releases and waste management\n\n\nactivities by significant toxic polluters and federal facilities. In developing countries, however,\n\n\nweak regulatory institutions may have much greater difficulty in implementing such emissions\n\n\ninventories. In addition, despite an emerging literature on stakeholders’ role in improving firms’\n\n\nenvironmental performance (Arora and Cason, 1998; Blackman and Bannister, 1998; Pargal and\n\n\nWheeler, 1996; Wheeler et al., 1997), concerns remain about the public’s ability to understand\n\n\nand utilize complex emissions reports. For example, Bui and Mayer (2003) find that the release\n\n\nof TRI’s highly-detailed information on facilities’ toxic emissions has virtually no effect on\n\n\nhousing prices in neighboring areas, even when the release is unexpected. The dual problems of\n\n\nemissions inventories in developing countries – technical feasibility and public understanding –\n\n\nhave led to a preference for programs that condense complex information into environmental\n\n\nperformance ratings that are disclosed to the public.\n\n\nResearch on the effectiveness of performance rating and disclosure (PRD) programs suggests\n\n\nthat that have a significant, positive impact on regulatory compliance (Afash et al., 1997;\n\n\nDasgupta et al., 2006; Garcia et al., 2007, 2009; Wang et al., 2004). Dasgupta et al. (2006)\n\n\nsummarize the changes in compliance rates for several PRD programs in Asia: One and two\n\n\nyears after the inception of a PRD, compliance rates increased from 37% to 61% in Indonesia,\n\n\n8% to 58% in the Philippines, 10% to 24% in Vietnam, 75% to 85% in Zhenjiang, China and\n\n\n23% to 62% in Hohhot, China.\n\n\nSeveral empirical studies also find that PRD programs have improved firms’ environmental\n\n\nperformance in Indonesia (Afash et al., 1997\n\nMention: \"Toxic Release Inventory\""}, {"role": "assistant", "content": "{\"role\": \"supporting\", \"usage_action\": \"source\", \"summary\": \"It discloses releases and waste management by major polluters in one country.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:004626:3:1", "occurrence_id": "ffd46bbf2035a43fb565af58", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: access to credit.\n\n\nAccording to the 2006 Doing Business Report, Malawi ranked 109 out of 129 countries\n\n\nin terms of private credit to GDP, a frequently-used measure of financial development. Malawi\n\n\nalso gets the lowest marks in the “depth of credit information index” which proxies for the\n\n\namount and quality of information about borrowers available to lenders. Using more micro data,\n\n1 The following quote from 1973 by Robert McNamara when he was the World Bank president exemplifies this\nview: “The miracle of the Green Revolution may have arrived, but for the most part, the poor farmer has not been\nable to participate in it. He simply cannot afford to pay for the irrigation, the pesticide, the fertilizer… For the small\nholder operating with virtually no capital, access to capital is crucial.”\n\nMention: \"2006 Doing Business Report\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"Its ranking on credit to output places the country low.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:004635:14:0", "occurrence_id": "017489269cde88081a27dec9", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: from a failed business (Sullivan, et al., 1989). While the personal guarantee of a firm’s owner\n\n\nmight encourage a level of financial discipline, in countries without a personal bankruptcy\n\n\nframework, a single business failure could doom an owner to a lifetime of outstanding debt\n\n\n(Uttamchandani and Menezes, 2010) and effectively prevent them from re-entering the market as\n\n\nseasoned entrepreneurs (Armour and Cumming, 2005).\n\n\n**3.** **Bankruptcy Regimes during the Crisis**\n\n\n**_3.1_** **_Bankruptcy Regime as One of the Main Tools for Entrepreneurship Recovery_**\n\n\nThe 2008 global financial crisis is causing a sharp increase in bankruptcies around the world.\n\n\nEnsuring that viable companies can continue to operate as going concerns and preserving jobs\n\n\nhas become especially important. In response, policymakers are debating whether existing\n\n\nbankruptcy regimes adequately address current business’ demands.\n\n\nIneffective procedures for dealing with bankruptcy can deepen and prolong a crisis. Low\n\n\ndemand may make firms reluctant to restructure and regain their health, affecting the health of\n\n\nthe banking sector and further restricting credit to firms that may be recovering. Distress among\n\n\nfinancial institutions can also reduce the incentives for firms to repay their loans. The\n\n\nbankruptcy processes – which are generally already under strain during normal times – can be\n\n\ncompletely overwhelmed (Demirgüç-Kunt, 2009).\n\n\nDuring 2009, the number of corporate bankruptcies in Japan was 13,306 (up 4.9% from\n\n\n12,681 in 2008, Teikoku Databank, 2010 vi ), in Great Britain 94,135 (5.88% growth compare to\n\n\n2008, Ministry of Justice, 2010 vii ), and in Germany, the number of corporate bankruptcies was\n\n\n32,687, which represents 11% annual increase, whereas the volume of debt\n\nMention: \"Teikoku Databank\""}, {"role": "assistant", "content": "{\"role\": \"supporting\", \"usage_action\": \"source\", \"summary\": \"Corporate bankruptcy counts for the country come from this data bank.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:004651:14:1", "occurrence_id": "78e85c580a3f05080572f010", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: team of at least three persons. Children are not allowed\n\n\nto bring any materials or stationery (other than pens) into the testing area. The grades selected for\n\n\nthe QAT are tested simultaneously in the same testing area and the seating for the students is\n\n\nmixed. All test materials provided to the test takers are collected back. All unused test materials\n\n\nare retained by the testing agency. ADU also reports that test item recycling across QAT rounds\n\n\nis presently rare given the size of its test item bank.\n\n\nThe QAT serves as the main source of data for the analysis of learning dynamics in\n\n\nprogram schools. While PEF has conducted nine QATs since the inception of the FAS program\n\n\n(QAT 9, the latest QAT, was administered in March 2010), this study uses data from QAT\n\n\n4−QAT 8 which spans November 2007–November 2009, a two-year period, covering, in whole\n\n\nor in part, three academic years. QAT 4 is the first QAT round in the analysis as it represents the\n\n\n13\n\nMention: \"data from QAT\n\n\n4−QAT 8\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"Five quarterly rounds spanning this period form the study sample.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:004665:37:0", "occurrence_id": "15dec647540d7eb973bfc040", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: where _dij_ is the Euclidean distance between the geographic centers of prefectures _i_ and _j_, _diport_\nis the Euclidean distance between the center of region _i_ and that of the nearest prefecture\nwhich has a major international port, and _area_ is a prefecture's land area (in km 2 ). The data\non land areas is taken from _Regional Economic Statistical Yearbook 2008_ . Eight major\ninternational ports are considered: Shanghai, Ningbo, Tianjin, Guangzhou, Qingdao City,\nDalian City, Qinhuangdao City and Shenzhen City. These correspond to the eight Chinese\nports which had the largest throughput (measured in million tonnes of traffic) in ISL (2006).\nPre-multiplication of a variable by **W** - **W** represents the second-order spatial lag of that\nvariable.\n\n_Additional parameters used in the numerical solution of the theoretical model:_\n\nAs outlined in section 3.2, to obtain a numerical solution for the system of equations [3] – [7],\nwhich describe the short-run equilibrium of our theoretical model, we also require measures\nfor the parameters , , . For 2007, the measures for and , which correspond to the\nregional shares of the national urban and rural workforces respectively, are constructed using\ndata on \"urban employed persons\" and \"total employed persons\" from the _Regional Economic_\n_Statistical Yearbook 2008_ . For , rural employment is calculated as total employed persons\nminus urban employed persons 35 [^35: In the various provincial statistical yearbooks, the numbers of urban and rural employed persons exactly sum\nto the number of total employed persons at the provincial level.] According to the _China Statistical Yearbook 2008_,\nemployed persons refer to \" _people aged 16 and over who are engaged in gainful employment_\n_and thus receive remuneration payment or earn business income_ \". , the national share of\nurban workers in\n\nMention: \"Regional Economic Statistical Yearbook 2008\""}, {"role": "assistant", "content": "{\"role\": \"supporting\", \"usage_action\": \"source\", \"summary\": \"Prefecture land areas are taken from this yearbook.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:004670:23:0", "occurrence_id": "7d04a3d9a04bb4c9f1987dbf", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: **Figure 3: Weights on life expectancy in the old and new HDI**\n\n\n\n.007\n\n\n.006\n\n\n.005\n\n\n.004\n\n\n.003\n\n\n.002\n\n\n.001\n\n\n\n|Col1|Old HDI
New HDI|Col3|Col4|Col5|Col6|Col7|Col8|\n|---|---|---|---|---|---|---|---|\n|||||||||\n|||||||||\n|||||||||\n|||||||||\n|||||||||\n|||||||||\n\n\n5 6 7 8 9 10 11 12\n\n\nGross national income ($ per person per year; log scale)\n\n\n\nSource (this figure and all following ones): Author’s calculation from data for 2008 provided in the 2010 HDR. The\nfitted line is a locally smoothed (nonparametric) regression.\n\n\n**Figure 4: Implicit valuations in HDI and marginal costs of an extra year of life expectancy**\n\n\n\n9,000\n\n\n8,000\n\n\n7,000\n\n\n6,000\n\n\n5,000\n\n\n4,000\n\n\n3,000\n\n\n2,000\n\n\n1,000\n\n\n0\n\n\n\n|Col1|Qatar
Liechtenstein
Implicit valuation
in HDI
Marginal cost
(Dowrick et al.)
Zimbabwe|Col3|Col4|Col5|Col6|Col7|Col8|\n|---|---|---|---|---|---|---|---|\n|||||||||\n|||||||||\n\nMention: \"2010 HDR\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"Underlying values for that year are extracted from this report.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:004676:56:2", "occurrence_id": "4b059a92f57bae0544ee5bf1", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text:
1.2
1.7
2.0
2.8
**8.6**
**12.2**|\n\n\nAuthors’ calculations using China’s Customs Statistics Data\n\n\n\n\n\n55\n\nMention: \"China’s Customs Statistics Data\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"analyze\", \"summary\": \"Export values by category are computed from these customs records.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:004687:24:0", "occurrence_id": "e4c0c91d00420095ced2003c", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: _Implications for Poverty Analysis_\n\n\nThe fact that both mean consumption and distributional measures vary substantially across\n\n\nthe modules implies that there will be complex comparability problems when poverty estimates\n\n\nfrom different modes of consumption measurement are combined. For example, consider a poverty\n\n\nmonitoring survey that switched from 14-day to 7-day recall. This switch would raise reported\n\n\nmean consumption (see Table 3) and lower measured inequality (see Table 7). In a setting where\n\n\nthe poverty line is set below median consumption, these effects will work in concert to make\n\n\npoverty look lower than it would if the method of consumption measurement had not changed (as\n\n\noccurred with changes in India’s NSS). Conversely, if a switch was made from a disaggregated\n\nrecall list to a collapsed list (as the Indonesian _Susenas_ does every 3 rd year), it would lower the\n\n\nmean (implying higher measured poverty) and lower inequality (lower measured poverty) with\n\n\nambiguous implications for poverty measures. Hence there are unlikely to be simple correction\n\n\nfactors that can be used to enforce comparability on different consumption modules when\n\n\nattempting to measure poverty consistently over either time or space. Similarly, the literature that\n\n\nreacts to possible survey understatement by combining survey measures of inequality with national\n\n\naccounts measures of mean consumption (such as Bhalla, 2000, and Sala-i-Martin and Pinkovskiy,\n\n\n2010) is likely to be misguided since survey design changes will also affect estimated inequality.\n\n\nWe attempt to quantify the implications of survey design for poverty analysis in a setting\n\n\nlike Tanzania by presenting aggregate poverty numbers based on an international poverty line, as\n\n\nwell as the characteristics of those households deemed poor by each module. Figure 1a presents the\n\n\npoverty headcount rate based on a common international poverty line of $1.25/person/day\n\nconverted into 2008 Tanzanian shillings on a PPP basis. 25 With this absolute poverty line\n\nMention: \"NSS\""}, {"role": "assistant", "content": "{\"role\": \"supporting\", \"usage_action\": \"validate\", \"summary\": \"Its change in consumption measurement method is the cautionary case.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:004712:30:1", "occurrence_id": "05e7eaf2ce1d7d9e69889490", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: u> Labor market shocks General economic distress Mobility intention Migration\n\n\n\nDo your military\nservice (all years)\n\n\nGet married (live in\ncouple)\n\n\nHave a child (birth\nor adoption)\n\n\n\nReceive unemployment\nbenefits\n\n\nHave to do a job below\nyour qualifications\n\n\nHave to accept wage\ncuts/arrears\n\n\n\nTurn to relatives for\nfinancial assistance\n\n\n\nHave to move in with\nFind a better job\nrelatives\n\n\nHave to sell some of your\nhousehold assets\n\n\n\nWork for wages\n(for an employer)\n\n\n\nMove from\nurban to rural\narea\n\nMove from\nrural to urban\narea\n\n\n29\n\n\n\nHave to cut down on\nDivorce\nbasic food consumption\n\nOfficially retire\nDecided not to\nwork\n\nSource: Life in Transition Survey data (Authors’ own calculation)\n\nMention: \"Life in Transition Survey data\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"analyze\", \"summary\": \"Household coping strategies such as cutting food consumption are tabulated here.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:004743:13:0", "occurrence_id": "0560fac9db465311ceb2ff7c", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: **Box 1: Global gains from migration**\n\nEven though quantitative estimates of the direct gains from migration are difficult to obtain,\neconomic simulations suggest that an increase in South-North migration would produce\nsubstantial income gains in the long-run; these income gains could exceed those from\ncomprehensive trade liberalization; and the destination countries in the North would\ncapture one fifth the overall benefits of increased immigration (World Bank 2006, Winters\n_et al._ 2003, Anderson & Winters 2008, van der Mensbrugghe & Roland-Holst 2009).\nDocumented welfare gains from South-North migration work primarily though the increase\nin the available labor force. Ortega and Peri (2009) found that immigration increases\nemployment in the destination countries in the North one for one, implying no crowdingout of natives. This result implies that immigration increases the total GDP of the receiving\ncountry without affecting average wages or labor productivity.\n\nImmigration has also been observed to boost productivity through innovation and\nspecialization. Data from the United States show that one percent increase in the share of\nmigrant university graduates increase the number of patent applications and grants issued\nper capita (Chellaraj _et al._ 2008, Hunt & Gauthier-Loiselle 2008). However, burdensome\nregulatory requirements and procedures that foreign doctors, engineers, architects and\naccountants have to meet in order to practice in the destination country can impose\nsignificant financial and other costs on these highly skilled immigrants (Mattoo and Mishra\n2009). Also the less-educated immigrants increase labor productivity as they complement\nthe uneducated local labor force that, based on their knowledge of the local language and\ninstitutions, will be better able to specialize in more productive complementary tasks (Peri\n& Spaber 2009). Furthermore, immigrants are often willing to do jobs that locals no longer\nare interested in, such as care for the elderly (UNDP 2009, p. 85). Also, the availability of\nlow-cost childcare by the immigrants can enable young\n\nMention: \"Data from the United States\""}, {"role": "assistant", "content": "{\"role\": \"supporting\", \"usage_action\": \"source\", \"summary\": \"Migrant graduate shares and patent counts come from these records.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:004751:11:0", "occurrence_id": "5a6554a399397b191b200055", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: fragility of the mechanisms governing public sector works and the difficulty in controlling for multiple\nconflict of interests.\n\n\nConcessionaires led by the Autostrade group try to block any government intervention aimed at the\nintroduction of a more harmonious tariff system. In 2006 Autostrade provocatively threatened to sue the\ngovernment and ask for compensation in case a new tariff law would be enacted. 23 [^23: [http://archiviostorico.corriere.it/2006/ottobre/08/Autostrade_soci_rivolta_governo_ora_co_9_061008023.shtml](http://archiviostorico.corriere.it/2006/ottobre/08/Autostrade_soci_rivolta_governo_ora_co_9_061008023.shtml)]\n\n\nNevertheless, statistical data on this subject are less univocal. As Figure 4 shows, the evolution of the tariff\nbefore and after 1999 (the dotted line) does not seem to show a significantly different trend, although from\n2003 onward tariffs seem to be growing more than inflation.\n\nHowever one possible explanation may be given for the “tariff rage” of both concessionaires and users.\nBefore 1999, tariffs were linked to the highest one imposed by Autostrade, so the whole network would have\na nationally-fixed tariff system, either directly or through shadow-tolls. After 1999, a new system was\nintroduced, which linked the tariff applied on each highway both to general aggregates (inflation) and to\nconcession-specific variables (quality and productivity). For this reason, the geography of the highway tariff\nhas evolved unevenly since 1999. This may also explain consumer aversion and the haste against the new\nconcession system.\n\n\nFigure 4: Tariff and Inflation Rate Evolution 24 [^24: Source: Italian statistical institute, Istat. The base year for the two series is 1995=100.]\n\n\n130\n125\n120\n115\n110\n105\n100\n95\n90\n85\n80\n\n\n1991 1993 1995 1997 1999 2001 2003 2005\n\n\nInflation Rate Tariff\n\n\n_Source: Italian Statistical Institute, ISTAT. Inflation refers to variation in the consumer price index (CPI);_\n_the base year for\n\nMention: \"consumer price index\""}, {"role": "assistant", "content": "{\"role\": \"supporting\", \"usage_action\": \"curate\", \"summary\": \"Variation in this index defines the inflation measure with that base year.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:004768:6:0", "occurrence_id": "7ae829c489a35b7d1594069c", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: _Tij_ = _β0_ + _β1 Aij_ + _β2 Fij_ + _β3S ij_ + _β4Iij_ + _єij_ (2)\n\n\nwhere _β0_ to _β4_ are the coefficients to be estimated. The standard procedure for analyzing the\ndeterminants of the test score differences over time is to fit equations between test scores and\nobserved characteristics. The observed test score differential can be decomposed as:\n\n\n_T2006_ - _T2003_ = ( _X2006_ - _X2003_ ) _2006_ + _X2003_ ( _2006_ - _2006_ ) (3)\n\n\nwhere _T_ is the standardized test score, _Xi_ is a vector of student, family, school, and institutional\ncharacteristics for the _i_ th individual, is a vector of coefficients, and 2006 and 2003 subscripts\nare identifiers of the PISA test score in math in years 2003 and 2006 evaluated at 2006 prices.\nThe overall increase in test score can, therefore, be decomposed into two components. One is the\nportion attributable to differences in characteristics ( _X2006_ - _X2003_ ) evaluated at 2006 prices or to\nthe performance of the 2006 group of students ( _2006_ ), while the other portion is attributable to\ndifferences in the effects on performance _(_ _2006_ - _2003_ ) of 2003 and 2006 students derived from\nthe same characteristics. This second (unexplained) component, while more difficult to interpret\nin the present context than an earnings gap decomposition framework, may have had more than\none explanation. The first and most obvious explanation is that the unexplained portion of the\ntest score increase may reflect certain unobserved family characteristics that are correlated with\nachievement over time, possibly related to household wealth. The second possible explanation\nmay be that\n\nMention: \"PISA test score\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"analyze\", \"summary\": \"Mathematics scores in these two years, valued at constant prices, are decomposed.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:004776:9:0", "occurrence_id": "2dabaaad1266bda593a70171", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: reference cluster. The variables and their sources are described in Appendix 2. The regressors fall into\nthree broad categories:\n\n\n**Figure 2: Correlations between Growth and the Sources of Vulnerability**\n\n\n\n\n\n\n\n\n\nSources: IMF’s World Economic Outlook database and authors’ calculations.\nNotes: The lower growth and lower vulnerability is identified by L, the lower growth and higher vulnerability is identified by V, the higher\ngrowth and lower vulnerability is identified by G, and the higher growth and higher vulnerability is identified by H. The absence of higher\ngrowth, higher vulnerability data in 2000 and 2008 reflects the lack of countries in such cluster.\n\n\n- Initial conditions. These comprise measures that may be susceptible to policies and institutional\nchanges over a relatively long period. This category includes measures that reflect a country’s\neconomic development and its economic structure, as well as the degree to which an economy is\nopen to the flows of goods and capital. This includes the initial level of income and oil trade balance\nas a share of total exports plus imports. In addition, measures of trade (exports and imports as a\npercentage of GDP) and financial (FX assets plus liabilities as a percentage of GDP) openness are\nincluded and, in turn, these are accompanied by indicators that serve to qualify the type of\nopenness experienced by individual countries. Specifically, the difference between export and\nimport growth rates is used to assess the type of trade openness. Also, FDI (net, as a percent of\n\n\n7\n\nMention: \"IMF’s World Economic Outlook database\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"Growth and vulnerability series plotted here come from this database.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:004780:10:0", "occurrence_id": "7a8a4a7d0166bf8bf073cb1d", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: KENYA’S INFRASTRUCTURE: A CONTINENTAL PERSPECTIVE\n\n\n**Table 2. Kenya’s road indicators benchmarked against Africa’s low- and middle-income countries**\n\n\n\nUnit Low-income\ncountries\n\n\n\n**Kenya** Middleincome\ncountries\n\n\n\nPaved road density km/1000 km2 of arable land 86.6 **152** 507.4\n\nUnpaved road density km/1000 km2 of arable land 504.7 **930** 1,038.3\n\n\n\nGIS rural accessibility % of rural population within 2 km of allseason road\n\n\n\n21.7 **32** 59.9\n\n\n\nPaved road traffic Average annual daily traffic 1,049.6 **1,108** 2,786.0\n\nUnpaved road traffic Average annual daily traffic 62.6 **38** 12.0\n\nPaved network condition % in good or fair condition 80.0 **84** 79.0\n\nUnpaved network condition % in good or fair condition 57.6 **63** 58.3\n\n\n\nPerceived transport quality % firms identifying roads as major\nbusiness constraint\n\n\n\n23.0 **37** 10.7\n\n\n\nSource: Gwillliam and others 2009, derived from AICD national database downloadable from http://www.infrastructureafrica.org/aicd/tools/data.\n\n\n**Challenges**\n\n\nNevertheless, the country faces a huge rehabilitation backlog that must be addressed before the trunk\nnetwork can be considered to be in a maintainable condition (figure 4). As of 2006, levels of capital\nspending for the roads sector—at around 1 percent of GDP—were low by regional standards and fell\nsubstantially short of what would be needed to clear the rehabilitation backlog in a reasonable period of\ntime. There is a need for a one-time push on road sector investment to remedy this situation.\n\n\n**Figure 4. Kenya is not spending enough\n\nMention: \"AICD national database\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"Constraints cited as a major business obstacle are drawn from this national database.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:004829:61:1", "occurrence_id": "ac48a47aee8b9528f81abce0", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: grades 1-4 of urban\nprimary schools, how many were enrolled in grades 1-4 of rural primary schools, how many were\nenrolled in grades 5-8 of urban primary schools, and how many were enrolled in grade 5-8 of\nrural primary schools. Beginning in 2007, under FUNDEB, the algorithm was complicated even\nmore, to depend (in addition to all these previous factors) on the number of children enrolled in\nurban vs. rural creches, preschools, secondary schools, and adult education (EJA). Fortunately,\nthe annual Census of Schools contains all of the required information, as it is the basis for the\ndistribution of FUNDEF funds. Minist´erio da Educa¸c˜ao (2008) describes the changes initiated\nin 2007.\n\nWhile the laws induced endogenous municipal responses, I can simulate the municipality’s\nvirtual tax revenue by using the exact algorithms of the laws in each year, but using pre-reform\n(1997) data on revenue and enrollments. To better predict how enrollments will expand over\nthe sample period without introducing endogenous information, I exploit the nation-wide rate\nat which municipal governments took over the state’s role in primary education during 19982008. Primary education is usually run by municipal governments, but the state government\nis involved in some municipalities more than in others. I wanted to account for the fact that\nsome municipalities had a greater potential to secure higher revenue through take-over than did\nothers. The federal rate of takeover is exogenous to pre-primary education policy in any given\nmunicipality. However, by taking this into account and thus allowing simulated revenue to grow\nmore in municipalities with heavy initial state and federal involvement in primary education in the\npre-period, I can better predict revenue without drawing on any one municipality’s endogenous\nresponse to the reforms.\n\nThe additional instruments are computed simply by interacting simulated revenue with the\nfollowing variables: year 2000 median per capita household income,\n\nMention: \"annual Census of Schools\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"It holds the school characteristics used to allocate education funds.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:004839:29:0", "occurrence_id": "e09a54bf6d04603b83fb7a58", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: and the synergy effect has a negative and significant coefficient, implying that\nfirms belonging to industries with high asset tangibility (essentially capitalintensive industries) are _less_ sensitive to the synergy effect. 17\n\n\nGiven that these interactions have significant explanatory power, we combine them to address a potential omitted variable bias, and to compare there\ncoefficients in a joint multivariate regression. In columns (4) and (5) we\ncombine one regressors capturing each of the three hypothesis that these interactions try to capture: information, financial constraints or capabilities.\nWe find that typically the same signs, magnitudes and statistical significance\nlevels persist as the ones just discussed, and the interpretations from above\nare valid when we control for all these effects simultaneously.\n\n#### **5 Concluding remarks**\n\n\nIn spite of their growing interest for the profession, firm-level datasets are\nstill rare for low-income countries, and virtually inexistent for African countries. Our exploration of African customs data on firm-level exports revealed\na set of stylized facts that are consistent with evidence from previous studies\nanalyzing rich or middle-income countries. We showed that exporters in our\nset of African countries experiment a lot on export markets, at a low scale\nand with low survival rates, particularly in the first year. That is, they operate in a difficult environment characterized by very high “infant-mortality\nrates”. Therefore we investigate more in detail what determines if they survive beyond their first year.\n\n\nThe most striking finding coming out of our analysis —and which could\nnot be observed on the product-level data used by previous studies of export\nsurvival—is that exporters of similar goods to the same destination exert a\n_positive_ externality on new entrants. That is, the more they are, the higher\nthe survival probability of new entrants—although the effect is relatively\nsmall. This finding is at first sight surprising, as one might expect that\n\nMention: \"African customs data\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"analyze\", \"summary\": \"Firm-level export records reveal a set of stylised facts.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:004869:10:1", "occurrence_id": "1ebdf75732f6049869f85f61", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: 246 positive cross-border trade ‡ows, 2,548 zeros and\n\n\n826 instances of missing values. We therefore need to account for potential sample selection issues in our\n\n\nmodel and econometric methodology.\n\n\nWe use 2005 GDP measured in constant (2000) US Dollars from the World Development Indicators.\n\n\nAs will become clear, each country’s GDP share is an important component of our analysis. We calculate\n\n\neach country’s share of world GDP by dividing its GDP by world GDP, where world GDP is the sum of\n\n\nthe 116 countries in our sample.\n\n\nThe measure of bilateral distance that we use captures the internal distance in a country, accounts\n\n\nfor the distance from a number of major cities and is constructed by CEPII. 9 [^9: The distance measure used is distw and is described at http://www.cepii.fr/anglaisgraph/bdd/distances.htm] Border data are also\n\n\nsourced from CEPII. Our control variables, including dummies for whether or not two countries share\n\n\na common language, 10 [^10: We construct a dummy that is equal to one if two countries share either a common o¢ cial or common ethnic language.] a common colonizer or were once the same country, as well as a dummy for a\n\n\nlandlocked country, are sourced from CEPII. Additional variables for identi…cation as …xed export costs\n\n\nor instruments are taken from the World Bank Doing Business database. These data include the number\n\n\nof procedures needed to start a business, the number of days it takes to start a business and the cost of\n\n\nregistering to start a new business in a country. We also considered data on the number of documents\n\n\nrequired to export or to import goods. Finally, we took the newly recoded data on religious similarity\n\n\nused by Helpman, Melitz & Rubinstein (2008) from Elhanan Helpman’s website.\n\n\n7 The 2009 version of this paper used the full LPI. That paper also restricted\n\nMention: \"World Development Indicators\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"Output for the reference year in constant dollars comes from this source.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:004869:10:1", "occurrence_id": "d1ed3f15b021d2fb471b1fd4", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: 246 positive cross-border trade ‡ows, 2,548 zeros and\n\n\n826 instances of missing values. We therefore need to account for potential sample selection issues in our\n\n\nmodel and econometric methodology.\n\n\nWe use 2005 GDP measured in constant (2000) US Dollars from the World Development Indicators.\n\n\nAs will become clear, each country’s GDP share is an important component of our analysis. We calculate\n\n\neach country’s share of world GDP by dividing its GDP by world GDP, where world GDP is the sum of\n\n\nthe 116 countries in our sample.\n\n\nThe measure of bilateral distance that we use captures the internal distance in a country, accounts\n\n\nfor the distance from a number of major cities and is constructed by CEPII. 9 [^9: The distance measure used is distw and is described at http://www.cepii.fr/anglaisgraph/bdd/distances.htm] Border data are also\n\n\nsourced from CEPII. Our control variables, including dummies for whether or not two countries share\n\n\na common language, 10 [^10: We construct a dummy that is equal to one if two countries share either a common o¢ cial or common ethnic language.] a common colonizer or were once the same country, as well as a dummy for a\n\n\nlandlocked country, are sourced from CEPII. Additional variables for identi…cation as …xed export costs\n\n\nor instruments are taken from the World Bank Doing Business database. These data include the number\n\n\nof procedures needed to start a business, the number of days it takes to start a business and the cost of\n\n\nregistering to start a new business in a country. We also considered data on the number of documents\n\n\nrequired to export or to import goods. Finally, we took the newly recoded data on religious similarity\n\n\nused by Helpman, Melitz & Rubinstein (2008) from Elhanan Helpman’s website.\n\n\n7 The 2009 version of this paper used the full LPI. That paper also restricted\n\nMention: \"World Bank Doing Business database\""}, {"role": "assistant", "content": "{\"role\": \"supporting\", \"usage_action\": \"source\", \"summary\": \"Procedure counts and days serve as fixed cost proxies and instruments.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:004905:20:2", "occurrence_id": "99a473b15452d138d817b481", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: 0.50 0.37\nMedium soil quality 0.36 0.36 0.37 0.37 0.34 0.41\nFlat land 0.71 0.70 0.72 0.73 0.69 0.73\nGently sloped land 0.24 0.24 0.23 0.23 0.23 0.25\nIrrigated land 0.05 0.05 0.04 0.04 0.03 0.01\n**Crop choice:**\nTeff 0.32 0.29 0.36 0.35 0.48 0.29\nWheat/barely 0.21 0.20 0.22 0.21 0.24 0.26\nSorghum/maize 0.30 0.34 0.23 0.23 0.20 0.31\nPulses 0.13 0.12 0.14 0.16 0.04 0.10\nOilseeds 0.05 0.05 0.04 0.04 0.04 0.03\nNumber of observations 5443 3360 2083 1728 238 102\n_Source:_ Own computation from AU/WB/UG land tenure survey.\n_Note:_ Only plots with cereals, pulses and oilseeds included.\n\n\n\n19\n\nMention: \"AU/WB/UG land tenure survey\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"analyze\", \"summary\": \"Plot-level cereal, pulse and oilseed results are computed from this survey.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:004910:30:0", "occurrence_id": "34327645035b0c5951103f75", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: On the basis of 50 subsamples of 1012 observations, we get the results for _g_, numbers of\nmodels visited and model size presented in Figure 10. Results are now a bit different from\nthose in the growth applications, as a result of the much larger value of _n_ . In particular,\nthe Maruyama-George, Forte _et_ _al._ and Zellner-Siow priors as well as the case with fixed\n_g_ = _n_ lead to much higher posterior medians of _g_, a smaller number of models visited in\nthe chain and smaller mean model size than in the previous applications. Of course, all of\nthese priors depend on _n_, but it is interesting that the F-Z prior with _a_ = 2 + 2 _/n_ and the\nhyper- _g/n_ and horseshoe _/n_ priors are less affected. Of course, the benchmark priors and\nthe Bottolo-Richardson prior depend on _n_ through max _{n, k_ 2 _}_, which is here of the same\norder of magnitude as for the FLS data.\n\n\n\nlog ( g ) : Random θ, m = 7\n\n\n\nNumber of Models: Random θ, m = 7\n\n\n\nModel Size: Random θ, m = 7\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n1 2 3 4 5 6 7 8 9 11 13 15\n\n\n\n1 2 3 4 5 6 7 8 9 11 13 15\n\n\n\n1 2 3 4 5 6 7 8 9 11 13 15\n\n\n\n**Fig.** **10.** Tobias-Li data: log posterior medians of _g_, number of models visited\n\nand posterior mean model size.\n\n\nPrediction based on prediction subsamples of 178 observations each is summarized in the\nlower panel of Figure 7. Even though there is some variability in the posterior inclusion\nprobabilities of the regressor\n\nMention: \"FLS data\""}, {"role": "assistant", "content": "{\"role\": \"supporting\", \"usage_action\": \"validate\", \"summary\": \"The estimator's order of magnitude matches that found on these data.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:004911:21:0", "occurrence_id": "df5cc7fbfafc7d2e501ab422", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: 20\n\n\nget more or less allocations), and budget implementation (whether the allocations\ntranslated into better services or outcomes) appears to be almost entirely missing.\n\nThere _is_ evidence on a specific type of budget information which was\npioneered in the education sector in Uganda. Purposefully designed survey\ninstruments—named the Public Expenditure Tracking Surveys (PETS)—were used\nto measure discrepancies between budget allocations to schools in Uganda, and\nwhat actually reached the schools (Reinikka and Svensson, 2004). One study argues\nthat the publication in mass media of estimated “leakage” in the flow of funds led to\ndramatic improvements, with most of the intended funds reaching the schools\nsubsequent to the information campaign (Reinikka and Svensson, 2005). In this\nargument, accountability for the flow of funds improved because of addressing\ninformation gaps among parents in schools, and thus enabling them to exercise their\nclient power _vis a vis_ district authorities responsible for transferring funds to\nschools.\n\nFollowing the celebrated success of the Uganda case there has been a\nproliferation of PETS activities, and external investments in strengthening the\ncapacity of civil society organizations to undertake such surveys to uncover and\npublicize “leakage” and thereby stem it. More qualitative evaluations of these efforts\nsuggest that they can be frequently successful in getting the funds to reach the\nintended destinations, although to a lesser degree than the estimates in Uganda\n(McGee and Gaventa, 2010).\n\nHowever, alternate arguments about the drivers of success in the Uganda\ncase indicate that the client-power channel was only part of the story. Hubbard\n(2007) examines larger changes in school funding policies in the Ugandan Ministry\nof Education, and suggests that the information that activated client-power may\nhave been only one element in increasing the amount of resources available in\nschools; that other, perhaps larger, elements consisted of strengthening of the\ncompact between the Ministry and the districts following President Museveni’s\n1996 election campaign in which free and universal primary education\n\nMention: \"Public Expenditure Tracking Surveys\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"Purpose-built instruments measured gaps between allocations and receipts.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:004916:53:1", "occurrence_id": "713a784acba0bbc572eadced", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: u> 2,198 3,621\n\nPanel B: Women\n**Industry of main employment**\nRCA=0 RCA=1 Total\nAgriculture, Hunting and Forestry 48.2 56.28 53.04\nEducation 16.92 12.64 14.35\nSale, maintenance and repair of motor vehicles and 8.92 8.53 8.69\nmotorcycles, retail sales of automotive fuel\n\n\n\n8.85\n\n\n\n3.37\n\n\n\nSale, maintenance and repair of motor vehicles and 8.92 8.53 8.69\nmotorcycles, retail sales of automotive fuel\n\nHealth and social work 10.08 6.74 8.08\nPublic administration and defense 2.67 3.41 3.11\nManufacture of textiles 2.55 1.32 1.81\nHotels and restaurants 1.85 1.78 1.81\nManufacture of wearing apparel; dressing and dyeing of fur 0.81 1.4 1.16\nManufacture of food products and beverages 1.27 0.93 1.07\nSub-total 93.27 93.03 93.12\nN obs (total) 863 1,290 2,153\nSource: Author’s calculations using TLSS (2007). The industry is included in the table if it had more than 1% of\ntotal employment.\n\n\n\n8.92\n\n\n\n8.53\n\n\n\n52\n\nMention: \"TLSS\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"analyze\", \"summary\": \"Employment shares by industry above one percent are computed from this round.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:004940:8:0", "occurrence_id": "2bf780fa377204aa3b46b0e9", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: **Figure 2: Map of Budget Execution Rates**\n\n**of Capital Expenditures, 2009**\n\n\nSource: Authors’ calculations based on MEF data.\n\n\nWhile capacity and political economy considerations have been widely studied, the\n\n\nextent to which the budget size and allocation process, as well as needs, affect spending has\n\n\nbeen less investigated, in part because these features are more specific to the design of the\n\n\nPeruvian decentralization reform. Although they do relate to some extent to capacity, they\n\n\nhave relevance on their own: in fact, our empirical analysis suggests that budget-related issues,\n\n\nin particular the adequacy of the transferred budget with respect to the local capacity, are\n\n\namong the most important determinants of spending ability. This is of particular relevance for\n\n\nPeru, since capacity building and planning are long term investments, but the recent boom in\n\n\ncommodity prices and generous revenue sharing agreements have spurred transfers to some\n\n\nmunicipalities that may simply not be able to manage the sudden increases in revenues.\n\n\nBecause of some peculiar features of the Peruvian decentralization reform,\n\n\n7\n\nMention: \"MEF data\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"analyze\", \"summary\": \"Capital expenditure execution rates are computed from these finance ministry records.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:004946:15:1", "occurrence_id": "7817e75ca7f9d80894379218", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: In 2008, monetary policy\nwas tightening, the banks' lending interest rates remained almost unchanged, and the deposits\ninterest rates were increasing in order to attract additional sources after low deposit growth at the\ninitial stage of the world crisis. In 2009, the tightening of the monetary policy was only partially\nfollowed by the banks' interest rates. Like in 2008, the stronger reaction was again shown by the\nincrease of deposit interest rates (by 1.2 percent) relative to the increase of the average lending\ninterest rate (by 0.4 percent). In both years, the banks were reducing the interest rate spread,\n\n\n11 Different analyses within the NBRM for different analyzed periods have shown that only 2 to 10 percent of the\nmain monetary policy interest rate change was transmitted over average lending interest rates on the banks' denar\ncredits, in the same month or with a one month time lag. The accommodation of the short-run dynamics of the\nbanks' lending interest rates to their long-term equilibrium usually is slow.\n\n\n13\n\nMention: \"the NBRM\""}, {"role": "assistant", "content": "{\"role\": \"supporting\", \"usage_action\": \"source\", \"summary\": \"Analyses within this bank estimate limited policy pass-through.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:004950:31:1", "occurrence_id": "c4b8e5cd717feecb5fc08737", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: March 2006. In\n\n\norder to minimize exposure to the violence, and due to the security situation, the TLSS 2007 was\n\n\ninterrupted and resumed in January 2007. All households interviewed previously were re\n\ninterviewed. It is, however, still possible that some biases may remain. In particular, it is possible\n\n\nthat some of the results we obtain are not due to exposure to the 1999 violence but to exposure to\n\n\nthe civil upheaval in 2006.\n\n\nIn order to control for this potential exposure to the violence in 2006, we explore a variable\n\n\nin the 2007 dataset that captures whether an individual has been absent from home in the past 12\n\nmonths for security reasons. 27 Our calculations show that individuals who have been absent from\n\n\nhome for security reasons in 2006 are all residing in Dili. Therefore, we believe that this dummy\n\n\nreliably captures quite well the level of exposure to the 2006 violence.\n\n\n27 Those that declare being absent from home for security reason represents the 2.7 % of our sample.\n\n30\n\nMention: \"TLSS 2007\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"Fieldwork was interrupted by the security situation and resumed the following January.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:004956:1:0", "occurrence_id": "a7f80dce99cb0faad6052d9c", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: Policy Research Working Paper 5780\n\n### **Abstract**\n\nUsing a cross-section of more than 40,000 manufacturing\nand services firms in 79 developing countries from the\nWorld Bank’s Enterprise Surveys Database, this paper\nassesses how firm location determines the likelihood and\nextent of exporting in developing countries. Descriptive\nstatistics confirm higher export participation (but not\nintensity) for firms in core versus non-core regions,\ndespite the finding that firms in the core assess many\naspects of the investment climate more negatively.\nResults from a probit model show that, in addition to\nfirm-specific characteristics, both regional investment\nclimate and agglomeration factors have a significant\nimpact on export participation. Specifically, customs\nclearance and electricity quality matter for export\nparticipation for manufacturing firms. Although\nlocalization economies and export spillovers are\nassociated with increased exporting, the opposite is found\n\n\n\nfor urbanization economies for both manufacturing\nand services firms. The analysis finds that firm-level\ndeterminants of exporting matter more for firms located\nin non-core regions, while regional determinants and\nagglomeration economies play a larger role in core\nregions.\nThe findings point to the presence of congestion costs\nin the core, and suggest that policy interventions to target\nexport participation are likely to have a greater impact if\nthey are focused on core regions over non-core regions,\nwhere firm-specific factors predominate. Moreover,\nthe importance of export spillovers and localization\neconomies highlights the potential value of efforts to\nremove barriers to natural agglomeration both in core\nand non-core regions, for example through investments\nin infrastructure, the provision of social services, and\nregional integration arrangements.\n\n\n\nThis paper is a product of the International Trade Department, Poverty Reduction and Economic Management Network. It\nis part of a larger effort by the World Bank to provide open access to its research and make a contribution to development\npolicy discussions around the world. Policy Research Working Papers are also posted on the Web at http://econ.worldbank.\norg. The authors may be contacted at t\n\nMention: \"Enterprise Surveys Database\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"Over forty thousand firms across 79 countries test how location shapes exporting.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:005014:7:0", "occurrence_id": "69c45c21434858c59e3d3aeb", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: declining trend, in particular among the EU candidate and EU neighborhood countries, and in\nboth of these groups a decline in national savings ensued.\n\n\nThe case of emerging Europe also appears to be consistent with what economic theory\nwould predict: capital flows to high-growth countries (Figure 3; left chart). Hence, the allocation\npuzzle—that, paradoxically, capital flows to low-growth countries instead of high-growth\ncountries—does not appear true in Europe either. These figures also suggest that the underlying\nstrength of the link between foreign savings and growth might vary across groups. Still, an\nincrease in current account deficits (i.e., capital inflows that happen to be absorbed) and an\nincrease in growth are common among two of these country groups in emerging Europe (Figure\n3; right chart). The opposite is the case, however, among emerging markets outside Europe—that\nis, high growth in incomes occurs jointly with an increase in current account surpluses (i.e., the\nallocation puzzle holds).\n\n\n**Figure 3. Current Account Balances (% GDP) and Growth in Emerging Economies**\n\n\n\n\n\n\n\nSource: Authors’ calculations based on World Bank and IMF data (2011). Note: Period 1997-2008.\n\n\nIn terms of the composition, capital flows take the form of FDI, portfolio, and banking\n(or other) flows. Clearly, FDI in emerging Europe played a key role; it is particularly large across\nall three groups of emerging European countries and is positively correlated with growth (Figure\n4). This is even more evident in the period immediately preceding the crisis. But the most\ndistinctive feature is the large role played by banking flows, which comprise both wholesale\nfunding and financial FDI. The latter relates to the relationship between parent banks and their\nsubsidiaries. Indeed, no other region appears to experience such a degree of ―ownership-driven‖\ncapital integration. Financial FDI may well combine the best aspects of alternative financing\nsources; namely\n\nMention: \"World Bank and IMF data (2011)\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"External balances and growth over this period are computed from these sources.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:004969:10:0", "occurrence_id": "f837c2f3ed6b8e6ab1abccce", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: **Figure 6: Annual growth in modern and traditional services, 2000-08.**\n\n\n_Notes:_ Modern Services include communication, insurance, finance, computer & information, royalties and\nlicense fees and other business services. Traditional service are Transport, Travel, Construction, Personal, cultural\nand recreational services.\n\n\n**2.5** **Europe’s comparative advantage in service exports**\n\nNext we study the revealed comparative advantage (RCA), as defined by the share of a\nparticular export in a country‘s export basket compared to the share of that export in the global\nexport basket, in the three European groups. 4 EU-15 has RCA in services and the gap between\ngoods and services is increasing. NMS has also a comparative advantage in services (see Figure\n7). The gap to goods was large in the 1990s but has now decreased to the same level as in EU15. ACC did have a comparative advantage in services until early 2000s when it dropped and\nhas since had a comparative disadvantage in services.\n\n**Figure 7: Revealed comparative advantage in services and goods, for EU-15, NMS and ACC, 1990-007.**\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n_Source_ : Authors‘ calculation using Balance of Payments, IMF. 2011.\n\n\n4 Formally, the RCA index for country _C_ and product _J_ is defined as: _RCA_ _ECJ_ / _ECT_ / _EWJ_ / _EWT_ , where _E_ denotes exports, _T_\n\ndenotes all products, and _W_ denotes the world.\n\n\n9\n\nMention: \"Balance of Payments, IMF\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"Regional flow series are computed from this publication.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:005029:16:1", "occurrence_id": "6e2a9441201f826563721838", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: >0.44
0.44
0.50
0.09
0.29
0.27
0.44
0.18
0.38
0.02
0.14
0.44
0.50
0.12
0.32
0.37
0.48
0.26
0.44
0.17
0.38
0.03
0.18
0.04
0.19
0.12
0.32
0.18
0.38|\n\n\n\nSource: Own computations using June 2010 (EFSA II) surveys. Note:\nThe sample is restricted to the households residing in the six strata that\ncover areas directly affected by the earthquake. See Table 16 for a\ncomplete description of variables in directly affected and non directly\naffected areas.\n\n\n_(e)_ _Pre-earthquake conditions_\n\n\nTable 5 presents summary statistics by quintile of pre-earthquake wealth. The poorest\nhouseholds lived mostly in the East of the directly affected area (Léogane, Gressier, Jacmel, Petit\nGoâve, Grand Goâve and Croix-des-Bouquets). They were mostly agricultural households: 66%\nof them were practicing agriculture, compared to only 5% among the wealthiest, who were\nmostly concentrated in Port-au-Prince or Pétionville. The poorest households lived in houses\nwith no electricity and no toilets, and do not have access privately to water. They had no car and\n\n\n15\n\nMention: \"June 2010 (EFSA II) surveys\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"analyze\", \"summary\": \"Household statistics for the six strata are computed from this round.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:005030:23:0", "occurrence_id": "52306a326a34c2085ca99a21", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: of a foreign competitor, given the controls in our framework. 32 [^32: While Ayyagari et al. (2007) find that the presence of a foreign competitor matters for innovation, their\nspecification is quite different from ours: they test for the correlation of different business environment variables\nseparately rather than controlling for a number of key variables simultaneously as we do.] This empirical result is not\nunexpected -- in light of our discussion above of the logically ambiguous and countervailing\neffects of the degree of active competition on R&D investment and the resulting innovation.\n\n\n**_National-level market competitiveness variables_**\n\nTo explore the importance of national-level measures of the openness to competition of\nthe business environment, we follow the spirit of Loayza, Oviedo and Serven (2010) and\nDjankov, McLiesh and Ramalho (2006) by examining the associations between our innovation\nvariables and the aggregate national rank across regulations that affect all 10 stages of the life of\na business, as covered by the Doing Business Indicators (DB) (see the discussion in Section 3,\nabove).\n\n\nRather than replace the country-level fixed effects with the DB rank order variables as\nadditional explanatory variables in the existing firm-level regressions, we examine the rank\ncorrelation between the country-level fixed effects from the firm-level regressions and the DB\nvariables. A key advantage of this approach is that it overcomes the challenging interpretation\nproblem, both economically and statistically, of including a rank order variable in regressions\nhaving a mix of discrete and continuous variables. This approach also allows the relative\nimportance of the 10 constituent DB sub-indices to be examined, as the collinearity of the\nindividual DB variables does not conflate the econometric results when correlations are\nexamined one-by-one. We report correlation results only for innovation outcomes, as the fixed\neffects from employment growth and TFP reflect a broader and more various range of factors –\nincluding important cross-country differences in macroeconomic facets of growth in the case of\nemployment growth, and firm-specific knowledge and other assets that have built up over time in\nthe\n\nMention: \"Doing Business Indicators\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"Regulations across ten business stages are ranked using these indicators.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:005037:7:0", "occurrence_id": "57fcb7513cf72f5ff0670b94", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: —Insert Figure 1b—\n\n\nAlthough debt relief has brought the debt of HIPCs to sustainable levels and allowed these\ncountries to gain access to external financing, the evidence suggests that such countries remain\nsomehow credit constrained (for instance vis-à-vis other IDA countries that, despite their higher\ndebt ratios, could build a track record of creditworthiness). Furthermore, the new borrowing from\nprivate creditors to HIPC has come at high interest rates. The default risk premium that postMDRI countries have to pay on new debt can be measured by the spreads between the yields on\nthe dollar bonds issued by Ghana and Senegal and the yield on US Treasuries of the same maturity.\nFigure 2a shows that the yield spread on the Ghana bond has remained above 4% while the spread\non the Senegal bond has been even higher at 6.5%.\n\n\n—Insert Figure 2a—\n\n\nFurther evidence of the relative high interest rates at which post-MDRIs borrow comes from the\nGDF database. Figure 2b shows the simple mean for post-MDRI countries of the average interest\nrates that they pay on new public and publicly guaranteed debt from private creditors and from\noffi cial creditors. 6 [^6: Country data on interest rates are weighted averages of the interest rates on new debt commitments taken from\nthe GDF database.] While interest rates on concessional offi cial lending has remained below 2% over\nthe whole period, interest rates on private lending has fluctuated around 4% reaching 6% in 2007\nwhen new borrowing became available after the implementation of MDRI relief. 7 [^7: Evidence of higher borrowing costs would emerge from excluding bank credit covered by guarantees of exportcredit agencies.] More importantly,\nthere is no evidence that debt relief initiatives have brought about a reduction in the interest rate\non new private debt despite the fall in debt levels.\n\n\n—Insert Figure 2b—\n\n\nThis brings us to the critical question of our paper: Would it have been possible to design the\ndebt relief initiative so that markets could distinguish\n\nMention: \"GDF database\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"Average borrowing rates for relieved countries are shown in this database.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:005038:7:0", "occurrence_id": "d17f755fc37d8b772ac3067f", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: External Wealth of Nations Mark II database developed by Lane and Milesi-Ferretti (2007) as\n\n\nthe ratio of the sum of total financial assets and financial liabilities to GDP. Finally, we relied on\n\nCalvo and Reinhart (2000) to construct banking crisis and currency crisis. 2 [^2: The period from 2000 through 2005 represents a time of stable economic growth in most countries in our sample,\nalso known as the ―Great Moderation‖ (Stock and Watson (2002)). The exception to this is Argentina, where a crisis\nlasted from 1999 through 2002.]\n\n\nTable 1 [about here]\n\n\nTable 1 shows summary statistics for financial sector real value added growth rates\n\n\n(calculated as log differences of dollar amounts at 1995 prices) for each country. The mean\n\n\ngrowth rate for each country is positive; however, the series for 17 out of the 28 countries exhibit\n\n\nnegative skewness. These countries, mostly emerging markets, are: Argentina; Bolivia; Chile;\n\n\nColombia; Costa Rica; Denmark; Hong Kong SAR, China; India; Indonesia; Italy; Korea;\n\n\nMexico; Philippines; Singapore; Sweden; Thailand; United States; and Venezuela. In contrast, as\n\n\ncan be seen from Table 1, countries with positively skewed financial sector growth series include\n\n\nmostly OECD economies.\n\n\nFigure 1 [about here]\n\n\nFurthermore, the average level of kurtosis is higher for countries with negative skew in\n\n\nthe series (6.619 compared to 5.527). Figure 1 illustrates the significance of the difference in the\n\n\nskew via a probability plot. The difference is seen in a greater degree of deviation from the\n\n\nnormal distribution (Gaussian bell curve) in the tails of the distribution of financial sector growth\n\n\nrates for the subsample of countries with negative skew. The difference is substantial: for\n\n\ninstance, an annual growth rate of minus 20 percent in financial sector real value added has 0.0\n\n\nprobability of occurrence under normality, while the empirical probability in countries with\n\n\npositive skew is 0\n\nMention: \"External Wealth of Nations Mark II database\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"Net foreign asset positions are measured as financial assets less liabilities here.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:005042:40:0", "occurrence_id": "1fbbc70b056b222ccbef0af2", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: **Table 10: Household meal-consumption status during non-monga by membership status in safety-net program**\n\n**and receipt of support during non-monga (%)**\n\n\n\n\n\n\n\n16.4\n\n\n51.3\n\n\n32.4\n\n\n\n10.5\n\n\n59.0\n\n\n30.5\n\n\n\n8.5\n\n\n50.7\n\n\n40.8\n\n\n\n8.5\n\n\n50.9\n\n\n40.6\n\n\n\n**Total**\n\n\nStarvation\n\n\nMeal rationing\n\n\nFull meals\n\n\n\n6.4\n\n\n52.8\n\n\n40.8\n\n\n\n**No. observations** **38,476** **7,143** **695** **434,604**\n\n\n_Source_ : InM survey data (2006–07).\n\n\n39\n\nMention: \"InM survey data (2006–07)\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"Large-sample household observations come from this survey round.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:005052:6:3", "occurrence_id": "b814aaa72f89cc834d80e3d0", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: ss database includes a panel of firms. The panel feature allows us to tract\nfirms over time. It is also among the few databases that records annual information on firms’ product\n\n\n4 A formal proof of this relationship is presented in Klette and Kortum (2004).\n\n\n5\n\nMention: \"ss database\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"Its firm panel allows tracking the same enterprises over time.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:005058:72:2", "occurrence_id": "2f4e2d0dac264d3607e61f61", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: >239
16.4
11.6
14.4
7.9
84
62
94
9.2
6.8
10.3
147
140
137
10.1
9.6
9.4
2.0
2.4
1.6
18
16
7
2.0
1.7
0.8
29
29
16
2.0
1.9
1.1
42.4
41.9
367
547
62.2
59.9
798
775
54.7
53.2|\n|Total|544|
912
1456
|\n\n\n_Note: Multiple answers possible_\n\n_Source: Calculations based on the FinScope Survey 2009 data._\n\n\n\n\n\n\n\n\n\n**Table A1.15: Distribution of Credit Sources, by Gender, 2006 (percent)**\n\n|1.8.2|Credit sources, by gender|\n|---|---|\n|**_1.8.2 _**
|Male
Female
Total|\n|
Relative or friend
Rotating saving & credit group (UPATU)
Saving and credit co-\n\nMention: \"the FinScope Survey 2009 data\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"analyze\", \"summary\": \"Credit source distributions by gender are computed from this round.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:005061:11:0", "occurrence_id": "cec7abd306677ddb0c628e13", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: MOZAMBIQUE’S INFRASTRUCTURE: A CONTINENTAL PERSPECTIVE\n\n\n**Figure 2. Mozambique’s population, income, and mineral resources are concentrated in the center and south**\n\n\na. Population b. Poverty\n\n\nc. Topography d. Natural resources\n\n\n_Source_ : AICD Interactive Infrastructure Atlas for Mozambique (www.infrastructureafrica.org).\n\n\n6\n\nMention: \"AICD Interactive Infrastructure Atlas for Mozambique\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"Population, poverty, terrain and resource panels come from this atlas.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:005070:10:1", "occurrence_id": "ec3f84bc62ebde5424093a72", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: regulation (such as, the number of documents required to\n\n\n4 We also experimented with using an overall (weighted) tariff rate, average values over 2001 to 2005 and taken\nfrom World Development Indicators, World Bank. However, our main results did not change much on adding the\ntariff measure interacted with _Documents_ to any of the specifications discussed in the paper. In fact, our results for\nthe main interaction terms were strengthened by using the weighted tariff measure stated.\n\n\n9\n\nMention: \"World Development Indicators\""}, {"role": "assistant", "content": "{\"role\": \"supporting\", \"usage_action\": \"source\", \"summary\": \"Average weighted tariff rates over this window come from this source.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:005085:15:3", "occurrence_id": "4d58645adaa39e5426c6edfb", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: form, All coefficient statistically significant.|\n\n\nSource: Author‘s calculations based on LFS data sets from years 2003-2008.\n\n\nThe results presented in Table 5 are not surprising. At first the relative risk of transition to the\nsame state as in previous year is always much (even thousands in some cases) higher than to\nfull time/open term employment. Such high coefficients result from very low probability of\ntransition from full time/open term contract to any form of contract and also from low\nprobabilities of transitions from any other state to full time/open term contract.\n\n\nIn addition, the relative risk of transition to non-employment increases for any type contract\nother than a full time/open term one. What is most interesting is that this relative risk is the\nhighest for the self-employed. Partially it is a result of very low probability of transition from\nself-employment to full time/open term employment, but on the other hand it also means that\nif one treats the open term/full time employment as the ―ideal‖ state, engagement in selfemployment is in relative terms the ―worse‖ possible option with the highest risk to end up\nwithout any employment next year instead of reaching the goal. So it proves the earlier\nobservations drawn from the analysis of actual labor market transitions (Table 4).\n\nMention: \"LFS data sets\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"analyze\", \"summary\": \"Coefficients across this window are computed on these labour rounds.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:005088:35:0", "occurrence_id": "b44a5935d1205562d435f8d9", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: |Norway|6.44|2.50|3.94|\n|---|---|---|---|\n|**Poland**|n.r.|
9.60|
n.r.|\n|**Portugal**|n.r.|
8.10|
n.r.|\n|**Romania**|n.a.|
6.40|
n.a.|\n|**Slovak Republic**|16.53|
11.10|
5.43|\n|**Slovenia**|10.90|
4.90|
6.00|\n|**Spain**|24.00|
8.30|
15.70|\n|**Sweden**|6.88|
6.10|
0.78|\n|**United Kingdom**|n.r.|
5.30|
n.r.|\n\n\n_Source: Eurostat: European Union-Statistics on Income and Living Conditions (EU-SILC), own calculations_\n_Note: n.a. – data not available, n.r. – data not reliable due to divergent development in time or too low value_\n_compared with the unemployment rate._\n\n**_Informal employment in Europe: share of labor force working in small firms or being self-_**\n\n**_employed (%), 2006-2007_**\n\n|Col1|Workers in firms with less
than 10 employees
(% of labor force)|Col3|Self-employers
(\n\nMention: \"European Union-Statistics on Income and Living Conditions\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"Country figures with reliability flags are computed from this survey.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:005092:36:2", "occurrence_id": "05efbba5084d5378d902f356", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: J., and G. Sedlacek (1985). Heterogeneity, aggregation, and market wage functions: and\n\n\nempirical model of self-selection in the labor market. _Journal of Political Economy_ 93 (6):\n\n\n1077–1125.\n\n\nHeckman, J. and C. Pagés (2004). _Law and Employment: Lessons from Latin America and the_\n\n\n_Caribbean._ The University of Chicago Press: Chicago.\n\n\n[Heritage Foundation (2011). The 2011 Index of Economic Freedom, http://www.heritage.org/index/.](http://www.heritage.org/index/)\n\n\n35\n\nMention: \"2011 Index of Economic Freedom\""}, {"role": "assistant", "content": "{\"role\": \"supporting\", \"usage_action\": \"inform\", \"summary\": \"A reference-list entry for this index publication.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:005087:36:0", "occurrence_id": "57ab45fa94e12ab0b7e06da2", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: **_Perceived discrimination._** In a number of countries, estimated proportion of informal\n\n\nemployees who consider themselves belonging to a discriminated group, is well above similar\n\n\nproportion among both formal employees and informal self-employed (Figure 15), once again\n\n\nsupporting the hypothesis that exclusion or poverty escape motive plays an important role in\n\n\nthe way how employees end up working without a contract. Table 7 provides evidence that\n\n\nwithin European regions the differences between informal and formal employees are\n\n\nstatistically significant (at the country level the relevant sub-samples are too small).\n\n\n\n\n\n\n\n**Figure 15 Perceived discrimination among formal and informal workers,**\n\n**by country. 2004-2009**\n_Note:_ The sample size of employees without contracts is less than 30 for IT, SE and FI; between 50 and 90\n\nfor CZ, RO, SK, HU, EE, BE, FR, DE and CH; between 100 and 745 for other countries.\n\n_Source:_ Calculation with ESS data\n\n\n**_Union experience._** Another indicator which helps to understand where the informal\n\n\nworkers are coming from is trade-union membership (current or past). Informal workers with\n\n\nunion experience have clearly been working in the formal sector some time ago (and those\n\n\nwith current membership probably plan to return). Figure 16 compares union coverage\n\n\n(current or past) among formal and informal workers. It appears that transition from formal to\n\n\ninformal sector is quite common in Nordic countries, Cyprus, Israel, Belgium, Ireland, UK,\n\n\nGermany, and Austria, where from 35% to 80% of informal employees (and, except for\n\n\nCyprus, similar fractions for informal self-employed) come from the unionized sector. In\n\n\nIsrael, Greece, Portugal, and France these proportions are lower (around 20%), but still\n\n\nsimilar to the ones found among formal workers, again suggesting that the two sectors are not\n\n\nisolated from each other.\n\n\n35\n\nMention: \"ESS data\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"Country samples of varying size underpin the calculated indicator.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:005112:71:0", "occurrence_id": "73e27188386f788b650cd500", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: 111. The current account balance of a country reflects its savings-investment balance. The\nabove analysis explains China‘s large current account surplus. The reasons for the large and\ngrowing trade imbalance between the U.S. and China were, however, mainly the relocation of\nmany of the low value-added labor-intensive products from other East Asian economies to\nChina. The U.S. has long had a trade deficit with East Asia because of imports of labor-intensive\nproducts. This relocation concentrates the trade surplus of East Asia with the U.S. on China,\nwhich can be observed in the changing patterns of the United States‘ trade deficits with Japan\nand China from 1985 to 2009 (Figure 53).\n\n\n**Figure 53: Share of US-Japan and US-China Trade Deficits in Total US trade**\n\n**Deficit**\n\n50%\n\n\n45%\n\n\n40%\n\n\n35%\n\n\n30%\n\n\n25%\n\n\n\n20%\n\n\n15%\n\n\n10%\n\n\n5%\n\n\n0%\n\n\n\nChina\n\n\nJapan\n\n\n\nSource: United Nations Comtrade, World Integrated Trade Solution database; authors' calculations.\n\n\n112. This relocation as well as the regional integration through production networks also\ncaused China‘s trade deficit with other East Asian economies. Figure 54 illustrates the rising\nimportance of China in U.S. imports from East Asia. Related to this, Figure 29 above shows how\nChina‘s trade balance with other East Asian economies deteriorated, as China increasingly\nimported raw materials and semi-finished products from these countries. Many subcomponents\nof these commodities are produced in advanced countries and assembled in China, as a result of\nrelocation of labor-intensive production to China. Figure 55 shows the decomposition of the\nproduction of an iPhone assembled in China, which illustrates the small share of value added in\nChina versus inputs from other countries, notably Japan, Korea, Germany and the United States.\n\n\n70\n\nMention: \"World Integrated Trade Solution database\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"Share series over this span are computed from this portal's data.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:005135:13:0", "occurrence_id": "f3cf86791facf4bb4717696c", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: _V.II_ _Results: Sensitivity Analysis of poverty and inequality impact_\n\n\nAmong the modifications in the assumptions tested for robustness are the following: (a) allowing\n\n\nlayoffs in the formal sector but no wage reductions, and in the informal sector, allowing only\n\n\nwage reductions but no layoffs; (b) allowing formal sector layoffs and wage reductions but only\n\n\nwage reductions in the informal sector; (c) allowing layoffs in both the informal and formal sector\n\n\nand endogenously determining the wage reduction; (d) same as (b) but with no unemployment\n\n\nbenefits paid out; (e1) same as (b) but with a proportional tax to pay for the increased\n\n\nunemployment benefits; and (e2) same as (b) but with a proportional tax on households in\n\n\nquintile 4 and 5 to pay for the increased unemployment benefits. Based on discussions with\n\n\nvarious stakeholders in Latvia, model (b) was chosen as the preferred model.\n\n\nThe sensitivity tests concluded that the increase in poverty from 14.4 to 20.2 is very robust to\n\n\ndifferent scenarios (Figure 4) with one exception. If post-layoff incomes are not comparable to\n\n\nunemployment benefits that workers would be eligible to receive, the impact on poverty can be as\n\n\nhigh as 23 percent.\n\n\n**Figure 4: Sensitivity analysis of poverty simulations for various assumptions**\n\n\n\n\n\n\n\n\n\nSource: Authors calculations based on 2006 EU-SILC.\n\n\n\n12\n\nMention: \"2006 EU-SILC\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"analyze\", \"summary\": \"Poverty simulations under alternative assumptions run on this round.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:005157:10:0", "occurrence_id": "31d9d4714c7764e205444049", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: ernment consumption minus social security contribution and capital consumption\n\nallowances. Government investment spending is de…ned as development expendi\nture from the Ministry of Finance government spending accounts. The data on\n\ntax revenues, Tt, are also taken from the same source, and is de…ned as the sum\nof total indirect taxes, direct taxes on households, social security contributions\nand other capital transfers received. Finally Yt is the cyclical component of real\noutput extracted by a Hodrick-Prescott …lter. Following the de…nition laid out in\nStock and Watson (2002), growth below trend is classi…ed as a growth recession. 14\n\n\nThe real GDP data is taken from Abeysinghe and Gulasekaran (2004).\n\nThe ordering of the variables in Xt assumes that shocks in tax revenues and\nreal output have no contemporaneous e¤ect on government spending. As argued\n\nin Blanchard and Perotti (2002), this identifying minimum-delay assumption may\n\nbe a sensible description of how government spending operates given that in the\n\nshort-run government spending may be unable to adjust to spending in response\n\nto changes in the …scal and macroeconomic conditions. On the other hand, Barro\n\nand Redlick (2011) argue that the government spending shock in a structural VAR\n\nis likely to be endogenous, as a higher GDP leads to higher taxes and therefore to\n\nmore government spending. However, Barro and Redlick (2011) use yearly data\n\nand their argument, thus, is unlikely to hold at the quarterly frequency. Due to\n\ndecision lags, contemporaneous discretionary government spending is unlikely to\n\nrespond within a quarter to any news about the economy.\n\n\nThe identi…cation of tax shocks is more problematic in the framework outlined\n\nin this paper. As noted in Blanchard and Perotti (2002) identi…cation of tax shocks\n\ndepend on purging innovations in revenues of automatic responses to output.\n\nMention: \"data on\n\ntax revenues\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"Indirect and direct tax totals are taken from the same spending accounts.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:005168:40:2", "occurrence_id": "95a6d11769190fcd714f0454", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: 0.339 0.286 0.318\n\n**Note:** - significant at 10%, ** significant at 5%, *** significant at 1%\n\nSource: Worldwide Governance Indicators (WGI) project, Political Institutions Database DPI (2009) and Reinhart & Rogoff (2009).\n\n\n39\n\nMention: \"Worldwide Governance Indicators\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"Governance measures enter the regression alongside the institutional controls.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:005168:40:2", "occurrence_id": "d334199c235d60b70afc498f", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: 0.339 0.286 0.318\n\n**Note:** - significant at 10%, ** significant at 5%, *** significant at 1%\n\nSource: Worldwide Governance Indicators (WGI) project, Political Institutions Database DPI (2009) and Reinhart & Rogoff (2009).\n\n\n39\n\nMention: \"Political Institutions Database DPI\""}, {"role": "assistant", "content": "{\"role\": \"supporting\", \"usage_action\": \"source\", \"summary\": \"Its political variables are the companion source.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:005173:18:0", "occurrence_id": "e8616a0858d4dba2f68912d0", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: **5.** **VF Financial Information and Performance**\n\n\nThe discussion of VF performance begins with an examination of the financial position of Village Funds, as\n\nreported in the 2010 survey and summarized in Table 10. Information relevant to the balance sheet is given\n\nin the first two panels, and income and expenditure data near the bottom of the table. The first two columns\n\nof numbers show the median and mean amounts per village fund, _for those reporting values for these variables_ . The\n\nworking assumption is that when values are not reported, they are really zeros; thus, for instance, while the\n\nmean donation received by the 50 village funds that got funding from NGOs was 101,000 baht, this\n\nrepresents an average of just 2,000 baht per village fund when averaged over all VFs.\n\n\nBy far the most important source of capital is the initial contribution of a million baht by the government,\n\nwhich mainly occurred in 2002-2004. In the first couple of years of the VF, some Village Funds received\n\nadditional working capital from the government, which pushed the mean contribution up to 1.165 million\n\nbaht (for those Village Funds reporting). Two other sources of funding are relatively important: the first is\n\nborrowing from banks such as the BAAC. Over one in five Village Funds have borrowed from the\n\nestablished banks, and the median amount borrowed by these VFs was a million baht. The other important\n\nsource of capital is savings deposits by VF members, which averaged 161,000 baht, or about a tenth of total\n\nloanable funds.\n\n\nMost capital is used to lend to VF members, although at the time of the survey – May 2010 – about three\ntenths of all VF funds were held as deposits in the banking system. Some of this money was thus available\n\nfor loans later in the year – for instance, for emergency purposes – and some of it remained idle, in the sense\n\nof not being lent to villagers, for the\n\nMention: \"2010 survey\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"Village fund balance sheet positions are reported in this round.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:005185:14:2", "occurrence_id": "4a3dbb07914f2869292156fb", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: important during a crisis, as well as for consistency with the overall frequency of the dataset. However,\nQoQ data for inflation may result in extreme outliers, which we ameliorate by taking logarithms. Dropping these\ncases would potentially bias the results, since we lose valuable information from those observations. In any case,\nthe results reported here remain robust to either artificially limiting the inflation rate in these cases to 1,000\npercent, or dropping these observations entirely.\n\n16The measure of loan demand is from the Fed’s Senior Loan Officer Survey. The ECB collects comparable data\non loan demand faced by European banks, but we use the U.S. measure since U.S. banks lend less in developing\ncountries.\n\n\n13\n\nMention: \"Senior Loan Officer Survey\""}, {"role": "assistant", "content": "{\"role\": \"supporting\", \"usage_action\": \"source\", \"summary\": \"It supplies the measure of loan demand; the European equivalent is not used.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:005203:1:0", "occurrence_id": "859a8cb05433d56287d23627", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: Policy Research Working Paper 6030\n\n#### **Abstract**\n\nThis paper analyzes the impact of two distinct shocks\nstemming from the cross-border transmission of the\n2007-2009 crisis on credit availability for small firms.\nThe paper uses data from AccessBank Azerbaijan which\nwas affected in its liquidity position during the second\nand third quarters of 2008 by delays in its refinancing.\nThe Azeri real economy was hit by the global crisis from\nthe fourth quarter of 2008 onwards with a combined\ndecline in oil prices, exports, remittances, and domestic\ndemand. Therefore, a pure supply side shock con be\n\n\n\ncontrasted with a real economy shock that hit exactly\nwhen the bank’s funding position strengthened again.\nThe paper finds that during the _funding shock_ (potential)\nborrowers are discouraged from applying for loans.\nHowever, for those applications made, the likelihood of\nloan approval is not affected. The _real economy shock,_ in\ncontrast, reduces the approval likelihood for SME loans\nin particular, while agro and micro loans are considerably\nless affected. Finally, bank relationships increase credit\navailability in good as well as in bad times.\n\n\n\nThis paper is a product of the Finance and Private Sector Development Unit, Africa Region. It is part of a larger effort by\nthe World Bank to provide open access to its research and make a contribution to development policy discussions around\nthe world. Policy Research Working Papers are also posted on the Web at http://econ.worldbank.org. The author may be\ncontacted at gberg@worldbank.org.\n\n\n_The Policy Research Working Paper Series disseminates the findings of work in progress to encourage the exchange of ideas about development_\n_issues. An objective of the series is to get the findings out quickly, even if the presentations are less than fully polished. The papers carry the_\n_names of the authors and should be cited accordingly. The findings, interpretations, and conclusions expressed in this paper are entirely those_\n_of the\n\nMention: \"AccessBank Azerbaijan\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"Its records show how the crisis affected small-firm credit.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:005205:26:2", "occurrence_id": "9f97c88e1ab84227b7981b03", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: non-ag. wage 0.175 0.213 0.219 0.199 0.189 0.267\n…from non-ag. self 0.058 0.087 0.096 0.062 0.055 0.137\n…from remittances 0.309 0.348 0.387 0.299 0.412 0.256\n**Community char.**\nDist. to nearest bank (km) 4.009 3.753 3.914 4.070 5.201 2.784\nAccess to extension 0.203 0.241 0.206 0.313 0.216 0.200\nAccess to vet service 0.280 0.291 0.263 0.339 0.223 0.272\nMigration share in comm. 19.948 22.437 22.231 22.974 22.492 21.984\nShortage of labor in comm. 0.352 0.443 0.373 0.583 0.489 0.352\nShare of hhs with credit 0.319 0.478 0.397 0.617 0.511 0.424\nNo. of obs. 1480 316 201 115 177 139\n_Source:_ Own computation from 2005 Albania LSMS\n\n\n24\n\nMention: \"2005 Albania LSMS\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"analyze\", \"summary\": \"Household counts by group are computed from this round.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:005227:13:0", "occurrence_id": "81f67468961b0aa680b354f4", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: matching of children to parents allows us to estimate both sibling and intergenerational correlations\n\n\nfor the same sample of children. The second advantage of NFHS is that education data are more\n\n\ndetailed. Instead of reporting education level in discrete intervals as is done in the case of NSS,\n\n\nNFHS collected information on years of schooling for both parents and children, which facilitates\n\n\nmore precise estimates of sibling and intergenerational correlations.\n\n\nTo define the estimation sample, we follow the literature and restrict our sample to closely\n\n\nspaced young adult siblings between the age of 16 and 27 years. The argument for estimating sibling\n\n\ncorrelations from closely spaced siblings rests on the fact that there may be important changes in the\n\n\nfamily structure as well as shocks to family life over a longer time horizon diluting the already\n\n\nconservative estimate of family background on children‘s outcome. To check the sensitivity of our\n\n\nresults, we report the estimates of sibling and intergenerational correlations for other age groups also.\n\n\nWhile the sample for estimation of the sibling correlations should ideally focus on co\n\nresident children, it may bias the estimation of intergenerational link in education between parents\n\n\nand children. If, for example, among older children, the best educated ones tend to leave household\n\n\nearlier than less educated children, it may bias intergenerational regression coefficient β downward,\n\n\nbut may not necessarily bias the estimate of intergenerational correlation. Because such exit of better\n\n\neducated children from the household would also reduce the variance in children‘s education, thus\n\n\noffsetting the decline in the intergenerational regression coefficients.\n\n\nThe problem of not observing all of the children as co-residents in the household is more\n\n\nprevalent in the case of older age cohorts, particularly for women who usually leave their natal\n\n\nhousehold upon marriage. In the case of women, if educated women delay marriage and we have\n\n\nbetter probability of observing them as co-resident children, then estimate of intergenerational\n\n\ncorrelations from our sample may be biased upward. On the other hand, if marriage timing follows\n\n\nbirth order and there is a substantial birth order effect as reported in\n\nMention: \"NFHS\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"Its more detailed education data aid the intergenerational analysis.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:005228:18:0", "occurrence_id": "356b168fdc962c7bfb46fb04", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: The evolution of unpaid family work has been strongly gender biased. The increase in the\n\n\nshare of unpaid family work in employment was due to the increase of women’s\n\n\nemployment in this type of work. The share of working women in this type of\n\n\nemployment went from 13.8 percent to 22.2 percent of employment between 2007 and\n\n\n2009, while the share of men’s employment remained around 11.8 percent. Women\n\n\nshifted from own-account work into unpaid family work and to some extent into wage\n\nemployment and to a small extent into being employers (Table 14). 4 [^4: Nguyễn et al (2010) suggest that the shift between own-account work and unpaid family work may be due\nto misallocation of women between the two, very similar, categories.]\n\n\n**Table 14: Structure of employment for working age population (15+) in 2007 and 2009 (%)**\n**2007** **2009**\n**All** **Male** **Female** **All** **Male** **Female**\nEmployer 3.2 3.8 2.7 4.8 6.3 3.2\n\n\nSelf-account worker 53.5 48.55 58.6 44.7 42.6 46.9\n\n\nUnpaid family worker 12.9 11.8 13.95 16.8 11.8 22.2\n\n\nWage worker 30.0 35.4 25.45 33.4 38.9 27.5\n\n\nMember of cooperative 0.1 0.2 0.1 0.1 0.2 0.1\n\n\nOthers 0.2 0.25 0.2 0.2 0.3 0.1\n\n\nTotal 100.0 100.0 100.0 100.0 100.0 100.0\n\n\n_Source: (LFS, 2007, 2009)_\n\n\nThis gender bias is also translated\n\nMention: \"LFS\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"Distribution shares across these two rounds give the gender bias.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:005229:3:0", "occurrence_id": "09d43bb4d0f5365e6fdec955", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: 2\n\n\n**1** **Introduction**\n\n\nInfant and under-5 mortality has declined markedly in Sub-Saharan Africa during the last decade.\n\n\nAmong the 20 Sub-Saharan African countries that have conducted Demographic and Health\n\n\nSurveys (DHS) since 2005, 18 countries showed improvements in infant survival since the\n\n\ncountry‘s previous survey, and broad improvements have taken place in under-5 mortality as\n\n\nwell. The Millennium Development Goal for under-5 mortality is a reduction of two-thirds over\n\n\nthe 25 year period 1990-2015, which implies an annual rate of decline of 4.4 percent; twelve of\n\n\nthe 20 recent DHS countries have rates of decline that exceed this rate. For infant mortality,\n\n\nKenya stands out among the success stories, with an annual rate of decline of 7.6 percent, the\n\n\nhighest among the 20 countries.\n\n\nThe gains in infant mortality are just one element of a wide set of improvements in human\n\n\nwelfare in Kenya and many countries in Sub-Saharan Africa. In one review of these changes,\n\n\nRadelet (2010) argues that five fundamental changes have driven the broader turnaround in the\n\n\n―emerging African countries‖ that he profiles: 1) more democratic and accountable governments,\n\n\n2) more sensible economic policies, 3) the end of the debt crisis and major changes in\n\n\nrelationships with the international community, 4) new technologies that are creating new\n\n\nopportunities for business and political accountability, and 5) a new generation of policymakers,\n\n\nactivists, and business leaders. Accompanying these changes has been a new push by\n\n\ngovernments and the international community to implement public health initiatives, including\n\n\nthose advanced by the Gates Foundation, the Global Fund to Fight AIDS, Tuberculosis and\n\n\nMalaria, as well as other organizations.\n\n\nMillions of dollars have been poured into these initiatives, many of which have been shown to be\n\n\neffective on a small scale in randomized controlled trials. However, given the challenges of\n\n\ngovernance and large-scale implementation in many countries, the effectiveness of such\n\n\ninitiatives\n\nMention: \"Demographic and Health\n\n\nSurveys\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"Eighteen of twenty countries show improved infant survival in these rounds.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:005233:19:1", "occurrence_id": "229f4bfaceb0bb9c28056ae2", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: **_k_** indexes the 4-digit industries within the 3-digit industry _j_ and\n**Ek-1** **_Ykt_**\n_Y_ refers to employment.\n\nData on trade policy are obtained from Das **(2003).** The author computes the effective\n\nrate of protection _(ERP)_ for 3-digit Indian manufacturing industries in four sub-periods:\n\n**1980-81** to **1985-86,** **1986-87** to **1990-91,** **1991-92** to **1994-95,** and **1995-96** to **1999-00.23** We\n\nalso use tariff data from Topalova and Khandelwal (2011) which are available for every year\n\nbut only from **1987** to **1999** therefore reducing our sample size. However, these data have rich\n\ncross-sectional and time-series variation **-** which the ERP data lack. We estimate all our main\n\nspecifications with both measures of trade protection. We use the FDI deregulation variable\n\nfrom Sivadasan **(2009)** which is a dummy variable indicating which 4-digit industries were\n\nFDI-deregulated in **1992.24** We combine this dummy variable with the **ASI** data to calculate\n\nthe proportion of employment in a 3-digit industry that was exposed to FDI. Hence, our\n\n**_Nj_**\nmeasure of FDI deregulation is given by _FDIjt_ _FDIktyt_ where **_k_** indexes the 4-digit\nindustries within the 3-digit industry **_j_** and _Y_ refers to **Ek=1** employment.Ykt\n\n23Das\n\nMention: \"ASI\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"analyze\", \"summary\": \"Combined with a deregulation dummy it yields exposed employment shares.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:005242:16:0", "occurrence_id": "d8277ab25c568c29f95a65db", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: such regimes the availability of substantial resources is more likely to be channeled in ways that\n\n\ndeter rebellion (the military and rents), plausibly countering the grievances generates by natural\n\n\nresources and rebels’ viewing of such resources as a prize for taking over the state.\n\n\nFollowing the theoretical discussion we derive two hypotheses:\n\n\n_H1: Presence of natural resources increases the risk of civil war for semi-democratic and_\n\n\n_unstable regimes and states where leaders appeal to ethnicity in order to govern._\n\n\n_H2: While coup risk increases the risk of rebellion, natural resource rents allow high coup d’état_\n\n\n_risk regimes to lower the risk of civil war._\n\n\n**3. Data and research design**\n\n\nWe use two alternative definitions for civil war onset, based on widely used measures in the\n\n\nliterature: Fearon and Laitin (2003) and the Prio/Uppsala data (Gleditsch et al. 2002) for years\n\n\n1946-2003. The Fearon and Laitin definition captures the onset of large scale civil wars, coded\n\n\nusing a threshold of 1000 battle deaths over the course of conflict with a yearly average of at\n\n\nleast 100 deaths. This data is updated to 2003 using Fearon (2011). The Prio/Uppsala measure\n\n\ncaptures the onset of smaller scale conflict, earlier onsets for the large scale conflicts and flare\n\nups of violence in a dormant conflict. This definition uses a lower threshold of 25 battle deaths\n\n\nper year and we use the Lujala (2010) as a data source. The dependent variable is coded 1 for\n\n\ncountry years with a civil war onset and 0 in all other cases, and we do not eliminate the\n\n\nobservations with an ongoing civil war.\n\n\nWe attempt to measure state weakness in ways that capture the theoretical account. To\n\n\ncapture mixed regimes we use the same indicator variable for anocracy as Fearon and Laitin\n\n\n(2003) based on Polity IV scores. An\n\nMention: \"Prio/Uppsala data\""}, {"role": "assistant", "content": "{\"role\": \"supporting\", \"usage_action\": \"source\", \"summary\": \"Its conflict onset definition over this span is one of two standard measures.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:005246:11:0", "occurrence_id": "6348250dce681f6e3b1fc97f", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: **Figure 4. Average Proportion of Own-Source Revenue to GRDP 2008 and 2010:**\n**Provinces (Provinsi), Districts (Kabupaten), and Cities (Kota)**\n\n\n_Undermining agreements with special autonomy regions._ The Government of Indonesia (GOI)\nhas entered into special arrangements with Aceh, Papua and Papua West and allows them a\ngreater share of resource revenues through the tax sharing system. The DAU offsets a large part\nof those gains by including 95% of those gains as increases in fiscal capacity for the provinces\nand 63% for cities and districts. Thus the GOI taxes back most of the gains to resource rich\nregions through the operation of the DAU formula.\n\n_Incentives for local governments to serve as employment creation agencies to the neglect of_\n_their role as service providers._ The basic allocation provides financing for public sector wages.\nThis creates incentives for padding up local rolls. Such perverse behavior in Indonesia is\ncircumvented by central controls over local recruitment and staffing. But this takes away local\nautonomy for hiring and firing and setting terms of employment of local employees. It also ties\nlocal governments to the personnel policies of the central government taking away any\nincentives they might have to experiment with new public management paradigms to improve\naccountability for servicer delivery performance e.g. through contracting out or partnership\narrangements within and beyond government agencies. In short, wages compensation creates\nan incentives and accountability regime that works against good local governance.\n\n_Inappropriate indicators of fiscal need._ Beyond basic allocation, formula based expenditure\nneeds determination as done in Indonesia has important limitations. Regional per capita income\nis used twice as a need factor—real per capita GDP adjusted for purchasing power parity in the\nformation of the Human Development Index and nominal per capita GDP more directly.\nRegional per capita income is an imperfect measure of fiscal capacity but not a very useful\nmeasure of fiscal need. The\n\nMention: \"the Human Development Index\""}, {"role": "assistant", "content": "{\"role\": \"supporting\", \"usage_action\": \"source\", \"summary\": \"Its purchasing-power-adjusted income measure serves as the need factor.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:005255:8:0", "occurrence_id": "cca740b20d711d689fed0162", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: , then the OLS estimate of β (namely, RIF-OLS estimator) provides a consistent\nestimator of the marginal effect on the unconditional quantile of a small location shift in the\ndistribution of X, holding else constant. So, one can decompose any two distributions at\nquantiles in a similar spirit as Oaxaca-Blinder approach. It is worth noting, however, that the\nassumption of linearity used in implementing this detailed decomposition implies that the\noutcome distribution depends on the marginal distribution of covariates only through their mean\n(Rothe 2010b).\n\nThe decomposition of test score change over-time can be rewritten as 3 [^3: Since and, taking expectations on both sides yields .\nSo, .] :\n\n\nwhere and are approximation errors that appear because of the first order approximations\nand the assumption of linear specification. They are calculated as differences between the\naggregate explained effect and the total composition effect:, and that between\nunexplained component and the total coefficients structure effect: .\n\nAn identification problem exists in this sort of detailed decompositions as pointed out by Oaxaca\nand Ransom (1999), as the coefficients effect is not invariant to the choice of reference group;\nthis problem has no easy solution. One approach is to derive results using more than one\nalternative reference group. The other is to use one of the solutions suggested to deal with this\nproblem. We used the averaging approach proposed by Yun (2005).\n\n**3.** **Data and Summary Statistics**\n\n_3.1._ _Data_\n\nWe used the Trends in International Mathematics and Science Study (TIMSS) data for 8 th grade\nGhanaian students. TIMSS is an international assessment conducted every four years in order to\ngenerate information about trends in mathematics and science achievement in each country and\nover time. The age of tested student population is 9 to10 years (4 th grade) and 13 to 14 years (8 Pseudo R2 0.176 0.176 0.0905 0.0907\nSource: MHYS 2009-2010. Probit estimations. Marginal effects, evaluated at sample means for continuous variables, are\nshown. Standard errors in parentheses: *** p<0.01, ** p<0.05, * p<0.1. The reference groups is rural unmarried youth aged 1519 without any education (for model 1 and 2 add female)\n\n\n\nWe would expect youth who wish to migrate abroad to be unsatisfied with domestic labor market\nconditions and suffer from stronger feelings of deprivation. Interestingly, employment status in itself is\nnot a significant predictor of the wish to migrate. However, relative labor deprivation among men is\n\n\n6 Specifying the above regression as a probit with the dependent variable being defined as satisfied/dissatisfied\n(1/0) yields results that are similar in interpretation.\n\n\n21\n\nMention: \"MHYS 2009-2010\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"analyze\", \"summary\": \"Probit marginal effects are estimated on this household round.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:005264:12:0", "occurrence_id": "ed4123466097a2c1964a2c2a", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: however, considerable variation in these demographic variables despite being drawn from the\n\n\nsame population of tobacco farmers in central Malawi.\n\n\nThe summary statistics reveal important features of participants’ wealth and income. When\n\n\ncompared to typical households from low-income countries, the households in the sample are\n\n\npoor. In the central Malawi region we study, however, tobacco farmers have similar poverty and\n\nincome levels to those of non-tobacco-producing households. 22 [^22: Based on authors’ calculations from the 2004 Malawi Integrated Household Survey (IHS), individuals in tobacco\nfarming rural households in central Malawi live on PPP$1.48/day on average, while the average for central\nMalawian rural households overall is PPP$1.51/day.] At the time of the baseline\n\n\nsurvey, the median participant’s household has zero balances in a formal bank, and the 90th\n\n\npercentile of the bank balance distribution is just 700 Malawi Kwacha (henceforth MK), or\n\napproximately US$4.67. 23 [^23: At the time of the study, the relevant exchange rate was roughly 150 MK per US dollar.] The survey also inventoried the household’s non-cash assets\n\n\nincluding livestock and agricultural and household durables; and participants were asked to\n\n\nestimate how much they could earn by selling those assets. When we include the self-reported\n\n\nvalue of these assets, we find that the median household held just 4,446 MK of wealth and the\n\n\n90th percentile held 25,800 MK.\n\n\nSince the baseline was conducted during the rainy season, several months would elapse\n\n\nbefore the cash crop or primary staple (maize) would be ready to be harvested in mid-April or\n\n\nearly May. The summary statistics bear this out. The median household expects virtually no\n\n\nincome between the interview date and April 2010.\n\n\n**2.3** **Stage One: Choices Under Commitment**\n\n\nFigure 3 presents the timeline of the experiment. Upon initiating the interview, the\n\n\nhousehold\n\nMention: \"the 2004 Malawi Integrated Household Survey (IHS)\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"Its calculations give daily consumption for tobacco-farming households.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:005309:27:0", "occurrence_id": "86010abe3bfc36a728eff682", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: **3.4 Tangible versus intangible investment in Brazil**\n\n\nFigure 10 compares tangible and intangible investment in Brazil. 21 [^21: Note that for reasons of comparability with tangible investment, the chart shows estimates of intangible\n_investment_, and not expenditure. CHS and similar papers also present the same comparison of business tangible and\nintangible investment.] Compared to gross fixed capital\n\n\nformation (GFCF) in Brazil, which has ranged between 15-18 percent of GDP during 2000-2008,\n\n\nintangible investment is a small share of GDP. However, GFCF includes non-business tangible\n\n\ninvestment (such as government and household investment, and a part of infrastructural investment), so it\n\nis strictly speaking comparable to our estimate of intangible investment. 22 [^22: Source of GFCF Data: National Accounts] So we have also presented an\n\n\nestimate of business tangible investment, estimated from IBGE's surveys on Industry, Services,\n\n\nCommerce and Construction Industry using data on acquisitions and improvements to the firms‘\n\n\npermanent assets. Our estimates indicate that the ratio of tangible to intangible investment in Brazil‘s\n\n\nfirms is close to 1, which is lower than that reported for for the US and the UK, but comparable to that\n\n\nreported for some other advanced economies like France and Germany(CHS, 2004; Marrano and Haskel,\n\n\n2006). It is, however, markedly higher than China‘s ratio, which is estimated to be 0.2 (Hulten and Hao,\n\n\n2011).\n\n\nThere is some hint that in recent years, growth in intangibles has fallen behind that in tangibles. A caveat\n\n\nto this observation is that that the particularly sharp increase in business tangible investment after 2007\n\n\nappears to be associated with a revision of IBGE's methodology for their surveys on Industry, Services,\n\n\nCommerce and Construction Industry. However, even the GFCF series – which should not have been\n\n\naffected by this methodological revision –shows a markedly higher post-2005 rate of growth than\n\n\nintangible investment.\n\nMention: \"IBGE's surveys\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"analyze\", \"summary\": \"Tangible business investment is estimated from surveys across four sectors.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:005314:19:0", "occurrence_id": "54e9ff0953f595e5883f3476", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: Although the total number of non-production workers is about one-fifth of production workers’\n\n\nin the data and the number is stable for the entire sample period, household data from _Susenas_\n\n\nshow that the estimated share of non-production workers (ages 15-65) in the manufacturing\n\nsector in 2006 is non-trivial, about 47%. Tables 3A, 3B, and 3C summarize the results using the\n\n\nlog of paid non-production worker employment as the dependent variable for all firms, small\n\n\nfirms, and large firms, respectively.\n\n\n**Table 3A: Employment Effects of Min. Wages on Non- Prod. Workers - All Firms**\n\n\nDependent variable: Log (Number of paid non-production workers)\n(1) (2) (3) (4)\nLog (Min. Wage) 0.5997*** 0.3341*** -0.0585*** -0.0542**\n(0.0402) (0.0357) (0.0211) (0.0255)\nLog (Firm Age) 0.1969***\n(0.0101)\nForeign Share 0.0012***\n(0.0003)\nExport Share 0.0007***\n(0.0001)\nGovt. Share 0.0007***\n(0.0003)\nFixed Effects No Province Firm Firm\nYear Effects Yes Yes Yes Yes\nObservations 233,512 233,512 233,512 160,013\nNumber of firms 32,390 32,390 32,390 30,945\nR-squared 0.0093 <\n\nMention: \"Susenas\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"Its household data give the stable share of non-production manufacturing workers.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:005332:9:0", "occurrence_id": "9daf318496a8279ede614f0b", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: Most migrants (40 percent), regardless of their origins and destinations, migrate to accompany\nsomeone. Marriage is the second most frequent reason for migration in any direction; with the\nexception of rural to urban migration where 26.6 percent migrants move to seek work.\n\n\nTable 7 – Direction of Migration and Reasons\n\n\nDirection of Migration\nReason of Migration Urban-Urban Urban-Rural Rural - Urban Rural - Rural\nFor work only 18.8 16.3 26.7 17.5\nEducation 1.3 0.3 0.7\nMarriage 33.3 33.9 23.4 28.1\nAccompany 40.9 40.2 42.1 45.2\nOthers 5.7 9.5 7.2 9.2\nTotal 100 100 100 100\nSource: Authors’ calculations using Labor Force Survey\n\n\nMost men migrate either to work or accompany another migrant (more than one-third each).\nEmployment is the reason behind migration from rural to urban localities (53 percent) as well\nas from one rural area to another. Women mostly migrate because of marriage or to\naccompany a migrant. The percentage that migrates for work is negligible (see Tables A3 and\nA4 in the appendix).\n\n\n**Internal Migration – Labor Mobility**\n\n\nThose who migrate to work are mostly males (97.8% of migrants to work are males while 2.2%\nare females), and the distribution of these migrants by level of education is multimodal (Table\n8): the biggest fraction is composed by illiterate workers (26%) and starts decreasing gradually\nwith the level of attainment until it reaches the technical secondary level (25%), and then the\nuniversity level at 17%.\n\n\nTable 8 – Educational Attainment of Migrants (for work only)\n\n\nEducation level Percent\nIlliterate 26.1\nRead & write 13.0\nLess than Intermediate level 10.2\nGeneral Secondary 2.7\nTechnical Secondary 25.3\nAbove Intermediate level 4.4\nUniversity 17.1\n\nMention: \"Labor Force Survey\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"analyze\", \"summary\": \"Migration reasons and occupational shares are calculated from this survey.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:005353:7:0", "occurrence_id": "ab34257768e254b6faaa5350", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: CLICROP was run at a 1°×1° resolution (i.e., 111 square kilometer grids in a country\nmeasuring 945,000 square kilometers). Separate models were developed for the 9 major crops of\nTanzania (i.e., cassava, groundnuts, maize, millet, potatoes, sorghum, soybeans, sweet potatoes\nand wheat). Predicted yields for each sub-national region are calculated as the sum of overlaid\ngridded results weighted by geographic area. CLICROP was calibrated to information on soil\nparameters from the FAO Soils Database (e.g., field capacity, wilting point and saturated\nhydraulic conductivity) (FAO-UNESCO, 2005). Regional information on crop growing seasons\nand planting dates were provided by Sacks et al. (forthcoming). Finally, crop locations were\nbased on You et al. (2006) for the year 2000, and crop parameters were drawn from Allen et al.\n(1998) and Doorenbos and Kassam (1979). Overall, the process is detailed with more than 13\nmillion potential simulation sets. 3 [^3: The product of approximately 8500 grids times nine crops times 43 crop years times four climate scenarios.]\n\n\n_Crop modeling results_\n\n\nAlthough CLICROP analysis was conducted for nine crops, we focus on the results for maize for\npurposes of exposition. Maize is the principal food crop in Tanzania, representing 35 and 45\npercent of calories consumed by poor urban and rural households, respectively (Pauw and\nThurlow, 2010). Tanzanian farmers allocate about one-third of their crop land to growing maize,\nmainly without the use of irrigation. Deviations in dry-land maize yields therefore provide a\nfirst-cut indicator of food availability in Tanzania (Thornton et al. 2009). In addition, the\nimplications of climate outcomes for maize are likely to be similar for sorghum and millet,\nmaking the coverage of caloric sources and land use, particularly for more vulnerable\npopulations, even broader.\n\n\nTable 2 summarizes the deviations in mean maize\n\nMention: \"the FAO Soils Database\""}, {"role": "assistant", "content": "{\"role\": \"supporting\", \"usage_action\": \"source\", \"summary\": \"Soil parameters calibrate the crop model.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:005355:13:0", "occurrence_id": "8a3ce85d1f9f0ee433846148", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: |El Salvador|National Development
Plan 2010-2014|X|Col4|\n|---|---|---|---|\n|Mexico|Vision 2030|X|X|\n|Panama|National Concertation|X||\n|Peru|National
Competitiveness Plan
2003-2010
National
Competitiveness
Agenda
|
X
X
||\n|Uruguay|Industrial
Development
Strategy (2008)
Sectoral
Industrial
Plans (2011)|
X
X|
X
X|\n\n\n*Discontinued by the current government\n\n\n\nSource: The authors based on Official Data\n\n\nTable 2 also shows that some of the strategies combine with promotion of new activities, which\nwould fall into the Hausmann, Rodrik and Sabel industrial policies “in the large”. However,\nmany of these more ambitious initiatives are “in the large ‘ _light_ ’ ”, i.e., they are not grand bets\ndistant from existing comparative advantages or learning capabilities. As an illustration, Table 3\nlists the initiatives in Colombia for productive transformation that aim to build capacities\nleading to new world class sectors/activities in that country. In Chile, the 2007 innovation\nstrategy’s push for new activities was focused on cluster development of eight carefully\nselected sectors, but most are based on activities close to country’s abundant natural\nresources 14 .\n\n\n14 The current government, which entered power in 2010, suspended the strategy launched by the opposition.\nThe National Innovation\n\nMention: \"Official Data\n\n\nTable 2\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"Government strategy records, some discontinued by the current administration.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:005371:5:1", "occurrence_id": "78fcf45902a5ce99fa362797", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: . 4 Finally, on key water, sanitation, and health indicators the study sample meets or exceeds the\n\n\nnational level statistics. Ninety-six percent of households have access to an improved water source, 68%\n\n\nimproved sanitation, 81% a place for handwashing with soap and water available, and just 14% of children\n\n\nunder two are stunted at baseline.\n\n\nVietnam was selected for the HWWS project due to its engagement in handwashing promotion under the\n\n\nPublic Private Partnership for Handwashing (PPPHW), a global handwashing initiative established in 2001.\n\n\nHandwashing promotion activities began in 2006 under the name of the Handwashing Initiative (HWI) with\n\n\nvarious partners including the Vietnam Ministry of Health, Women‟s Union and WSP. The HWWS\n\n\nproject sought to improve and scale-up these efforts through capacity building of local organizations, such as\n\n\nthe Vietnam Women‟s Union, training them in behavior change approaches, and providing technical support\n\n\nfor development of behavior change communication campaign materials. WSP-supported HWWS activities\n\n\ntargeted at caregivers and schoolchildren have been underway since 2007 in 7 provinces. These activities had\n\n\na target of reaching over 2 million mothers and children with the goal of improving the handwashing\n\n\n3 MDG 4 seeks to reduce infant and child mortality by two-thirds\n4 Vietnam Population and Housing Census, 2009\n\n4\n\nMention: \"Vietnam Population and Housing Census, 2009\""}, {"role": "assistant", "content": "{\"role\": \"supporting\", \"usage_action\": \"inform\", \"summary\": \"A footnote listing this enumeration as a source.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:005372:37:0", "occurrence_id": "13d5afeae7ebe5bd5d7ed28c", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: particles. In particular, PM10 has an impact on the respiratory diseases. The most\nwidely known adverse health impact of PM10 is premature mortality. Long-term\nexposure to PM10 can impact mortality and morbidity levels. Levels of particulate\nmatter are often much higher in developing countries as compared to those in developed\ncountries. Ostro (1994) coefficients are used to calculate PM10 health effects.\n\nSince PM10 causes premature death, one of the implications of high PM10 levels in the\ncountry would be a decrease in the available labor force. With a large population the\neffect on mortality rates and on the labor force are calculated using estimates from the\nJakarta study (Ostro, 1994). The health damages calculated outside of the CGE model\nproduced central, upper and lower estimates for the coefficients of change in mortality.\nAll three figures have been used to calculate a range of results in the CGE simulations.\n\nAs for the PM10 emissions, the projections from the CGE results have been used to\ncalculate the PM10 concentrations for India. The base year concentration level of\n97.58 g/m 3 is the average concentration level of the pollutant across all cities in India\n(calculated using Central Pollution Control Board of India data). The concept of\nuniform rollback was used to calculate the concentrations for the subsequent years.\nUniform rollback states that the percent change in pollutant emissions on an annual\nbasis will equal to the percent change in pollutant concentrations on an annual basis.\nTherefore, using the base year average for PM10 for the year 2010, projections can be\nmade for PM10 concentrations using the percent change in PM10 emissions from the\nCGE model.\n\nThe dose response coefficients are from the Ostro study on Jakarta (Ostro, 1994). Such\nan epidemiological study has not been carried out for India Jakarta is the next best study\nas its data provide more plausible health estimates than data from industrialized\nnations. For the\n\nMention: \"Central Pollution Control Board of India data\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"Average pollutant concentrations across cities are calculated from these records.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:005406:19:0", "occurrence_id": "aba80df1c1ae08371532633f", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: - _Factor-shift effect:_ Post-regulation production technologies may be more or less\n\nlabor intensive, as more /less labor is required per dollar of output.\n\n\nMorgenstern, Pizer and Shih (2002) empirically estimate a model incorporating these\ndifferent effects of regulation on employment for four highly polluting/regulated\nindustries using data for the period 1979-91. Importantly, they measure regulation by the\nplant’s expenditures on pollution controls, as self-reported in the Commerce\nDepartment’s survey on Pollution Abatement Control Expenditures (PACE).\n\n\nWhile there are some differences across the four industries, Morgenstern et al. find that\nincreased abatement expenditures generally do _not_ cause a significant change in\nemployment at the industry level. Since these estimates do not consider the effect that\nregulation in one industry may have on other industries that make complementary or\nsubstitute products, the results should not be interpreted as relevant to the whole\neconomy, but they do highlight the complex responses to the new regulations exhibited\nby plants in the four industries.\n\n\nInterestingly, other studies have focused on air pollution control induced changes in\nemployment, using measures of regulation tied to specific policy actions rather than to\nself-reported pollution control expenditures. Examples include the stringent air quality\nstandards imposed in the South Coast Air Quality Management District in the 1990s, and\nthe nationwide attainment/nonattainment designations used for criteria air pollutants, as\nwell as the realignment of such designations following the 1990 Clean Air Act\nAmendments.\n\n\nIn an early study, Berman and Bui (1997) found small, statistically insignificant\nemployment _gains_ associated with the more stringent South Coast air quality rules,\nconsistent with the later findings of Morgenstern et al. In contrast, in the analyses of\nfederal attainment/nonattainment designations, studies by Greenstone (2002) and Walker\n(2011) found adverse employment impacts associated with the regulations.\n\n\nImportantly, all three of these studies use measures of regulation tied to specific policy\nactions rather\n\nMention: \"survey on Pollution Abatement Control Expenditures\""}, {"role": "assistant", "content": "{\"role\": \"supporting\", \"usage_action\": \"source\", \"summary\": \"Firms self-report their pollution control spending in this survey.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:005427:8:1", "occurrence_id": "e1ac47accf9622ecf4446ceb", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: we know,\nthere are no applications to the gravity model of trade.\n\n### **3. Data**\n\nBilateral trade in current USD comes from the United Nations’ (2012) _COMTRADE_ database,\naccessed through WITS. 9 Exporter and importer GDPs are from the World Bank’s (2012) _World_\n_Development Indicators_ and, consistent with the underlying theory, are measured in nominal\nUSD. 10 Bilateral country characteristics come from the CEPII distance dataset (Mayer and\nZignago 2011).\n\nThe analysis focuses on a country’s total merchandise exports disaggregated into differentiated\nproduct exports and commodity exports. A commodity is defined according to the International\nMonetary Fund’s (2012a) _Primary Commodity Prices_ and is coded at the six-digit HS 1988/92\n\n\n9 Instead of combining exports and imports for each country pair to construct symmetric trade flows, we use the\nThis technique is commonly used to minimize the risk of underreporting due to the fact that customs agencies unidirectional value of trade from country 𝑖 to country 𝑗 and introduce both importing and exporting country fixed\nusually monitor imports more closely than exports. effects. The exports from country 𝑖 to country 𝑗 are inferred using the imports reported by country 𝑗 from country 𝑖.\n10 On the use of trade and GDP data in current USD, see Baldwin and Taglioni (2006).\n\n\n7\n\nMention: \"CEPII distance dataset\""}, {"role": "assistant", "content": "{\"role\": \"supporting\", \"usage_action\": \"source\", \"summary\": \"Bilateral country characteristics come from this distance dataset.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:005446:41:2", "occurrence_id": "1a7613c60ba567a1b55989d0", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: |
91|\n|Is there a regulatory requirement for general provisions on loans and advances?|63|36|73|\n|Do you require banks to write off non-performing loans after a specific time period?|40|14|49|\n|Does accrued, though unpaid, interest/principal enter the bank's income statement
while the loan is classified as non-performing?|28
(14)|39
(31)|23
(8)|\n|If a customer has multiple loans and advances and one of them is classified as non-
performing, are all the other exposures classified as non-performing as well?
|53
(50)
|48
(35)
|54
(55)
|\n|**C. Some Additional Information**
|**Median**|**Median **|**Median**|\n|
What is the maximum time (in months) that a loan or advance can be non-performing
before it has to be written off?|
12|
18|
12|\n|
Up to what level (if any) is specific provisions tax deductible?|0|0|1|\n|Up to what level (if any) is general provisions tax deductible?
|0
|0
|0
|\n\n\nparentheses refer to the 2007 Bank Regulation and Supervision Survey, which captures data as of 2005.\nADV: advanced economies, EMDEs: emerging and developing economies (Table 1 provides the complete list of countries).\n\n\n40\n\nMention: \"2007 Bank Regulation and Supervision Survey\""}, {"role": "assistant", "content": "{\"role\": \"supporting\", \"usage_action\": \"source\", \"summary\": \"Its questions on tax deductibility capture conditions as of that earlier year.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:005462:16:2", "occurrence_id": "67e53398896afadfb412a7b1", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: -,\n\nA final international comparison issue our data can shed light on is the association between the\ndissimilarity index (the measure of inequality of opportunity contained within the HOI) and the index of\ninequality of economic opportunity (IEO-R). The dissimilarity index can be interpreted as the proportion\n\n\n\n17 A possible caveat with viewing the dissimilarity index within the HOI as a measure of inequality of opportunity is\nthat the index is typically calculated “for children”. This justifies the use of certain variables - like geographic\nlocation or education of the adults in the household - as circumstances, which are clearly in the realm of choices\nfor the adults. The argument is that the index applies to children, and these are circumstances from their\nperspective. But this then raises the issue of age of responsibility, and whether or not all inequalities in access to\nservices for children below a certain age should not be considered inequality of opportunity. Under that view,\nunequal access to water or sanitation among five-year olds within the same type (i.e. sharing identical observed\ncircumstances) should also be counted as inequality of opportunity.\n18 The correlation with the inequality-adjusted Human Development Index introduced for the first time in 2011 is\nalmost the same: 0.95.\n\n15\n\nMention: \"inequality-adjusted Human Development Index\""}, {"role": "assistant", "content": "{\"role\": \"supporting\", \"usage_action\": \"source\", \"summary\": \"Introduced in that year, it correlates almost fully with the opportunity measure.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:005496:38:0", "occurrence_id": "58dbfa72aa964abdee3da42f", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: highest growth firms and products (Melitz, 2003). Pakistan’s performance in this respect is\nconsiderably deteriorating over time. The rates of survival after 2004 increased. At the same\ntime, the number of new exporters each year steadily decreased. These two results together are\na potentially worrisome signal of a decrease in firm dynamism, whereby the greater persistence\nin export relationships is due to less competition in the domestic market. This may contribute to\nexplain why Pakistan’s export performance in the past decade was positive but more moderate\nthan the one of other Asian economies.\n\n\n**Figure 28**\n**Survival rates after 1 year of export activity**\n\n\n\n\n\n\n\nSource: Authors’ calculations based on data from the Exporter Dynamics Database (World Bank).\n\nTo investigate further, whether the lower dynamism of firms’ exports has had a detrimental\neffect on export growth, the next sub-section will decompose the year-on-year contribution of\nthe extensive and the intensive margin to aggregate export growth.\n\nExports growth is computed using the mid-point growth rate (Davis and Haltiwanger 1992 as\napplied to firm-level exports by Bricogne et al 2011). The main advantage of this approach is\nthat it allows the computation of the contribution of the extensive and the intensive margin to\nexport growth. Other methodologies only allow a static assessment of the extensive margin\n(Hummels and Klenow 2005).\n\nTable 11 that provides the decomposition reads as follows. In each of the columns the average\nannual growth relative to the indicated period is reported. The aggregate figure for all trade\nflows is reported in the last row. The remainder of the table reports the contribution to\naggregate growth by each of the margins. For example, looking at annual growth over the year\n2002-2003, the first row indicates that export growth due to entry of new firms into exporting\nequaled 9.3%. Since the corresponding loss in export growth due to the exit of firms equaled\n7.8%,\n\nMention: \"Exporter Dynamics Database\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"analyze\", \"summary\": \"Survival after one year of exporting is calculated from this database.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:005537:44:8", "occurrence_id": "316c127fa02c81a371151902", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: -0.052**\n\nUruguay -0.006 0.015 0.021\n\n-0.001 -0.034 -0.017\n\n\n\n**0.031**\n\n**LAC** **-0.052**\n\nUruguay -0.006 0.015 0.021\n\n-0.001 -0.034 -0.017\n~~Source: Author’s calculations with data from SEDLAC (CEDLAS and The World Bank) using labor population-weighted~~\n~~averages.~~\n\n\n\n43\n\nMention: \"SEDLAC (CEDLAS and The World Bank)\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"analyze\", \"summary\": \"Labour population-weighted averages are computed from this distributional database.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:005485:6:1", "occurrence_id": "11aca465a1d7bfe6a22075f1", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: NSECURITY**\n\n\n**INDICATOR**\n\n\nIn this section, we provide an overview of the GWP and the specific food security indicator\n\n\nused in this study. Our goal is limited to answering three questions. First, what is the general\n\n\nquality of the GWP surveys? Second, what limitations might the GWP indicator of self-assessed\n\n\n5\n\nMention: \"GWP surveys\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"validate\", \"summary\": \"The study's object is the general quality of these surveys' indicator.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:005525:2:0", "occurrence_id": "7b938eb4a7fd5518beea1591", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: ### **Gender and Agriculture: Inefficiencies, Segregation, and** **Low Productivity Traps 1**\n\n##### **Andre Croppenstedt, Markus Goldstein and Nina Rosas †**\n\n\n\n1 This paper was prepared as a background paper for the World Development Report 2012. It has\n\nbenefitted from numerous conversations with the core team, especially Carolina Sanchez-Paramo, Ana\n\n\n\n1 This paper was prepared as a background paper for the World Development Report 2012. It has\n\nbenefitted from numerous conversations with the core team, especially Carolina Sanchez-Paramo, Ana\n\nRevenga, and Sudhir Shetty, as well as numerous colleagues at the World Bank and the FAO. In addition, this\n\n\n\nbenefitted from numerous conversations with the core team, especially Carolina Sanchez-Paramo, Ana\n\nRevenga, and Sudhir Shetty, as well as numerous colleagues at the World Bank and the FAO. In addition, this\n\npaper draws on work performed for the FAO’s State of Food and Agriculture 2010–2011. We are grateful to\n\n\n\nRevenga, and Sudhir Shetty, as well as numerous colleagues at the World Bank and the FAO. In addition, this\n\npaper draws on work performed for the FAO’s State of Food and Agriculture 2010–2011. We are grateful to\n\nKatia Covarrubias (FAO) for her support with the Rural Income Generating Activities data.\n\n\n\n1\n\n\n\npaper draws on work performed for the FAO’s State of Food and Agriculture 2010–2011. We are grateful to\n\nKatia Covarrubias (FAO) for her support with the Rural Income Generating Activities data.\n\nMention: \"the Rural Income Generating Activities data\""}, {"role": "assistant", "content": "{\"role\": \"supporting\", \"usage_action\": \"source\", \"summary\": \"Acknowledged support in handling this rural livelihood dataset.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:005549:46:44", "occurrence_id": "e5328d2f101ff97dedb9cdd6", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: Swaziland, and Zambia.|
If the table shows only one row for a country, it is equivalent to the bottom row for countries with two rows and means that no years were designated as
intensity 3 in the PRIO/Uppsala data.
African countries for which the data set reports no year of “internal armed conflict” or “internationalized internal armed conflict” of intensity 1, 2, or 3
between 1960 and 2004 are Benin, Malawi, Swaziland, and Zambia.|
If the table shows only one row for a country, it is equivalent to the bottom row for countries with two rows and means that no years were designated as
intensity 3 in the PRIO/Uppsala data.
African countries for which the data set reports no year of “internal armed conflict” or “internationalized internal armed conflict” of intensity 1, 2, or 3
between 1960 and 2004 are Benin, Malawi, Swaziland, and Zambia.|
If the table shows only one row for a country, it is equivalent to the bottom row for countries with two rows and means that no years were designated as
intensity 3 in the PRIO/Uppsala data.
African countries for which the data set reports no year of “internal armed conflict” or “internationalized internal armed conflict” of intensity 1, 2, or 3
between 1960 and 2004 are Benin, Malawi, Swaziland, and Zambia.|
If the table shows only one row for a country, it is equivalent to the bottom row for countries with two rows and means that no years were designated as
intensity 3 in the PRIO/Uppsala data.
African countries for which the data set reports no year of “internal armed conflict” or “internationalized\n\nMention: \"PRIO/Uppsala data\""}, {"role": "assistant", "content": "{\"role\": \"supporting\", \"usage_action\": \"source\", \"summary\": \"Its conflict intensity coding leaves some countries without a year designated.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:005551:14:2", "occurrence_id": "aae0e20970425c0b1a930252", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: sex ratio, and the literacy\nratio are all statistically similar across treatment assignment. Similarly, the sex ratio of workers\nand non-workers also does not vary between treated and untreated blocks. Thus, these t-tests also\nfail to yield evidence that would cause us to believe that the program was systematically targeted\nat villages where women were either less empowered or already more empowered, and hence more\nlikely to respond to the treatment.\n\n\n10Blocks are small groups of villages and are the administrative unit directly above the village council. Within each\ndistrict, the placement decision of _Mahila_ _Samakhya_ is made by block, rather than by village, hence these blocks are\nthe appropriate unit of analysis when examining whether the program is targeted in any way. For blocks without\nthe program, we use data from the 2001 census.\n\n\n13\n\nMention: \"the 2001 census\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"For areas without the programme, block characteristics come from this enumeration.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:005572:23:1", "occurrence_id": "eb8a97f315bf9ba80e9ab0ae", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: in turn reflect the changes in both hourly wages and hours worked. The\n\n\naverage weekly wage growth of 23 percent is slightly higher than the average hourly wage\n\n\n40 For changes in ownership categories within the formal sectors, the changes may reflect either the change in\nnationality of the establishment for which an individual works or individual’s move from one sector to another.\n41 The VHLSS is likely to exclude migrants who hold a temporary or no registration status since the sampling of the\nsurveys is limited to the households who had permanent registration status. Based on the _Vietnam Migration Survey_\n(VMS) data in 2004, Fukase (2013b) finds that only 10 percent of migrants who work for foreign firms possess\npermanent registration status.\n42 The wages are converted to January 2002 constant prices using the deflators available in the VHLSS.\n\n22\n\nMention: \"VHLSS\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"validate\", \"summary\": \"Its sampling frame may exclude migrants without registration.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:005584:5:1", "occurrence_id": "879872c96ce13136f6abaacd", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: emphasis on the potential for agricultural-policy\nreforms.\n\n\n**2. Stylized Facts**\n\nMany agricultural- and trade-policy developments of the past half-century have happened\nquite suddenly and been transformational. Such events include decolonization in Africa and\nelsewhere around 1960; the creation of the Common Agricultural Policy (CAP) in Europe in\n1962; the introduction of flexible exchange rates from the 1970s; liberalization, deregulation,\nprivatization, and democratization in many countries from the mid-1980s; the opening of\nmarkets in China in 1979, in Vietnam in 1986, and in Eastern Europe (following the fall of\nthe Berlin Wall) in 1989; and the demise of the Soviet Union in 1991. More subtle are the\ninfluences of policies that change gradually in the course of economic development, as\nincomes grow and comparative advantages evolve. But what do the quantitative measures of\ndistortions and reforms reveal?\n\nEmpirical indicators of agricultural price distortions (called Producer Support and\nConsumer Subsidy Estimates, or PSEs and CSEs) have been provided consistently for 25\nyears by the Secretariat of the OECD (2011) for its thirty member countries. However, the\nOECD provides no comprehensive time-series rates of assistance to producers of nonagricultural goods to compare with the PSEs, nor of what took place in those advanced\neconomies during earlier decades. Data for these earlier decades from developed economies\nis needed in order to assess how various countries’ policies evolved during stages of\ndevelopment similar to those of today’s middle-income countries. As for developing\ncountries, almost no comparable time-series estimates were generated in the two decades\n\n\npolicies more thoroughly (while giving somewhat less attention to factor market distortions). And third, we\nplace particular emphasis on the substantial body of theoretical and empirical research that has been published\nduring the past fifteen years (that is, since the most recent citations in Binswanger and Deininger).\n\nMention: \"Producer Support and\nConsumer Subsidy Estimates\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"Its secretariat has provided price distortion indicators consistently for twenty-five years.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:005598:35:0", "occurrence_id": "2cdb3b7c9e7cd8015ac50125", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: **Table 3. Job Status and political attitudes. World Value Survey**\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n|Col1|High income Higher middle income Low income Lower middle income|\n|---|---|\n|
Dependent
variable
unemp
Job qual
Observations
|
Confidence in
government
Confidence in
government
Confidence in
government
Confidence in
government
Confidence in
government
Confidence in
government
Confidence in
government
Confidence in
government
-0.007
0.018
-0.025
-0.005
(0.018)
(0.012)
(0.024)
(0.015)
-0.000
0.001
-0.002
-0.001
(0.003)
(0.002)
(0.007)
(0.003)
11827
9614
17534
\n\nMention: \"World Value Survey\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"analyze\", \"summary\": \"Job status and political attitudes are estimated across income groups from it.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:005600:11:0", "occurrence_id": "1d415aff7c99e55fe9c372d7", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: we have inequality estimates) and 2010 increased by more than 16 times. 9 [^9: GDP per capita data, expressed in 1990 Geary-Khamis PPPs, are from Maddison (2007). The physiological\nsubsistence minimum in the same prices is assumed to be $PPP 300 (for discussion see MLW 2011, p. 262).] The figure\n\nshows the large difference between the IERs calculated with subsistence only, and under\n\nthe assumption that the social minimum increases as the mean income goes up. Under the\n\nfirst assumption, the IER in England/UK oscillated around 60 percent throughout 18 th and\n\n19 th century. But if we assume that the social minimum had risen in proportion with real\n\nincome (b=0.5), the IERs attained 80 percent. The numbers for the United States are very\n\nsimilar.\n\n\nThe political implications of b=0 and b=0.5 are very different. If the elites had to\n\nacquiesce to a rise of the minimum living standard for the masses, then an 80% inequality\n\nextraction ratio shows that they were able or willing to push overall inequality rather close\n\nto the maximum. If, on the other hand, we believe that there was no social pressure to\n\nincrease the social minimum, then the elites’ appetites may be thought to have been\n\nrelatively modest.\n\n\nIn both countries, it is only in the 20 th century, as illustrated more clearly in Figure 5,\n\nthat the IER, calculated under the more stringent conditions of a changing social minimum,\n\nbegan its downward slide, to be arrested and reversed in the last quarter of the 20 th century\n\nand early 21 st . But because real incomes have by then risen to very high levels (exceeding,\n\nin the United States, 100 times the subsistence minimum), the inequality possibility\n\nMention: \"1990 Geary-Khamis PPPs\""}, {"role": "assistant", "content": "{\"role\": \"supporting\", \"usage_action\": \"source\", \"summary\": \"Output per head and the subsistence minimum are both expressed in these prices.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:005604:13:1", "occurrence_id": "ae933d8b4ac88929ec11b202", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: 21 912.0\n\n110 3.26 3.93 1119.7 3.20 910.6\n\n115 3.41 4.07 1157.9 3.20 909.2\n\n120 3.55 4.20 1196.0 3.19 907.8\n\nSource: calculated\n\n\nThe very close co-movement of actual and predicted soybean oil prices depicted in\nFigure 2 empirically supports the theoretical link between biodiesel and soybean oil prices\nestablished by equation (6). 19 [^19: The underlying data come from the “Historical Biodiesel Operating Margins” spreadsheet of the Centre for\nAgricultural and Rural Development of the Iowa State University.\n[http://www.card.iastate.edu/research/bio/tools/hist_bio_gm.aspx](http://www.card.iastate.edu/research/bio/tools/hist_bio_gm.aspx)] This link appears to be very strong because prices of biodiesel and\nsoybean oil exhibit almost identical development as do actual and predicted soybean oil prices\n(not shown). 20 [^20: Biodiesel prices ran up in 2007-08 because of ‘splash and dash’ (see de Gorter et al. 2011) and then crashed as the\nEuropean Union invoked anti-dumping and countervailing duties. But the U.S. biodiesel mandate started to be\nenforced in mid-2010, causing prices to rise sharply again.] The three visible periods when our model over predicts (April – September 2007,\nFebruary 2008 – April 2009, and February 2011 – April 2012) correspond to the periods of\npositive profits earned in biodiesel production, likely due to capacity constraints.\n\n**5.** **Conclusions**\nThis paper has advanced an analytical framework to analyze the economics of biodiesel\npolicies (tax exemptions/tax credits and mandates) and the effects of crude oil price shocks under\neither of these policies. We show how the jointness in soybean (rapeseed) crushing – i.e\n\nMention: \"Historical Biodiesel Operating Margins\""}, {"role": "assistant", "content": "{\"role\": \"supporting\", \"usage_action\": \"source\", \"summary\": \"Its spreadsheet supplies the underlying margin data.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:005611:3:0", "occurrence_id": "041370a27db5e673d3fd841c", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: **1.** **Introduction**\n\nCentral banks intervene in foreign exchange (FX) markets when they target particular levels of\n\nthe exchange rate, through pegs, crawls, or bands with respect to other currencies or currency\n\nbaskets. Even when they do not target a particular rate, they may intervene when there is\n\nexcessive volatility in the exchange rate, which can be destabilizing for traders and ordinary\n\nconsumers. When faced with current account surpluses or capital inflows, central banks that\n\ntarget the exchange rate end up accumulating large amounts of FX reserves. Accumulation of\n\nreserves can also be a symptom of an undervalued exchange rate that some governments have\n\nused to promote exports—or to prevent an appreciation that could undermine competitiveness.\n\nThe extraordinary accumulation of reserves by the People’s Bank of China since the mid-1990s\n\nand by the Swiss National Bank in the aftermath of the 2008-09 global financial crisis—\n\nespecially following the Swiss franc’s peg to the euro in September 2011—have been the focus\n\nof a lot of discussion and analysis. 1 [^1: See, for example, Ross and Jones, (2013), who point to evidence that, in the face of excessive accumulation of FX reserves in a\nnear-zero interest rate environment for US dollar and euro denominated bonds, central banks have been increasingly searching\nfor opportunities to diversify reserve holding into higher-yielding assets, including from emerging market economies. According\nto IMF statistics, worldwide FX reserve holdings had more than doubled, from US$ 5 trillion in 2006 to US$ 10.8 trillion in\n2012.] By contrast, central banks that intervene to prevent exchange\n\nrate depreciation could see their FX reserves get depleted.\n\n\nCentral banks committed to a floating exchange rate intervene in foreign exchange markets for\n\nvarious reasons: When, for instance, a country’s currency appreciates because of some shock and\n\nthe central bank believes that this is a temporary fluctuation, it may want to prevent the\n\nappreciation of the exchange rate that may undermine growth\n\nMention: \"IMF statistics\""}, {"role": "assistant", "content": "{\"role\": \"supporting\", \"usage_action\": \"source\", \"summary\": \"Worldwide foreign exchange reserve holdings doubled between these years.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:005620:13:0", "occurrence_id": "b6537c5a03504debb415665b", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: empirical evidence on the precise magnitude of such indirect impacts for the long-term income growth\nof the beneficiaries (reviewed in Alderman and Yemtsov 2013). However, all of these studies typically\ncover the effect of one program in one country, and it is hard to generalize across the world.\n\n\nTo approach the issue of cross-country comparability and comprehensiveness, we limit our\nattention to just the first, direct, channel of transfer impact on the current wellbeing of beneficiaries.\nFor this we use household survey information and compute what the household’s income would be\nwithout the transfers it receives from social protection programs. Thus, generally the transfer value is\nsubtracted from individual or household welfare 30 [^30: Welfare is a measure of well-being, and is defined either as per capita income or consumption], providing a synthetic counterfactual. Of course these\nresults are more indicative than authoritative since behavioral effects, for example, are not simulated. 31 [^31: For example, it is assumed that if a person stops receiving a pension, he or she will try to survive on the\nremaining income after the pension is taken away. In practice that person can seek assistance from relatives and\ncommunity that will partly compensate this loss of income, so will not be as poor as assuming no replacement.]\nIn the short run, if households reduced their efforts to earn market income in response to income\ntransfers through social protection, then this method would give an overestimate of the impact on\npoverty. Evidently _any_ medium term improvements in household market income discussed above, imply\nthat the direct assessment would be an underestimate of the poverty and inequality impact. It is difficult\nto know where exactly the balance would come out, but our estimates can provide an anchor for\ndiscussion and sensitivity analysis.\n\n\nUsing the ASPIRE dataset and an international poverty line of $1.25 per day per capita in PPP, Figure\n2 below uses this simulation to estimate how many people are moved out\n\nMention: \"ASPIRE dataset\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"analyze\", \"summary\": \"Estimates anchored to the international line are computed from this dataset.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:005634:9:0", "occurrence_id": "c1b0ad5c1f768cefa040b71c", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: leveraged buy-outs (LBOs) that resulted in complete transfer of control to the PE investor.\n\n\nHowever, in recent years PE firms have also started to take minority equity stakes in already\n\n\npublicly-listed firms via PIPE transactions.\n\n\nPE firms are usually credited with three potential value creating strategies. Kaplan and\n\n\nStromberg (2009) define them as financial, governance and operational improvements. Financial\n\n\nengineering entails the use of higher levels of debt to create tax shields as well as to sharpen the\n\n\nincentives of the management team. Governance improvement is largely driven by providing a\n\n\nsignificantly larger share of equity to the operating management and through mitigation of\n\n\nagency problems via concentrated ownership. Operational improvement entails deploying\n\n\nsignificant industry-specific knowledge to create better-run organizations. Thus, unlike other\n\n\ninstitutional investors, PE firms are more likely to be involved in the day to day operations of the\n\n\nfirms that they invest in. Successful PE investors are credited with the ability to source and\n\n\nscreen investment ideas as well as the ability to monitor firms, especially those with poor\n\n\ncorporate governance, using mechanisms such as board representation and active involvement in\n\n\nthe strategic decisions of the firm.\n\n###### **3. Data and Summary Statistics**\n\n\n**3.1** **PIPE and SEO Sample**\n\n\nOur data on PE financed PIPE issues come from the Asian Venture Capital Journal (AVCJ)\n\n\nDatabase, a new electronic database that maintains information on private equity (PE), venture\n\n\ncapital (VC), and mergers and acquisitions (M&A) transactions in Asia. We consider PIPEs from\n\n\na set of nine countries, including Australia, China, Hong Kong, Special Administrative Region of\n\n\nChina, India, Japan, Singapore, South Korea, Taiwan, China, and Thailand, all of which report at\n\n\n8\n\nMention: \"Asian Venture Capital Journal (AVCJ)\n\n\nDatabase\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"A new electronic record of private equity and venture capital activity.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:005641:5:0", "occurrence_id": "cfe743d33b68ce0280017157", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: Figure 3\n\n\n\nChina\nIndustry Share of CO2 Emissions\nand Four Energy Intensive Industries Share\n\n\n\nof Industry CO2 Emissions\n\n\n\n1.0\n\n\n0.8\n\n\n0.6\n\n\n0.4\n\n\n0.2\n\n\n0.0\n\n1960 1965 1970 1975 1980 1985 1990 1995 2000 2005 2010\n\n\nSource: IEA Online Data Services, 2012\n\n\n\nCO2 Emissions from 4 Energy Intensive Industries as a Share of Industry Emissions\nCO2 Emissions from Industry as a Share of Total Emissions\n\n\n\nAlong the way, we argue that China’s success in reducing the CO2 intensity of industrial\nproduction has not been easy or without cost. Following adoption of a new industrial policy to\n“grasp the large, let go the small” (Sutherland 2003: 2 and 10), attempts to create a small number\nof technologically sophisticated national champion enterprises that can save energy and\ndominate in each of these industries have not been entirely successful. 8 [^8: See discussion in the appendix.] Even where successful,\nsome (World Bank 2012) have worried about the economic costs associated with the anticompetitive effects of this strategy. Others (Allen et al 2008) argue that bank loans to China’s\nstate-owned enterprises, including those to national champions, undermine an efficient allocation\nof capital thereby imposing additional significant economic losses on the Chinese economy.\nFinally, given China’s highly fragmented industrial structure (Oh 2012: 5) and its highly\ndecentralized industrial governance system, it should not be surprising that the central\ngovernment has not been entirely successful in “letting go the small” by closing nearly all of the\nsmall scale, energy inefficient, and polluting facilities in these industries. Yet despite these\nproblems, as we show, China has been quite successful in reducing the CO2 intensity of\nproduction in the industries we study.\n\nOur argument proceeds in four steps. Because improving energy efficiency in particular\nenterprises and industries depends on the ability of enterprises in particular industries to\nsuccessfully adopt the minor process changes and the major technological changes that enable\nthem to reap environmental technique effects\n\nMention: \"IEA Online Data Services\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"Emissions shares across energy-intensive industries over these years come from this service.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:005613:33:1", "occurrence_id": "316b34b6c47a9a37e91fccdd", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: with the decline in\n\nthe treasury rate following the 2007-2008 crisis.\n\n\nSecond, the model generates a decline in investment in the developed\n\neconomy, and an increase in investment in the emerging economy. The decline\n\nin investment in the developed economy reflects the lower private return to\n\ncapital. The increase in investment in the emerging economy is a result of the\n\ndeveloped economy running down its capital stock: in part, this is achieved\n\nthrough saving in emerging economies, to smooth the declining consumption\n\n\n14Source: World Development Indicators.\n\n\n32\n\nMention: \"World Development Indicators\""}, {"role": "assistant", "content": "{\"role\": \"supporting\", \"usage_action\": \"source\", \"summary\": \"Consumption smoothing across emerging economies is traced with this source.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:005663:16:1", "occurrence_id": "74bcb7dfe4a01a600fc2522a", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: + 𝛾𝑋𝑖𝑣𝑘 + 𝜇𝑘 + 𝛥𝜀𝑖𝑣𝑘 (4)\n\n\n\nwhere 𝛥𝑙𝑛(𝑦𝑖𝑣𝑘) is real income growth for household _i_, in village _v_ and kecamatan _k_ . It is the log\n\n𝐼09,𝑖𝑣𝑘 𝐼07,𝑖𝑣𝑘\n\n\n\ndifference of real per capita income: ∆𝑙𝑛(𝑦𝑖𝑣𝑘) = 𝑙𝑛 ~~�~~\n\n\n\n~~𝑛~~ 𝐼09,𝑖𝑣𝑘 ~~09,𝑖𝑣𝑘~~ � −𝑙𝑛 �\n\n\n\n~~𝑛~~ 𝐼07,𝑖𝑣𝑘 ~~07,𝑖𝑣𝑘~~ ~~�~~ where 𝐼𝑡 is weekly\n\n\n\nearning (in real term, deflated by the consumer price index in Aceh province from BPS ( _Badan Pusat_\n\n\n\nearning (in real term, deflated by the consumer price index in Aceh province from BPS ( _Badan Pusat_\n\n_Statistik_ ) website) and 𝑛𝑡 is household size in year _t_ . Right hand side includes a dummy for fishing\n\n\n\n15\n\nMention: \"BPS\""}, {"role": "assistant", "content": "{\"role\": \"supporting\", \"usage_action\": \"source\", \"summary\": \"Its provincial consumer price index deflates real earnings.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:005687:6:0", "occurrence_id": "60927cc447f5a189a5ee7c54", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: Federal Reserve, suggesting that median wealth has declined. 4 Hence, the prospects of current\nand future retirees are clearly much diminished.\n\n\nWe know that one dollar will buy three times as much in Thailand and twice as much in Costa\nRica as it does in the United States. 5 Retirees could maintain their standard of living by relocating to places with a lower cost of living. In 2011, there were about 567,000 beneficiaries\nliving abroad, of whom 350,000 were retired American workers or about 1 percent of American\nretirees (US Social Security Administration, 2012, Table 5.J2). 6 A quarter of retirees live in\ndeveloping countries (Table 5.J11). Between 2008 and 2010, 35 percent of new overseas\nAmerican retirees headed for the developing world –double the flows over the preceding 7 years.\nAccording to US Census Bureau projections, by 2020, the number of people above age 60 will\nincrease by about 22 million and by a further 14 million by 2030. If the fraction of those\nchoosing to live overseas increases to say 2 percent by 2020 and 3 percent by 2030, about 2.5-3\nmillion US retirees could be living abroad within two decades.\n\n\n_Infirm_\n\n\nThe rising costs of healthcare in the United States imply that if current levels of access to health\ncare are maintained, spending on the major federal health care programs alone would grow from\nmore than 5 percent of GDP today to almost 10 percent in 2037. 7\n\n\nSince healthcare of comparable quality is much cheaper in other countries, treatment abroad\ncould yield big savings. For example, inpatient knee surgery, roughly 400,000 of which were\nperformed in 2010 in the United States, costs more than $15,000 in a typical community hospital\n(Centers for Disease Control and Prevention,\n\nMention: \"US Census Bureau\""}, {"role": "assistant", "content": "{\"role\": \"supporting\", \"usage_action\": \"source\", \"summary\": \"Its projections give the increase in older migrants.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:005702:4:0", "occurrence_id": "b35c38f11a2a8e77254a8b9c", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: expansion of social program provisions. 3 The cost of health insurance through employment in\n\n\nColombia is often cited as anecdotal evidence of a powerful disincentive for formal employment.\n\n\nHowever, prior to this paper, no systematic empirical evidence has been presented to confirm or\n\n\nreject this hypothesis. 4\n\n\nTo determine whether the SR expansion generated incentives for informal employment, we\n\n\nuse two datasets and different identification strategies. The first comes from repeated cross\n\nsections of the Colombian Household Survey. Using individual-level data and controlling for\n\n\nmunicipality and year effects, we estimate whether there was an increase in informal employment\n\n\nafter the municipality started conducting the interviews needed to determine eligibility for the SR\n\n\n(known as SISBEN interviews). These interviews were implemented at different points in time\n\n\nacross municipalities, which allows us to disentangle the effects of the expansion of the health\n\n\ninsurance provision from other labor market reforms and macroeconomic shocks occurring at\n\n\nthe national level during the same period of time. In section III, we show that pre-existing\n\n\ninformality rates are uncorrelated with the timing of the SISBEN, and we find robust and\n\n\nconsistent effects of an increase in informal employment of approximately 4 percentage points.\n\n\nThis finding corresponds to approximately 8% of the labor force not entering the formal sector\n\n\nand an increase in the government’s health expenditures of approximately 11%.\n\n\nOur second dataset is a panel of people interviewed in the first and second SISBEN. Using\n\n\ninformation about an individual’s eligibility status (as determined by her Poverty Index Score\n\n\nfrom the first SISBEN) 5 and individual fixed effects, we corroborate the increase in informal\n\n\nemployment found with the household survey dataset. Additional estimations that account\n\n\n3See Grosh (1994) for a review of 30 social programs in 11 Latin American countries.\n4For example, in a news article reported by _Presidencia_ _de_ _la\n\nMention: \"Colombian Household Survey\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"Repeated cross-sections with municipality and year effects.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:005702:4:0", "occurrence_id": "7d9ae80374f908b207d52229", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: expansion of social program provisions. 3 The cost of health insurance through employment in\n\n\nColombia is often cited as anecdotal evidence of a powerful disincentive for formal employment.\n\n\nHowever, prior to this paper, no systematic empirical evidence has been presented to confirm or\n\n\nreject this hypothesis. 4\n\n\nTo determine whether the SR expansion generated incentives for informal employment, we\n\n\nuse two datasets and different identification strategies. The first comes from repeated cross\n\nsections of the Colombian Household Survey. Using individual-level data and controlling for\n\n\nmunicipality and year effects, we estimate whether there was an increase in informal employment\n\n\nafter the municipality started conducting the interviews needed to determine eligibility for the SR\n\n\n(known as SISBEN interviews). These interviews were implemented at different points in time\n\n\nacross municipalities, which allows us to disentangle the effects of the expansion of the health\n\n\ninsurance provision from other labor market reforms and macroeconomic shocks occurring at\n\n\nthe national level during the same period of time. In section III, we show that pre-existing\n\n\ninformality rates are uncorrelated with the timing of the SISBEN, and we find robust and\n\n\nconsistent effects of an increase in informal employment of approximately 4 percentage points.\n\n\nThis finding corresponds to approximately 8% of the labor force not entering the formal sector\n\n\nand an increase in the government’s health expenditures of approximately 11%.\n\n\nOur second dataset is a panel of people interviewed in the first and second SISBEN. Using\n\n\ninformation about an individual’s eligibility status (as determined by her Poverty Index Score\n\n\nfrom the first SISBEN) 5 and individual fixed effects, we corroborate the increase in informal\n\n\nemployment found with the household survey dataset. Additional estimations that account\n\n\n3See Grosh (1994) for a review of 30 social programs in 11 Latin American countries.\n4For example, in a news article reported by _Presidencia_ _de_ _la\n\nMention: \"SISBEN\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"A panel of people scored for eligibility across two rounds.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:005704:21:0", "occurrence_id": "8dcfe9100cfa9f846797be4d", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: Figure 1. Budget share of wheat consumption and food consumption\n\n\n\n\n\nData source: PSLM 2007-08\n\n\n20\n\nMention: \"PSLM\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"Budget shares of wheat and food consumption come from this round.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:005709:19:0", "occurrence_id": "c5cbb27a815cd1c3d1c093d5", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: **Table 4: Length and percentage of federal road network not meeting standards (2009)**\n\n|Col1|Length (km)|Percentage|\n|---|---|---|\n|Failing to meet minimum riding quality requirements
Failing to meet minimum grip requirements
Failing to meet minimum strength requirements
Failing to meet minimum defects requirements
|28,500
12,200
24,900
35,100
|57.1
24.4
49.9
70.3
|\n\n\n\nDecember 31, 2009.\n\n\n**Given these findings based on descriptive statistics, the question arises whether they**\n**can be corroborated by econometric analysis and to what extent infrastructure**\n**deficiencies affect firm productivity.** This is the question we take up by explicitly\nmodeling changes in TFP productivity growth using a vector of infrastructure variables\nfrom the BEEPs surveys, combined with firm characteristics.\n\n**Since BEEPs surveys are infrequent, and in this case were conducted in 2004 and**\n**2008 only, results in this section use data for 2004 and 2008 only.** Following\nEscribano and Gausch (2004) and Alam et al (2008), we postulate the general regression\nmodel, with changes in productivity being the dependent variable, and include controls\nfor firm characteristics.\n\n\n∆lnTFPijt=α + β1∆ **infrastructure** t-1 + **_∑ⱷn X_** **_n_** **_i.t_** + ε i,t\n\n\nFor each of Russia’s regions, and for each sector (2-\n\nMention: \"BEEPs surveys\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"analyze\", \"summary\": \"Infrastructure variables from these infrequent rounds feed the productivity model.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:005729:8:1", "occurrence_id": "33fda3198e27857a072b9014", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: household were randomly selected\n\nbased on a listing of all household members aged 16 years and above, using the Kish Grid-diagram. 4\n\n\nWe use the FinAccess surveys in our analysis for a number of reasons. _First_, it captures important\n\ndimensions of financial inclusion as it was specifically designed to measure access to financial\n\nservices in Kenya. _Second,_ it also provides information on individual and household characteristics,\n\nsuch as education level, gender, asset ownership, income source, age group, language, location and\n\nhousehold size. _Third,_ it is a nationally representative household survey that covers the universe of\n\ndistricts in Kenya, alleviating potential sample selection bias problems. _Fourth,_ its implementation\n\nover different years allows us to explore the within-district time variation in financial inclusion.\n\n\n4 The Kish Grid-diagram is a method that uses a pre-assigned table of random numbers for selecting individuals within a\nhousehold to be interviewed.\n\n7\n\nMention: \"FinAccess surveys\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"Selected for the financial dimensions it captures among adults.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:005735:29:0", "occurrence_id": "97facd09490004c2af0dd110", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: Domic´ılios (PNAD), a representative survey of the Brazilian population, are used.\n\n\nThe unit of observation is the household, and the individual outcome is measured as the monthly\n\n\nhousehold equivalent income, expressed in 2008 Brazilian real. 32 Household income is computed\n\n\nas the sum of all household members’ individual incomes, including earnings from all jobs, and all\n\n\nother reported income, including income from assets, pensions, and transfers.\n\n\nThe population is partitioned into 15 types using the information on two circumstances: region\n\n\nof birth and race. Region of birth is coded in five categories (North, Northeast, Southeast, South,\n\n\nCenter-west), and race is coded in three categories (white/east Asian, black/mixed race, and in\n\ndigenous). Individuals who were born abroad and those classified as “other” for the variable race\n\n\nare excluded because the number of observations is too low to make appropriate inference. Hence,\n\n\nthe sample sizes of each wave considered in this analysis are as follows: 366,388 households in 2002,\n\n\n390,046 in 2005, and 372,581 in 2008. 33 .\n\n\nThe full opportunity profiles for the three waves are reported in Table 4 in the appendix. 34 In\n\n\nthis table, it is clear that race is the main determinant of the disparity in opportunities. Consistent\n\n\nwith a number of contributions on socio-economic inequality in Brazil, racial relationships appear\n\n\nto be the major source of outcome and opportunity inequality in Brazil (Telles 2004; Bourguignon\n\n\net al. 2007; among others).\n\n\nTo analyze the distributional impact of growth in Brazil according to the EOp perspective,\n\n\ntwo three-year period growth processes are considered: 2002–05 and 2005–08. The choice of these\n\n\nparticular periods is driven by the observation that during these years, Brazil experienced\n\nMention: \"Domic´ılios (PNAD)\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"A representative national household survey forming the observation unit.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:005749:40:0", "occurrence_id": "eeeeb5a7d18ace7efd33b6f8", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: 39\n\n\nilliteracy. Alternatively, there may be a lack of profitable investment projects in the economy\n\n\nthat deserve financing based on their expected return. This problem can actually not be\n\n\nillustrated in our figure as it focuses on loan applicants. A second type of access problem can\n\n\narise from regulatory distortions or insufficient contestability that cause lenders not to fully\n\n\nexploit all the outreach opportunities and thus settle at a point below the access possibilities\n\n\nfrontier with a higher marginal interest rate (Figure 10, Point II, B). A third and very\n\n\ndifferent access problem is associated with “excess access,” that is, an equilibrium above the\n\n\naccess possibilities frontier with loans being granted to a larger share of loan applicants than\n\n\nis prudently warranted or SMEs achieve too high a leverage, given the lending interest rate\n\n\nand the institutional framework (Figure 10, Point III, C). A final access problem consists of\n\n\ntoo low a prudent access possibilities frontier, caused by deficiencies in an economy’s\n\n\ninstitutional framework compared with that of countries with similar levels of economic\n\n\ndevelopment. An improvement along these lines would lead to an expansion of the frontier\n\n\nfrom S* to S*’’ in Figure 11. Similarly, lower opportunity costs of funding (imc), e.g. due to\n\n\nbetter macroeconomic conditions, will increase the universe of potential loan applicants\n\n\nreceiving finance (Figure 11, Point II, B).\n\n\n**6.2.** **Matching the concept with data**\n\n\nAs in the case of aggregate indicators, the frontier concept can be matched with\n\n\nempirical data. First, using the benchmarking model described above, one can predict the\n\n\nshare of (small) firms with access to a credit line or loan by a formal financial institution and\n\n\ncompare them to the actual share, as gauged by the Enterprise Surveys, undertaken by the\n\n\nWorld Bank/IFC. Figure 12 graphs the gap between the predicted and the actual share of\n\n\nsmall enterprises that use a credit line or loan from a formal financial\n\nMention: \"the Enterprise Surveys\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"Actual loan uptake by firms is gauged in these surveys.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:005753:14:1", "occurrence_id": "d0ea4416fc1921350ef2029a", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: 80 percent of MFIs in Bangladesh charge 11\n15 percent interest rate, and about 1 percent charges more than 20 percent (Rahman (2003)). Starting\n\nfrom July 2004, the wholesale microcredit fund provider PKSF capped the interest rate at 12.5 percent\n\nflat.\n\nThe average MFI coverage rate is about 42 percent in our sample of villages (Table A.1) which is\n\ncomparable to coverage rate from our panel data (38 percent). According to the Household Income and\n\nExpenditure Survey (HIES) 2010, about 45 percent of households with less than an acre of land in the\n\nRangpur division covering areas included in our sample are active borrowers from MFIs. The summary\n\nstatistics for all other variables used in the regression are also reported in Table A.1.\n\n\n**2.4. OLS, MATCHING AND IPW ESTIMATES**\n\n\nWe start with the simplest specification where the moneylender interest rate is regressed on the\n\nMFI coverage dummy (D=1 if coverage in a village is more than the mean coverage rate) without any\n\n23 According to one estimate reported in late eighties, the average interest rate charged by moneylenders was 51.86\npercent in rural India (Dasgupta, 1989); Aleem (1993) reports an average lending rate of 78.5 percent in Pakistan.\nFor a summary of the evidence on informal interest rates in developing countries see Banerjee (2003).\n24 It is not uncommon to have 25-50 percent interest rate for a consumption loan for a month, which becomes\nextremely high interest rates when annualized. Most of the moneylender interest rates reported in the literature are\nannualized rates on short term consumption loans.\n25 Note, however, that it assumes that the repayment schedule is enforced strictly, which is unrealistic, for both the\nmoneylender loans and MFI loans.\n\n\n13\n\nMention: \"Household Income and\n\nExpenditure Survey\""}, {"role": "assistant", "content": "{\"role\": \"supporting\", \"usage_action\": \"source\", \"summary\": \"Its coverage rate for smallholders benchmarks the panel figure.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:005764:6:0", "occurrence_id": "2b9493d12b07b6e7632e3477", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: account at a post office. 4 [^4: For seven countries (Algeria, Congo, Rep., Egypt, Arab Rep., Greece, Morocco, Tunisia, and Yemen, Rep.) the\ndata is for 2012 instead of 2011 because of data quality issues in the 2011 round.] In our sample, we focus on the over 65,000 individuals who were\n\n\ninterviewed in 60 of these countries. 5 [^5: We drop Madagascar from our sample because more than 20% of the population is not sampled and Taiwan, China\nbecause no country-level post office information is available.] Appendix 1 lists all the countries included in our sample.\n\n\nThe Global Findex data allow us to distinguish between three types of account\n\n\nownership: an account at a financial institution only, accounts at both a financial institution and\n\n\nthe post office, and an account at the post office only. Within our sample of countries that offer\n\n\npostal accounts, we find that 49.9 percent of adults have an account at either or both institutions,\n\n\n11.6 percent of adults have an account at the post office, and 2.8 percent of adults have an\n\n\naccount at the post office only (5.6 percent of account holders).\n\n\nFigure 1 shows a wide variation in overall account ownership between high income and\n\n\ndeveloping countries. While account penetration is close to universal in the developed countries\n\n\nincluded in our sample (90 percent), on average, only 44 percent of adults in developing\n\n\ncountries offering postal financial services report having an account. 6 [^6: This compares to 89 percent account penetration in high income countries and 41 percent account penetration in\ndeveloping countries for the full sample of countries in the Global Findex database. The data are population\nweighted.] However, beyond account\n\n\npenetration, we are interested in the types of accounts owned by individuals. In most of countries\n\n\nin our sample\n\nMention: \"Global Findex data\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"These data distinguish three types of account ownership.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:005779:0:0", "occurrence_id": "a4204fc79663241e60f83173", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: ## WPS6651 Policy Research Working Paper 6651\n\n# Demand Collapse or Credit Crunch to Firms?\n\n## Evidence from the World Bank’s Financial Crisis Survey in Eastern Europe\n\n#### _Ha Nguyen_ _Rong Qian_ The World Bank Development Research Group Macroeconomics and Growth Team October 2013\n\nMention: \"the World Bank’s Financial Crisis Survey\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"Firm demand and credit conditions across Eastern Europe are examined in this survey.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:005783:59:1", "occurrence_id": "a46b3417fe474f880d96a4b4", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: .6 standard
deviation drop in the net interest margin. For instance, giving Mexico the same level
of activity restriction as Korea would lead to a 1 percentage point decrease in net
margins in Mexico. However, once institutional framework is controlled for,
regulations cease to have an impact on efficiency. Better institutional environment
(according to the World Governance Indicators) and economic freedom are strongly
associated with lower net interest margins. Specifically, a one standard deviation
improvement in economic freedoms (0.54) would lower interest margins by 1.1
percentage points.
• If Romania had the same banking concentration as Poland, its net interest margin
would drop from 8.45 to 7.97. Also, if Burundi had the same banking concentration
as Kenya, its net interest margin would drop from 10.74 to 9.95.
|\n|Pasiouras,
Tanna, and
Zopounidis
(2009)
|
• A one-unit increase in capital requirements reduces bank’s cost inefficiency by 9
percent. Under the same scenario, market discipline, activity restrictions, and
official supervisory power lead to 10 percent, 9 percent, and 8 percent reductions in
cost inefficiency. The effect of official supervision on profit inefficiency is about
6.6 percent, whereas market discipline leads to a 25 percent reduction in profit
inefficiency.
|\n|Bayraktar and
Wang (2004)|
• A one standard deviation increase in the asset share of foreign banks in the
economy (i.e., 15.9 percent) leads to a 0.03 percentage point decrease\n\nMention: \"the World Governance Indicators\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"Institutional environment and economic freedom are measured with these indicators.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:005787:2:0", "occurrence_id": "0a1483e97173c9e58fcb0c35", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: ### Effects of Early-Life Exposure to Sanitation on Childhood Cognitive Skills: Evidence from India’s Total Sanitation Campaign\n\nDean Spears and Sneha Lamba _∗_\n\n\nOctober 11, 2013\n\n\nKeywords: sanitation, cognitive achievement, human capital, early-life health, India\nJEL codes: I25, I15, O15\n\n\n_∗_ Spears is corresponding author: dean@riceinstitute.org. Affiliations: Spears: Centre for Development\nEconomics, Delhi School of Economics, Delhi, India and r.i.c.e. (www.riceinstitute.org); Lamba: Barcelona\nGraduate School of Economics. We deeply appreciate the outstanding research assistance of Aashish Gupta.\nWe appreciate helpful comments from Anne Case, Diane Coffey, Juan Costain, Janet Currie, Aashish Gupta,\nJeff Hammer, Payal Hathi, Avinash Kishore, Manisha Shah, and Sangita Vyas. We are grateful to Pratham\nand the ASER Centre for making the ASER data available for this project; we particularly thank Natasha\nArora, Ranajit Bhattacharyya, and Sushmita Das. Dean Spears acknowledges with thanks support for the\nresearch program of which this paper is a part from the World Bank Water and Sanitation Program (WSP)\nand the Bill and Melinda Gates Foundation. All conclusions and any errors are our own.\n\n\n1\n\nMention: \"ASER data\""}, {"role": "assistant", "content": "{\"role\": \"supporting\", \"usage_action\": \"source\", \"summary\": \"Acknowledged provision of these learning outcome data for the project.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:005780:12:1", "occurrence_id": "c2bf078cefc67ed54f275517", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: constructed.\n\n\nThe vector of individual controls for individual i in country j includes education level,\n\ngender, access to formal banking, age and income quintile. We set up the first three of these\n\nvariables as 0/1 dummy variables - whether the individual has completed secondary school,\n\nwhether the individual is female, and finally whether the individual had access to a formal bank\n\naccount. Income quintile refers to the within country relative income provided by the Global\n\nFindex dataset, and we include a set of four dummy variables in our analysis to capture the\n\nvariable. Age is measured both by the age and age squared to account for non-linearity in how\n\nage affects usage as young adults could be more likely to use m-banking.\n\n\nThe country controls vary depending of the specification we use, but for our baseline\n\nregression it includes log of GDP per capita, percent of unbanked population, percent of urban\n\npopulation, percentage of population owning a mobile phone, concentration of banks (top three),\n\n\n11\n\nMention: \"the Global\n\nFindex dataset\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"Within-country relative income quintiles come from this dataset.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:005798:35:0", "occurrence_id": "1b8865a185b5e4281d737354", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: The third speci…cation deals with the possibility that the potential negative e¤ects of heavy\n\n\nrainfall (and ‡ood) on wages may induce substitution e¤ects. We report IV estimates that control\n\n\nfor agricultural wages and spatial cost of living index (using our main IV, the heavy rainfall dummy\n\n\nbased on the period 2000-2009). The results are reported in columns (5) and (6) in Table 6. They\n\n\ncon…rm the argument that the potential negative e¤ects on wages and prices are not relevant for\n\n\nour results.\n\n\nAlternative Time Period for the Rainfall Instrument\n\n\nThe heavy rainfall dummy we so far used for identi…cation is de…ned on the basis of 10\n\n\nyears data on average rainfall for the period 2000-2009. If our estimates are in fact the e¤ects of\n\n\n‘economic status’(i.e, permanent income) of a household on bribing in schools, then the estimates\n\n\nshould not change signi…cantly if we use average rainfall data from a somewhat di¤erent period.\n\n\nWe checked the sensitivity of the estimates for alternative periods, and it is reassuring that the\n\n\nestimates remain robust. For example, consider the estimates using rainfall data for 1999-2005\n\n\npresented in columns (7) and (8) in Table 6, they are almost identical to the estimates we found\n\n\nearlier using the 2000-2009 rainfall data.\n\n\n(9) Discussion and Interpretation of the IV Results\n\n\nIt is now widely appreciated that, when the monotonicity condition is satis…ed, the IV es\n\ntimates provide us with Local Average Treatment E¤ect (LATE), i.e., they provide estimates\n\n\nof the average causal e¤ect for those households which are a¤ected by the instrument (i.e., the\n\n\n‘compliers’). Since we exploit variations in the rainfall for our identi…cation, our estimates are\n\n\nmost relevant for those households whose income primarily\n\nMention: \"10\n\n\nyears data on average rainfall\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"analyze\", \"summary\": \"The heavy rainfall instrument is defined from this decade of averages.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:005801:7:0", "occurrence_id": "244d8ed1e31f81b825ed180a", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: The rest of the paper is organized as follows. Section II discusses the data. Section III\n\n\nlays out the empirical methodology. Section IV presents the empirical results. Section V\n\n\nconcludes.\n\n\n**II-** **Data**\n\n\nOur database combines annual bank-level financial information from Bankscope, a\n\n\ncommercial dataset provided by Bureau van Dijk, with bank ownership information collected\n\n\nfrom various sources including Fitch Research, The Bankers’ Almanac, bank websites, Central\n\n\nBank publications, parent company’s reports and bank regulation authorities. Overall, our dataset\n\n\ncovers 1,194 banks 5 operating in 51 countries from 2005 to 2009. Our sample spans three\n\n\nregions, including 7 countries in East Asia and the Pacific (EAP), 25 in Europe and Central Asia\n\n\n(ECA), and 19 in Latin America and the Caribbean (LAC). Because ECA is the largest and most\n\n\ndiverse region in terms of the number of countries, we further divide the region into three sub\n\ngroups: 5 countries that participated in the so-called “Vienna Initiative” (ECA VI) 6 [^6: The Vienna Initiative was an action plan in which multinational banks, international financial institutions (EBRD,\nIMF, World Bank), and European governments agreed to cooperate to support the local banking systems in Bosnia,\nHungary, Latvia, Serbia, and Romania. The international financial institutions provided support in exchange for\ncountries’ commitments to keep their economic programs on track. In turn, various multinational banks (Alpha Bank,\nBayerische Landesbank, Erste Group, Eurobank EFG, Hype Alpe-Adria, ING, Intesa San Paolo, KBC Group,\nNational Bank of Greece, Nordea Bank, OTP, Piraeus Bank, Raiffeisen International, Skandinaviska Enskilda\nBanker, Societe Generale, Swedbank, UniCredit, and Volksbank) signed commitment letters in which they pledged\nto maintain exposures and keep their affiliates in these countries adequately capitalized.], 8 countries\n\n\nthat were part of the former Soviet Union (ECA FSU\n\nMention: \"Bankscope\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"Annual bank-level financial information comes from this commercial dataset.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:005839:12:0", "occurrence_id": "a93c11d46e19f03525832e92", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: Nevertheless, if the national poverty line is used to identify the poor, could we still\ndefend the Tendulkar line as adequate? We argue in the affirmative.\n\n\nSource: Calculations from the NSSO expenditure survey, 2004-05, by Rahul Ahluwalia\nof International School of Business, Hyderabad\n\n\nGoing by the urban and rural population weights of 0.298 and 0.702 implicit in\nthe population projections for January 1, 2010, the average countrywide per-capita MRP\nexpenditure during 2009-10 works out to 40.2 rupees per person per day. Therefore,\n\n\n9\n\nMention: \"the NSSO expenditure survey, 2004-05\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"analyze\", \"summary\": \"Calculations testing the adequacy of the poverty line use this round.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:005843:52:1", "occurrence_id": "1711f0c2413c00d830450edf", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: -19
20-24
25-29
30-34
35-39
40+
Age
Small-firm, Capital Intensive|50
100 150 200 250
Employment (Linear Prediction)
<5
5-9
10-14
15-19
20-24
25-29
30-34
35-39
40+
Age
Low Dependence on External Finance|
100 200 300 400 500
Employment (Linear Prediction)
<5
5-9
10-14
15-19
20-24
25-29
30-34
35-39
40+
Age
High Dependence on External Finance|\n\n\n\n\n\nSource: ASI Data pooled from the following census years: 1983/84, 1989/90, 1994/95, 2000/01, 2004/05\n\n\n\n51\n\nMention: \"ASI Data\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"Pooled across five benchmark years for the age and finance analysis.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:005862:7:1", "occurrence_id": "4252c251215dc6436dfc27f2", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: environment resulting in continued contamination of soil and water, and poten\ntially infecting others in the community who practice safe sanitation. In other words, even\n\nif my household has chosen to practice safe sanitation, if others in my community continue\n\nto defecate in the open, what are the consequences for the welfare of my household?\n\n\nObservational and quasi-experimental studies have looked at the impact of improved sanita\ntion on child health outcomes including diarrhea, infant mortality, and stunting. However,\n\nmost of these studies have focused on the effects at the household level and have not consid\nered the importance, or additional effects, that may be present when an entire community\n\nhas access to sanitation. The most relevant for the current study is a recent paper that\n\nused propensity score matching to estimate the effect of access to improved sanitation on\n\ndiarrhea in children under five using the District Level Household Survey (DLHS-3) (Ku\n\n3Indeed, some have suggested there is too little evidence on the complementary effects of WSH in\nterventions and that too much attention has been focused on understanding the epidemiology of single\n\ntransmission pathways (see Eisenberg (2007 and 2012)).\n\n4This effect also goes the other way, with poor nutritional status associated with increased risk of diarrhea\n\n(see for example Chen et al. (1981)).\n\n\n6\n\nMention: \"District Level Household Survey\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"Child diarrhoea and sanitation access are estimated from this round.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:005862:7:1", "occurrence_id": "8a96505132d9bf9ea6b2b552", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: environment resulting in continued contamination of soil and water, and poten\ntially infecting others in the community who practice safe sanitation. In other words, even\n\nif my household has chosen to practice safe sanitation, if others in my community continue\n\nto defecate in the open, what are the consequences for the welfare of my household?\n\n\nObservational and quasi-experimental studies have looked at the impact of improved sanita\ntion on child health outcomes including diarrhea, infant mortality, and stunting. However,\n\nmost of these studies have focused on the effects at the household level and have not consid\nered the importance, or additional effects, that may be present when an entire community\n\nhas access to sanitation. The most relevant for the current study is a recent paper that\n\nused propensity score matching to estimate the effect of access to improved sanitation on\n\ndiarrhea in children under five using the District Level Household Survey (DLHS-3) (Ku\n\n3Indeed, some have suggested there is too little evidence on the complementary effects of WSH in\nterventions and that too much attention has been focused on understanding the epidemiology of single\n\ntransmission pathways (see Eisenberg (2007 and 2012)).\n\n4This effect also goes the other way, with poor nutritional status associated with increased risk of diarrhea\n\n(see for example Chen et al. (1981)).\n\n\n6\n\nMention: \"DLHS-3\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"The same round as the short-name reference.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:005880:10:2", "occurrence_id": "7864d5050e449e325ad0a380", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: total gross value added divided by total employment|* Usage of power is ignored and only the criteria of 10 or more employees is considered for registration under the Factories Act,1948.
Excludes firms with missng or zero employment.
**Includes unpaid family membes/helpers working in the firm.
***Labor productivity is total gross value added divided by total employment|* Usage of power is ignored and only the criteria of 10 or more employees is considered for registration under the Factories Act,1948.
Excludes firms with missng or zero employment.
**Includes unpaid family membes/helpers working in the firm.
***Labor productivity is total gross value added divided by total employment|* Usage of power is ignored and only the criteria of 10 or more employees is considered for registration under the Factories Act,1948.
Excludes firms with missng or zero employment.
**Includes unpaid family membes/helpers working in the firm.
***Labor productivity is total gross value added divided by total employment|\n\n\nSome idea of the trends is given by comparing the 2010-11 NSSO survey and 2009-10 ASI with the 200506 NSSO survey and ASI in (Table 2). Share of formal firms went from 0.7% of all firms to 0.8% over this five year\nperiod, and their employment share increased from 19.5% to 24.8%. Thus, the employment share of total\ninformality (B, C and D) declined correspondingly. The employment share of noncompliant firms (B) went from\n8.9% to 9.8%, a clear upward trend. The share of employment of the avoiders (C) does not seem to have\nchanged at all, while the share of the outsiders (D\n\nMention: \"NSSO survey\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"analyze\", \"summary\": \"Two rounds bracket the change in the formal firm share.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:005880:10:2", "occurrence_id": "6a58ecca2ecfccdc45b42d90", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: total gross value added divided by total employment|* Usage of power is ignored and only the criteria of 10 or more employees is considered for registration under the Factories Act,1948.
Excludes firms with missng or zero employment.
**Includes unpaid family membes/helpers working in the firm.
***Labor productivity is total gross value added divided by total employment|* Usage of power is ignored and only the criteria of 10 or more employees is considered for registration under the Factories Act,1948.
Excludes firms with missng or zero employment.
**Includes unpaid family membes/helpers working in the firm.
***Labor productivity is total gross value added divided by total employment|* Usage of power is ignored and only the criteria of 10 or more employees is considered for registration under the Factories Act,1948.
Excludes firms with missng or zero employment.
**Includes unpaid family membes/helpers working in the firm.
***Labor productivity is total gross value added divided by total employment|\n\n\nSome idea of the trends is given by comparing the 2010-11 NSSO survey and 2009-10 ASI with the 200506 NSSO survey and ASI in (Table 2). Share of formal firms went from 0.7% of all firms to 0.8% over this five year\nperiod, and their employment share increased from 19.5% to 24.8%. Thus, the employment share of total\ninformality (B, C and D) declined correspondingly. The employment share of noncompliant firms (B) went from\n8.9% to 9.8%, a clear upward trend. The share of employment of the avoiders (C) does not seem to have\nchanged at all, while the share of the outsiders (D\n\nMention: \"ASI\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"analyze\", \"summary\": \"The companion industry series for the same comparison.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:005952:18:0", "occurrence_id": "68d999a2b0bb1492c2d35026", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: poor could not benefit as much from the increase in formal jobs (structural changes are discussed further\nin section 3.2) because of entry barriers such as good education, networks and so forth. 8 [^8: This hypothesis is supported by the findings from Grun et al. (2013) showing that in the post-crisis period most of the jobs were\nformal jobs requiring university education.] Besides wages,\npensions were the second most important equalizing factor during the considered period. The share of\nadults in the household and social assistance also contributed to the reduction of the Gini coefficient.\n\n**Figure 3.4a: Sources of welfare improvement** **Figure 3.4b: Sources of welfare improvement**\n**across classes in 2002-2011, %** **for the bottom 40 percent of the population in**\n\n**2002-2011, %**\n\n\nSource: Authors’ calculation based on ECAPOV data.\nNotes: Welfare aggregate is income per capita. Negative share means negative contribution to welfare. Thresholds for poor,\nvulnerable and middle class are 5 and 10 USD/PPP 2005 per day. Methodological details are presented in Azevedo and Nguyen\n(2014).\n\n26. **The contribution of women to poverty and inequality reduction was very limited.** Income\npoverty decomposition across gender demonstrates that female contribution to poverty reduction through\nthe labor market, share of adults and pensions was much lower than that of males (figure 3.5). Moreover,\nboth female earnings and added worker effects were inequality increasing (figure 3.6). This may be\nrelated to the fact that women with better education benefit from entering the labor market and earning\nhigher wages. One possible explanation of lower contribution of the share of female adults to poverty\nreduction is that women tend to get married earlier than men and leave the household. In addition, there\nwas a tendency for men to\n\nMention: \"ECAPOV data\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"analyze\", \"summary\": \"Welfare contribution shares over this decade are calculated from these data.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:005956:26:1", "occurrence_id": "8b664b62c54e1c1f43e2e2a0", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: in the Reinhart & Rogoff\n\n\n(2009) dataset that are represented in our aggregate crisis experience variable (as described in\n\n\nSubsection 4.1). The most striking result is that every single crisis type has a negative coefficient—\n\n\nin line with our aggregate—but only experiences in currency and domestic debt crises enter with a\n\n\nsignificant coefficient. We also note that experience in banking crises enters with a relatively high\n\n\ncoefficient, and is statistically insignificant mainly because it is accompanied by correspondingly\n\n\nlarge standard errors. This latter result may be understood by recognizing the fact that banking\n\n\ncrises are generally rather heterogeneous in terms of both context and causes. As a result, banks\n\n\nmay acquire mixed experiences as a result of past banking crises, and accordingly respond to them\n\n\nin ways that go beyond contractions in their loan portfolio.\n\n\nThe relative importance of currency crises and domestic debt crises in terms of crisis experience\n\n\nsuggests that these sorts of crises offer important learning opportunities, insofar as lending activity is\n\n\nconcerned. Currency and domestic debt crises often impose real costs (Caballero & Krishnamurthy\n\n\n2001), which may or may not always occur with stock market and banking crises. However, there\n\n\nis also the possibility that these crises are especially important because they directly impact bank\n\n\nbalance sheets (as opposed to stock market crashes or external debt crises, which would have either\n\n\na small or indirect impact on bank balance sheets, or banking crises, which affect bank operations\n\n\nacross their entire spectrum of operations, not just their lending).\n\n\nAnother approach to decomposing the crisis experience variable is to capture the independent\n\n\ncomponents embedded in the crisis experience measure after stripping out correlated elements\n\n\nwithin each separate type of crisis experience. We perform this decomposition with principal\n\n\ncomponents analysis (PCA). More specifically, we calculate the proportion-weighted average of the\n\n\n25\n\nMention: \"the Reinhart & Rogoff\n\n\n(2009) dataset\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"Its crisis episodes feed the aggregate crisis experience variable.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:005970:42:2", "occurrence_id": "645345f6777e294c86ad92d6", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: 06
|\n\n\n\n_Figure B1: Roofer wages in an area where losses have been significant after the 2004 hurricane season in_\n_Florida. Data from the Bureau of Labor Statistics, Occupational Employment Surveys in May 03, Nov 03,_\n_May 04, Nov 04, May 05, May 06, May 07._\n\nFigure B2 is a classical quantity-price plot, showing the long-term demand and supply curves for a goods\nor service aggregated at the macroeconomic level. The green line is the demand curve: it shows how the\n\n33 The only case where this result does not hold is when the production function is in the form: _Y=f(K1+K2+…+Kn)._\n\n\n41\n\nMention: \"Bureau of Labor Statistics, Occupational Employment Surveys\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"Employment across these survey dates traces hurricane employment losses.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:005974:11:0", "occurrence_id": "0627778f3ec18feef0ec5cbc", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: _migrants’ transfers_, which are a capital account transfer reflecting the movement of assets by a\n\nmigrant from one country to another when he or she migrates (IMF 1993). The World Bank\n\ncombines workers’ remittances and compensation of employees together to form the remittance\n\nmeasure reported in its World Development Indicators, and this has been the definition of\n\nremittances used in a number of studies in the literature (e.g. Catrinescu et al. 2009). 3 [^3: There has been some debate over this definition with Barajas et al. (2009) just using workers’ remittances, and Guiliano and\nRuiz-Arranz (2009) using the sum of all three components, but then making adjustments on a country-by-country basis.]\n\n\nHowever, in practice it often proved difficult to separate transfers made by migrant workers from\n\ntheir employment income from a number of other transfers. The Balance of Payments Manual 6\n\n(BPM6) therefore replaced the category of _workers’ remittances_ with _personal transfers_ which\n\nconsist of “all current transfers in cash or in kind made or received by resident households to or\n\nfrom nonresident households” (IMF 2009, p. 20). Personal remittances in the World\n\nDevelopment Indicators (and Figure 1) are then the sum of these personal transfers and\n\ncompensation of employees.\n\n\nThe underlying data that feeds into these aggregates comes from central banks in each individual\n\ncountry. They typically require banks, money transfer operators and other institutions to provide\n\nreports on the transactions they process (Orozco 2006). However, in many cases the coverage of\n\nthis reporting has been partial. De Luna Martínez (2005) reports on a survey of central banks in\n\n40 developing countries that took place in 2004. He finds that 90 percent of the countries\n\ncollected remittance data from commercial banks, but such data were collected in only 65\n\npercent of the countries in which credit unions and exchange houses processed remittances, in\n\nonly 38 percent of the countries in which money transfer operators processed remittances, and in\n\nonly 35 percent\n\nMention: \"World Development Indicators\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"Its combined transfers and compensation measure defines the remittance series.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:005979:27:0", "occurrence_id": "1ed49339c6c4337822ed96d3", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: 26\n\n\npocket payments than immiserized families. Nonetheless, as a count-based measure\n\n\nit is not bad, capturing as it does the idea that from a poverty-reduction perspective\n\n\nimpoverishing and immiserizing payments are worse than catastrophic payments\n\n\n(at least if defined in terms of whether they leave a family close to the poverty line),\n\n\nwhich are in turn worse than non-catastrophic payments, which are in turn worse\n\n\nthan no payments (especially if this group is restricted to users). Moreover, this\n\n\nindex is easy to explain to a non-technical audience.\n\n\nWe have illustrated our ideas using data from 51 countries for which out-of\n\npocket spending data are available in the World Health Survey. We use $1.25-a\n\nday, $2-a-day and $5-a-day international poverty lines, and a catastrophic payment\n\n\nthreshold of 40 percent. While intended to be only illustrative, the results are not\n\n\nwithout interest. For the 51 countries as a whole, we find very small shares of\n\n\nhouseholds falling into the impoverishment and catastrophic spending categories,\n\n\nand a much larger fraction falling into the immiserizing category. We also find a\n\n\nlarger fraction of households in the catastrophic payment category when\n\n\ncatastrophic payments are defined as payments that leave a family’s nonmedical\n\n\nconsumption below _Z_ times the poverty line. Unsurprisingly, as we raise the\n\n\npoverty line, the share of households falling into the immiserizing spending\n\n\ncategory increase, and the shares falling into the impoverishing and catastrophic\n\n\nspending categories decrease. In our more detailed analysis of the BRICS countries\n\n\n(Brazil, China, India, Russia and South Africa), we see appreciable fractions of the\n\n\npopulation in some countries falling into the impoverishing and catastrophic\n\nMention: \"World Health Survey\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"Out-of-pocket spending for 51 countries is available in this survey.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:006004:27:3", "occurrence_id": "5511d899c38e382dab1a0dde", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: 2.5\nmillion has of national park land). In turn, this means that the maximum carrying capacity of about 1.65 million,\n\n**Appendix 2 Description of SAM and CGE Multipliers** which is close to the estimate of the carrying capacity in Stratton ( _op cit_ ).\n\n\n\nπ _N_\n\n\n\n**Appendix 2 Description of SAM and CGE Multipliers**\n\n\n\nThe model is based on a SAM estimated on the basis of the GTAP data set supplemented by official and other\nstatistics. The basic model represents the Tanzanian economy with 10 economic sectors, 4 production factors, 2\ninstitutions, Capital Formation and The Rest of the World, or, in more detail:\nOur model represents the economy with 29 sectors. In the GTAP model the Natural Resources sector only\nincludes the value of the resources used by mining and extraction. The factor Land includes only cultivated land.\n\n26\n\nThe GTAP SAM is augmented in to take better account of the Serengeti economy:\n\nMention: \"the GTAP data set\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"The social accounting matrix for one economy is estimated on this basis.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:006045:24:0", "occurrence_id": "1daec309c40c56443d2a7ea9", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: distributed somewhat differently across countries. Egypt sees the most new city-to-city routes (6) with\n\n\nTurkey under this specification.\n\n\n**VI.** **Conclusions**\n\n\nIn this study, we estimate a set of empirical models of air passenger traffic, in order to better\n\n\nunderstand the relationship between air transport policy and international traffic. We use a WTO index\n\n\nmeasure of policy commitments in both bilateral and plurilateral air services agreements, and relate these\n\n\nmeasures to ICAO data on air passenger traffic. We find that country pairs with more liberal policy\n\n\ncommitments see greater air passenger traffic. Subsequent work at the city level indicates that, to a large\n\n\ndegree, larger passenger numbers in more liberal agreements occur because more city pairs are served by\n\n\na flight.\n\n\nWe use our empirical models to investigate the likely impact of two policy changes. First, we\n\n\nconsider the impact of deepening the ACAC agreement, awarding it the same policy score as the UK\n\nSingapore bilateral agreement. Because policy within the ACAC is already fairly liberal, the deepening\n\n\nof the agreement has modest, but significant effects. Our estimates suggest a 30% increase in traffic\n\n\nbetween ACAC countries as a result of the policy change.\n\n\nIn a second scenario we add Turkey to the deeper ACAC agreement, assigning the same liberal\n\n\nmeasures to Turkey-ACAC passenger flows. Due to the restrictive nature of policy commitments\n\n\nbetween Turkey and many Arab countries, this scenario generates much more growth in passenger traffic.\n\n\nOur estimates suggest that passenger traffic would more than double. Much of this would arise through\n\n\nincreasing numbers of direct flights between Turkish cities and cities in the ACAC member states.\n\n\nWhile these results may seem optimistic, there are three reasons to suggest they are not\n\n\nunrealistic. First, current air passenger traffic levels in the region are low, and fast growth is plausible off\n\n\na small base. Second, much faster growth rates have been observed in recent years in selected regional\n\n\nmarkets. Finally, the policy changes\n\nMention: \"ICAO data on air passenger traffic\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"analyze\", \"summary\": \"Traffic outcomes are related to the liberalisation of air services agreements.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:006057:10:1", "occurrence_id": "7d7c433bd80d5adfb5257653", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: quality of\n\npolitical institutions. 9 [^9: Van de Ploeg and Poelhekke 2010 show that adverse growth effects of natural resources results mainly from the\nvolatility of commodity prices, especially for point-based resources. Indeed, the indirect effects of resource exports\non growth via the volatility channel outweigh a direct positive effect of resource endowments on growth. Arezki,\nHamilton and Kazimov 2011 find that overall government spending in resource-exporting countries has been procyclical relative to commodity prices and that in the long run resource windfalls have negative effects on the growth\nof non-resource GDP. Both the effects of windfalls on macroeconomic stability and on growth are moderated by the\nquality of political institutions.] Improved capacity to manage shocks, a more robust financial sector, and efforts to\n\nencourage a more diversified economy are some of the ways in which resource-rich countries can work to\n\nminimize the curse. A few, like Chile, have succeeded in sustaining counter-cyclical policies using fiscal\n\nrules and transparent and independent projections of long-run resource prices to guide policy (de Gregorio\n\nand Labbe 2011), but even for these it has not been easy to resist the pressures to increase spending at\n\n\n7 Oil prices have very high long-term volatility and hard mineral prices are not far behind. Hamilton 2008 estimates\nthe likely price band for oil prices up to four years into the future, assuming that the logarithm of prices follows a\nGaussian random walk. Starting from an initial price of $115 per barrel, the 95% confidence range for the four year\ndistribution was between $34 and $391. At the time, in the middle of the super-boom with prices spiking up to\n$140, no one could have imagined prices at the low end of the scale, but they collapsed to that level shortly after the\npublication of the study with the onset of the global crisis. In addition, many of the new producers face high base\nproduction costs, further increasing the sensitivity of rent flows to market prices.\n8 The IMF commodities outlook for December 17, 2013, putsmod\n\nMention: \"IMF commodities outlook\""}, {"role": "assistant", "content": "{\"role\": \"supporting\", \"usage_action\": \"source\", \"summary\": \"Its outlook puts forward the price path behind rent sensitivity.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:006065:21:2", "occurrence_id": "85d61ba4dba7a4b9af89158c", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: .017 0.026\nSewing Machine 0.0396 0.0089 0.447 0.451\nPesticider 0.0816 0.0201 0.043 0.048\nThree wheeler 0.2041 0.0212 0.048 0.074\nHas own or shared toilet 0.0561 0.0242 0.976 0.983\nTractor 2 wheel 0.1571 0.024 0.031 0.038\nTractor 4 wheel 0.1487 0.0709 0.007 0.009\nTV 0.067 0.011 0.777 0.818\nUnemployed ratio to household size -0.0784 0.0315 0.048 0.052\nVCD 0.0691 0.0099 0.259 0.346\nWall: pressed soil blocks -0.09 0.0162 0.051 0.041\nWashing machine 0.0907 0.018 0.088 0.121\n\nSource: Authors’ calculations using HIES 2006/07 and 2009/10\n\n\n20\n\nMention: \"HIES\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"analyze\", \"summary\": \"Regression results are computed across these two household rounds.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:006093:29:0", "occurrence_id": "c3329aa355b8db4fbd37dda3", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: granted in Croatia in 2011 amounted to 2.47% of GDP 22 ; which is much higher than the\naverage for EU 27 in the same period (0.51% of GDP). 23 In addition, the perception of\nintensity of local competition in the Croatian economy is well below the regional peers (see\nWEF data for 2011-12).\n\n\n22 Annual State Aid report Croatian Competition Agency\n23 Croatian data draws on the “Annual Report on State Aid for 20122”- Croatian Competition Agency. EU-27\naverage is from European Commission- DG Competition.\n\n\n20\n\nMention: \"WEF data for 2011-12\""}, {"role": "assistant", "content": "{\"role\": \"supporting\", \"usage_action\": \"source\", \"summary\": \"Competition intensity relative to regional peers is measured in these data.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:006099:13:1", "occurrence_id": "9c068248d90e4f1ce92a9e60", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: 10-29 years.\n\n\n**3.** **Inequities in Learning Achievements**\n\n\nIn Section 2, we showed that while there has been democratization in access to basic\n\n\neducation in Egypt, there remain persistent disparities in access to general secondary and college\n\n\neducation. Given that educational trajectories depend to a large extent on tracking into general and\n\n\nvocational secondary schools at completion of basic education, the quality of the education at lower\n\n\nlevels of schooling is likely to be a major determinant of educational inequalities in Egypt. 4 We now\n\n\nturn to inequalities in learning achievements, as measured by TIMSS evaluation of pupils’\n\n\n4 The tracking is determined by scores at the preparatory completion exam organized at the level of governorate.\n\n\n12\n\nMention: \"TIMSS evaluation of pupils\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"Inequalities in learning achievement are measured by this assessment.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:006111:43:1", "occurrence_id": "9517eefb1e5cbed595a1756c", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: -19
20-24
25-29
30-34
35-39
40+
Age
Small-firm, Capital Intensive|50
100 150 200 250
Employment (Linear Prediction)
<5
5-9
10-14
15-19
20-24
25-29
30-34
35-39
40+
Age
Low Dependence on External Finance|
100 200 300 400 500
Employment (Linear Prediction)
<5
5-9
10-14
15-19
20-24
25-29
30-34
35-39
40+
Age
High Dependence on External Finance|\n\n\n\n\n\nSource: ASI Data pooled from the following census years: 1983/84, 1989/90, 1994/95, 2000/01, 2004/05\n\n\n\n42\n\nMention: \"ASI Data\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"Pooled across five benchmark years for the age and finance analysis.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:006112:46:0", "occurrence_id": "7f8a0dd7ded3f7cfdc2c378f", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: where the parameter _ξ_ 1 _P_ captures the curvature of the liquid fossil fuel cost\n\nfunction. We calibrate the values of the parameter _ξ_ 1 _P_ to match observed ex-\n\ntraction rates of oil and natural gas in the rst decade of the 21st century. We\n\n\nobtain the extraction quantities of oil and natural gas from the BP Statistical\n\nReview of World Energy database (2013).\n\n\nB.1.1.3 Other Primary Resources\n\n\nThe initial values for the production of other primary inputs come from GTAP\n\n\nv.7 database and are de\u001cned as the value of output from labor (skilled and\n\n\nunskilled), capital, and natural resources. We set the growth rate of other\n\n\nprimary resources as the di\u001berence between global GDP growth and total factor\n\n\nproductivity growth rates from Jorgenson and Vu (2010) projections based on\n\n\neconometric estimates for 122 economies over the 1990 - 2008 period (see Figure\n\n\nB.1, panel b).\n\n\nB.1.2 Intermediate Inputs\n\n\nB.1.2.1 Petroleum Products\n\n\nThe re\u001cning of petroleum, _x_ _p_ _t_ _,_ <\n\nMention: \"BP Statistical\n\nReview of World Energy database\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"Oil and gas extraction quantities come from this edition.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:006112:46:0", "occurrence_id": "8b00030dda15ee50124b8179", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: where the parameter _ξ_ 1 _P_ captures the curvature of the liquid fossil fuel cost\n\nfunction. We calibrate the values of the parameter _ξ_ 1 _P_ to match observed ex-\n\ntraction rates of oil and natural gas in the rst decade of the 21st century. We\n\n\nobtain the extraction quantities of oil and natural gas from the BP Statistical\n\nReview of World Energy database (2013).\n\n\nB.1.1.3 Other Primary Resources\n\n\nThe initial values for the production of other primary inputs come from GTAP\n\n\nv.7 database and are de\u001cned as the value of output from labor (skilled and\n\n\nunskilled), capital, and natural resources. We set the growth rate of other\n\n\nprimary resources as the di\u001berence between global GDP growth and total factor\n\n\nproductivity growth rates from Jorgenson and Vu (2010) projections based on\n\n\neconometric estimates for 122 economies over the 1990 - 2008 period (see Figure\n\n\nB.1, panel b).\n\n\nB.1.2 Intermediate Inputs\n\n\nB.1.2.1 Petroleum Products\n\n\nThe re\u001cning of petroleum, _x_ _p_ _t_ _,_ <\n\nMention: \"GTAP\n\n\nv.7 database\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"Initial values for other primary inputs come from this version.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:006124:9:0", "occurrence_id": "e0a78e679bd7cc9f3b2b9deb", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: empirical measure is the stock of education (years of schooling per person available from Barro and Lee,\n2013) averaged over 1970-2010.\n\n\n_Food sufficiency_ : Adequacy of food among mothers is likely to be related positively to higher baby\nweight, better health at birth, and higher levels of breastfeeding and thus to better chances for baby\nand child survival. Similarly, adequacy of food among children is likely to lead to stronger and healthier\nchildren with a reduced susceptibility to disease and death. In the regression analysis below we have\nincluded a variable called “undernourishment” which measures food intake status. This measure is\navailable from the WDI database but only since 1992 and so the average over 1992-2010 is used in the\nempirical work. 5 [^5: The measure is called “Prevalence of Undernourishment” in the WDI database and refers to the proportion of the\npopulation whose food intake is insufficient to meet minimum dietary energy requirements continuously. The\nstatistical methodology note in the database states: “Data on undernourishment are from the Food and\nAgriculture Organization (FAO) of the United Nations and measure food deprivation based on average food\navailable for human consumption per person, the level of inequality in access to food, and the minimum calories\nrequired for an average person.” This measure is among those used to track the Millennium Development Goal\ntargets related to poverty and hunger (MDG1C).]\n\n\n_Urbanization_ : The link between urbanization and child mortality could go either way. Greater\nurbanization usually reflects higher population densities. On the positive side, this means that a given\nhealth facility is likely to be able to cover more people in more urban settings. Thus, all other things\nbeing equal, urbanization should result in greater economies of scale from health spending and better\nhealth outcomes, including for child mortality. More urban settings are also likely to be associated with\neasier access to health facilities through better transport than more rural settings. On the negative\nside, greater population densities could also be associated with higher probabilities of disease incidence\n\nMention: \"WDI database\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"Its food intake measure begins only in this year, so an average is used.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:006129:0:0", "occurrence_id": "496e1bee71b462cde184f7fa", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: Policy Research Working Paper\n7028\nGLS Estimation and Empirical Bayes \nPrediction for Linear Mixed Models \nwith Heteroskedasticity and Sampling Weights\nA Background Study for the POVMAP Project\nRoy van der Weide\nDevelopment Research Group\nPoverty and Inequality Team\nSeptember 2014\nWPS7028\nPublic Disclosure Authorized\nPublic Disclosure Authorized\nPublic Disclosure Authorized\nPublic Disclosure Authorized\nPublic Disclosure Authorized\nPublic Disclosure Authorized\nPublic Disclosure Authorized\nPublic Disclosure Authorized\n\nMention: \"the POVMAP Project\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"inform\", \"summary\": \"This methodological background study was prepared for that project.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:006135:14:0", "occurrence_id": "e9cb4f8932b77561b22cf830", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: village that had experienced payouts would have also experienced uninsured rainfall shocks during the\n\n\nsame season. Therefore it may be possible that there are effects of trust and learning, but they are\n\n\noutweighed by opposite effects of the weather. As we saw in the previous section, rainfall shocks tend\n\n\nto have a negative effect on insurance demand, so the (lack of) evidence of spillovers may be a result\n\nof a more complex interaction between trust/learning and direct effects of weather.\n\n\nOverall, these results do not support the hypothesis that trust, learning, or any other effects of\n\n\nsimply witnessing insurance payouts are driving increased purchasing. While it is possible that our\n\n\nmeasurements of spillovers are too crude and miss more subtle effects, the data simply does not provide\n\n\nevidence that here are strong spillover effects. Since we do not see these spillover effects, this casts\n\n\ndoubt on the theory that repurchases are being driven by increased trust in the insurance company or\n\n\nlearning about insurance payouts.\n\n\n**4.3** **Direct** **Effects** **of** **Payouts** **on** **Wealth** **and** **Liquidity**\n\n\nThe previous two sections discount the possibility that trust, learning, or weather effects are driving\n\n\nthe result that receiving an insurance payout is correlated with purchasing insurance the following\n\n\nyear. This points to the actual reception of money from the insurance company as being the driving\n\n\nforce behind greater takeup. The most natural explanation for this phenomenon would be that recving\n\n\nan insurance payout could directly affect choices the next year due to its effects on wealth and liquidity.\n\n\nFor instance, if insurance is a normal good then increased wealth would result in greater insurance\n\ndemand. 16\n\n\nWhile the BASIX data set does not offer the opportunity to test the direct effects of a cash payment\n\n\nseparately from an insurance payout, there are a number of reasons why it\n\nMention: \"BASIX data set\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"validate\", \"summary\": \"It does not allow testing the direct effect of a cash payment separately.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:006140:18:0", "occurrence_id": "4e2381fe0c1211d4382bd702", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: curves accessed from the AIDSinfo Online Database from the 2012 and 2013 UNAIDS\nreports, only differing by one more years of data, several countries showed considerable\ndifference between the two incidence curves. In many cases estimated peak incidence\nwas higher from the 2013 report (12 out of 19 countries had higher incidence peaks\nusing the 2013 report data; median difference between highest incidence from 2013 to\n2012 report among these 12 countries, 0.33, but as high as 1.37) sometimes occurring in\na different year than the 2012 report, and these changes were evident as far back as\n1990 (Annex 2).\n\nStill, changes in incidence, estimated by Spectrum, have been important for measuring\nprogress in the global fight against HIV/AIDS at regional and country levels. The 2012\nGlobal AIDS report grouped countries by overall changes in incidence between 20012011, with those falling into categories of increasing incidence over 25%, stable\nincidence (less than 25% change in incidence, up or down), and those with reductions in\nincidence greater than 25% and 50%. Although the majority of countries in the 2012\nreport have estimated incidence reductions over 25%, a third of them are estimated to\nhave experienced stable incidence, or worse, incidence increases over 25% between\n2001 and 2011 (including Congo, Lesotho, Nigeria, Tanzania, and Lesotho, which have all\nexperienced stable incidence over that period).\n\n**2.2. Effect of ART on prevalence data, mortality, and infectiousness**\n\nAchieving universal access to ART (reaching 80% of those in need of treatment) is a\nglobal priority, and the provision of ARVs is a key component of combination HIV\nprevention strategies, as ART reduces the likelihood of both sexual and mother-to-child\ntransmission of HIV. Following the hallmark HPTN052 study showing that early HIV\ntreatment of HIV positive partners among sero-discordant couples significantly reduced\ntransmission to their partners (Cohen\n\nMention: \"AIDSinfo Online Database\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"Prevalence curves are accessed from these two report editions.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:006140:18:0", "occurrence_id": "3329c1b0b37941c65d484d7c", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: curves accessed from the AIDSinfo Online Database from the 2012 and 2013 UNAIDS\nreports, only differing by one more years of data, several countries showed considerable\ndifference between the two incidence curves. In many cases estimated peak incidence\nwas higher from the 2013 report (12 out of 19 countries had higher incidence peaks\nusing the 2013 report data; median difference between highest incidence from 2013 to\n2012 report among these 12 countries, 0.33, but as high as 1.37) sometimes occurring in\na different year than the 2012 report, and these changes were evident as far back as\n1990 (Annex 2).\n\nStill, changes in incidence, estimated by Spectrum, have been important for measuring\nprogress in the global fight against HIV/AIDS at regional and country levels. The 2012\nGlobal AIDS report grouped countries by overall changes in incidence between 20012011, with those falling into categories of increasing incidence over 25%, stable\nincidence (less than 25% change in incidence, up or down), and those with reductions in\nincidence greater than 25% and 50%. Although the majority of countries in the 2012\nreport have estimated incidence reductions over 25%, a third of them are estimated to\nhave experienced stable incidence, or worse, incidence increases over 25% between\n2001 and 2011 (including Congo, Lesotho, Nigeria, Tanzania, and Lesotho, which have all\nexperienced stable incidence over that period).\n\n**2.2. Effect of ART on prevalence data, mortality, and infectiousness**\n\nAchieving universal access to ART (reaching 80% of those in need of treatment) is a\nglobal priority, and the provision of ARVs is a key component of combination HIV\nprevention strategies, as ART reduces the likelihood of both sexual and mother-to-child\ntransmission of HIV. Following the hallmark HPTN052 study showing that early HIV\ntreatment of HIV positive partners among sero-discordant couples significantly reduced\ntransmission to their partners (Cohen\n\nMention: \"2013 report data\""}, {"role": "assistant", "content": "{\"role\": \"supporting\", \"usage_action\": \"source\", \"summary\": \"Its incidence peaks are higher in most countries relative to the prior edition.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:006195:25:0", "occurrence_id": "21eac065a516f1bb53f647d1", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: housing expenditures for three African cities (Table 4) suggest that housing expenditure is less responsive\nin these cities than in other developing countries (see Malpezzi and Mayo 1987).\n\nMalpezzi and Mayo (1987) review previous housing demand studies in over a dozen developing country\ncities and find that income elasticities are fairly consistent across countries, and in most cases fall\nbetween 0.5 and 1, with renters generally have slightly lower income elasticities than owners. 31 [^31: Likewise, Struyk, et al. (1990) find a similar difference between renters and owners in Indonesia and also note that income\nelasticities decrease with city size.] These\nestimates however, were mostly for Latin American and East Asian countries/cities, with little to no\nrepresentation of low-income or SSA countries. Using the SHIP data to estimate income elasticity of\nhousing expenditures in Kigali, Abidjan, and Maputo yields coefficients on log income ranging from 0.15\nand 0.37 (Table 4). Interestingly, early estimates of the income elasticity for low income housing in the\nUS are in a similar range: 0.19 for renters and 0.45 for owners (Mulford 1979). The estimated elasticities\nsuggest that a 10 percent increase in income will only lead to increases in housing expenditures ranging\nbetween 1.5 and 3.6 percent. Cash transfers to households would not lead to increased expenditures in\nhousing unless strongly earmarked.\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n|Col1|Kigali|Col3|Abidjan|Col5|Maputo|Col7|\n|---|---|---|---|---|---|---|\n|Log Income
|0.162
(.016)***
|0.159
(.016)***
|0.150
(.015)***
|0.150
\n\nMention: \"SHIP data\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"analyze\", \"summary\": \"Housing expenditure elasticities are estimated for three cities from these data.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:006181:48:0", "occurrence_id": "747274ab0bccf452d3bed884", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: [29] Itskhoki, Oleg and Elhanan Helpman (2014). “Firms, Trade and Labor Market Dynam\n\nics.” Mimeo, Princeton University.\n\n\n[30] Jones, Ronald I. (1971). “A Three-factor Model in Theory, Trade and History.” In\n\n\n_Trade,_ _Balance_ _of_ _Payments_ _and_ _Growth:_ _Essays_ _in_ _Honor_ _of_ _C.P._ _Kindleberger_, ed.\n\n\nby Bhagwati et. al. Amsterdam: North Holland.\n\n\n[31] Jovanovic, Boyan and Robert Moffitt (1991). “An Estimate of a Sectoral Model of Labor\n\n\nMobility,” _Journal_ _of_ _Political_ _Economy_, 98:4, pp. 827-852.\n\n\n[32] Karp, Larry and Thierry Paul (1994). “Phasing In and Phasing Out Protectionism with\n\n\nCostly Adjustment of Labour,” _Economic_ _Journal_ 104:427 (November), pp. 1379-92.\n\n\n[33] King, Miriam, Steven Ruggles, J. Trent Alexander, Sarah Flood, Katie Genadek,\n\n\nMatthew B. Schroeder, Brandon Trampe, and Rebecca Vick (2010). “Integrated Public\n\n\nUse Microdata Series, Current Population Survey: Version 3.0.” Minneapolis: Univer\n\nsity of Minnesota.\n\n\n[34] Kovak, Brian (2013). “Local Labor Market Effects of Trade Policy: Evidence from\n\n\nBrazilian Liberalization.” _American_ _Economic_ _Review_ 103:5, pp. 1960-1976.\n\n\n[35] Magee, Stephen P. (1989). “Three Simple Tests of the Stolper-Samuelson Theorem.”\n\n\nCh. 7 in Stephen P. Magee, William A. Brock, and Leslie\n\nMention: \"Integrated Public\n\n\nUse Microdata Series\""}, {"role": "assistant", "content": "{\"role\": \"supporting\", \"usage_action\": \"source\", \"summary\": \"A harmonised microdata series published by a university population centre.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:006181:48:0", "occurrence_id": "a17055c5806d52b401b31da8", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: [29] Itskhoki, Oleg and Elhanan Helpman (2014). “Firms, Trade and Labor Market Dynam\n\nics.” Mimeo, Princeton University.\n\n\n[30] Jones, Ronald I. (1971). “A Three-factor Model in Theory, Trade and History.” In\n\n\n_Trade,_ _Balance_ _of_ _Payments_ _and_ _Growth:_ _Essays_ _in_ _Honor_ _of_ _C.P._ _Kindleberger_, ed.\n\n\nby Bhagwati et. al. Amsterdam: North Holland.\n\n\n[31] Jovanovic, Boyan and Robert Moffitt (1991). “An Estimate of a Sectoral Model of Labor\n\n\nMobility,” _Journal_ _of_ _Political_ _Economy_, 98:4, pp. 827-852.\n\n\n[32] Karp, Larry and Thierry Paul (1994). “Phasing In and Phasing Out Protectionism with\n\n\nCostly Adjustment of Labour,” _Economic_ _Journal_ 104:427 (November), pp. 1379-92.\n\n\n[33] King, Miriam, Steven Ruggles, J. Trent Alexander, Sarah Flood, Katie Genadek,\n\n\nMatthew B. Schroeder, Brandon Trampe, and Rebecca Vick (2010). “Integrated Public\n\n\nUse Microdata Series, Current Population Survey: Version 3.0.” Minneapolis: Univer\n\nsity of Minnesota.\n\n\n[34] Kovak, Brian (2013). “Local Labor Market Effects of Trade Policy: Evidence from\n\n\nBrazilian Liberalization.” _American_ _Economic_ _Review_ 103:5, pp. 1960-1976.\n\n\n[35] Magee, Stephen P. (1989). “Three Simple Tests of the Stolper-Samuelson Theorem.”\n\n\nCh. 7 in Stephen P. Magee, William A. Brock, and Leslie\n\nMention: \"Current Population Survey\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"The underlying survey behind this harmonised version.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:006197:3:1", "occurrence_id": "993ec90a011befb2baece777", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: and investment in irrigation (World Bank 2008).\n\nThe literature on agricultural intensification in Africa developed significantly in the 1980s\n\n\n\nand so have fertilizer use, mechanization and investment in irrigation (World Bank 2008).\n\nThe literature on agricultural intensification in Africa developed significantly in the 1980s\nand has resumed over the past decade. It generally finds that in most areas studied intensification\nhas progressed along the lines predicted by Boserup and Ruthenberg, and that agricultural\ninvolution is confined to few areas. These studies have been done using samples of locations for\nintensive studies. Under the Intensive Agricultural Surveys (ISA) that have been imbedded in\nbroader Living Standard Measurement Studies (World Bank, 2009), national household data for six\nAfrican countries is becoming available that contains the intensification and technology variables as\nwell as income. These panel data will over time present a unique opportunity to test the BR model\nin different countries and different agroclimate zones, and to see whether there are signs of\ninvolution. At the present cross section data are available for six countries, while panel data are or\nwill become available for all countries over the next few years. As we will show, only panel data\nover a sufficient period of time will be able to rigorously test the BR theory.\n\nIn this paper we are setting the stage for such later studies by describing the status of\n\n\n\nover a sufficient period of time will be able to rigorously test the BR theory.\n\nIn this paper we are setting the stage for such later studies by describing the status of\nintensification across the six countries (Ethiopia, Malawi, Niger, Nigeria Uganda and Tanzania).\nFollowing Binswanger et al. (1993) we also study the impact of the agro-ecological endowment and\naccess to markets of the environments in which the farmers live on population density,\ninfrastructure and agricultural variables including output, and use of modern inputs. We construct\na single variable for each of these, the agro-ecological potential derived from the potential yield\nestimates of To\n\nMention: \"Intensive Agricultural Surveys\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"Location samples embedded in broader household studies.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:006197:3:1", "occurrence_id": "47aa5d452e4096ebf2845666", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: and investment in irrigation (World Bank 2008).\n\nThe literature on agricultural intensification in Africa developed significantly in the 1980s\n\n\n\nand so have fertilizer use, mechanization and investment in irrigation (World Bank 2008).\n\nThe literature on agricultural intensification in Africa developed significantly in the 1980s\nand has resumed over the past decade. It generally finds that in most areas studied intensification\nhas progressed along the lines predicted by Boserup and Ruthenberg, and that agricultural\ninvolution is confined to few areas. These studies have been done using samples of locations for\nintensive studies. Under the Intensive Agricultural Surveys (ISA) that have been imbedded in\nbroader Living Standard Measurement Studies (World Bank, 2009), national household data for six\nAfrican countries is becoming available that contains the intensification and technology variables as\nwell as income. These panel data will over time present a unique opportunity to test the BR model\nin different countries and different agroclimate zones, and to see whether there are signs of\ninvolution. At the present cross section data are available for six countries, while panel data are or\nwill become available for all countries over the next few years. As we will show, only panel data\nover a sufficient period of time will be able to rigorously test the BR theory.\n\nIn this paper we are setting the stage for such later studies by describing the status of\n\n\n\nover a sufficient period of time will be able to rigorously test the BR theory.\n\nIn this paper we are setting the stage for such later studies by describing the status of\nintensification across the six countries (Ethiopia, Malawi, Niger, Nigeria Uganda and Tanzania).\nFollowing Binswanger et al. (1993) we also study the impact of the agro-ecological endowment and\naccess to markets of the environments in which the farmers live on population density,\ninfrastructure and agricultural variables including output, and use of modern inputs. We construct\na single variable for each of these, the agro-ecological potential derived from the potential yield\nestimates of To\n\nMention: \"Living Standard Measurement Studies\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"National household data for six African countries are becoming available.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:006203:17:1", "occurrence_id": "a2e4aaad547a37fca3fcbb39", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: _,jlocal_ _ODipsc ×_ ln ( _densitypsc_ ) _j_ +\n\n\n_β_ 4 _household_ _ODipsc_ + _Xipscθ_ + _αpsc_ + _εipsc._\n\n\n\n(4)\n\n\n\nAs before, we are estimating health outcomes for child _i_, in region _p_, in DHS survey _s_, and\n\n\nin country _c_ . As described above, we introduce fixed effects _α_ at country, survey, and region\n\n\nlevels, in stages. We also include the same vector of extended controls _X_, as well as the\n\n\nhousehold’s own open defecation, as described above.\n\n\nThis functional form implies that the change in health associated with a change from 0%\n\n\nto 100% local open defecation is:\n\n\n\n_∂health_ �\n_∂local_ _OD_ = _β_ ˆ1 +\n\n\n\n5\n\n\n\n_j_ =1\n\n\n\n_β_ ˆ3 _,j_ ln ( _densitypsc_ ) _i_ (5)\n\n\n\nPanel A of figure 1 plots the dependence of the infant mortality-open defecation gradient\n\n\non population density; panel B plots the height-open defecation gradient as a function of\n\n\npopulation density. In both cases, the same six specifications that were used in section 3.3\n\nMention: \"DHS survey\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"analyze\", \"summary\": \"Health outcomes are estimated within survey and country fixed effects.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:006224:17:0", "occurrence_id": "a2207db78eca0b1b799ea8e1", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: Figure 9. Growth of hourly wages in Brazil, Mexico and Peru, 2002-2012\n\n\na. Brazil b. Mexico\n\n\nc. Peru\n\n\nSource: Authors’ calculation from SEDLAC (CEDLAS and the World Bank). Note: The figures report the growth of\nhourly wage for the bottom, fifth and top decile of labor income, indexed as a proportion.\n\nThe growth rates seen across the income distributions of Brazil and Peru are consistent with the\nfalling skill premiums in the region, one of the main drivers of the reduction in inequality during the\nfirst decade of the 2000s (Gasparini et al. 2008; World Bank 2011; Lustig and Lopez-Calva 2010; and\nLustig et al. 2013). Since 2010, however, the skill premium’s rate of reduction has fallen, and in some\ncountries, reversed trends and increased (Table 1 and Table A3 in the annex). 24 Between 2003 and\n2010, most countries in Latin America saw a narrowing of the skill premium (measured using the\nhourly wage gap) between high skill and low skill workers. However, between 2010 and 2012, six out\nof the 15 countries showed increases in the skill gap, including four of six countries in the Central\nAmerica and Mexico region. Moreover, the gap between tertiary and secondary education increased in\neight countries, including in all of the countries of Central America, Mexico and Chile. This suggests a\nreduction in the relative returns to finishing secondary school and a widening gap between those with\nonly a secondary education and those with tertiary education in Mexico and Central America.\n\n\n24 Skill premium estimates are obtained from Mincer equations of log hourly wages on education levels, controlling for age\nand age squared.\n\n\n15\n\nMention: \"SEDLAC\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"analyze\", \"summary\": \"Hourly wage growth for the bottom decile is calculated from this database.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:006231:24:0", "occurrence_id": "2b4e86cb4937f965789460c7", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: **8.** **APPENDIX 1:**\n\n\n**Table A.1: Local Budget module of the Life in Kyrgyzstan survey for 2012**\n\n**8.D. LOCAL BUDGET**\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n|Now I would like to ask your opinion and involvem government authorities|ment in the process of budget decision of local|\n|---|---|\n|
How do you think, how informed are you about the
I828 budget of your local government body (Aiyl Aimak
or municipal government)?|Very well 1|\n|
How do you think, how informed are you about the
I828 budget of your local government body (Aiyl Aimak
or municipal government)?|Well 2|\n|
How do you think, how informed are you about the
I828 budget of your local government body (Aiyl Aimak
or municipal government)?|Badly 3|\n|
How do you think, how informed are you about the
I828 budget of your local government body (Aiyl Aimak
or municipal government)?|Absolutely not informed 4|\n|Please estimate, how much it is interesting to you,
how your local government body (Aiyl Aimak or
municipal
I829
government) spends your money from taxes and
payments?
|Very interesting 1|\n|Please estimate, how much it is interesting to you,
how your local government body (Aiyl Aimak or
municipal
I829
government) spends your money from taxes and
payments?
|Interesting 2|\n|Please estimate, how much it is interesting to you,\n\nMention: \"Life in Kyrgyzstan survey\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"Its local budget module is reproduced in the appendix.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:006244:1:0", "occurrence_id": "77a74f7355894b88e053e640", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: Policy Research Working Paper 7167\n\n### **Abstract**\n\nDuring the early 2000s, Moldova experienced strong economic growth and poverty and inequality reductions. This\npaper aims at uncovering the patterns behind these poverty\ntrends by looking at economic mobility and its associated\nfactors in Moldova. The findings build on the synthetic\npanel approach and allow for a non-anonymous view of the\nprocess of poverty reduction. The data used for this country\nstudy on Moldova come from the Household Budget Survey,\nwhich is conducted on a yearly basis. The paper presents\n\n\n\ntransition matrices to look at the patterns of economic\nmobility across selected consumption thresholds, as well\nas descriptive statistics and a linear probability model aimed\nat identifying correlates of economic mobility. The findings\nshow that the observed poverty reductions happened with\nlittle churning, and highlight the importance of education\nand employment on upward economic mobility in Moldova\nin the 2000s, as well as the role of public and private transfers.\n\n\n\nThis paper is a product of the Poverty Global Practice Group. It is part of a larger effort by the World Bank to provide\nopen access to its research and make a contribution to development policy discussions around the world. Policy Research\nWorking Papers are also posted on the Web at http://econ.worldbank.org. The authors may be contacted at mmeyer3@\nworldbank.org.\n\n\n_The Policy Research Working Paper Series disseminates the findings of work in progress to encourage the exchange of ideas about development_\n_issues. An objective of the series is to get the findings out quickly, even if the presentations are less than fully polished. The papers carry the_\n_names of the authors and should be cited accordingly. The findings, interpretations, and conclusions expressed in this paper are entirely those_\n_of the authors. They do not necessarily represent the views of the International Bank for Reconstruction and Development/World Bank and_\n_its affiliated organizations, or those of the Executive Directors of the World Bank or the governments they\n\nMention: \"the Household Budget Survey\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"Conducted yearly, it carries the transition matrices for the country study.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:006257:36:0", "occurrence_id": "5a421cd6ed789c0357d7468b", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: spouse by cohort of entry (see table 8). 45 The only group for which we find a statistically impor\ntant impact on employment (after accounting for multiple hypotheses testing) are spouses (who are\n\nfemales in 98% of the cases), who were not employed before 2002, and who (potentially) entered\n\nthe program after 2004. We reject the null that the effects on early and later cohorts are the same\n\n(p-value is 0.02). This suggests that CS promotes the employment of married women. With an\n\naverage participation of 30%, female labor force participation in Chile is low by Latin American\n\nstandards, overall and among the poorest sections of the population. In this context, CS coupled\n\nwith the support of employment programs could constitute an important avenue to improve fe\nmale labor market participation. The expansion of access to child care might have enhanced these\n\nimprovements, although there are no reasons to expect that the access to public day care centers\n\nexhibits a discontinuity at the effective cutoffs we estimate (Medrano, 2009).\n\n\n**Other Outcomes** We also study program impacts on four other sets of outcomes: housing, ed\nucation, health and variables associated with behaviors. The effects we find in most of these\n\noutcomes are not statistically significant (even without adjusting inference for multiple hypothesis\n\ntesting).\n\n\nThere are seven variables related to housing conditions (collected from the CAS), related to\n\nconnections to the water and sewage networks, ownership of the house, and quality of the walls\n\nand ceilings (see table A.9 in Appendix A). We also analyze nine variables (collected from the FPS)\n\nconcerning school enrolment of children, health coverage of children and adults in the household,\n\nand participation in employment centers. The variables where we find a positive impact of par\nticipation in CS indicates that all adults aged 65 or above in the family have completed health\n\ncheck-ups (see\n\nMention: \"CAS\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"Seven housing condition variables are collected in this survey.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:006257:36:0", "occurrence_id": "602a68d646c2510a6f36dd37", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: spouse by cohort of entry (see table 8). 45 The only group for which we find a statistically impor\ntant impact on employment (after accounting for multiple hypotheses testing) are spouses (who are\n\nfemales in 98% of the cases), who were not employed before 2002, and who (potentially) entered\n\nthe program after 2004. We reject the null that the effects on early and later cohorts are the same\n\n(p-value is 0.02). This suggests that CS promotes the employment of married women. With an\n\naverage participation of 30%, female labor force participation in Chile is low by Latin American\n\nstandards, overall and among the poorest sections of the population. In this context, CS coupled\n\nwith the support of employment programs could constitute an important avenue to improve fe\nmale labor market participation. The expansion of access to child care might have enhanced these\n\nimprovements, although there are no reasons to expect that the access to public day care centers\n\nexhibits a discontinuity at the effective cutoffs we estimate (Medrano, 2009).\n\n\n**Other Outcomes** We also study program impacts on four other sets of outcomes: housing, ed\nucation, health and variables associated with behaviors. The effects we find in most of these\n\noutcomes are not statistically significant (even without adjusting inference for multiple hypothesis\n\ntesting).\n\n\nThere are seven variables related to housing conditions (collected from the CAS), related to\n\nconnections to the water and sewage networks, ownership of the house, and quality of the walls\n\nand ceilings (see table A.9 in Appendix A). We also analyze nine variables (collected from the FPS)\n\nconcerning school enrolment of children, health coverage of children and adults in the household,\n\nand participation in employment centers. The variables where we find a positive impact of par\nticipation in CS indicates that all adults aged 65 or above in the family have completed health\n\ncheck-ups (see\n\nMention: \"FPS\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"Nine enrolment and coverage variables are collected in this survey.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:006272:14:0", "occurrence_id": "fdbd3e634d0849c6c440cdcc", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: ###### **2. Estimate deaths among women aged 15-49**\n\nThe consequent distribution of deaths by gender and age distribution is presented in Table A2.\n\n\n**Table A2: Estimated EVD Deaths by Age & Gender**\n\n\nGuinea Liberia Sierra Leone\n\nTotal Deaths **11** 1,995 3,826 3,341\n\nFemale deaths <15 years old 167 360 380\n\n\n15-44 years old 540 1,028 895\n\n\n≥45 years old 322 490 444\n\n\nMale deaths <15 years old 159 373 359\n\n\n15-44 years old 514 1,064 847\n\n\n≥45 years old 306 507 420\nSource: Total mortality by country is from WHO (2014). Distribution by age and gender is inferred by the author based on WHO Ebola Response\nTeam (2014).\n\n###### **3. Calculate surviving children**\n\nThe age distribution of Ebola deaths among women age 15-44 is assumed to reflect the age distribution of\nwomen age 15-44, in five-year age groups. For example, in Sierra Leone, 23% of women age 15-44 are\nbetween the ages of 15 and 19, so 23% of the 895 female deaths are applied to women age 15-19. b The\nsame process is applied for women age 45-49, using the distribution of deaths for women over age 45.\nThese five-year age group mortality counts are then multiplied by the mean number of living children\n(MNLC) for women in the same age groups, from the most recent DHS for the\n\nMention: \"the most recent DHS\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"Its fertility measures for women in age groups feed the calculation.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:006275:24:0", "occurrence_id": "56e83bee928685167b0a5bb4", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: **Table A2: Toilet facilities (Bangladesh DHS 2004, 2007)**\n\n|Facility Type|DHS Description|Freq.|%|\n|---|---|---|---|\n|**Dummy variables included**||||\n|**Flush toilet**|Flush to piped sewer system|2,496|6.38|\n||Flush to septic tank|2,646|6.76|\n||Flush to pit latrine|870|2.22|\n||Flush to somewhere else|690|1.76|\n||Flush, don't know where|36|0.09|\n|**Pit latrine**|Ventilated improved pit latrine|3,192|8.16|\n||Pit latrine with slab|9,846|25.16|\n||Pit latrine without slab/open pit|11,466|29.31|\n||Pit latrine, other|465|1.19|\n|||||\n|Dummy variables excluded
(for comparison)||||\n|No toilet facility|No facility/bush/field|3,453|8.83|\n|Excluded
(ambiguous definition or
insufficient data)||||\n||Bucket toilet|12|0.03|\n||Hanging toilet/latrine|2,160|5.52|\n||Not a de jure resident|1,794|4.59|\n|||||\n||Total|39,126|100|\n\n\n\n23\n\nMention: \"Bangladesh DHS 2004, 2007\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"Sanitation facility types and their frequencies come from these two rounds.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:006283:10:0", "occurrence_id": "39e72266b3066e7128a958c4", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: Figure 1: Reported Days in Customs - Trading Across Borders\n\n\n\n\n\n\n\nNote: Distributions of days in import customs and days in export customs, respectively.\n\nData from _Doing_ _Business_ _-_ _Trading_ _Across_ _Borders_ _2012_ for 182 countries.\n\n\n**3.2** **Quantitative** **measures** **of** **border** **policy**\n\n\nThe primary goal of this paper is to relate border management policies and procedures to border\n\n\noutcomes. Heretofore this has been a difficult issue to address empirically because quantitative\n\n\nrepresentations of border policies/procedures have not been available. 15 In anticipation of the Bali\n\n\nnegotiations the OECD set out to correct this problem, identifying 12 categories of trade facilitation\n\n\npolicies and procedures. After documenting national policies and procedures, the OECD scored\n\n\ncountries on their proximity to the world’s best practice in each of the 12 policy categories.\n\n\nThe raw material for the OECD’s 12 trade facilitation indicators was a detailed catalogue of\n\n\nthe policies and procedures used in border management agencies around the world. The OECD’s\n\n\ninitial catalogue, based in 2010, attempted to document 95 different indicators of border manage\n\nment procedures in OECD countries. A subsequent catalogue, representing the situation in 2012,\n\n\nattempted to track 78 procedures in non-OECD countries. 16 The OECD dropped 7 questions be\n\n15Measures such as the World Bank’s Logistics Performance Index, or information from TAB on the number of\ndocuments required to trade provide some high-level information. But these do not represent the breadth of the policy\nreforms considered in the TFA, nor do they provide sufficient policy detail for our purposes.\n\n16Our empirical specifications pool the two data series, but includes an OECD dummy variable. Among other things,\nthis should control for any systematic differences between the situations in 2010\n\nMention: \"Logistics Performance Index\""}, {"role": "assistant", "content": "{\"role\": \"supporting\", \"usage_action\": \"source\", \"summary\": \"It and trade document counts give only high-level trade facilitation measures.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:006295:34:1", "occurrence_id": "45bbb5a2b3393bf0792bb155", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: *\n\n\n**Scenario**\n\n\n\n**Pre-**\n**reform**\n\n\n\n**1 (30%**\n**reduction**\n\n**in**\n**subsidies)**\n\n\n\n**Scenario 2**\n**(Elimination**\n\n\n\n**reform** **subsidies)** **of subsidies)**\n\nTotal real household expenditure (bn LYD) 12.53 11.79 9.29\nHousehold expenditure loss in real terms (% of pre-reform) n.a. -6 -19.9\nTotal subsidies (bn LYD) 2.49 1.74 0\nIncidence of subsidies (% tot exp.) 19.9 14.8 0\nChange in government spending following reform (bn LYD) n.a. -1.22 -2.49\nSavings to the government following reform (% govt. exp.)* n.a. 1.9 3.9\nPoverty headcount (%, international poverty line) 8.5 11.2 21.7\nPoverty headcount (%, national poverty line) 14.4 18.2 30.4\nInequality (%, Gini) 30.2 30.8 33.4\nSource: Libyan Household Consumption Survey 2007/8; Libyan authorities; and Bank staff calculations.\n\n\n\nClearly, energy subsidy reform would have a huge impact on the Libyan economy, which calls for\ngradualism. Full liberalization would imply price increases of between 7 and 10 times the existing prices,\nin a context where alternatives (such as more efficient production processes for electricity\n\nMention: \"Libyan Household Consumption Survey 2007/8\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"Consumption levels and inequality behind the subsidy reform analysis.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:006297:42:2", "occurrence_id": "1e1a4733b39b6fcdfe742b8c", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: 24276.68 23763.79 23250.9 22738.01 22225.13 21712.24 21199.35 20686.46 20173.58 19660.69 19147.8\n\n\nbased on original Table 5.1. World Bank Cairo Pollution report\n\n\n41\n\nMention: \"World Bank Cairo Pollution report\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"Its original table supplies the pollution cost series.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:006318:21:2", "occurrence_id": "83a4c0775f0ee42fd04f7ee3", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: |9|10|10|\n\n\n\nVery insecure Insecure\n\n\nSecure Very secure\n\n\n\n**How secure do you feel alone**\n\n**on the street at night?**\n\n\n\n|Col1|Col2|Col3|2|Col5|5|Col7|6|Col9|\n|---|---|---|---|---|---|---|---|---|\n||24||14
||43
5||8
6||\n||24||58|58|58|58|52|52|\n||24|24|24|24|24|24|24|24|\n||32|32|32|32|30|30|30|30|\n||20|20|26|26|23|23|34|34|\n\n\nVery insecure Insecure\n\n\nSecure Very secure\n\n\n\n\n\n\n\n\n\n\n\n\n\nSource: Listening to Displaced People Survey, 2014.\n\n\n15 Victims of the crisis refers to death as well as physical violence.\n16 Respondents in our survey have been exposed to less violence than the average population in northern Mali.\nComparing our results to Afrobarometer findings, the latter finds that 15% of the population in Timbuktu and 8% in\nGao reported death in their family as a result of the conflict. In our survey, the 5% of those originating from Timbuktu\ndo so and 7% for those from Gao.\n\n\n20\n\nMention: \"Listening to Displaced People Survey, 2014\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"Perceptions of security and crisis victimisation come from this survey.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:006332:17:1", "occurrence_id": "77cd1aadb83ce550453ff46c", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: capita, at constant 2000 US dollars ( _Income_ ). We use\n\n\naverage values of the variable over the period 2007 and 2009 taken from World Development\n\n\nIndicators (WDI), World Bank. The variable serves as a useful proxy measure for various aspects\n\n\nof economic development that could be correlated with both women managers and women’s access\n\n\nto education.\n\n\nIt is natural to expect that ceteris paribus, countries with proportionately more women in\n\n\nthe population to have proportionately more women in top management. At the same time,\n\n\npopulations with more women could also reflect more favorable attitudes towards female children\n\n16\n\nMention: \"World Development\n\n\nIndicators\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"Averages over these two years serve as a proxy measure.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:006346:16:0", "occurrence_id": "8e6fc2dabf005209c15a9907", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: Business indicators apply to a standardized case and firm, and emphasize formal, required procedures.\n\nActual implementation may differ from formal procedures, however; e.g. the indicators assume no\n\nbribes are paid or personal connections exploited to bypass or expedite any procedures. Moreover,\n\nthe standardized case and firm (necessary for cross-country comparability) cannot possibly reflect\n\nreality for firms of all sizes, locations, and industries. For example, the standardized firm is assumed\n\nto be located in a country’s largest city. In a small number of countries, the Doing Business indicators\n\nhave been measured for multiple cities, and often show large differences between them. Other\n\nindicators based on expert perceptions may emphasize priorities and knowledge of Western-based\n\nadvocacy NGOs or commercial risk assessment firms, which may incorporate certain biases or neglect\n\nconcerns or views of domestic investors (Arndt and Oman, 2006).\n\n\nWhen the explanatory variable is measured with error (say _e_ ), the error, _e_, is embedded in the\n\nresidual. But the observed explanatory variable also contains _e_, causing a correlation of the regression\n\nerror term and the explanatory variable, and results in general in attenuation bias. The bias is especially\n\nsevere when the variability of _e_ is large—a case of particular concern for us if institutional variables\n\ntend to have large measurement errors. We attempt to correct for measurement error using an\n\ninstrumental variable approach (Greene, 1997, p.437). Specifically, we identify a second institutional\n\nvariable that is strongly related to the mis-measured variable, but with measurement error that is\n\nuncorrelated to the measurement error in the first variable. In our context, we have natural candidates\n\nfor such variables: our multiple indicators of contracting and property rights institutions are produced\n\nby different sources that reflect different methods and information sets. In implementing this\n\napproach for any particular institutional measure, we choose an instrument that has similar theoretical\n\ncontent, a relatively small incidence of missing values,\n\nMention: \"Doing Business indicators\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"validate\", \"summary\": \"In some economies they are measured for several cities, showing large gaps.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:006367:9:0", "occurrence_id": "3b459cd82c6d1b34e2c5322b", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: **figure 2.** **Evolution of parity fertility by cohort in Turkey**\n\n\nData Source: Census (i-pums) 2000\n\n\nFigure 3 confirms a low and stable proportion of childless women for the 1969 to 1974 cohort (SILC\n2011) but suggests an increase in the proportion of women having one and two children in comparison\nto older cohorts illustrated in figure 2. The proportion of women havingr three children stagnates, while\nthe proportion of women having at least four children has decreased (note however that the\nunderestimation bias in the SILC data leads to an overemphasis of this decline). Most importantly, figure\n3 illustrates that the majority of Turkish women of cohorts 1969 to 1974 either have two or three\nchildren. Just like on average in Europe, having two children is the norm for cohorts born around 1970\nin Turkey, which was not the case for younger cohorts born before 1960. At the same time, the\nproportion of women having three or more children is larger in Turkey than on average in other European\ncountries.\n\n\nWhen calculating parity progression ratios 5 [^5: Parity progression ratio (idem “transition probability”) from zero to one child: 89% Turkey and 85% EU; from three to four children: 40% in\nTurkey and 6% EU.] based on the proportions illustrated in figure 3, we find that\n80% of women having one child pass on to have a second child in Turkey, while the EU(26) average is\n72%. Among women having two children, 47% are likely to have a third child in Turkey, against only\n23% on average in the EU (26) as reported by SILC.\n\n\nFurther calculations based on the proportions of figure 3 reveal that almost half of the gap in approximate\ncompleted fertility between the EU(26) and Turkey (1.7 vs. 2.3 children per women) can be explained\nby an overrepresentation of women having at least two children in Turkey\n\nMention: \"SILC data\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"validate\", \"summary\": \"Its underestimation bias overemphasises the decline in larger families.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:006369:5:0", "occurrence_id": "1511a8b5c870afd639ae719a", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: However, during the final years of the Ali regime and the recent post-revolution period, the\nspending and composition of Tunisia’s subsidies have notably changed (Figure 1). During the\nlast 10 years, the combined spending on energy, food, and transportation has more than tripled,\nrising from 2% of GDP in 2005 to 7% in 2013. Energy subsidies, in particular, increased even\nmore, fourfold, during that period. Energy subsidies reached 4.7% of GDP in 2013, with\nsustained increases since 2010, reflecting the partial (rather than the full) pass-through of\ninternational oil prices to domestic prices sought by the government (IMF 2014). Regarding the\ncomposition of subsidies, during the post-revolution period, energy subsidies increased both in\nabsolute and relative terms. As a result, energy subsidies went from one-third of total public\nsubsidies prior to the revolution to about two-thirds in 2013. In contrast, food and other basic\nneeds’ subsidies have lost relative weight in the total subsidy bill despite having notably\nincreased in absolute terms. With respect to other public expenditures, energy subsidies in\nTunisia account for one-fifth of all public spending, or 7% of the GDP in 2013, the latest\navailable figure. Because they are considered the backbone of the social protection strategy, it is\nnot surprising that public spending on subsidies exceeds that of social assistance, health and\neducation, and individual programs on youth, children, or women (Figure 2).\n\n\n\n\n\n\n\n\n\n\n\n_Source:_ WB staff calculations using data from Ministère des Finances (October 2013).\n_Notes:_ Basic products refer to food products such as cereals, bread, sugar, and vegetable oil. * = forecast.\n\n\n4\n\nMention: \"Ministère des Finances (October 2013)\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"Basic product price data behind the incidence figures come from this ministry.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:006370:15:0", "occurrence_id": "5f104a92c4588f567908c8a7", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: Applying 2015 tariffs has little negative impact on the per capita wellbeing of households. Given small\nincreases in tariffs that are focused mostly on rich consumers, expenditures per capita are expected to\ndecline on average by JD0.6 or about 0.03 percent (table 13). This would bring no changes in poverty and\npoverty gap measures.\n\n\n**Table 13. The impact of 2015 tariffs on economic wellbeing**\nQuintiles Impact, JD Impact, %\nQuintile 1 -0.02 0.00\nQuintile 2 -0.05 0.00\nQuintile 3 -0.15 -0.01\nQuintile 4 -0.31 -0.01\nQuintile 5 -2.48 -0.06\nTotal -0.60 -0.03\nSource: Authors’ calculations based on extrapolated HEIS 2010 data.\nNotes: Population quintiles based on consumption per capita before the reform.\n\nFull removal of subsidies, in contrast, will have a considerable impact on economic wellbeing. Fully\nremoving subsidies with a flat tariff rate is expected to reduce consumption per capita on average by JD\n72.5 or by 3.6 percent. The negative impact is expected to be the strongest for the poorest households, with\nthe bottom quintile experiencing on average a 5.7 percent reduction in per capita consumption. The negative\nburden on the poorest households can be reduced if a progressive increase of tariffs is applied. In this case,\nthe negative impact would be less pronounced for the poor even though the average household consumption\nwould drop by the same amount. Nevertheless, both sub-scenarios are quite severe and would be difficult\nto implement. A semi-progressive increase in tariffs leading to\n\nMention: \"HEIS 2010 data\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"analyze\", \"summary\": \"Extrapolated consumption quintiles before the reform rest on this round.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:006391:10:0", "occurrence_id": "4951f08362d77926ce4a8090", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: effectively provide public goods - for instance, when on group seeks to actively obstruct the\n\n\nauthority of the other - we also expect inter-elite competition to harm local development\n\n\noutcomes.\n\n\nThere are also theoretically based reasons to expect that relationships defined by\n\n\ncooperation, rather than competition, will be beneficial to the provision of local public goods.\n\n\nFor instance, as Fearon et al. (2009) suggest, chieftaincy support of local council projects may\n\n\nincrease the chances of programmatic success. Further, Logan’s (2008, iii) analysis of Afro\n\nbarometer data from 15 countries on the continent, finds that respondents’ evaluations of newly\n\n\ndecentralized local authorities and hereditary chiefs move together, noting “local traditional\n\n\nleaders appear to draw their sustenance and legitimacy from the same well as elected officials.”\n\n\nThis suggests that rather than control over local power and resources being a zero-sum game,\n\n\ncooperative relationships between chiefs and councilors may be beneficial for public goods\n\n\noutcomes as well as public perceptions of the quality of local government. If these types of\n\n\ncooperative inter-elite relationships are at play, closer ties between councilors and chiefs should\n\n\nbe associated with greater levels of public goods.\n\n\nYet other research on the political economy of Africa suggests an opposite effect. Close\n\n\ninter-elite relationships may indicate that councilors are benefitting from chiefs’ clientelistic\n\n\nnetworks to buy votes and ensure future electoral support. In such instances, patronage-based\n\n\nredistribution may come at the expense of public goods provision (Bratton 2008; Collier &\n\n\nVicente 2012; Keefer 2005; van de Walle 2003, 2012; Wantchekon 2003). In addition, if\n\n\ncouncilors draw their legitimacy indirectly from the support of chiefs rather than from their\n\n\nperformance, the accountability of local governance and thus councilors’ incentives to invest in\n\n\npublic goods also decline. In such scenarios, we expect that closer inter-elite relationships\n\n\ndefined by frequent contact in the absence of disputes and a higher frequency of councilor/chief\n\n\nfamilial ties will lead to worse\n\nMention: \"Afro\n\nbarometer data\""}, {"role": "assistant", "content": "{\"role\": \"supporting\", \"usage_action\": \"source\", \"summary\": \"Its 15-country analysis records evaluations of new institutions.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:006393:12:1", "occurrence_id": "012c677d1bfaf18c8dfa3d40", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: household. 22 For each enterprise we compute net income as total annual sales minus\n\ncosts. In the Malawi ISA, households report the average net income for a bad, standard, and\n\ngood month. Households are then asked how many of each type of month occurred in the past\n\nyear. In Uganda, households report both gross income and costs. In Tanzania households report\nnet income directly. 23\n\n\n19In Malawi, the majority of households receive seed and fertilizer subsidies by the Farm Inputs Subsidy Program.\nWe use the subsidized (coupon) prices reported by each household.\n\n20This is innocuous for our purposes of measuring household income because the labor income generated by\nhousehold members in agricultural production is also part of household income. Under some assumptions, this\nlabor income can be separated from net profits, but this is beyond the scope of our paper.\n\n21Previous LSMS datasets provide information on labor supply with the reference period of “the past 7 days”.\nISAs complement that information with recalled hours worked per day, week, and month over the past 12 months,\nwhich greatly facilitates the determination of the annualized labor supply. In particular, this avoids potential\nmeasurement error from labor supply seasonality. See Rosenzweig and Udry (2014) for a discussion on how wages\nare affected by seasonal weather patterns.\n\n22Privately held businesses per household (potentially more than one) include owned nonagricultural businesses\nthat process/sell agricultural byproducts (e.g. flour, juice, beer, jam, oil, seed, and livestock by-products),\nsales of forest-based products, street or market trading businesses, taxi or pickup truck drivers, bar/restaurants,\nprofessional services (e.g., doctor, accountant, lawyer, and midwife) etc..\n\n23As was the case for agricultural net income, business net income includes the contribution of household labor\n\nMention: \"LSMS datasets\""}, {"role": "assistant", "content": "{\"role\": \"supporting\", \"usage_action\": \"source\", \"summary\": \"Earlier rounds used a seven-day labour reference period.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:006393:12:1", "occurrence_id": "daa30c1c4837bddc937868b6", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: household. 22 For each enterprise we compute net income as total annual sales minus\n\ncosts. In the Malawi ISA, households report the average net income for a bad, standard, and\n\ngood month. Households are then asked how many of each type of month occurred in the past\n\nyear. In Uganda, households report both gross income and costs. In Tanzania households report\nnet income directly. 23\n\n\n19In Malawi, the majority of households receive seed and fertilizer subsidies by the Farm Inputs Subsidy Program.\nWe use the subsidized (coupon) prices reported by each household.\n\n20This is innocuous for our purposes of measuring household income because the labor income generated by\nhousehold members in agricultural production is also part of household income. Under some assumptions, this\nlabor income can be separated from net profits, but this is beyond the scope of our paper.\n\n21Previous LSMS datasets provide information on labor supply with the reference period of “the past 7 days”.\nISAs complement that information with recalled hours worked per day, week, and month over the past 12 months,\nwhich greatly facilitates the determination of the annualized labor supply. In particular, this avoids potential\nmeasurement error from labor supply seasonality. See Rosenzweig and Udry (2014) for a discussion on how wages\nare affected by seasonal weather patterns.\n\n22Privately held businesses per household (potentially more than one) include owned nonagricultural businesses\nthat process/sell agricultural byproducts (e.g. flour, juice, beer, jam, oil, seed, and livestock by-products),\nsales of forest-based products, street or market trading businesses, taxi or pickup truck drivers, bar/restaurants,\nprofessional services (e.g., doctor, accountant, lawyer, and midwife) etc..\n\n23As was the case for agricultural net income, business net income includes the contribution of household labor\n\nMention: \"ISAs\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"They add recalled hours per day, week and month.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:006395:9:0", "occurrence_id": "a461299e9e9bef8ce79360ca", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: **2.2.** **The Participants**\n\n\nThe recruitment of a total number of 700 participants took place between March 2010 and August\n\n\n2011. Five individuals had to be excluded from the trial because of a missing consent form,\n\n\nbecoming pregnant, developing cancer, and internal documentation problems. 9 [^9: Results are robust with respect to treating these individuals as dropouts in sensitivity checks described\nin Section 3.] The last\n\n\nparticipant finished the follow‐up phase by the end of July 2013.\n\n\nTable 1 provides some descriptive statistics of the study population. The average body\n\n\nweight at the start of the experiment (at the end of the rehabilitation stay) was 113.0 kg (249.4\n\n\nlbs.) or 37.6 in terms of BMI (Figure A1 shows the distribution of the BMI over time). About 68\n\n\npercent of the participants are men and 21 percent have a migration background. 10 [^10: These shares are substantially lower than the corresponding averages for obese individuals in Germany,\nwhich we obtained using the German Socioeconomic Panel (SOEP) – a representative panel of German\nhouseholds. The mean age of the study population (48 years) lies about ten years below the average age of\nobese in Germany, while the share of employed participants (82 percent) is almost twice as large. Only the\nshare of married participants does not deviate considerably from the respective share of obese in Germany.] For most\n\n\npatients of the cooperating clinics, medical rehabilitation is paid by the German pension fund,\n\n\nwhose predominant goal is to avoid work disability and early retirement. Since there are many\n\n\nobese in the overall population that are already retired, our study population oversamples\n\n\npersons that are available for the labor market.\n\n\nAs already noted, four rehabilitation clinics, located in different towns, have been involved\n\n\nin the trial. About 42 percent of the participants were recruited by the clinic in Bad Mergentheim,\n\nMention: \"the German Socioeconomic Panel (SOEP)\""}, {"role": "assistant", "content": "{\"role\": \"supporting\", \"usage_action\": \"source\", \"summary\": \"A representative household panel supplying the comparison averages.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:006409:8:0", "occurrence_id": "18491eaf0236bea249a05ff0", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: the capital market activity. Section 4 presents the results on which firms use these markets. Section 5\n\n\nshows the results on firm performance and the evolution of the FSD. Section 6 explores additional\n\n\nheterogeneity in firm behavior according to the type of securities issued, market of issuance, and firms’\n\n\nhome market. Section 7 studies the role of firm age. Section 8 concludes.\n\n\n**2.** **Data**\n\n\nTo assess which firms issue securities, the comparative performance of issuing and non-issuing firms,\n\n\nand the evolution of the size distribution of firms as they issue securities, we assemble a\n\n\ncomprehensive data set covering corporate bond and equity issuances in capital markets around the\n\n\nworld as well as balance sheet information on publicly listed firms. The data on firm capital raising\n\n\nactivity cover the period 1991-2011 and come from the Thomson Reuters Security Data Corporation\n\n\n(SDC) Platinum database, which provides transaction-level information on new issuances of common\n\n\nand preferred equity and publicly and privately placed bonds with an original maturity of more than\n\n\none year. 5 [^5: SDC Platinum collects data on security issuance mostly from filings with local regulatory agencies and stock exchanges.\nThese data are augmented with data from other sources such as offering circulars, prospectuses, surveys of investment\nbanks, brokers, and other financial advisors, news sources, trade publications, and wires.] Given that the SDC Platinum database does not collect data on debt issuances with\n\n\nmaturities shorter than one year, the data set does not cover commercial paper. For offerings in more\n\n\nthan one market, we consider each market a separate issuance. The data set includes 532,423 security\n\n\nissuances: 138,968 equity issuances and 393,455 bond issuances by listed and unlisted firms. Security\n\n\nissuances are classified as domestic or international based on the location of the main exchange where\n\n\nthe issuances take place and compared with the issuing firm’s nationality. The data set includes 411,180\n\n\nissuances in domestic markets and 116,811 issuances in foreign\n\nMention: \"SDC Platinum database\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"validate\", \"summary\": \"It does not collect debt issues with maturities shorter than one year.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:006410:19:2", "occurrence_id": "998e92d7e74ac20021c71212", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: complex (including the media company, hotels, theatres, etc.) by a politically connected businessman. The\ncomplex was declared a special economic zone shortly after, allowing him to benefit from tax exemptions (Ahram Online,\nvarious issues).\n\n28 Moreover, while the WBES is a survey, it covers most large firms within a sector, which typically includes the connected\nfirms in sectors where these firms are present.\n\n29 Among the 91 manufacturing sectors, 59 have no politically connected CEOs, while 32 have at least one politically\nconnected CEO; 26 have no politically connected owners, while the remaining 65 sectors have between one (18 sectors)\nand 35 (one sector) politically connected owners; and 19 have no politically connected firms of any kind, while the\nremaining 72 sectors exhibit between one (16 sectors) and 35 (two sectors) connected firms. In sectors with multiple\n\n\n18\n\nMention: \"the WBES\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"validate\", \"summary\": \"Though a survey, it covers most large firms within a sector.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:006400:9:0", "occurrence_id": "beab511dd22c5652a00751d3", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: **Table 2: Effects of Health Care Worker Deaths from Ebola on Maternal Mortality**\n\n\nDoctors, nurses, & midwives Maternal mortality ratio (per 100,000 live births)\n\n\n\nUpper\nbound %\n\nchange\n\n(95%)\n\n\n\nStock\npre-Ebola\n\n\n\nStock\n\npostEbola\n\n\n\n% change\n\n\n\nPreEbola\n\nratio\n(2013)\n\n\n\nMay\n2015\nratio\n\n\n\n% change\n\n\n\nLower\nbound %\n\nchange\n\n(95%)\n\n\n\nGuinea 5395 5317 -1% 650 897 **38%** 26% 50%\n\n\nLiberia 1029 946 -8% 640 1347 **111%** 76% 145%\n\n\nSierra Leone 1153 1074 -7% 1100 1916 **74%** 51% 97%\n\n\nSource: Author calculations based on Ebola mortality data from the WHO, 8 population and maternal mortality data\nfrom World Development Indicators, 9 and health worker-mortality coefficients from Speybroeck et al. 18\nNote: Data on pre-Ebola stock of health workers is for the most recent years available for each country: 2004 (nurses\nand midwives) and 2005 (doctors) for Guinea, 2008 for Liberia, and 2010 for Sierra Leone.\n\n\n**Table 3: Effects of Health Care Worker Deaths from Ebola on Infant Mortality***\n\n\nDoctors, nurses, & midwives Infant mortality rate (per 1,000 live births)\n\n\n\nUpper\nbound %\n\nchange\n\n(95%)\n\n\n\nStock\npre-Ebola\n\n\n\nStock\n\npostEbola\n\n\n\nLower\nbound %\n\nchange\n\n(95%)\n\n\n\n% change\n\n\n\nPreEbola\n\nrate\n(2013)\n\n\n\nMay\n2015 rate % change\n\n\n\nGuinea 5395 5317 -1% 64.9\n\nMention: \"population and maternal mortality data\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"Denominators and maternal mortality rates behind the projection come from this source.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:006400:9:0", "occurrence_id": "a867347df4c855ade39cb20c", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: **Table 2: Effects of Health Care Worker Deaths from Ebola on Maternal Mortality**\n\n\nDoctors, nurses, & midwives Maternal mortality ratio (per 100,000 live births)\n\n\n\nUpper\nbound %\n\nchange\n\n(95%)\n\n\n\nStock\npre-Ebola\n\n\n\nStock\n\npostEbola\n\n\n\n% change\n\n\n\nPreEbola\n\nratio\n(2013)\n\n\n\nMay\n2015\nratio\n\n\n\n% change\n\n\n\nLower\nbound %\n\nchange\n\n(95%)\n\n\n\nGuinea 5395 5317 -1% 650 897 **38%** 26% 50%\n\n\nLiberia 1029 946 -8% 640 1347 **111%** 76% 145%\n\n\nSierra Leone 1153 1074 -7% 1100 1916 **74%** 51% 97%\n\n\nSource: Author calculations based on Ebola mortality data from the WHO, 8 population and maternal mortality data\nfrom World Development Indicators, 9 and health worker-mortality coefficients from Speybroeck et al. 18\nNote: Data on pre-Ebola stock of health workers is for the most recent years available for each country: 2004 (nurses\nand midwives) and 2005 (doctors) for Guinea, 2008 for Liberia, and 2010 for Sierra Leone.\n\n\n**Table 3: Effects of Health Care Worker Deaths from Ebola on Infant Mortality***\n\n\nDoctors, nurses, & midwives Infant mortality rate (per 1,000 live births)\n\n\n\nUpper\nbound %\n\nchange\n\n(95%)\n\n\n\nStock\npre-Ebola\n\n\n\nStock\n\npostEbola\n\n\n\nLower\nbound %\n\nchange\n\n(95%)\n\n\n\n% change\n\n\n\nPreEbola\n\nrate\n(2013)\n\n\n\nMay\n2015 rate % change\n\n\n\nGuinea 5395 5317 -1% 64.9\n\nMention: \"World Development Indicators\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"The compilation supplying the demographic and health series.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:006430:21:1", "occurrence_id": "cd38e920c7580ca3b82e24eb", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: but retroceded in 2013. The introduction of performance\nagreements is associated with the implementation of school-level performance agreements.\nWhile the state remains above the regional average, the gap is rapidly closing because Rio de\nJaneiro and Espiritu Santo recorded large improvements.\n\n\nSimilarly, in the case of Rio de Janeiro, there is a clear discontinuity that is concomitant to the\nintroduction of the results agreements and bonus system for school employees in 2010. After\nshowing no change in three rounds of IDEB, the state recorded a sizable increase of 14 percent in\n2011 and 12.5 percent in 2013. As a result, Rio de Janeiro rose from the 23 rd position in the\nnational ranking of IDEB 2009 to 5 th place in 2013. The state achieved one of Brazil’s most\nremarkable turn-arounds in the education sector.\n\n\n_Before-and-After Comparison of Outcomes_\n\n\nThe comparison of the average measures corresponding to the periods of time before and after\nthe introduction of performance agreements and variable pay shows that in several cases there\nare significant differences in outcomes after the implementation of the intervention (Table 3).\nThe before-and-after design is a quasi-experimental model that compares two groups of\nobservations, before and after time points. The state-years preceding the program are averaged\nto estimate the counterfactual and the later ones to measure results.\n\n\n20\n\nMention: \"national ranking of IDEB 2009\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"Its ranking position improves markedly by the later year.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:006431:34:0", "occurrence_id": "a01fe27108957ce1b68e244e", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: |Nigerian 2006’s SAM|GTAP database version 8.1|Aggregated 21 GTAP sectors|\n|---|---|---|\n|No. Code
Description|No. Code Description|No. Code
Description|\n||34
nmm Mineral products nec|
|\n||35
i_s
Ferrous metals|35
i_s
Ferrous metals|\n||36
nfm
Metals nec|36
nfm
Metals nec|\n||37
fmp
Metal products|37
fmp
Metal products|\n||38
mvh
Motor vehicles and parts|38
mvh
Motor vehicles and parts|\n||40
ele
Electronic equipment|40
ele
Electronic equipment|\n||41
ome
Machinery and equipment
nec|41
ome
Machinery and equipment
nec|\n||42
omf
Manufactures nec|42
omf
Manufactures nec|\n|48 croil
Refined oil|32
p_c
Petroleum, coal products|16
RefinedOil\n\nMention: \"GTAP database\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"Version 8.1 supplies the global counterpart to the national matrix.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:006432:64:9", "occurrence_id": "89091867c75d9daf7b5f69fa", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: ]
[0.015]
[0.014]|0.026
-0.031
-0.020
[0.085]
[0.080]
[0.103]|\n|N
1,957
1,942
1,922
1,892
1,876|1,846
1,836
1,815|1,617
1,423
1,403|\n\n\n\n_Notes:_ The predicted values are based on the estimates in Table S5. Statistical significance is *** at 1 percent level, ** at 5 percent level, * at 10 percent level.\n\n\n_Source:_ Authors' analysis based on data from 2003 and 2008 Demographic and Health Surveys for Turkey.\n\n\n63\n\nMention: \"2003 and 2008 Demographic and Health Surveys for Turkey\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"analyze\", \"summary\": \"The analysis is carried out on these two rounds.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:006457:18:0", "occurrence_id": "f8e53f5e2b1a05a42796847b", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: by the Federal Reserve, there has been a trend toward the overall liberalization of capital\ntransactions, notably on capital and money market instruments. Globally, the world is\nroughly evenly split between countries relying on an exchange rate anchor for monetary\npolicy (mostly small islands and members of currency unions in Africa, for example), and\nthose with more independent monetary policy (including most high-income countries).\n\n\n4. _Cities and livability_ . Apart from the economic arguments suggesting that agglomeration\neconomies can be significant, “smart cities” have become a dominant theme in the recent\neconomic development literature. Fuller and Romer (2014) argue that “Nothing else [other\nthan the urbanization project] will create as many opportunities for social and economic\nprogress.” The New Climate Economy Report 2014 argues that cities are crucial for\nsustainable development and that “the stakes for growth, quality of life and carbon\nemissions could not be higher.”\n\n\nGlaeser (2010) 15 [^15: Glaser (2010) Agglomeration Economics…] shows a strong link between area density and per capita gross\nmetropolitan product at all income levels. Density is strongly correlated with wages and\nproductivity, as well as with future housing price growth. This seems to reflect the benefits\naccruing from labor market pooling and the exchange of ideas, rather than from the benefit\nof reduced transport costs of goods between, for example, suppliers, manufacturers and\ncustomers. Skilled labor pooling seems to be particularly important. Unfortunately, East\nAsian countries have paid scant attention to cities. Among developing East Asia, Bangkok\nis ranked at 117, Beijing at 118, Manila at 136, Ho Chi Minh and Hanoi at 152 and 153 in\nthe Mercer 2015 City Rankings. Only Kuala Lumpur, at 84, among all cities in developing\nAsia, breaks into the top 100 global cities.\n\n\n5. _Cohesion and inequality_ . We had argued that middle-income countries would need to pay\nspecial attention to inequality because the shifting growth and urbanization strategies\nwould likely worsen the\n\nMention: \"the Mercer 2015 City Rankings\""}, {"role": "assistant", "content": "{\"role\": \"supporting\", \"usage_action\": \"source\", \"summary\": \"City liveability positions across developing Asia come from this ranking.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:006461:40:0", "occurrence_id": "7cd323c3187fe82fa859e9b3", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: **Figure A2. Age–wage profile, 2011**\n\n\n_Source:_ Authors’ calculations based on RLMS, 2011.\n\n\n39\n\nMention: \"RLMS, 2011\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"analyze\", \"summary\": \"The age-wage profile is calculated from this round.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:006462:5:0", "occurrence_id": "bf124246ce93424d7cc3ee6e", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: states, and these states lag behind on measures like poverty reduction and other develop\n\nmental outcomes (World Bank 2011b). 1 Understanding the cost of public infrastructure is\n\n\nimportant in particular for these countries in which resources for public investment are of\n\nten scarce. Further, public work contracts, including roads, are subject to substantial levels\n\n\nof corruption. According to Transparency International’s Bribe Payers Survey of over three\n\n\nthousand business executives worldwide, public works contracts and construction is the sec\n\ntor with the highest propensity of paying bribes to officials and other firms (Transparency\n\n\nInternational 2011). As this paper attempts to establish a first set of facts on differences in\n\n\ncosts in low and middle income countries, a focus on the link between corruption and costs\n\n\nis a natural priority. 2\n\n\nA review by the World Bank’s Transport Research Support Program on the roads sector\n\n\nin conflict countries states that _“...projects_ _that_ _take_ _place_ _in_ _conflict_ _settings_ _would_ _almost_\n\n\n_always_ _be_ _more_ _costly_ _than_ _in_ _other_ _settings_ _because_ _of_ _challenges_ _such_ _as_ _insecurity_ _and_ _low_\n\n\n_government_ _capacity”_ (Rebosio and Wam 2011). Higher costs can be due to the costs of\n\n\nmonitoring an areas security situation, the potential for incurring substantial risks to visit\n\n\nthe construction site, and the possibility of limitations on planning. In addition to pro\n\ntection of the staff working on the particular roads project, firms also risk supplies being\n\n\ncut off due to disruptions of transport networks. 3 Not only the construction but also the\n\n\nprocurement process can be riskier in conflict countries. Rebosio and\n\nMention: \"Bribe Payers Survey\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"Over three thousand executives report corruption in public works contracts.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:006474:12:0", "occurrence_id": "584b0368c44f7871027043b3", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: countries shows that the gender gap in math is present as early as 4th grade (Bharadwaj et al.\n\n\n2012). This is not the case for Mexico. In order to assess whether our sample is representative\n\n\nof the Mexican population, we follow the nationwide cohort of 6th grade ENLACE takers in\n\n\nthe year 2007 over to 9th (in 2010) and 12th grade (in 2013). Girls do consistently better\n\n\nthan boys in language and the gap stays constant throughout the different grades. Neither\n\n\nin 6th grade nor in 9th grade is there evidence of a gender gap in math, but girls’ 12th grade\n\n\nscore in math is 30 points (0.30 _σ_ ) lower than boys’ (Table 1). The gender gap in 12th grade\n\n\nmay be partly explained by differential selection: 28.6% of the boys who took the ENLACE\n\n\n6th grade in 2007 completed the 12 grade exam in 2013, as opposed to 34.9% of the girls.\n\n\n**3.3** **Follow-up** **Data**\n\n\nStudents enrolled in 10th grade in 2009 were supposed to complete high school in 2012. 16 We\n\n\nuse data from the 2012 12th grade ENLACE exam to measure the three main outcomes of\n\n\ninterest: the probability of taking the test, math scores, and Spanish scores. We interpret the\n\n\nprobability of taking the 12th grade test in 2012 as a proxy for the probability of completing\n\n\nupper secondary on time. 61% of the students surveyed at the baseline took part in the\n\n\n12th grade ENLACE exam three years later. Not observing a student who was originally\n\n\nenrolled in EMS in 2009 take part in the 12th grade ENLACE exam in 2012 has four possible\n\n\nexplanations: 1) the student dropped out of school at any point between 9th and 12th grade,\n\n\n2\n\nMention: \"2012 12th grade ENLACE exam\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"Its results measure test participation, matriculation and achievement.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:006483:5:0", "occurrence_id": "d818cac2335d36be55227c78", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: factor outputs. For example, looking mostly at U.S. public capital stocks, the macro‐level literature finds\nvery large estimates for the elasticity of infrastructure—between 0.20 and 0.40.\n\nConnective infrastructure, such as roads, is likely to have the greatest impact on economic growth.\nImproved connectivity within a country and within a region increases firms’ access to markets for their\ngoods and for cheaper inputs; assists businesses in developing competitive advantages; and provides\nworkers, particularly those in lagging areas, with greater job and income opportunities. Transport typically\nfacilitates agglomerations, which in turn promotes economic growth. For example, Njoh (2009) finds a\nstrong positive relationship between transportation infrastructure and growth based on evidence from\n24 West African countries. As countries develop, economic growth becomes more closely linked to a\n“principle of connectivity” (Biller and Nabi 2013).\n\nOther capital intensive infrastructures such as power are also closely related to economic growth via\nconnectivity. While not directly linked to connectivity (in terms of moving people, goods, and services),\npower facilitates information flows, thereby enabling agglomerations. More importantly, power is a key\ninput in the production process, and power constraints have been identified as a major bottleneck for\ngrowth and job creation in several developing countries. A good example can be found in Nepal. Over the\npast few years, Nepal has faced up to 16 hours of electricity load shedding in dry months – stalling the\nmanufacturing sector and severely curtailing basic services (like health care), other services, and\ncommerce. The economic loss of such a huge power outage must be tremendous. In transport, Nepal has\nsimilar constraints, being a mountainous landlocked country. Yet while geography may be more benign in\nother South Asian countries like Pakistan and India, connective infrastructure is also severely lacking and\nthe existing ones are poorly used. 6\n\n\n\n\n\n\n\n\n\n_Source:_ World Development Indicators 2012 Online Database, the World Bank\n\nMention: \"World Development Indicators 2012 Online Database, the World Bank\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"Its edition supplies the infrastructure statistics behind the claim.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:006490:14:1", "occurrence_id": "08dfed9f0d21d3d9e34f1ba8", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: risk preferences. The KLPS2 survey was\n\n\nlaunched in August of 2007, and 1,180 respondents were surveyed in 2007 prior to the elections.\n\n\nThe crisis led to a two-month suspension of survey activities, which resumed in March of 2008\n\n\nand continued through the end of 2009. We employ two complementary identification strategies.\n\n\nFirst, we estimate the impact of the crisis in a straightforward linear framework, controlling for\n\n\nmonth-of-the-year fixed effects. In these specifications, we also include enumerator fixed effects\n\n\nand controls for sociodemographic characteristics such as respondent age, educational attainment,\n\n\nvalue lottery as a risky alternative.\n\n\n13\n\nMention: \"KLPS2 survey\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"Launched in that year with 1,180 respondents surveyed beforehand.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:006502:22:0", "occurrence_id": "f8d00c53cba33abddc7bfc6b", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: that informal financing almost always carries associated informal costs (i.e., costs not reflected\n\n\nin interest rates), such as informal gifts and implied obligations to assist lenders in the future,\n\n\nmaking them relatively less attractive to borrowers with formal options. Another reason for\n\n\ntheir greater reliance on formal loans is that better-educated people tend to have fewer siblings\n\n\nand a higher opportunity cost of their time, which would raise their relative costs of using\n\n\ninformal financing. They also have higher-paying jobs in general, and likely steadier incomes,\n\n\nmaking them better candidates for bank financing. The overall effect is therefore that better\n\neducated residents rely more on formal financing.\n\n\nContrasts in the configurations and effectiveness of various social networks on access to\n\n\nfinance shed light on how finance works for Chinese households. Rural households with an\n\n\naffiliation to the Communist Party are 10.2 percentage points more likely to have a bank loan\n\n\n(model 6). For urban households, incidence of affiliation with the Communist Party is relatively\n\n\nhigh (18%, in contrast to 9.5% in rural areas), 20 and party affiliation is not associated with a\n\n\ngreater likelihood of having a bank loan.\n\n\nWhile party membership is associated with greater use of bank loans in rural areas, it is\n\n\nnot associated with more usage of informal loans. These pieces of evidence suggest that\n\n\naffiliation with political power can affect access to formal credit in some rural Chinese contexts,\n\n\nperhaps because state-owned banks have greater influence over credit markets in rural areas.\n\n\nThe number of siblings, a proxy for the extent of private social networks, also influences\n\n\ninformal financing. Each additional sibling is associated with 4.7 and 3.9 percentage point\n\n\ngains in the likelihood of informal borrowing in urban and rural areas, respectively (models 8\n\n\nand 9). Thus, private social networks also play an important role in facilitating informal credit\n\n\nmarkets.\n\n\n20 Figures based on CHFS data.\n\n\n21\n\nMention: \"CHFS data\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"The informal credit figures rest on this household survey.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:006506:8:0", "occurrence_id": "498b5ba90add8445044941e5", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: midyear population according to the World Bank’s World Development Indicators 2011. Costs are\nrecorded exclusive of value added tax and only include the fees associated with completing the\nprocedures to connect a warehouse to electricity. This includes the costs in related to obtaining\nclearances from government agencies, applying for the connection, receiving inspections of both\nthe site and the internal wiring, purchasing material, getting the actual connection works and\npaying a security deposit 7 [^7: Connection costs can be broadly divided into the following categories: often utilities charge a fixed connection fee\nthat spreads the fixed costs of operating a distribution grid over all customers; in addition, customers are required to\npay for the variable costs for each connection, including labor and material costs. Sometimes the costs also include\nfees for inspections that the utility or outside contractors are legally required to carry out. In many economies costs\nalso include payments to other agencies for permits, inspections and approvals.] . Costs associated with electricity consumption are not included.\nInformation from local experts and specific regulations and fee schedules are used as sources for\ncosts. If several local partners provide different estimates, the median reported value is used. In all\ncases, the cost excludes bribes.\n\n\nCost estimates for 86 economies also include the present value of the lost interest earnings on the\nsecurity deposits that utilities require as a guarantee against the possible failure of customers to\npay their consumption bills. Instead of recording the full amount of the guarantee, we record the\npresent value of the losses in interest earnings experienced by the customer because the utility\nholds the security deposit over a prolonged period. In most cases this is until the end of the contract\n(assumed to be after 5 years) 8 [^8: In the few cases in which the security deposit is used to cover the first monthly consumption bills, it is not recorded\nat all.] . To calculate the present value of the lost interest earnings, the end2010 lending\n\nMention: \"World Development Indicators 2011\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"Midyear population denominators come from this edition.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:006516:43:0", "occurrence_id": "5af9d2a7378f01570c5a01bf", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: 42\n\n\n‘achievement’ index? One possibility is to conduct an exit survey of users of health\n\n\nfacilities, the aim being to gather information not only on the health services\n\n\nreceived and the need for them, but also on the living standards of the person’s\n\n\nhousehold; the latter data can be used to construct a wealth index using the same\n\n\nscoring system as in a national survey (like the DHS), so that users can be placed in\n\n\nthe national wealth distribution. As Wagstaff and Waters (2005) report, several\n\n\nstudies in the ‘Reaching the Poor’ volume (Gwatkin et al. 2005) used such an\n\n\napproach. The increased use of electronic personal identification systems to target\n\n\npublic resources on the poor and vulnerable, such as the smart card used in India’s\n\n\naforementioned RSBY program, provide another potential source of information on\n\n\nthe living standards of a user’s household; sometimes this may only indicate\n\n\nwhether the household is above or below a poverty line, but over time more\n\n\ngranular data may be recorded in the system, such as the household’s score on\n\n\nwhatever means test (or proxy means test) was used to determine the position vis-à\n\nvis the poverty line or eligibility for a subsidy.\n\n\nAn additional area for future work is using the index to shed light on policy. A\n\n\ncouple of approaches suggest themselves. One is to use the index to quantify the\n\n\nimpacts of reforms on UHC. Reforms and programs often focus on specific\n\n\nchallenges, sometimes those deemed most important by the international\n\n\ndevelopment community, and will, because of their limited focus, likely affect only\n\n\nsome of the indicators in the UHC index. If one has good evidence on the impacts of\n\n\na reform or program on a subset of indicators, one could use these estimates to see\n\n\n42\n\nMention: \"DHS\""}, {"role": "assistant", "content": "{\"role\": \"supporting\", \"usage_action\": \"source\", \"summary\": \"Its wealth index scoring system is replicated for the smaller survey.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:006521:13:2", "occurrence_id": "f31d321e9160cda12a2d7da6", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: ** **3.4** **0.7** **20.9%** **0.2%** **0.6%**\n**World** **408.9** **235.7** **57.7%** **343.3** **206.3** **60.1%** **24.9%** **21.8%**\n\n\n\n**(%)**\n\n\n\n**(%)**\n\n\n\n**Mortality**\n\n\n\nCoastal populations are those living within 100 kilometers (km) of the coast, and excluding countries without\nterritory within 100 km of a coastline measured using an Azimuthal Equidistant (world) projection.\n\n\nHigh infant mortality is 50 or more deaths within the first year of life per 1,000 births (or 500 deaths/10,000 live\nbirths).\n\n\nChild malnutrition counts are the product of malnutrition rates and population counts. Malnutrition rates are\nbased on the percentage of children with a weight‐for‐age z‐score more than two standard deviations below the\nmedian of the NCHS/CDC/WHO International Reference Population.\n\n\nSee the appendix for details on the spatial methods in calculating these coastal population distributions.\n\n\nLow‐income economies are those in which 2013 per capita income was $1,045 or less, lower‐middle‐income\neconomies are those in which 2013 per capita income was between $1,046 and $4,125, upper‐middle‐income\neconomies are those in which 2013 per capita income was between $4,126 and $12,745, and developed countries\nare those in which 2013 per capita income was more than $12,745, as defined by the World Development\nIndicators\n\nMention: \"NCHS/CDC/WHO International Reference Population\""}, {"role": "assistant", "content": "{\"role\": \"supporting\", \"usage_action\": \"source\", \"summary\": \"Its median defines the standard deviations used for the stunting cutoff.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:006537:17:0", "occurrence_id": "84b6b46845d0f4b6a01c7a13", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: statistics (p. 110). This suggests that small and medium size …rms are routinely omitted\n\n\nfrom the IO table samples, and that the industry import intensities inferred are often based\n\n\non data of mostly large …rms. For China, according to the National Input-Output Survey\n\n\nMethods of China (2007) published by the National Bureau of Statistics of the People’s\n\n\nRepublic of China, the sample used to construct the IO tables consists of all large …rms\n\n\nthat have at least 300 million yuan in revenue (about 38 million USD during the sample\n\n\nperiod), along with some small- and medium-sized …rms sampled with unknown proportions\n\n\n(see item 5 on p. 3 about sample selection and item 4 on p. 27 about size cuto¤s). In other\n\n\nwords, the sampling method behind the construction of Chinese IO tables is heavily biased\n\n\ntowards the very large …rms.\n\n\nSecond, recent research by Amiti, Itskhoki and Konings (2014) and Blaum, Lelarge and\n\n\nPeters (2014) shows that large …rms tend to have a higher import-to-sales ratio. This is also\n\n\ncon…rmed by our sample of Chinese …rms. When we regress a …rm’s import intensity on\n\n\n…rm size (measured by log(sales)), controlling for industry-year …xed e¤ects, we …nd that\n\n\ndoubling …rm sales is associated with a 0.5 percentage-point increase in the …rm’s import\n\n\nintensity (signi…cant at the 1% level). 29 Given that …rms’import intensity and DVAR are\n\n\nnegatively correlated, by omitting the smaller …rms, IO tables by construction tend to include\n\n\n…rms with a lower DVAR. Such\n\nMention: \"National Input-Output Survey\n\n\nMethods of China\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"Its published methods define how the input-output coefficients are derived.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:006539:32:1", "occurrence_id": "ab7f43abcf097ae88d135b7d", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: \nNo discussion on gross job\ndestruction and firm size.\n\n\n\nNo discussion on\nfirm exit rates.\n\n\nNo discussion\non firm exit rates.\n\n\nNo discussion on\nfirm exit rates.\n\n\nSmall firms have\na higher exit\nrates.\n\n\n\nPage and Soderbom\n(2012); various\ncountries.\n\n\n\nWorld Bank Enterprise\nSurveys, and Manufacturing\ncensus data from Ethiopia.\n\n\n\nNo explicit definition\nof SMEs ;firms with\n100+ employees are\ndefined as large; those\nwith fewer are\ncategorized as small\n\n\nNo explicit definition\nof SMEs; various size\ncutoffs provided.\n\n\nNo explicit definition\nof firm size; various\nsize cutoffs provided\nusing firm sales.\n\n\nNo explicit definition\nof SMEs.\n\nMention: \"World Bank Enterprise\nSurveys\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"Combined with one national manufacturing census for the exit rate evidence.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:006545:5:1", "occurrence_id": "9899482f9de6194046d5601a", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: GDP by\nindustry and department (expressed in year 1994 constant new soles), and population by department.\n\n\nBecause of gaps in the regional and industry level employment estimates in SIRTOD, we complete this\ndata using the employment information – also at regional and industry levels – found in the National\nHousehold Survey (ENAHO). ENAHO is also our source for data on poverty rates by department. The\npoverty rate is the percentage of population living below a specified threshold of income.\n\n\nThe definitions of the key variables in our study are as follows:\n\n\n\n1. Value Added per worker =\n2. GDP per capita = Value Added\n3. Poverty level =\n\nHere,\n\n\n\nValue Added _i_, _j_ Total employment _i_, _j_\nValue Added _i_ Total population _i_\nPopulation below income threshold _i_ Total population _i_\n\n\n\n_i_ Department, _j_ Industry\n\n\n\n5 We discuss this in more detail in Section 5.\n6 Departments of Lima and Callao are grouped into one region (Lima‐Callao), following the classification used by INEI in the initial\nyears of the sample (early 2000s).\n\n\n4\n\nMention: \"National\nHousehold Survey\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"Its employment information at regional and industry levels carries the analysis.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:006545:5:1", "occurrence_id": "ae2abf2d0b46bb7598fb0ca9", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: GDP by\nindustry and department (expressed in year 1994 constant new soles), and population by department.\n\n\nBecause of gaps in the regional and industry level employment estimates in SIRTOD, we complete this\ndata using the employment information – also at regional and industry levels – found in the National\nHousehold Survey (ENAHO). ENAHO is also our source for data on poverty rates by department. The\npoverty rate is the percentage of population living below a specified threshold of income.\n\n\nThe definitions of the key variables in our study are as follows:\n\n\n\n1. Value Added per worker =\n2. GDP per capita = Value Added\n3. Poverty level =\n\nHere,\n\n\n\nValue Added _i_, _j_ Total employment _i_, _j_\nValue Added _i_ Total population _i_\nPopulation below income threshold _i_ Total population _i_\n\n\n\n_i_ Department, _j_ Industry\n\n\n\n5 We discuss this in more detail in Section 5.\n6 Departments of Lima and Callao are grouped into one region (Lima‐Callao), following the classification used by INEI in the initial\nyears of the sample (early 2000s).\n\n\n4\n\nMention: \"ENAHO\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"Also the source for poverty rates by department.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:006551:14:0", "occurrence_id": "4a43b9a4c3454235dabea0a9", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: ##### **5 Results**\n\n**5.1** **Nation-wide** **effect** **on** **lean-season** **food** **security**\n\n\nWe begin by presenting results from equation (1) which estimates the direct effect of the\n\nprogram on treated households and the indirect effect on untreated households. 12 The sum\n\n\nof the coefficients _β_ 1 + _β_ 2 ( _PWP_ and _PWP_ _∗_ _Top −_ _up_ ) compares households in treatment\n\n\nvillages that were themselves included in PWP to households in control villages. This total\n\n\neffect on top-ups is reported in the tables, along with 95 percent confidence intervals (upper\n\n\nand lower bounds). Table 4 displays the effect of the program on food security measured\n\n\nduring the lean season (in survey round 2). Higher values indicate better food security for\n\n\nthe first five measures and the PCA index, and lower values indicate better food security for\n\n\noutcomes in columns 6-8. Panel A contains results from the full sample. The total effect\n\n\nof the program on top-up households moves in the direction of worse food security for all\n\n\nmeasures: negative coefficients for the first five outcomes, positive coefficients for the next\n\n\nthree outcomes, and a negative coefficient in column (9) for the PCA index. The effect on the\n\n\nPCA index is equivalent to one-tenth of a standard deviation of that outcome for households\n\n\nin control villages, but the coefficient - like those for all but one of the individual outcomes\n\n\n- is not statistically different from zero.\n\n\nHowever, these differences are at least partially driven by pre-existing differences in food\n\n\nsecurity. To account for this imbalance, we first limit the sample to the 159 villages covered\n\n\nby the IHS3 survey (Panel B) and and then include pre-treatment values\n\nMention: \"the IHS3 survey\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"curate\", \"summary\": \"The sample is limited to its 159 villages to correct an imbalance.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:006544:5:0", "occurrence_id": "bd70d4b4f6d29bfdd5f70369", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: incremental value when it focuses on areas which are not being addressed multilaterally (Mattoo\n\n\nand Fink, 2004).\n\n\nThere are some broad caveats to our analysis. Market access in many of the countries was not\n\n\npredictable due to a discretionary licensing regime. From banking to transport, entry was\n\n\nrestricted by the explicit and implicit limits on new licenses and the licensing process tended to\n\n\nbe opaque and discretionary. In several ASEAN countries, licenses and foreign equity ownership\n\n\nwere decided on a case-by-case basis, subject to requirements or approvals that involved several\n\n\nregulators and ministries. Some countries in certain sectors had no regulation at all, especially\n\n\nthe lower income countries in the region and pertaining to the supply of services through the\n\n\ncross border and consumption abroad modes. In some of these cases, the supply of services was\n\n\nallowed in practice, while in others it was prohibited. In general, the high level of discretion and\n\n\nthe absence of regulation created a less predictable policy environment and made it hard to\n\n\ndefine and assess the policy regime.\n\n\nSection 2 describes the nature of services trade policy data as well as how it was collected and\n\n\nverified. Section 3 presents the ASEAN policy patterns and places them in a global context.\n\n\nSection 4 takes a closer look at the policy measures used by ASEAN countries, highlighting\n\n\ncertain aspects of the regulatory environment. Section 5 assesses whether ASEAN countries\n\n\nliberalized their policies between 2008 and 2012. Section 6 examines instances of where\n\n\nASEAN countries became more open vis-à-vis each other and provides two examples. Section 7\n\n\ncompares the regional and multilateral commitments of ASEAN countries with actual policy.\n\n\nSection 8 concludes.\n\n\n**2.** **SERVICES TRADE POLICY DATA AND MEASUREMENT**\n\n\nA detailed description of the original World Bank Services Trade Restrictions Database—\n\n\nincluding details on the data collection process, the policy measures covered and the\n\n\nquestionnaire used in the data collection—is provided in Borchert, Gootiiz and Mattoo (2012)\n\n\nand in supplementary\n\nMention: \"World Bank Services Trade Restrictions Database\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"Its collection process and policy coverage are described in detail here.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:006564:24:0", "occurrence_id": "ab98fe54103f410abb459ed0", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: _Figure 6: Isolated PISA Effect of Changes in Selected Parameters in the Production Function,_\n\n_2006-2012_\n\n\n25\n\n\n\n20\n\n\n15\n\n\n10\n\n\n5\n\n\n0\n\n\n‐5\n\n\n‐10\n\n\n‐15\n\n\n‐20\n\n\n\n\n\n\n\n\n\n\n\n_Source_ : Authors’ simulations using estimation results.\n\n\n**VI.** **Conclusions**\nArgentina’s education system, which has shown virtually no improvements in basic\ncognitive abilities as measured by PISA test scores in the last 15 years, will have long-lasting\nnegative effects on the country’s productivity and economic growth prospects. Moreover, since\nthe learning gap between students in public versus private schools increased during the same\nperiod, the education system’s ability to reduce income inequality and promote social mobility is\ncompromised. It is therefore central to Argentina’s development agenda to understand the causes\nbehind these unwelcome trends in learning outcomes.\n\nDespite an important increase in the public resources invested in education inputs, such as\nrises in teacher numbers, teacher salaries, school infrastructure, and laptops, none of it seems to\nhave significantly improved learning outcomes. Our simulation shows that the trends in PISA\nlearning outcomes are explained not by the amount of inputs in the system but by how efficiently\nthose inputs are used in the production of learning. This reinforces the finding from our regression\nanalysis that quantity of teachers (as measured by pupil-teacher ratios) does not correlate with\nlearning, and that other inputs (such as computers and instructional materials) seem to have\nmarginal returns and diminish over time. In fact, the decline in learning outcomes between 2000\nand 2006 is largely explained by the drop in test scores of students in public schools, while much\nof the recovery between 2006 and 2012 is accounted for by improvements in socioeconomic\nvariables such as wealth and mothers’ education levels.\n\nThe results presented here highlight the failure of input-based education policies to\nimprove learning outcomes. This is not to say that education inputs are not important in the\nlearning process, but their impact is limited and seems to\n\nMention: \"PISA test scores\""}, {"role": "assistant", "content": "{\"role\": \"supporting\", \"usage_action\": \"source\", \"summary\": \"Basic cognitive abilities show no improvement across fifteen years on this measure.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:006580:8:0", "occurrence_id": "378400e5311f0d8391ae1826", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: renewed relatively frequently. This can explain a preference for long-term debt on the part of\n\n\nfirms, and increased firm volatility if long-term debt is not available when it is preferable. If\n\n\nlong-term finance is undersupplied in a country due to reasons such as poor information or\n\n\ncontract enforcement, firms can either reduce investment in long-term assets or bear\n\n\nadditional liquidity risk (Aghion et al., 2010). To minimize liquidity risk as well as interest\n\n\nrate risk, firms often match the maturity structures of their assets and liabilities (Hart and\n\n\nMoore, 1995). 4 [^4: For empirical evidence on asset and liability maturity matching by firms, see Schiantarelli and Sembenelli\n(1997), Stohs and Mauer (1996), Jaramillo and Schiantarelli (2002), and Schiantarelli and Srivastava (1997).] Limited access to long-term finance inhibits maturity matching when\n\n\ninvesting long-term, possibly resulting in more volatile firm growth.\n\n\nIn summary, long-term debt may reduce firm-level volatility by reducing roll-over risk,\n\n\nwhile conversely a lower ability to monitor and enforce debt contracts may lead to greater\n\n\ninefficiency and risk-taking by firms. We empirically explore these relationships by relating\n\n\nmeasures of firm volatility to proxies for the availability of long-term finance, also\n\n\ncontrolling for the availability of overall external finance in some specifications.\n\n\n**3** **The data**\n\n\nIn this study, we relate measures of firm-level volatility to firm debt maturity structure.\n\n\nThe sample consists of firms in all sectors with the exception of financial firms and firms in\n\n\nthe public sector, as these firms’ capital structure decisions and risk profiles are very different\n\n\nfrom other firms.\n\n\nWe use two measures of firm volatility. In particular, we construct Asset volatility\n\n\n(book) as the standard deviation of the growth rate of the book value of total assets over the\n\n\n1995-2013 period using balance sheet information obtained from the Worldscope database.\n\n\n4 For empirical evidence on asset and liability maturity matching by firms, see Schiantarelli and Sembenelli\n(1997), Stohs and Mauer (\n\nMention: \"the Worldscope database\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"Balance sheet information across this period comes from this database.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:006607:36:0", "occurrence_id": "4f377ce527b13219004bb190", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: **Table 3.a. Relation between PACC's Presence and Real Per Capita Household Expenditure from ENIGH 2002‐2008**\n\n\n(1) (2) (3) (4) (5) (6) (7) (8)\n\n\n\nLog Per Cap\nVARIABLES\nExpenditure\n\n\n\nLog Per Cap\nExpenditure\n\n\n\nLog Per Cap\nExpenditure\n\n\n\nLog Per Cap\nExpenditure\n\n\n\nLog Per Cap\nExpenditure\n\n\n\nLog Per Cap\nExpenditure\n\n\n\nLog Per Cap\nExpenditure\n\n\n\nLog Per Cap\nExpenditure\n\n\n\nPACC Presence (dummy) 0.00635 0.0757** 0.101** 0.0783**\n(0.035) (0.032) (0.043) (0.033)\nPACC Coverage (% of land sowed) 0.0020 0.0849** 0.0913** 0.0848*\n(0.049) (0.040) (0.046) (0.043)\nLog of Maize Yield 0.0870*** 0.0875*** 0.0389* 0.0409** (0.042) (0.038) ‐0.0852** ‐0.0859**\n(0.030) (0.\n\nMention: \"ENIGH\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"analyze\", \"summary\": \"Real per capita household expenditure across these rounds carries the regressions.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:006633:15:0", "occurrence_id": "60cdd0134caab2eff0221fcc", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: ### **4 Parameterization**\n\nIn this model, labor productivity is a function of the calendar, as well as\n\ntwo depreciation rates, _δr_ and _δm_, and two intensity parameters, _αr_ and _αm_ .\n\nIn this section, I narrow down the parameter space based on three criteria.\n\nFirst, the parameters must imply labor productivity that peaks during the\n\nworkweek, consistent with the patterns of electricity usage documented be\nlow. Second, the variation in productivity over the workweek must be within\n\nthe range of predicted variation in electricity usage per worker. Finally, the\n\nparameters must be such that a year of absence from work is associated\n\nwith a reentry penalty, consistent with magnitudes estimated in the labor\n\nliterature.\n\n\nThe first two criteria are based on predicted variation in electricity per\nworker over the workweek. Variation in electricity usage is informative of\n\nvariation in the utilization rate of capital, which, in the context of the model,\n\nis proportional to variations in _Lt_ (equation 4). I use data on electricity loads\n\nfrom seven regional transmission organizations (RTOs): ERCOT, PJM, ISONE, CAISO, MISO, NYISO and SPP. 11 The aggregate generating capacity of\n\nthese RTOs corresponds to roughly 60% of US totals, though coverage varies\nby RTO. 12 Observations range from January 1st, 2003 and February 15th,\n\n2015. Data are available on an hourly frequency (and on a higher frequency\n\nfor some RTOs) and are aggregated to a daily frequency. To remove long-run\nand seasonal trends, the data is de-trended using a weekly moving average. 13\n\n\nTo account for potential variation in the number of workers over the\n\nworkweek, I use the American Time Use Survey (ATUS) for\n\nMention: \"American Time Use Survey\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"Accounts for variation in the number of workers across the workweek.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:006635:6:0", "occurrence_id": "57194997ae244f5820f3f4d1", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: transformation has to be used to assign first period characteristics to the second-period observations\n(Inchauste et al., 2012; Azevedo et al., 2013a; Azevedo et al., 2013b).\n\n\nRank preservation implies anonymity, where the identity of the individual experiencing a particular\noutcome (such as income) is irrelevant—a permutation of outcomes between any two individuals in\nany of the two distributions being compared has no effect on the comparison. With this assumption,\none can compare across the same quantiles of two distributions (including distributions at two periods\nof time) _as if_ they are the same observations. But such a comparison may not account for the true\nnature of mobility trajectories (Bourguignon, 2010). 5 [^5: This is most easily seen by a thought experiment of two households with vastly different incomes, where the\nincomes switch perfectly from one period to another (household A’s income in period 1 becomes household\nB’s income in period 2, and vice-versa), while every other household’s income remains constant. With\nanonymity, no change can be detected; whereas in a panel data, there will be change.] By using panel data, where the assumption of\nrank preservation is not needed since households can be observed over both periods, we account for\nthe true trajectories of mobility, which results in more precise estimates of the contribution of each\ncomponent to poverty reduction. As we will see later, the ability to account for mobility is particularly\nimportant in this case, given the vast differences in the distribution of income growth across\nhouseholds that are observed, depending on whether one uses an anonymous or nonanonymous\nmeasure of growth incidence.\n\n\n**3.** **Data and Descriptive Statistics**\n\n\nWe use the India Human Development Survey (IHDS) for 2005 and 2012, a nationally representative\nsurvey that was conducted in all states and union territories of India (with the exception of Andaman\nand Nicobar and Lakshadweep). Both rounds of the\n\nMention: \"India Human Development Survey\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"A nationally representative survey across all states in these two rounds.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:006648:14:1", "occurrence_id": "1ed64814109808486d09d285", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: , 2009). World Governance Indicators\nvalues are normalized between -2.5 and 2.5 with a higher value being associated with better\ngovernance. The WGI Voice and Accountability indicator captures the quality of interaction\nbetween citizens and government and is particularly relevant for the MENA region, as well as\nbeing instrumental towards promoting a stable environment for production and investment (World\nBank, 2003a). Among all six WGI indicators, the MENA region averages the lowest in this\nmeasure. Voice refers to the voice of the citizens and their freedom of expression, choice in\ngovernment, and ability to demand action from those in power. Accountability refers to the\naccountability of the government and refers to the presence of sanctions whether through voting,\ninstitutional oversight, or oversight from a free media.\n\n\n13\n\nMention: \"World Governance Indicators\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"Normalised between minus 2.5 and 2.5, higher values meaning better governance.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:006649:13:0", "occurrence_id": "fc7caad95892e03582266087", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: measurements. Ignoring the weights completely would introduce bias, as it would only be approximately\nunbiased if dwellings were identical in size and equidistant.\n\n\nIn addition to the above concerns weight calculations, another potential issue with this group of methods\nis that there are points in the PSU that would not lead to the selection of any households. Consider the\nshaded area of figure 5. If any of these points were selected, the interviewer would not find any household\nbefore she left the boundaries of the PSU. This issue raises questions for the field protocols. Should\ninterviewers stop at the PSU boundary, or should they continue and select housing units outside of the\nselected PSU? If the former, how would the interviewer know where the PSU boundaries are? If the latter,\nthe probabilities should be adjusted for the fact that the _Ai_ region extends outside of the PSU, which is\nnot straightforward. Additional structures outside of the boundaries of the PSU would need to be\nmapped, requiring additional preparation time. For the purposes of this paper, we mapped all households\nin a 50 meter buffer zone around the PSU\nboundaries. This increased the number of\nstructures required from 309 to 408, 68 to 207,\nand 353 to 724, respectively, nearly doubling\nthe required mapping time if manual\ndelineation is used. A third option would be to\nallow interviewers to travel outside of the PSU\nin search of a selected household, but then\nremove these interviewed households outside\nthe selected PSUs from the data set, because\ntheir probabilities of selection are too complex\nto calculate. This approach preserves the\nprobabilities of selection and is easy for the\ninterviewer to implement, but deleting data is\ninefficient in terms of cost.\n\n\n_3.5_ _Random Walk_\n\n\nThere are many different implementations of\nthe random walk procedure, of which each\ninvokes choosing a starting point within the\nselected area and then proceeding along a\npath, selecting every _k_ _th_ household. The\n\nAfrobarometer survey.\n\nMention: \"Afrobarometer survey\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"Households selected by a skip interval along a path from a starting area.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:006673:13:0", "occurrence_id": "35c4aa7a5ff5888f8fe96c52", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: **Figure 8. Estimated coefficient for the dummy indicator of urban SSA by food headings**\n_Note:_ Reported are coefficient estimates for the SSA dummy in column (4) of Table 3.\n_Source:_ Authors’ calculations are based on the 2011 ICP data.\n\n\nAlthough results for the categories of household consumption except for housing rent, household\nconsumption except for housing rent and food, and food would be more robust than the ones for smaller\ncomponents, we also examined other groups of items. Our estimation for housing rent is based on nonadjusted PLIs for countries that collected price data predominantly in urban areas because national-tocapital city price ratios for housing rent are not available. The estimation result shows that housing rent is\n55% more expensive in urban SSA (Table 6). 10 [^10: In its broadest category in the ICP data, the PLI of housing includes not only household expenditure on actual and\nimputed housing rent, but also maintenance and repair of the dwelling and utilities (see Appendix C). We focus on\nonly PLI for housing rent in the present paper.] Other groups of relatively expensive items include\ntransport (42%), communication (46%), and restaurants and hotels (41%). Transport items include\nhousehold expenditure on purchase of vehicles, operation of personal transport equipment, and transport\nservices (see Appendix C). Figure 9 summarizes our results.\n\n\n**Table 6. Estimated coefficient for the indicator of urban SSA for non-food expenditures**\n\n\n\n\n\n|Col1|Housing rent|Transport|Communication|Restaurants & hotels|\n|---|---|---|---|---|\n|Coefficient estimate
for SSA dummy|0.546***
(0.188)|0.424**
(0.183)|0.457*
(0.225\n\nMention: \"2011 ICP data\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"analyze\", \"summary\": \"Household consumption categories are analysed against this comparison programme's prices.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:006683:12:1", "occurrence_id": "147ff7162cb1eec185212b7d", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: month, a level deemed to represent “gainful” employment.\nInterestingly, about 15 percent of the sample was already engaged in the same trade for which training they\napplied (denoted as “trade-specific IGA”), indicating that a significant minority of applicants were looking\nto upgrade their existing skills. Though they are not older than the men in the sample, women are more\nlikely to be married and have a child, and have lower employment and earnings at baseline. 31 [^31: More details about the characteristics of the study population are found in a separate baseline report, available upon request\nfrom the authors.]\n\nAs discussed in Section II, the EF provides financial incentives for T&E providers to recruit and train people\nfrom the Dalit and Janajati ethnic groups. For Janajatis, the T&E providers appear to respond to these\nincentives, as 44 percent of the applicants are Janajatis, and they are statistically more likely to be in the\ntreatment group than control. 32 [^32: For reference, the 2001 census indicated that Janajatis made up 37% and Dalits made up 13% of the total Nepali population.] The T&E providers appear to have less success with attracting Dalit\napplicants: only 8 percent of the applicants are Dalits (a bit less than the population average), and they are\nequally divided between the treatment and control groups.\n\n\n**b.** **Estimating the EF Training Program Effects**\nTo estimate causal effects of the EF training program on various outcomes, first we employ a “difference\nin difference” (DID) technique. We will refer to this as the OLS specification in the remainder of this report.\nThe main equation we estimate is:\n\n\n29 The survey team deployed a fixed number of staff to each district center, with a schedule of all events in that district. Events\nconducted by high-capacity T&E providers and in popular trades were more likely to\n\nMention: \"the 2001 census\""}, {"role": "assistant", "content": "{\"role\": \"supporting\", \"usage_action\": \"source\", \"summary\": \"Its shares for two population groups give the reference population.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:006699:13:1", "occurrence_id": "ffd9b398e8fccc338f07e3a0", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: and large with\n100 or more employees.\n\n\nThe survey included 424 enterprises stratified by sector, region and size, with between 40 and 76\nenterprises in each sector. About half the sample (224 firms) is located in Dar es Salaam and the\nbalance divided rather evenly across each of the remaining regions (each with about 50 firms).\nOverall, small firms make up 63 percent of the sample, medium-size firms 26 percent and large\nfirms 11 percent. However, this firm-size distribution varies considerably across sectors and\nregions. Small firms are mostly found in textiles and garments, fabricated metals, furniture and\nIT, while large firms are more prevalent in food, construction, and transportation. Mbeya and\nZanzibar are dominated by small and medium firms while Dar es Salaam and Arusha have most\nlarge firms.\n\n\nTESS builds on the recently completed 2013 Enterprise Survey for Tanzania, retaining selected\nkey variables on firm characteristics, firm performance and productivity, and adding an expanded\nmodule of questions on employment and skills. It elicited qualitative and quantitative information\nfrom firms about the education and occupational composition of their workforce, their perceptions\nabout skill gaps in education as well as different cognitive, non-cognitive and technical skills and\nthe constraints these pose for their operations, their strategies for addressing skill gaps including\nthe hiring of new workers, use of foreign workers and outsourcing skills, and their in-house and\n\n\n12\n\nMention: \"2013 Enterprise Survey for Tanzania\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"The panel builds on it, retaining firm characteristics and performance variables.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:006703:6:1", "occurrence_id": "54b71d17ccd9b27cf8a20e7b", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: , date of birth, and\n\n\nmaximum schooling level achieved. Only full-time wage earners with complete information\n\n\non demographics and job attributes were kept for the analysis. 2\n\n\nUsing the unique firm identifiers, we have merged these data with customs records on\n\n\nexport transactions collected by _Secretaria do Com´ercio Externo_ (SECEX) of the Ministry\n\n\nsee Greenaway and Nelson (2000), Bastos and Silva (2009), Falvey, Greenaway and Silva (2008, 2010) and\n\n\nthe references therein.\n\n2In particular, we kept for analysis employees working more than 20 hours per week, aged between 16\n\n\nand 65, and earning at least the national minimum wage.\n\n\n5\n\nMention: \"customs records on\n\n\nexport transactions\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"Merged to the firm data through unique identifiers.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:006705:18:0", "occurrence_id": "07cfdf479f82a30e19236d9f", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: Figure 4: Likelihood and intensity of social support from children.\n\n\n**3.1.6.Financial transfers from children to parents**\n\n\nAs noted in previous literature, the upward flow of economic resources within European families is almost\nnegligible. In general less than 2% of respondents in the sample have received financial support from a child.\nThere are a few exceptions. In two countries, Czech Republic and Greece the quota of elderly people receiving\nfinancial help is above 7% - possibly a consequence of weaker public pension provision. In 6 other countries\n\n- Poland, Austria, Estonia, Germany, Italy and Spain – between 3 and 5% of the respondents have received\n\neconomic support from their children.\n\n\n**3.1.7.Intergenerational coresidence**\n\n\nBesides exchanging support while living in separate households, family generations can adopt a further\nstrategy to support each other: co-residence. As it has been shown in previous research, parents support their\nchildren also by letting them to prolong their co-residence in the parental home when they are adult and already\n\nworking, or letting them come back after a divorce or when becoming unemployed. On the other hand, children\nmight support their elderly parents by co-residing with them when they become frail and need assistance. So\nfar, when using the SHARE data, it has proven difficult to separate the two different motives for co-residence\nand, thus, answer the question: who is helping whom through co-residence? Some analyses, though, indicates\nthat the needs of the children are more strongly correlated with intergenerational co-residence that the needs\nof the parents (see for instance Albertini and Kohli 2013). This result suggests that it is more frequently the\ncase that co-residence is a strategy adopted by parents to support their adult children than the other way around.\nMore research is needed, however, to clearly sort out the main reasons behind intergenerational co-residence,\nalso taking into consideration external constraints\n\nMention: \"SHARE data\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"validate\", \"summary\": \"Its measures make separating two co-residence motives difficult.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:006720:27:0", "occurrence_id": "aadfd388c548455bc345e1bb", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: **Figure 4**\nSaving for old age around the world and age\n\n\n\n55%\n\n\n50%\n\n\n45%\n\n\n40%\n\n\n35%\n\n\n30%\n\n\n25%\n\n\n20%\n\n\n15%\n\n\n10%\n\n\n5%\n\n\n0%\n\n\n\nWorld East Asia &\n\nPacific\n\n\n\nEurope & Central\n\nAsia\n\n\n\nHigh Income:\n\nOECD\n\n\n\nLatin America &\n\nCaribbean\n\n\n\nMiddle East &\n\nNorth Africa\n\n\n\nSouth Asia Sub-Saharan\n\nAfrica\n\n\n\nNotes: Notes: Weighted averages from the Global FINDEX (2015) data\n\n\n26\n\nMention: \"FINDEX (2015) data\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"analyze\", \"summary\": \"Weighted regional averages of financial access come from this round.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:006765:5:0", "occurrence_id": "30f030ddc90626c7d7a40581", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: In modeling the impact of the ECU adopting a CET that mirrors Russia’s WTO commitments through\n2020, it was assumed that those commitments would be fully implemented 4 [^4: There have been concerns that introducing compound tariffs into the CET, adding a specific duty to ad valorem rates, may exceed Russia’s\nbound rates in products such as large-capacity refrigerators. The EU Market Access Database (MAD) also suggests that a total of 1,576 product\nlines have been “corrected” by Russia (abolished or introduced) relative to its 2007 tariff schedule, including tariff sub-codes (presumably\nnational tariff lines below the HS-6 level). This could be characterized as “manipulation” to avoid implementing the tariff commitments. EU\nMAD also states that Russia’s import duties on coated paper and cardboard in the Single Customs Tariff were three times higher than its WTO\ncommitment (15 percent instead of 5 percent).] ; for example, if the current\nCET for a product is higher than Russia's bound commitment for any given year, the applied CET would\nfall to the lower bound rate. Conversely, if the current CET were below the bound rate, presumably there\nwould be no change in the tariff.\n\nThe results suggest that full acceptance of Russia’s WTO tariff bindings through 2020 would increase\ngoods imports by about $3.5 billion (1.1 percent of total imports), measured against a 2012 baseline.\nLower prices for these imports as a result of tariff cuts in affected sectors would benefit Russian\nconsumers by some $371.39 million. The largest increases in import values are estimated for electrical\nand electronic equipment ($592 million, 1.7 percent increase); pharmaceutical products ($365 million, 2.7\npercent); meats ($248 million, 3.4 percent); plastics and plastic products ($238 million, 2.1 percent);\nmachinery ($151 million, 0.3 percent);\n\nMention: \"EU Market Access Database\""}, {"role": "assistant", "content": "{\"role\": \"supporting\", \"usage_action\": \"source\", \"summary\": \"It reports product lines corrected by the accession country.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:006776:17:0", "occurrence_id": "a0b40e28f2565e3c15f0cd39", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: 100\n\n\n90\n\n\n80\n\n\n70\n\n\n60\n\n\n50\n\n\n40\n\n\n30\n\n\n20\n\n\n10\n\n\n0\n\n\n\nWon't\nmake\nthings\nbetter\n\n\nCould\nmake\nthings\nbetter\n\n\n\nall low\neducation\n\n\n\nfood\ninsecure\n\n\n\nall low\neducation\n\n\n\nfood\ninsecure\n\n\n\n**Uganda** **Nigeria**\n\n\n_Source:_ World Bank (2016) using data from Afrobarometer Round 4.5.2 (Uganda 2011), Round 3.5\n(Nigeria 2007).\n\n\n_Notes_ : The survey question is the following: “Which of the following statements is closest to your view?\nChoose Statement 1 or Statement 2.Statement 1: No matter how you vote, it won’t make things any\nbetter in the future. Statement 2: The way you vote could make things better in the future.”\n\n\nNot only do Ugandan and Nigerian citizens believe in the importance of voting, and vote at high rates,\nbut they also express interest in receiving information about elections. More than 80 percent of\nrespondents said they wanted a little more or a lot more information ahead of the 2007 elections in\nNigeria and the 2011 elections in Uganda (Figure 5). Again, those with less education and food security\nare just as interested in receiving more information as others.\n\n\n**Figure 5. How Much More Information Do Citizens Want in Order to Decide How to Vote, Uganda and**\n**Nigeria**\n\n\n16\n\nMention: \"Afrobarometer Round 4.5.2\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"Its module on food insecurity carries the two-country comparison.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:006777:31:0", "occurrence_id": "10d2e6b2439516e9d0e80973", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: **Figure 6 Cotton Output per Farmer: Administrative Delivery Data vs. Survey Data, 2009/10 Season**\n\n\nSource: Author’s analysis based on data provided by Fink Masiye.\nNote: This chart juxtaposes the data unerlying Fink Masiye (2015) with the same farmers’ deliveries (in kg) to the cotton buying company\nin the same year, where available. Deliveries are translated from bales into kilos using the average weight of 80kg per bale. Values are not\nlog-transformed in order to retain observations with values equal to zero. To visualize the majority of observations that lie below 1,000 kg,\na subset of the data is displayed on the right.\n\n\n30\n\nMention: \"Administrative Delivery Data\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"Output per farmer is compared between these records and the survey.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:006779:46:2", "occurrence_id": "976dcbd6b4c26d25c889b375", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: Yes Yes Yes Yes Yes Yes Yes\n\n\nN 2246 2246 2246 2246 2294 2145 2145 2145 2145 2170\n\n\nR2 0.082 0.090 0.080 0.083 0.069 0.074 0.081 0.068 0.082 0.047\n\n\nNotes: Table presents coefficients estimated from Panel sub‐sample Fixed Effects model. * 0.10 ** 0.05 *** 0.01 significance level. Values in\nparentheses indicate standard errors, which are corrected for cluster correlation at commune‐level in regressions (1) – (4). Regressions include\nhousehold controls as presented in Table A.5.\nSource: Author’s calculation based on VHLSS 2010, 2012 & 2014 and CRU data.\n\n\n45\n\nMention: \"VHLSS\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"analyze\", \"summary\": \"Household controls in the appendix table are computed across these rounds.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:006779:46:2", "occurrence_id": "36748c635fcff6ddfd8398c7", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: Yes Yes Yes Yes Yes Yes Yes\n\n\nN 2246 2246 2246 2246 2294 2145 2145 2145 2145 2170\n\n\nR2 0.082 0.090 0.080 0.083 0.069 0.074 0.081 0.068 0.082 0.047\n\n\nNotes: Table presents coefficients estimated from Panel sub‐sample Fixed Effects model. * 0.10 ** 0.05 *** 0.01 significance level. Values in\nparentheses indicate standard errors, which are corrected for cluster correlation at commune‐level in regressions (1) – (4). Regressions include\nhousehold controls as presented in Table A.5.\nSource: Author’s calculation based on VHLSS 2010, 2012 & 2014 and CRU data.\n\n\n45\n\nMention: \"CRU data\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"Weather station observations combined with the household rounds.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:006809:13:0", "occurrence_id": "c1192732966f67aac631480e", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: parametric cross-entropy methods, but keeping it consistent with the United Nations’ population\nprojections and levels of education observed in the household surveys. 11 [^11: The GIDD model also projects the share of skilled and unskilled workers by using initial information on education\navailable in the household surveys, following a methodology that assumes constant enrollment rate across age cohorts.]\n\n\nTo be consistent with the GIDD, LINKAGE is modified to adopt the former’s skilled-unskilled\nlabor definition, whereby a skilled worker is anybody with more than nine years of education,\nand an unskilled worker is anybody with nine years of education, or less. This redefinition\nnecessitates an adjustment of the GTAP data on value added by labor type in production, such\nthat the number of workers of a given skill type in a given sector is consistent in the 2007\nbenchmark year across the two modeling frameworks.\n\n\n**3.2 Scenarios**\n\n\nUsing the simulation framework described above, seven alternative future scenarios are\nconsidered. The scenarios are designed so as to be able to identify the marginal impact of a given\npolicy outcome as it interfaces with demographic change (Table 1). The policy outcomes are\nthose related to the demographic dividend and include the maintenance and improvement of\nemployment ratios, improvements in educational attainment and quality, and changes in savings\nbehavior. To achieve this, first a “business-as-usual” scenario is considered to establish a\nbaseline economic path till 2050 for the SACU economies. In the baseline, educational\nattainment rates are assumed to be constant, the total labor supply grows at the same rate as the\nworking-age population (based on the same rate as the UN WPP’s medium fertility scenario),\nand employment ratios remain constant at 2015 values. The current account balances and\ninvestment shares track the forecasts of World Bank (2015b) till 2017 before converging to longrun values. Labor productivity is assumed to grow in a fashion that real GDP grows till 2017\nfollowing the World Bank (2015b), and following growth projections under the\n\nMention: \"GTAP data\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"curate\", \"summary\": \"Value added by labour type is adjusted to the new education cutoff.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:006810:9:0", "occurrence_id": "d8440595ef42f5d2d84ef409", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: Hanna (2014), from a combination of CPCB online and print records. The dataset spans the whole of\n\n\nIndia and runs from 1986-2004; an observation is a pollution monitor-month.\n\n\nThe national dataset contains information from 470 monitors situated along 162 rivers in 28 states.\n\n\nExcluding all areas outside the Ganga Basin leaves us with 101 unique pollution monitors along 29\n\n\nrivers, in 62 districts representing 10 states; these are mapped in Figure 2. Over our 19-year period\n\n\nof observation, as many as 46 different measures of water quality are recorded at these monitoring\n\n\nstations, but only a few measures are consistently recorded over the entire sample time frame. The\n\n\ndata are noisy, suggesting significant measurement error, and the panel is imbalanced. To mitigate these\n\n\nproblems, we collapse monitor-level observations to the district level and construct moving averages\n\n\nof the data over a four-month window. These steps produce 8,725 district-month observations in the\n\n\nGanga Basin with at least one non-missing value from our pollution measures of interest.\n\n\nOur main indicator of river quality is BOD. This common, broad-based indicator of water pollution\n\n\ncaptures the amount of dissolved oxygen needed by water-borne, aerobic organisms to break down\n\n\norganic material present at a certain temperature (usually 20 degrees Celsius) and over a specific time\n\n\nperiod (usually five days). Its units are milligrams of oxygen consumed per liter (mg/l). Reduction of\n\n\nBOD is the primary goal of waste treatment plants in general (Brown and Caldwell 2001), but BOD is a\n\n\nparticularly good choice for pollution measurement in the setting of Kanpur. Pollution from the tanning\n\n\nprocess primarily comes from two sources: the animal hides themselves, and the chemicals used to tan\n\n\nthem. Both of these sources contain large amounts of organic matter, resulting in abnormally high\n\n\nBOD levels in tannery effluent. According to the United Nations Industrial Development Organization\n\n\n(UNIDO), effluent discharge into surface water typically is required to have BOD below\n\nMention: \"CPCB online and print records\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"Combined into a panel of observations spanning the whole country.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:006813:14:0", "occurrence_id": "b36d2e5f3b3a793c40371f91", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: For high income OECD economies, Chile, Japan, and Israel have the highest proportions of legal\n\n\ngender disparities while the Slovak Republic, Australia and Ireland have the lowest (figure A7).\n\n\nWhile Chile and Japan have the top two highest proportions of legal gender disparities, the\n\n\ncomposition of legal disparities differs. For Chile it is mostly due to legal disparities in Getting a\n\n\njob, while in Japan it is due to lack of domestic violence legislation. In South Asia, Afghanistan\n\n\nand Pakistan have the highest proportions of legal disparities while Bhutan and India have the\n\n\nlowest. Afghanistan is the only economy in the region with 100 percent legal disparities in three\n\n\nsubcategories - Building credit, Going to court, and Violence (figure A8). In MENA, the Islamic\n\n\nRepublic of Iran has the highest proportions of legal gender disparities followed by Saudi\n\n\nArabia, while Malta and Morocco have the lowest in the region (figure A9).\n\n\n**4.** **Correlations with Other Gender Indices**\n\nThe WBL composite measure of legal disparities provides a clean measure of differential\n\n\ntreatment of men and women before the law. There are two potential critiques of this measure.\n\n\nOn one hand it may be unrelated to gender equality where the law on the books does not reflect\n\n\nthe realities on the ground. Under this scenario, the WBL composite measure of legal disparities\n\n\nwould be uncorrelated with other measures of gender inequality. On the other hand, the measure\n\n\ncould be perfectly correlated with other gender indices, thereby making the WBL measure of\n\n\nlegal disparities redundant. To address both critiques, the correlations between the WBL measure\n\n\nof legal disparities and other gender-related measures are explored. The following gender-related\n\n\nmeasures are considered: CIRI Women's Social Rights, CIRI Women's Economic Rights, CIRI\n\n\nWomen's Political Rights, WEF Gender Gap Index, Social Watch Gender Equity Index, Ratio of\n\n\n13\n\nMention: \"WEF Gender Gap Index\""}, {"role": "assistant", "content": "{\"role\": \"supporting\", \"usage_action\": \"source\", \"summary\": \"One of several indices of rights and parity assembled in the list.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:006813:14:0", "occurrence_id": "dd0042d984ffdfea56a0c229", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: For high income OECD economies, Chile, Japan, and Israel have the highest proportions of legal\n\n\ngender disparities while the Slovak Republic, Australia and Ireland have the lowest (figure A7).\n\n\nWhile Chile and Japan have the top two highest proportions of legal gender disparities, the\n\n\ncomposition of legal disparities differs. For Chile it is mostly due to legal disparities in Getting a\n\n\njob, while in Japan it is due to lack of domestic violence legislation. In South Asia, Afghanistan\n\n\nand Pakistan have the highest proportions of legal disparities while Bhutan and India have the\n\n\nlowest. Afghanistan is the only economy in the region with 100 percent legal disparities in three\n\n\nsubcategories - Building credit, Going to court, and Violence (figure A8). In MENA, the Islamic\n\n\nRepublic of Iran has the highest proportions of legal gender disparities followed by Saudi\n\n\nArabia, while Malta and Morocco have the lowest in the region (figure A9).\n\n\n**4.** **Correlations with Other Gender Indices**\n\nThe WBL composite measure of legal disparities provides a clean measure of differential\n\n\ntreatment of men and women before the law. There are two potential critiques of this measure.\n\n\nOn one hand it may be unrelated to gender equality where the law on the books does not reflect\n\n\nthe realities on the ground. Under this scenario, the WBL composite measure of legal disparities\n\n\nwould be uncorrelated with other measures of gender inequality. On the other hand, the measure\n\n\ncould be perfectly correlated with other gender indices, thereby making the WBL measure of\n\n\nlegal disparities redundant. To address both critiques, the correlations between the WBL measure\n\n\nof legal disparities and other gender-related measures are explored. The following gender-related\n\n\nmeasures are considered: CIRI Women's Social Rights, CIRI Women's Economic Rights, CIRI\n\n\nWomen's Political Rights, WEF Gender Gap Index, Social Watch Gender Equity Index, Ratio of\n\n\n13\n\nMention: \"Social Watch Gender Equity Index\""}, {"role": "assistant", "content": "{\"role\": \"supporting\", \"usage_action\": \"source\", \"summary\": \"Another parity index included in the same set.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:006831:63:0", "occurrence_id": "292d7877e8326fa8f60fc9c7", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: **Figure 42: NonCU Destinations for Exports of Food and Agriculture**\n\n\n_Source_ : GTIS data.\n_Notes_ : MENA = Middle East-North Africa; nonCU-CIS = members of the Commonwealth of Independent States but not\namong the first three members of EACU; EU = European Union; ROW = Rest of World. Numbered regions: (1) Yaroslavl, (2)\nKaluga, (3) Vladimir, (4) Ivanovo, (5) Perm, (6) Moscow City, (7) Tula, (8) Nizhniy Novgorod, (9) Ryazan, (10) Mari El, (11)\nUdmurtia, (12) Mordovia, (13) Chuvashia [[ (14, 16) Tatarstan, (15) Penza, (17) Ulyanovsk, (18) Saratov, (19, 20) Samara,\n(21) Volgograd, (22) Kalmykia, (23) Adygea, (24) Stavropol, (25) Karachevo-Chercheskia, (26) Kabardino-Balkaria, (27)\nNorth Ossetia, (28) Chechnya, and (29) Ingushethia.\n\n\n0\n\nMention: \"GTIS data\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"Export destinations for food and agriculture come from these records.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:006838:27:1", "occurrence_id": "53e128b51af7fa824d026f93", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: * 1.43% 1.67% 2.43% 3.44% 3.16%\n\n**OECD** 2.30% 2.19% 2.71% 2.74% 2.58%\nEAP 0.44% 0.49% 1.01% 1.41% 1.27%\n\n**ECA** 1.73% 1.44% 1.79% 1.16% 1.03%\n\n**MENA** 0.04% 1.05% 0.40% 1.18% 0.90%\n\n**SHA** 0.24% 0.27% 0.78% 0.82% 0.63%\n\nSA 0.28% 0.42% 0.82% 0.69% 0.17%\n\n**LAC** **0.47%** **0.59%** **0.35%** **0.59%** **0.65%**\n\n\n_Source:_ Author’s calculations based on data from Lederman y Saenz (2005) and UNESCO\n**Note:** LAC: Latin America and the Caribbean; Scand.: Scandinavia, EAP: East Asia and the Pacific; ECA:\n\nEurope and Central Asia ; MENA: Middle East and Noth Africa (excluding Israel); SA: South Asia; SHA:\n\nSub-Saharian Africa . All previous groups exclude high income countries.\n\nMention: \"Lederman y Saenz (2005)\""}, {"role": "assistant", "content": "{\"role\": \"supporting\", \"usage_action\": \"source\", \"summary\": \"Its data are combined with the education body's figures for the comparison.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:006856:34:1", "occurrence_id": "27468210abe87588cbcdcbe6", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: .5 356.5\nTemperature inversion 16,846 0.24 0.43 0 1\n_Notes_ : Detailed statistics on wind direction converted to dummy variables representing the eight-point compass are\n\n\nomitted to save space.\n\n\n_Source_ : Data from RMCAB for 1997-1999 and 2008-2010. Author’s calculations.\n\n\n33\n\nMention: \"RMCAB\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"analyze\", \"summary\": \"Compass-direction wind observations across these periods come from this centre.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:006865:44:0", "occurrence_id": "dd1480926be645ac2da0d2b3", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: **Table S.6: Net Fuel Exports (as a % of GDP)***\n\n\nSource: World Development Indicators and authors’ own calculations. The blue shaded area represents the post-Arab Spring period.\nNet Fuel Exports (as a % of GDP) are calculated as the difference between Fuel Exports (as a % of GDP) and Fuel Imports (as a % of GDP). * n.a. means not\navailable\n\n\n11\n\nMention: \"World Development Indicators\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"Net fuel exports as a share of output come from this compilation.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:006871:37:4", "occurrence_id": "7d2a4ead9636ab50493d5ac9", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: trade balance by assumption – balancing regional budget constrains.\nAlternatively, we could pin down wages for some given deficit or surplus.\n\n\n###### **Appendix B. Data sources and construction of controls**\n\nThis appendix provides details on the data used and the data sources. A summary of the key\nvariables and the associated descriptive statistics are given in Table 3 in the main text and in\nTable 8 below.\n\n\n**B.1.** **Data sources.**\n\n\n**Plant-level** **data** **and** **industries.** Our analysis is based on the Annual Survey of Manufacturers (asm) Longitudinal Microdata file. This data cover the years from 1990 to 2010. Our\nfocus is on manufacturing plants only. For every plant we have information on: its primary\n6-digit naics code (the codes are consistent over the 20 year period); its year of establishment;\nits total employment; whether or not it is an exporter in selected years; its sales; the number of\nnon-production and production workers; and its 6-digit postal code. The latter, in combination\nwith the Postal Code Conversion files (pccf), allow us to effectively geo-locate the plants by\nassociating them with the geographical coordinate of their postal code centroids.\n\nThe survey frame of the asm has evolved over time. Early in the period, it was relatively\nstable with, on average, about 32,000 plants per sample year. The sample of plants was restricted to those with total employment (production plus non-production workers) above zero,\nand plants must have sales in excess of $30,000. Also, aggregate records were excluded. These\nrecords represent multiple (typically small) plants without latitudes and longitudes. In 2000,\nhowever, the number of plants in the survey increased substantially as the asm moved from\nits own frame to Statistics\n\nMention: \"Annual Survey of Manufacturers\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"Plant-level longitudinal file covering this span.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:006871:37:4", "occurrence_id": "9a11e47ab48ffab94d2f0f01", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: trade balance by assumption – balancing regional budget constrains.\nAlternatively, we could pin down wages for some given deficit or surplus.\n\n\n###### **Appendix B. Data sources and construction of controls**\n\nThis appendix provides details on the data used and the data sources. A summary of the key\nvariables and the associated descriptive statistics are given in Table 3 in the main text and in\nTable 8 below.\n\n\n**B.1.** **Data sources.**\n\n\n**Plant-level** **data** **and** **industries.** Our analysis is based on the Annual Survey of Manufacturers (asm) Longitudinal Microdata file. This data cover the years from 1990 to 2010. Our\nfocus is on manufacturing plants only. For every plant we have information on: its primary\n6-digit naics code (the codes are consistent over the 20 year period); its year of establishment;\nits total employment; whether or not it is an exporter in selected years; its sales; the number of\nnon-production and production workers; and its 6-digit postal code. The latter, in combination\nwith the Postal Code Conversion files (pccf), allow us to effectively geo-locate the plants by\nassociating them with the geographical coordinate of their postal code centroids.\n\nThe survey frame of the asm has evolved over time. Early in the period, it was relatively\nstable with, on average, about 32,000 plants per sample year. The sample of plants was restricted to those with total employment (production plus non-production workers) above zero,\nand plants must have sales in excess of $30,000. Also, aggregate records were excluded. These\nrecords represent multiple (typically small) plants without latitudes and longitudes. In 2000,\nhowever, the number of plants in the survey increased substantially as the asm moved from\nits own frame to Statistics\n\nMention: \"Postal Code Conversion files\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"curate\", \"summary\": \"Combined with six-digit postal codes to geo-locate plants.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:006880:8:1", "occurrence_id": "80af36f0321877ba1303ba07", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: \nThe main child health outcomes in this paper, infant mortality and neonatal mortality, are defined as\n\n\na baby dying before reaching his or her first birthday or month of life, respectively. Children born less\n\n\nthan twelve months prior to their mother’s interview are dropped since it is not possible to know whether\n\n\nthey will survive their first birthday. Also, only children born after their country’s year of independence\n\n\nare included in the sample. This gives a sample of 1,770,705 children born to 501,800 mothers between\n\n\n1967 and 2013 in the 56 countries. The sample average infant mortality rate is 7 percent and the neonatal\n\n\nmortality rate is 3.5 percent, indicating that half of the children that die before turning one year in fact\n\n\nlive less than one month. Figure 3 presents the yearly infant and neonatal mortality rates of the group\n\n\nof HIPCs and non-HIPCs. The differences between the groups are greater for infant mortality than for\n\n\nneonatal mortality and the general trend is decreasing for both mortality measures. Since there appears\n\n\nto be some differences in the trends between the two groups, I control for country-specific linear time\n\n\ntrends in the model specification presented below.\n\n\nTable 3 shows descriptive statistics on infant and neonatal mortality across different sub-groups of\n\n\nthe sample as well as other variables in the analysis (see Section 3.2 for more information on the other\n\n\n5I use the standard DHS unless stated otherwise.\n\n\n7\n\nMention: \"DHS\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"The standard rounds are used unless another is named.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:006886:16:0", "occurrence_id": "6e146f3c55e93506cc9e6dd8", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: **Figure 4. Intensity of computer use at work, workers ages 25 to 64, by employment type**\n**(percent distribution)**\n\n\n_Source_ : STEP Surveys (2014).\n\n\nWith regard to the distribution of workers by the complexity of their computer use, we find\n\n\nthat the largest proportion of computer users at work are using basic applications involving a word\n\n\nprocessor, spreadsheets, making presentations, or doing data entry. This group accounts for 40\n\n\nto 50 percent of computer users in most of the countries with the exception of Kenya and Bolivia\n\n\n(see Figure 5). In Kenya and Bolivia we find that the largest proportion of respondents who use\n\n\ncomputers on their job are using advanced programming skills. The proportion of workers\n\n\nhandling tasks involving basic programming skills like advanced functions in spreadsheets or\n\n\nbookkeeping applications is also substantial across all the countries (from about 15 percent in\n\n\nBolivia and Vietnam to more than 30 percent in Kenya and Ukraine). Finally, we find that less than\n\n\n10 percent of respondents who use computers at work limit their computer usage to browser\n\nbased tasks.\n\n\n15\n\nMention: \"STEP Surveys\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"Workers by employment type and competence complexity come from here.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:006887:20:0", "occurrence_id": "48f1f3caf40e105bc5cc88e9", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: tribution of transit migrants can now be expressed as\n\n\n \n\n\n,\n\n\n\n\n\n\n_k̸_ = _U_\n\n\n\n\n\n\n_j̸_ = _i_\n\n\n\n_M_ _s,i,j,U_ log _p_ _s,i,j,U_ ( _θ_ ) + _M_ _s,i,j,S_ log\n\n\n\n\n \n_p_ _s,i,j,k_ ( _θ_ )\n\n\n\n(10) log _L_ 1( _θ_ ) =\n\n\n\n\n\n\n_i_\n\n\n\nwhere _k̸_ = _U_ means the destination _k_ is any country other than USA.\n\n\nOur next dataset, the 2010 DIOC provides data on the number of people who migrated within\n\n\nthe last 10 years to OECD destination countries. This allows us to calculate the number of\n\n\nnatives who moved from _j_ to _k_ within the last 10 years if _k_ is an OECD country. We denote\n\nthis matrix _M_ _s,j,j,k_ . Next, we define _M_ _s,j,j,N_ as the number of people who move to non-OECD\n\ndestinations (labelled by _N_ collectively) and _M_ _s,j,j,j_ as the number of people who stayed in\n\n\ntheir birth country _j_ and did not migrate to any country. Both of these are 40 _×_ 1 vectors\n\n\nfor each skill group _s_ . In summary, natives (who were born in _j_ and living in _j_ ) are divided\n\n\ninto the following groups: Staying at\n\nMention: \"2010 DIOC\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"Counts of people who migrated within the last decade to destination countries.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:006889:40:0", "occurrence_id": "82ced5a685d1ec28b85829f2", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: In the simple theoretical framework presented in Section 3, we emphasize the imported input channel\n\n\nas the main mechanism through which trade liberalization affects firms’ decision to upgrade foreign\n\n\ntechnology. For the sake of simplicity we did not take into account the export side of the story and\n\n\nthe effects of trade liberalization through variations in trade variable costs affecting final goods that are\n\n\nalready well-documented in the theoretical literature (Yeaple, 2005; Bustos, 2011).\n\n\nExpansion of export opportunities due to foreign demand shocks might also increase the incentives\n\n\nfor firms’ to upgrade foreign technology embodied in imported capital goods. Moreover, importing\n\n\nintermediate inputs might lead to higher exports as documented in the empirical literature (Feng et al.,\n\n\n2016; Bas, 2012; Bas and Strauss-Kahn, 2015). Higher export profits would allow to overcome the fixed\n\n\ncost of importing capital goods. If input tariff changes are positively correlated with export performance\n\n\nor with variations in output tariffs set by India’s trading partners, our previous empirical findings might\n\n\nbe just picking up the effects of foreign demand shocks.\n\n\nThe industry-year fixed effects included in the estimations of the previous section already address\n\n\nthis issue since they capture all unobservable shocks at the industry level varying over time. In this\n\n\nsection, we provide additional evidence that foreign demand shocks at the sectoral level captured by\n\n\nexport tariffs are not picking up our results. We control for this alternative explanation by including\n\n\nin the previous specifications the average effectively applied tariff at the 3-digit NIC industry level set\n\n\nby the rest of the world to India (export tariff) during the 1989-1997 period from WITS dataset (World\n\n\nBank). Columns (1) to (3) of Table A5 in the appendix report the results. The effect of export tariff\n\n\nis negative but not significant. The coefficient of interest on the input tariffs remains robust and stable\n\n\nin all specifications when we take into account the role of foreign demand. This finding suggests that\n\n\nthe supply side\n\nMention: \"WITS dataset\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"Tariffs faced by one country's exports across this period come from here.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:006923:24:0", "occurrence_id": "f3a34c2b7ebbaeecab1be896", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: Croke et al. (2016)\n\n\nwould only involve the addition of the one multiple dose study the authors identify\n\n\nbut classify as separate from the MDA studies – Stephenson et al. (1993). 23 [^23: Note that we believe that Stephenson et al. (1993) should be included in the set of MDA studies, since\nindividuals were treated without first being screened, as discussed in Appendix A.3.]\n\n\n2. The 2012 Cochrane Review changed this approach, however, introducing a\n\n\ndistinction that effectively distinguished between test-and-treat and MDA studies\n\n\n(Taylor-Robinson et al. 2012). Applying this classification used in the 2012\n\n\nCochrane Review to the studies in TMSDG also leads to the inclusion of\n\n\nStephenson et al. (1993), which was classified as an MDA study by Taylor\n\nRobinson et al. 2012 (or, as a “target population treated” study, using the language\n\n\nin that review) rather than a test-and-treat study.\n\n\nThus, applying either of these procedures from Cochrane Reviews prior to TMSDG results\n\n\nin the addition of Stephenson et al. (1993) to the TMSDG sample. With Stephenson et al.\n\n\n(1993) classified in this way but otherwise using the data set in the TMSDG study, the null\n\n\nhypothesis of a common zero effect is strongly rejected with a p-value of 0.009 (see Table\n\n\n2, row 2).\n\n\n**5.2** **Testing the hypothesis of a common zero effect**\n\n\nWe now turn to the full sample of 22 treatment effect estimates. Table 3 shows that the null\n\n\nhypothesis of a common zero effect is rejected at p<0.001 in the full sample, in areas with\n\n\nprevalence above the thresholds at which WHO recommends MDA (20% prevalence), and\n\n\nin areas where it recommends multiple annual dose MDA (50% prevalence). This result is\n\n\nnot reliant on the addition of any one study to the TMSDG sample: any one of six updates\n\n\nleads to rejection\n\nMention: \"TMSDG study\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"Its dataset is reclassified to test whether a common effect can be rejected.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:006951:31:0", "occurrence_id": "7e22205285fe12abcf91e218", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: ###### **Appendices** **A.1 Robustness Checks**\n\nIn this section I conduct robustness checks on the main quantitative findings of the\nmodel with respect to two important parameters – the labor share of income - and the\ndepreciation rate of physical capital �. For the benchmark exercise, the labor share of income\nwas assumed to be 51 percent which was sourced from the GTAP database and the\ndepreciation rate was picked to be 3.2 percent which was sourced from the PWT 8.1. The labor\nshare of income for Bangladesh as sourced from the GTAP database is close but somewhat\nlower compared to the mean/median of lower‐middle income countries for which the data is\navailable in the PWT 8.1. In order to test the sensitivity of the main results of the model, I\nrepeat the quantitative exercises with a higher value of labor share of income. The chosen\nhigher value of the labor share – 55 percent, roughly corresponds to the mean labor share of\nlower‐middle income countries. In addition, I also consider two other extreme values of labor\nshare of income – 30 percent and 60 percent, to arrive at a broader range of results.\n\n\nThe following table compares the findings of section 3.1 when alternative values of\nlabor share of income are used for quantitative analysis. For clarity, the results are presented\nusing average growth rate over five year periods. The first set of results refers to the\nbenchmark exercise followed by simulations with other alternatives for labor share.\n\n\nThe resulting growth rate under each scenario is higher than the growth rate in the\ncorresponding scenario in the benchmark exercise when the labor share is reduced to 30\npercent. Equation (8) helps in understanding why this happens. The labor share of income\ndetermines the relative impact of factors pertaining to labor accumulation with respect to\nfactor pertaining to capital accumulation. A higher value of labor share increases the growth\nimpact from the former, for example\n\nMention: \"GTAP database\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"The labour share of income is sourced from this database.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:006951:31:0", "occurrence_id": "b001d99e0090a7bf0e9f9758", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: ###### **Appendices** **A.1 Robustness Checks**\n\nIn this section I conduct robustness checks on the main quantitative findings of the\nmodel with respect to two important parameters – the labor share of income - and the\ndepreciation rate of physical capital �. For the benchmark exercise, the labor share of income\nwas assumed to be 51 percent which was sourced from the GTAP database and the\ndepreciation rate was picked to be 3.2 percent which was sourced from the PWT 8.1. The labor\nshare of income for Bangladesh as sourced from the GTAP database is close but somewhat\nlower compared to the mean/median of lower‐middle income countries for which the data is\navailable in the PWT 8.1. In order to test the sensitivity of the main results of the model, I\nrepeat the quantitative exercises with a higher value of labor share of income. The chosen\nhigher value of the labor share – 55 percent, roughly corresponds to the mean labor share of\nlower‐middle income countries. In addition, I also consider two other extreme values of labor\nshare of income – 30 percent and 60 percent, to arrive at a broader range of results.\n\n\nThe following table compares the findings of section 3.1 when alternative values of\nlabor share of income are used for quantitative analysis. For clarity, the results are presented\nusing average growth rate over five year periods. The first set of results refers to the\nbenchmark exercise followed by simulations with other alternatives for labor share.\n\n\nThe resulting growth rate under each scenario is higher than the growth rate in the\ncorresponding scenario in the benchmark exercise when the labor share is reduced to 30\npercent. Equation (8) helps in understanding why this happens. The labor share of income\ndetermines the relative impact of factors pertaining to labor accumulation with respect to\nfactor pertaining to capital accumulation. A higher value of labor share increases the growth\nimpact from the former, for example\n\nMention: \"PWT 8.1\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"The depreciation rate is taken from this version.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:006978:16:2", "occurrence_id": "c64ccbc7e86c9e78f6355b5b", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: 937|\n|**World**
**Bank**|38.7|8.5|47.2|2.4|49.7|50.3|7,436|\n\n\nSource: IEG data set and staff calculation\n\n\nIn the SAR and EAP regions, a little over half of all projects have reported ERRs in the PAD or ICR (56.1 and\n57.6 percent, respectively). This is higher than for other regions where this ranges from 45.2 to 52\npercent. In contrast, in SAR and EAP, about 43.9 and 42.4 percent, respectively, of the projects do not\nreport an ERR either at the appraisal or at the completion stage. This number ranges from 48 to 55 percent\nfor other regions (Table 2).\n\n\nModel 1, described above, examines whether the frequency of ERRs has been declining in recent years.\nFigure 1 shows a long‐term declining trend, but also suggests there has been a slight uptick over the past\ndecade. Table 3 shows the declining trends by “high‐CBA” and “low‐CBA” sectors. The IEG study (World\nBank 2010) found that the changes were driven mainly by changes within the “high‐CBA” sectors (i.e.\ntransport, energy, water, agriculture, and urban development) and also a shift toward “low‐CBA” sectors.\nThis paper updates that analysis and finds that this result still holds (Table 4).\n\n\n15\n\nMention: \"IEG data set\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"Project evaluation ratings underlying the regional shares.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:006983:14:1", "occurrence_id": "9d6c9ed6f6508630e49fe35e", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: .04|0.02|\n|0.47|0.30|0.24|0.17|
0.14|0.09|0.06|0.04|0.02|\n|0.55|0.39|0.34|0.27|
0.26|0.19|0.17|0.13|0.08|\n\n\n\n_Source:_ Based on data of the 2011 Household Consumption Survey.\n_Note:_ The table shows the share of total consumption of each decile.\n\nTable 9 reports the income gains derived from the reduction in medical expenses for each income decile. The\nreduction in tobacco consumption would have a positive effect on income through the reduction in medical\ntreatments. The income gains would vary between 0.15 and 0.01 percentage points in the case of the lowerbound elasticity assumption, between 0.47 and 0.01 percentage points in the case of the medium-bound\nelasticity, and between 0.55 and 0.03 percentage points in the case of the upper-bound elasticity (figure 2).\nThese results show the importance of the elasticity assumptions; they also stress the relevance to the possible\nelasticity variations across income groups.\n\n\n13\n\nMention: \"the 2011 Household Consumption Survey\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"Each decile's share of total consumption is taken from this round.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:006972:23:0", "occurrence_id": "7cb08fc8be51ba7bfc4e26b8", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: **Figure 1. Part‐time employment trends in Europe.**\n\n\nNote: based on estimates from Eurostat, http://ec.europa.eu/eurostat/web/lfs/data/database.\n\n\n22\n\nMention: \"Eurostat\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"Part-time employment trends across Europe come from this office's database.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:007000:22:2", "occurrence_id": "1033adf736bccccf46a982ea", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: 0.0259) (0.0227) (0.0227) (0.0227) (0.0258) (0.0260)\n_DVAR*Internet_ 0.0010*\n(0.0006)\n_DVAR*LPI logistics_ 0.0513**\n(0.0211)\n_DVAR*LPI customs_ 0.0550***\n(0.0204)\n_DVAR*LPI overall_ 0.0621***\n(0.0232)\n_DVAR*Time to export_ -0.0053***\n(0.0019)\n_DVAR*Time to import_ -0.0033**\n(0.0014)\n_Constant_ 4.844*** 4.671*** 4.742*** 4.965*** 5.059*** 5.029***\n(0.165) (0.166) (0.157) (0.159) (0.174) (0.181)\nObservations 7,164 7,060 7,060 7,060 7,164 7,164\nR-squared 0.872 0.879 0.879 0.879 0.872 0.872\n\n\nSource: OECD ICIO database. *** p<0.01, ** p<0.05, * p<0.1.\nNotes: Robust standard errors in parentheses. _FVAX_ and _DVAR_ lagged. All level variables in natural logarithms.\n\n\nLooking at the income group specific results, we observe again\n\nMention: \"OECD ICIO database\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"Its estimates carry the reported trade-in-value-added regressions.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:007016:6:0", "occurrence_id": "c23b8312cae41e017d9b2483", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: efforts in the realm of policy and programming, at the local and national levels; failure to do so\n\n\nwill merely prolong the precarious role of women in the economic life of the nation.\n\n### 2. Female Labor Force Trends in Post-Liberalization India\n\n\n2.1 Database and Method\n\n\nConfining our analysis to the post-liberalization era in India, we consider the NSSO data sets for\n\n\nall rounds between Round-50 (1993-94) and the latest available, Round-68, that was collected in\n\n\n2011-12. In order to calculate labor force participation trends, we utilize information on Usual\n\n\nPrincipal and Subsidiary Status (UPSS) of the activity classification provided in these data sets. 2\n\n\nTotal FLFP rates, as well as those for rural and urban areas are provided below in Table 2. For the\n\n\npurposes of this study, we consider the working age population as inclusive of those in the age\n\n\ngroup of 15 years and above.\n\n\nTable 2: Female Labor Force Participation Rates, Using UPSS for Ages 15 and Above (%)\nRural Urban Total\n1993-94 49.0 23.7 42.6\n1999-00 46.0 21.0 39.5\n2004-05 49.4 24.4 42.7\n2009-10 37.8 19.4 32.6\n2011-12 35.8 20.5 31.2\n\n\n2 Activity status’ is the activity which a person reports for a given reference period, with regard to their participation in economic\nand non-economic activities. According to this, a person could be in one of the following three broad activity statuses during a\nreference period: (i) working or being engaged in economic activity (work) as defined above; (ii) being not engaged in economic\nactivity (work) but either making tangible efforts to seek 'work' or being available for 'work\n\nMention: \"NSSO data sets\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"Every round across this span is considered for the analysis.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:007029:4:0", "occurrence_id": "dbab7d8a535316211d4f2aaf", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: economics and how recent developments in economics can actually offer new instruments to model\n\n\nforced displacement. This is done from the perspective of utility theory and modeling choice. Next, we\n\n\ndiscuss data issues that are currently preventing economists from working on forced displacement.\n\n\nSection 5 will provide a concrete example of how economics research can serve policy makers and\n\n\nimprove the lives of refugees, IDPs and their hosts. Section 6 concludes.\n\n#### 2. Some facts\n\n\nThe United Nations High Commissioner for Refugees (UNHCR) reports that at the end of 2015 there were\n\n\n65.3 million forcibly displaced people worldwide. 5 This number includes 21.3 m. refugees and about 10\n\n\nm. stateless people with the rest mostly being accounted for by Internally Displaced Persons (IDPs). The\n\n\nforcibly displaced population accounts therefore for about 0.9 percent of the world population estimated\n\n\nat 7.3 bn people in 2015. The latest estimate of forcibly displaced people is the largest on record, since\n\n\nthe creation of the UNHCR in 1950. The growth in these numbers is evidently associated with episodes of\n\n\nconflict and violence. The Somalia, South‐Sudan and Syrian conflicts have been responsible for the major\n\n\noutflows of refugees and movements of IDPs over the past decade, with the Syrian conflict being\n\n\nresponsible for the latest spike (Figure 1).\n\n\n_Figure 1 ‐ Number of Forcibly Displaced Persons (1951‐2015)_\n\n\nSource: Constructed from UNHCR population data (http://popstats.unhcr.org/en/time_series). Note:\n\n\n2015 data are mid‐year and lower than end of year data.\n\n\n5 http://www.unhcr.org/en‐us/figures‐at‐a‐glance.html.\n\n\n3\n\nMention: \"UNHCR population data\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"Displaced totals since the mid-twentieth century, with the latest year mid-period.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:007056:16:1", "occurrence_id": "25741dd1880871799bda07f6", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: another\nrural area. 6 Of the 2,111 individuals who did not move, 331 live in an area that got reclassified\nfrom rural to urban and we drop them from our analysis to avoid confusion. Virtually everyone\nin the rural areas is in the informal sector (only 3.5 percent rely on a formal wage job), so this\ngroup corresponds closely to the rural population we have in mind in the model. In the towns,\n18.9 percent live in a household that relies on formal wage employment. This rises to 22.2\npercent in the cities. 7\n\n\nThe 2010 income distribution of these individuals could essentially be thought of as the\nmigration equilibrium outcome of the rural population of Kagera in 1991 across the 3\ndestinations, the rural area (i.e. no migration or another rural area), the secondary towns and the\ncities and across the informal and formal sectors within the two latter destinations. 8 [^8: Intrahousehold decision making is abstracted from.] It provides\nan ideal backdrop to give empirical content to the findings of the model under the different\nscenarios considered (as summarized in Table 1) and explore the model’s empirical relevance.\n\n\n6 We distinguish between urban and rural centers using the 2002 census classification. Urban centers with more than\n500,000 inhabitants are considered cities, the others are towns. Using this definition, the cities are Dar es Salaam\n(the economic capital of Tanzania with an estimated 4.36 million people according to the 2012 census) and Mwanza\n(with an estimated 0.7 million inhabitants)\n7 Of the formally wage employed, 70 and 80 percent work in the private sector in towns and cities, respectively. In\ntowns, 21 percent also work in the public sector, while that share is 11 percent in the cities. The remaining 7 percent\nwork for NGOs or religious organizations, in both the towns and the city\n\nMention: \"2002 census\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"Its classification separates urban from rural centres.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:007056:16:1", "occurrence_id": "393949565510c5ac8a64281d", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: another\nrural area. 6 Of the 2,111 individuals who did not move, 331 live in an area that got reclassified\nfrom rural to urban and we drop them from our analysis to avoid confusion. Virtually everyone\nin the rural areas is in the informal sector (only 3.5 percent rely on a formal wage job), so this\ngroup corresponds closely to the rural population we have in mind in the model. In the towns,\n18.9 percent live in a household that relies on formal wage employment. This rises to 22.2\npercent in the cities. 7\n\n\nThe 2010 income distribution of these individuals could essentially be thought of as the\nmigration equilibrium outcome of the rural population of Kagera in 1991 across the 3\ndestinations, the rural area (i.e. no migration or another rural area), the secondary towns and the\ncities and across the informal and formal sectors within the two latter destinations. 8 [^8: Intrahousehold decision making is abstracted from.] It provides\nan ideal backdrop to give empirical content to the findings of the model under the different\nscenarios considered (as summarized in Table 1) and explore the model’s empirical relevance.\n\n\n6 We distinguish between urban and rural centers using the 2002 census classification. Urban centers with more than\n500,000 inhabitants are considered cities, the others are towns. Using this definition, the cities are Dar es Salaam\n(the economic capital of Tanzania with an estimated 4.36 million people according to the 2012 census) and Mwanza\n(with an estimated 0.7 million inhabitants)\n7 Of the formally wage employed, 70 and 80 percent work in the private sector in towns and cities, respectively. In\ntowns, 21 percent also work in the public sector, while that share is 11 percent in the cities. The remaining 7 percent\nwork for NGOs or religious organizations, in both the towns and the city\n\nMention: \"2012 census\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"Estimated populations of the two largest cities come from this round.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:007070:26:0", "occurrence_id": "1cc2cb9090b8b859e4e98eb2", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: **Figure 2. Total Employment in High and Low Financially Dependent Sectors (Index, 2008=100.0)**\n\n\nSource: based on Eurostat National Accounts, detailed sectoral breakdown. Sample includes all countries in EU28. High\n\n\nFD sectors are those in the highest quartile of the distribution of the FD variable calculated using US data (see main text for full\n\n\ndescription of this variable).\n\n\n25\n\nMention: \"Eurostat National Accounts\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"Detailed sectoral breakdown across member states in that base year.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:007091:28:5", "occurrence_id": "47db0d2d2aa41a3f7c29f413", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text:
-0.0022
0.0023*
0.01**
(-4.41)
(-0.91)
(2.45)
(2.93)|\n|Observations
Adjusted R-squared|12584
0.302|8637
8637
8637
8637
0.087
0.122
0.118
0.135|8637
8637
8637
8637
0.205
0.090
0.024
0.086|\n\n\nNotes: (1) Source: Author's calculations based on data collected by Social Observatory, World Bank and Government of Bihar. (2) SC is the omitted caste\ngroup. (3) Each column represents a separate regression wherein an `empowerment indicator’ is regressed on variables that are reported as well as\nadditional controls: age, age squared, marital status of the woman, age at marriage, and a dummy variable for some schooling of the female respondent; a\ndummy variable for whether it is female-headed household, per-capital expenditure, per-capita expenditure squared, landholdings, education of the\nhousehold head, number of members in the household and panchayat level fixed-effects. The female employment is run for all female adults in the sample\n(individual level). (4) We report robust standard errors in the brackets. (5) We report the level of significance: * p value < .05, ** p value < .01 and *** p\nvalue < .001.\n\n\n\n\n\n27\n\nMention: \"Social Observatory, World Bank and Government of Bihar\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"Field data collected jointly by these three bodies carry the regressions.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:007109:29:0", "occurrence_id": "a0b737e45afaf02d6f3f67c3", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: **5.6** **Testing** **for** **different** **size** **of** **forecasting** **windows**\n\n\nThe IMF produces 5-year forecasts in each WEO edition. We use this five yearly forecast as our default\n\n\ntesting horizon, since it captures the maximum information regarding a country’s growth trajectory in any\n\n\ngiven year. In order to check the robustness of our results we can narrow this forecast window by excluding\n\n\nouter years from our variables and re-run our main specification.\n\n\nTable 16 below presents our results using forecast windows of 1, 2, 3 and 4 years in addition to our\n\n\nbaseline estimates using the 5 year window. For windows shorter than 4-years we fail to find a significant\n\n\neffect. This suggests that shorter windows we are unable to measure with precision our negative effect on the\n\n\nforecast error. The magnitude and significance is maximized at the longest window available in the WEO\n\n\nforecasts.\n\n\n(1) (2) (3) (4) (5)\nDiff 1y Diff 2y Diff 3y Diff 4y Diff 5y\n\n\nLag disc dum\n\n(disc in past 2 years (excl. t=0)) -0.599 -0.527 -0.350 -0.597 _∗∗_ -0.833 _∗∗∗_\n\n(0.509) (0.381) (0.305) (0.295) (0.308)\nDep var 1 yr window 2 yr window 3 yr window 4 yr window 5 yr window\nFixed effects CFE YFE CFE YFE CFE Y\n\nMention: \"WEO\n\n\nforecasts\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"Its longest available horizon gives the largest effect.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:007116:31:1", "occurrence_id": "6866a11f7eaf768a081398bb", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: >_\n\n\nThis approach to measuring decision-making roles has not been changed or adapted substantially\n\n\nover time, with its use increasing, especially in large-scale surveys in developing countries. This focus on\n\n\nthe main decision-maker stems from the notion that the greater number of decisions an individual is\n\n\ninvolved in, the greater control they have over their own life (Kishor 2005). The nationally-representative\n\n\nDemographic and Health Surveys (DHS), conducted in over 90 countries, form the largest source of data\n\n\non women’s participation in decision-making. Initially, the surveys used slightly different question\n\nwordings depending on the topic at hand. For example, questions regarding decision-making over health\n\n\ncare, household purchases, consumption, and visiting friends or relatives would ask “who in your family\n\n\nusually has the final say on [X]”, while questions regarding control over use of earnings would ask “who\n\n\nmainly decides how the money you earn will be used?” More recently, the DHS decision-making questions\n\n\nhave been standardized across countries and decision-making areas (‘domains’), asking the respondent\n\n\n“who usually makes decisions about [X]” (see Box 8 below).\n\n\n30\n\nMention: \"Demographic and Health Surveys\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"Run in over ninety countries, the largest source on the measured outcomes.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:007128:8:3", "occurrence_id": "b3c54784cb5bc35cb9bc9b77", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: ,m,t_ are respectively the online and total exports from\n\n\ncountry _x_ to country _m_ in year _t_ . _βx,m_ and _αx,m_ control for time-invariant country-pair specific\n\n\ndeterminants of trade flows such as distance, colonial linkages, common language, etc. _βx,t_ and _αx,t_\n\n\nare year and country specific shocks in the exporting country. We use the estimate in equations (2)\n\n(7) to predict the log of bilateral online and total exports. To estimate the impact of online trade\n\n\non the wage gap, we need to aggregate the bilateral exports flows at the exporter and year level.\n\n\nWe first take the exponential of the predicted bilateral trade flows estimated by equations (2)-(7).\n\n\nWe then aggregate these trade flows at the exporter and year level by summing the trade flows over\n\n\nall importers each year. After taking logs we use these six variables to instrument the log share of\n\n\nonline and total exports in GDP.\n\n##### **3 Data**\n\n\nThe variable of interest is the wage gap between skilled and unskilled workers. We borrow the\n\n\ndata and methodology from Cruz and Milet (2017). The data source is the International Income\n\n\nDistribution Database (I2D2) put together by the World Bank which compiles more than 1,000\n\n\nhousehold and labor force surveys from 164 countries over the period 1960-2014 covering more\n\n\nthan 120 million individuals. The data have been harmonized to the extent possible ensuring that\n\nconceptual variables have similar meaning, allowing for cross-country analysis. 4 For the purpose of\n\n\nthis study, we selected a restricted sample of 22 countries for which sufficient data are available. 5\n\n\n4See Montenegro and Hirn (2009) and Montenegro and Patrinos (2014) for more information about\n\nMention: \"I2D2\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"Compiles over a thousand household and labour surveys.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:007150:3:2", "occurrence_id": "a5ea8f141aec3a198e678087", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: percent) over the same period (Uganda Bureau of\nStatistics 2014). Yet some of this expansion is due to a redefinition of administrative boundaries for urban\nareas. An alternative measure of urbanization that is comparable across countries, the agglomeration\nindex, suggests that Uganda’s urban share is even higher – at 25 percent (World Bank 2012).\n\n\nWhile there are some studies that examine migration in Uganda, most rely on cross-sectional data that\npose methodological challenges for identification. Moreover, none of these analyses provides causal\nevidence of the impact of migration on welfare. In this paper, we examine the relationship between spatial\nand economic mobility in Uganda using data from 2005 through 2012. The paper makes two principal\ncontributions to the literature. First, it contributes to the policy and academic literature on internal\nmigration and structural transformation in developing countries through the use of multiple waves of\npanel evidence. The use of longitudinal data confers an advantage over cross-sectional analyses which,\nthough more common in the literature, fail to properly account for time-invariant factors that can\n\n\n3 While economic considerations lead many of Uganda’s migrants to move, other factors also drive migration\ndecisions. For example, insecurity and conflict, particularly in the North of the country during the 2000s, prompted\nthe displacement and forced migration of large segments of the rural population (Mulumba and Olema 2009). A\nperiod of reverse migration then followed, with an influx of displaced residents returning to\n\nMention: \"data from 2005 through 2012\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"analyze\", \"summary\": \"Spatial and economic mobility are related across these years.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:007174:34:1", "occurrence_id": "2748c00a51b1e5eaa0d57ac0", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: , 2010). The vignette is thus designed to focus on health inputs of\nvaccination and bed nets for all children to highlight the public good characteristics of the proposed\nspending.\n\n\nPublic employment or government jobs, on the other hand, have been documented as a classic form of\nprovision of private benefits in weak institutional contexts where public bureaucracies are not\nsufficiently professionalized and rules-based (Wantchekon, 2003; Robinson and Verdier, 2003;\nChandra, 2004; Kitschelt and Wilkinson, 2007; Grindle 2012; Gibson, Hoffman and Jablonski 2015).\nThe dismantling of political patronage in government jobs is at the heart of accounts of transition from\nweak to strong institutions, such as in the history of the United States during the Progressive Era\n(Glaeser and Goldin, 2006). Furthermore, there is systematic correlation between failures in delivering\nbroad public services and the provision of patronage jobs, and clientelist forms of vote mobilization\nmore generally (Callen et al, 2014; Khemani, 2015; Andersen et al, 2015). That is, when government\njobs are provided as political patronage, the job-holders have weak incentives to exert effort and perform\nwell in delivering public services (World Bank, 2004).\n\n\n20 Such questions are contained in the Afrobarometer surveys, for example.\n\n\n33\n\nMention: \"the Afrobarometer surveys\""}, {"role": "assistant", "content": "{\"role\": \"supporting\", \"usage_action\": \"source\", \"summary\": \"They contain the service delivery questions referenced.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:007185:9:0", "occurrence_id": "4e46203f173f779e924d9578", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: Figure 1: The spatial distribution of firms in Mexico (2004 and 2014)\n\n\n_Sources_ : DeLorme, aaa and denue (inegi). _Note_ : Universe of all formal firm in 2004 (top left panel) and\n\n\n2014 (top right panel). Manufacturing in 2004 (bottom left panel) and 2014 (bottom right panel).\n\n\nthe nearest available year before which we have firm data in the denue and in the Economic\nCensuses (1986, 1994, 1999, 2004, 2009 and 2014), leaving us with a road panel for the years\n1985, 1993, 1999, 2004, 2008 and 2016. 6 We grouped the aaa road classes into four categories,\nwhich we label ‘Multilane divided’, ‘Two lanes or Divided’, ‘Pavement’, and ‘Gravel and Earth\nRoad’.\n\nFigure 2 represents the evolution of the road network for the years 1985, 1999, 2008, and\n2016. As can be seen, major road improvements took place in the middle of the studied period,\nbetween 1999 and 2008. This is confirmed by table 13 in Appendix A, which provides road\nlength by road category for all six years during the 1985-2016 period. 7\n\n\n6We use the roads information for 2016 as the aaa map for recent years before or in 2015 were not available to\nus.\n\n7Observe that official statistics provided by inegi for Mexico provide significantly greater total road lengths\n\n\n7\n\nMention: \"Economic\nCensuses\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"Firm data are matched to the nearest preceding enumeration in this series.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:007185:9:0", "occurrence_id": "1caed312cfdefe493ccec98c", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: Figure 1: The spatial distribution of firms in Mexico (2004 and 2014)\n\n\n_Sources_ : DeLorme, aaa and denue (inegi). _Note_ : Universe of all formal firm in 2004 (top left panel) and\n\n\n2014 (top right panel). Manufacturing in 2004 (bottom left panel) and 2014 (bottom right panel).\n\n\nthe nearest available year before which we have firm data in the denue and in the Economic\nCensuses (1986, 1994, 1999, 2004, 2009 and 2014), leaving us with a road panel for the years\n1985, 1993, 1999, 2004, 2008 and 2016. 6 We grouped the aaa road classes into four categories,\nwhich we label ‘Multilane divided’, ‘Two lanes or Divided’, ‘Pavement’, and ‘Gravel and Earth\nRoad’.\n\nFigure 2 represents the evolution of the road network for the years 1985, 1999, 2008, and\n2016. As can be seen, major road improvements took place in the middle of the studied period,\nbetween 1999 and 2008. This is confirmed by table 13 in Appendix A, which provides road\nlength by road category for all six years during the 1985-2016 period. 7\n\n\n6We use the roads information for 2016 as the aaa map for recent years before or in 2015 were not available to\nus.\n\n7Observe that official statistics provided by inegi for Mexico provide significantly greater total road lengths\n\n\n7\n\nMention: \"aaa map\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"curate\", \"summary\": \"The recent-year road layer standing in for missing earlier maps.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:007191:22:0", "occurrence_id": "332dc5177de9c27259701ee9", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: Figure 4: Changes in poverty rates and migration\n\n\n\n\n\nSource: Author’s calculations from the 2001 and 2011 Census and Small Area Estimates of poverty.\nNote: This figure shows how changes in _illaka_ level migration rates is associated with changes in _illaka_ level poverty\nrates. The top panel plots the changes in Gulf-Malaysia migration rates and the bottom panel plots changes in India\nmigration rates in the horizontal axes. Each point represents an _illaka_ with the area proportional to the population\nin 2001. The line shows linear regression estimate of the relationship.\n\n\n21\n\nMention: \"2001 and 2011 Census\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"analyze\", \"summary\": \"Poverty rate and migration changes at sub-district level come from these rounds.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:007191:22:0", "occurrence_id": "b4cd3aa1c25f8127e504067d", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: Figure 4: Changes in poverty rates and migration\n\n\n\n\n\nSource: Author’s calculations from the 2001 and 2011 Census and Small Area Estimates of poverty.\nNote: This figure shows how changes in _illaka_ level migration rates is associated with changes in _illaka_ level poverty\nrates. The top panel plots the changes in Gulf-Malaysia migration rates and the bottom panel plots changes in India\nmigration rates in the horizontal axes. Each point represents an _illaka_ with the area proportional to the population\nin 2001. The line shows linear regression estimate of the relationship.\n\n\n21\n\nMention: \"Small Area Estimates of poverty\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"analyze\", \"summary\": \"Modelled small-area welfare figures paired with the enumerations.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:007194:6:1", "occurrence_id": "2c09de50397e1914e083491d", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: an up to date snapshot of\npower sector reform globally based on numerous indicators on the power sector structure and\ninstitutional arrangements in 2015. A second important source of data is the World Bank’s Private\nParticipation in Infrastructure database, 7 which records all developing country transactions involving the\nprivate sector going back into the 1990s, and makes it possible to understand how private sector\nparticipation has evolved over the same period. Important historic reference points are provided by\ncomparable earlier surveys conducted by Besant‐Jones (2006) and ESMAP (1999).\n\n\nThe paper will first individually examine the diffusion of each of the four dimensions of power sector\nreform: regulation, restructuring, competition and private sector participation. Along each of these four\ndimensions, a number of stages of reform are identified, which make it possible to examine diffusion\ntrends over time as well as the geographic patterns of uptake. The prevalence of power sector reform in\ndeveloping countries is compared to that in developed countries over the same time frame.\n\n\nThe final section of the paper turns to drawing out the main conclusions and insights from looking across\nexperiences on all four dimensions of reform. The ways in which different types of reforms are packaged\n\n\n1 Gassner, K., A. Popov, and N. Pushak. 2008a. “Does the private sector deliver on its promises? Evidence from a\nglobal study in water and electricity”. _Gridlines 44512_ . PPIAF, The World Bank, Washington D.C.\n2 Nagayama, H. 2010. “Impacts on investments, and transmission/distribution loss through power sector reforms”.\n_Energy Policy_, 38(7), 3453‐3467.\n3 Erdogdu, E. 2014. “Investment, security of supply and sustainability in the aftermath of three decades of power\nsector reform”. _Renewable and Sustainable Energy Reviews_, 31, 1‐8.\n4 Jama\n\nMention: \"Private\nParticipation in Infrastructure database\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"Records developing-country transactions involving private provision.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:007259:13:0", "occurrence_id": "c84fdeb60debcf25beedb799", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: 12\n\n\nus to better capture the change in labor productivity due to structural reforms. Second, although\n\n\nthe TFP, the most used measure of productivity, accounts for the level of capital and the\n\n\nproduction technology, we are unable to capture the change in TFP stemming from structural\n\n\nreforms as the WBES database collects information only on the current stock of capital. The\n\n\ninformation on the past stock of capital required for calculating retrospective TFP is not\n\n\nreported. Recall that the standardized WBES data set used in this study has a pseudo panel\n\n\nstructure. 12 [^12: The lack of panel data on firms limits the possibility to use robust measures of productivity such as the TFP\nfrom Levinsohn-Petrin (Levinsohn and Petrin, 2003).] The sensitivity analysis explores the robustness of the findings using TFP and\n\n\nvalue-added per worker as alternative measures of productivity.\n\n\nLabor productivity growth is computed as the annual average growth of labor productivity over\n\n\nthe last three years. Firms are asked during the surveys to report their total annual sales and\n\nfull-time employees at the end of the previous fiscal year (�−1) and three years ago (�−3),\n\n\nrespectively. At each period, labor productivity �� is computed as the ratio of total annual\n\n\nsales over total permanent full-time employees. Following Davis and Haltiwanger (1999) and\n\n\nWorld Bank (2016), we compute labor productivity growth by dividing the change in\n\nproductivity between �−1 and �−3 ������ – ������ by the average value of initial and final\n\n\n\nlabor productivity\n\n\n\n������ � ������\n\n. This approach helps to reduce the influence of outliers.\n\n \n\n\nFurther, since there were two full years between the two points in time, we calculate the annual\n\n\naverage labor productivity growth as follows:\n\n\n� ������ – ������<\n\nMention: \"WBES database\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"validate\", \"summary\": \"Only the current capital stock is collected, so structural TFP change is missed.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:007259:13:0", "occurrence_id": "cc3158776a284807a5c9261b", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: 12\n\n\nus to better capture the change in labor productivity due to structural reforms. Second, although\n\n\nthe TFP, the most used measure of productivity, accounts for the level of capital and the\n\n\nproduction technology, we are unable to capture the change in TFP stemming from structural\n\n\nreforms as the WBES database collects information only on the current stock of capital. The\n\n\ninformation on the past stock of capital required for calculating retrospective TFP is not\n\n\nreported. Recall that the standardized WBES data set used in this study has a pseudo panel\n\n\nstructure. 12 [^12: The lack of panel data on firms limits the possibility to use robust measures of productivity such as the TFP\nfrom Levinsohn-Petrin (Levinsohn and Petrin, 2003).] The sensitivity analysis explores the robustness of the findings using TFP and\n\n\nvalue-added per worker as alternative measures of productivity.\n\n\nLabor productivity growth is computed as the annual average growth of labor productivity over\n\n\nthe last three years. Firms are asked during the surveys to report their total annual sales and\n\nfull-time employees at the end of the previous fiscal year (�−1) and three years ago (�−3),\n\n\nrespectively. At each period, labor productivity �� is computed as the ratio of total annual\n\n\nsales over total permanent full-time employees. Following Davis and Haltiwanger (1999) and\n\n\nWorld Bank (2016), we compute labor productivity growth by dividing the change in\n\nproductivity between �−1 and �−3 ������ – ������ by the average value of initial and final\n\n\n\nlabor productivity\n\n\n\n������ � ������\n\n. This approach helps to reduce the influence of outliers.\n\n \n\n\nFurther, since there were two full years between the two points in time, we calculate the annual\n\n\naverage labor productivity growth as follows:\n\n\n� ������ – ������<\n\nMention: \"WBES data set\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"validate\", \"summary\": \"The standardised version has a pseudo-panel structure.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:007265:24:1", "occurrence_id": "ec97615bc97193995fa037a8", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: \neducation performance. Among middle income countries, those in Eastern Europe and Central Asia\n\n\nperform the best. Developing countries perform worse in both primary and secondary education\n\n\nthan developed countries, and have much larger variance, especially at the primary level. While\n\n\nvariation is high, and the top-performing country in Sub-Saharan African still performs lower\n\n\nthan the lowest performing country in developed economies.\n\n\nAn important note when interpreting these results is that they might capture a series of selection\n\n\neffects. One such selection effect is driven by immigration. If a country tends to attract the most\n\n\nable students from around the world, it will have high mean scores. For instance, PISA 2009\n\n\nresults showed that approximately 15 percent of pupils from Singapore have an immigrant\n\n\nbackground, while this proportion is more than 40 percent in Qatar, which might drive mean\n\n\nscores up due to immigration rather than school quality alone. We can check this empirically\n\n\n23\n\nMention: \"PISA 2009\n\n\nresults\""}, {"role": "assistant", "content": "{\"role\": \"supporting\", \"usage_action\": \"source\", \"summary\": \"Its results show the share of pupils with an immigrant background in one city-state.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:007306:17:0", "occurrence_id": "a7338696eaad9331adce9898", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: education or to take on a job. Families ended up prioritizing men’s work. 33 [^33: Contrary to that, Chioda (2016) shows that highly educated women tend to see work more as a\ncareer than merely a source of income.] This\narrangement is reinforced not only by men’s socially expected role as providers, but\nalso with participants’ expectation that men will earn higher wages. 34 [^34: The World Values Survey 2014 shows that in Brazil 16.8 percent of interviewees agree that when\njobs are scarce, men should have more right to a job than women.] It shows that,\neven when women value having a paid job, power dynamics within households and\nnegotiating the organization of domestic work is still a major barrier to equal\nparticipation in the work force.\n\n\n**Additionally, women with small children mentioned experiences of discrimination.**\nWomen reported being asked about whether they have a partner and small children\nduring job interviews and not being considered for the positions after their positive\nresponses. While it remains a speculation, the level of detail to which the interviewee,\nin the following quotation, was inquired about her childcare responsibilities suggests\nthat discrimination based on gender and care responsibilities may account for some of\nyoung women’s difficulties in accessing jobs.\n\n\n_Q7: P: I was interviewed last week and... I think I lost the opportunity, the owner told me he had really_\n_liked me and all, but I lost the opportunity when\n\nMention: \"World Values Survey 2014\""}, {"role": "assistant", "content": "{\"role\": \"supporting\", \"usage_action\": \"source\", \"summary\": \"Its item on job priority gives the share agreeing men should earn more.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:007311:42:1", "occurrence_id": "fe35bac9671e42c760f5f964", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: 6 1.4 0.2 3.5\n\n\n\n_Without Health Insurance (%)_ 99.9 99.7 14.3 99.0\n\n\n_Without Social Insurance (%)_ 99.9 99.6 16.0 99.3\nSource: Analysis of 2014 Labor Force Survey\n\n\n**Table A7: Number and Percentage of Jobs in the Wage Sector by Selected Characteristics**\n\n**Have Written Contract** **Have Health Insurance** **Have Social Insurance** **#** **%**\nNo No No 7,261,841 38.3\nNo No Yes 11,100 0.1\nNo Yes No 28,636 0.2\nNo Yes Yes 42,950 0.2\nYes No No 1,542,468 8.1\nYes No Yes 56,727 0.3\nYes Yes No 260,187 1.4\nYes Yes Yes 9,398,338 49.6\n\nSource: Analysis of 2014 Labor Force Survey\n\n\n41\n\nMention: \"2014 Labor Force Survey\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"analyze\", \"summary\": \"Coverage and job counts in the wage sector are analysed from this round.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:007317:27:0", "occurrence_id": "a6725edcfc8474bca2e796aa", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: _Source:_ Authors’ calculation based on NWSS (2015) survey data.\n\n\n26\n\nMention: \"NWSS (2015) survey data\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"analyze\", \"summary\": \"Access statistics are calculated from this round.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:007338:3:1", "occurrence_id": "933070d45a9e10d6bd0b822a", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: of skilled\nworkers, managers, and unskilled workers as well as supply chain relationships as a\nubiquitous effect of the war. The key conclusion of this analysis is that the damage to social\nand human capital is significant, and rebuilding that social and human capital is likely a\ngreater challenge than the bricks and mortar.\n\n\nDiscussion of the sample, methodology, and missing firms\n\n\nIt was extremely challenging to conduct a firm survey in Syria in early 2017 due to the\nongoing insecurity across the country. For this reason, the survey was conducted by phone.\nThe survey was designed to be completed in approximately 30 minutes and the questions\nfocused on changes that firms have experienced since the beginning of the crisis in 2010.\nThe questions covered the following topic areas: major problems and constraints to firms,\nsales, supplies and costs, finance, and employment. (See Annex B for the questionnaire.)\n\n\nThe survey was designed as a follow‐up to the 2009 Enterprise Survey of Syria. The 2009\nsurvey included 508 firms and the 2017 survey attempted to re‐survey all 508 firms which\nwere surveyed in 2009. Table 1 below provides a breakdown of the response outcomes for\n\n\n1 This paper and the supporting analysis was undertaken by Nabila Assaf, Kinley Salmon, and David C.\nFrancis based on a survey conducted in April and May 2017.\n\n\n2\n\nMention: \"2009 Enterprise Survey of Syria\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"Its five hundred firms form the frame the later survey re-interviews.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:007365:37:2", "occurrence_id": "93a21d2366e68498920c6c39", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: 125) (0.144)\nHow to learn work process - by yourself 0.009 −0.010\n\n(0.158) (0.118)\nHow to learn work process - from all 0.073 −0.018\n\n(0.088) (0.077)\nReported to TVI during in-company training\n(1=yes) 0.021 0.022\n\n(0.039) (0.039)\nTimes visited TVI teacher during incompany training (1=yes) 0.006** 0.002\n\n(0.003) (0.002)\nObservations 837 374 374 407 365 418\n_Source: DTS Tracking Survey, 2015, World Bank. World Bank calculations._\n_Note: Standard errors in parentheses. * p<0.1; ** p<0.05; *** p<0.01_\n\n\n36\n\nMention: \"DTS Tracking Survey, 2015\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"analyze\", \"summary\": \"Its tracking rounds carry the reported estimates.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:007377:5:1", "occurrence_id": "765c05149bf1f83eb742937d", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: same likelihood of making payments for security, the investing\n\n\nfirms allocate a larger share of their sales towards security arrangements. Second, we find a similar\n\n\nphenomenon with respect to firms’ access to finance. Firms with bank accounts and loan applications face\n\n\nhigher risks and uncertainty. This further lends credence to the thought that participation acts as a signal to\n\n\nexpropriating parties that see these firms as better targets having larger surpluses from firm operations. Our\n\n\nthird finding corresponds to the formal status of firms. While it is true for the Afghan case that formal firms\n\n\nare larger, both in terms of workforce and sales, they too are disproportionately affected by risks and\n\n\nuncertainty. All the above findings suggest that policy interventions in a volatile economic environment for\n\n\na country like Afghanistan are not independent of consequent risks and uncertainty. In other words, some\n\n\nbenefits of such policies are potentially seized via crime and corruption. Finally, we also find that a large\n\n\nsegment of firms headed by female managers perceive crime, corruption, and political instability as being\n\n\nserious roadblocks to operation.\n\n\nIn our final analysis, we turn our attention towards estimating the economic loss from crime-related\n\n\nevents. The World Bank enterprise survey reports firms’ loss due to such events together with firms’\n\n\n4\n\nMention: \"World Bank enterprise survey\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"Reports firms' losses from crime-related events.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:007378:15:2", "occurrence_id": "32f31a8ea9f9adf190029813", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: \nYears of implementation, cont. ‐1.153 ‐1.153 ‐0.220\n(1.494) (1.301) (1.630)\nGovernment implemented, dummy ‐0.0219** ‐0.0219*** ‐0.0259**\n(0.00870) (0.00758) (0.0120)\nSample size, continuous ‐0.00227 ‐0.00227 ‐0.00167\n(0.00389) (0.00339) (0.00370)\nUrban interventions, categorical ‐0.0141 ‐0.0141* ‐0.0175\n(0.00925) (0.00806) (0.0110)\nConstant 8.906 8.906 9.821\n(11.36) (9.895) (12.39)\n\nObservations 136 135 104\nR‐squared 0.621 0.573 0.650\n\n\n\n(pooled effects)\n\n\n\n_Source:_ World Bank GWSP‐SIEF WASH Impact Evaluation Database.\n_Note:_ Robust standard errors in parentheses. *** p<0.01, ** p<0.05, * p<0.1.\n\n\n14\n\nMention: \"SIEF WASH Impact Evaluation Database\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"Pooled impact estimates across water and sanitation interventions.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:007389:23:0", "occurrence_id": "3b7d2ae2c0550f8379824787", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: first and last date of receiving the social support. In 2014: about 59% of households were first\n\n\ntime beneficiaries. The remaining 41% of households have received some form of social\n\n\nassistance in the past, where the maximum length is 313 months (i.e., about 26 years). A large\n\n\nfraction of the beneficiary households are skewed towards a year or less assistance durations,\n\n\nsuggesting that social protection programs are becoming popular and expansive recently in\n\n\nNiger. To further understand these social interventions, Figure 5b illustrates the maximum span\n\n\nthat households have been receiving social assistance across the eight Nigerien regions. Spatial\n\n\ndifferences exist. The Dosso region records the highest followed by Niamey, Diffa, Zinder and\n\n\nTillabEri.\n\n\n**Figure 5a: Distribution: length of receiving social** **Figure 5b: Understanding social protection across**\n**assistance** **regions**\n\n\n**Notes:** Source: World Bank Household Panel, 2014\nNiger. The figure counts the number of months\nbetween the first and last time HH received assistance\nIn principle, the figure does not say anything about\nwhether HH receives assistance continuously; it only\ncaptures the span.\n\n\n22\n\nMention: \"World Bank Household Panel, 2014\nNiger\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"Months between first and last transfer receipt are counted from this panel.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:007396:23:0", "occurrence_id": "eb8b41e0d2e9922ea16bf7c4", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: an integral part of geographically-targeted poverty reduction strategies. Our review shows that capacity\n\n\ndevelopment is integral to improving productivity, stronger and equitable forest and land rights strengthen\n\n\nagency, and without effective public institutions and services, the poor cannot be expected to use their\n\n\naccess to forest resources to escape poverty. Of course, communities have demands that go beyond income\n\nand the non-cash contributions of forests can be very important. 26 Our focus on gender analyses also points\n\n\nto the importance of understanding the implications of rural development strategies for women and men.\n\n\nWhile the role forests play in enhancing rural resilience and food security is not fully addressed in\n\n\nthis paper, social and environmental safeguards will certainly need to go hand in hand with any forest\n\n\ninterventions that seek to reduce poverty. The FAO, CIFOR, IFRI and the WBG recently launched a global\n\n\neffort to develop a standard survey instrument, the Forestry Living Standards Measurement Survey, to\n\n\nmeasure forest use and the wellbeing of forest-dependent communities (FAO _et al_ ., 2016). Combining such\n\n\nfield-based surveys with participatory gender-disaggregated information and satellite data may ensure that\n\n\nforest sustainability and poverty are simultaneously monitored.\n\n\nOver time, poverty reduction in forest areas will likely be no different than what is seen in\n\n\nagricultural areas: ‘off-forest’ jobs and migration (Hecht _et al._ 2016) will play a significant role in changing\n\n\nthe relationship between forests and people. We see this in trends in forest villages in middle-income\n\n\ncountries such as Turkey and Albania (World Bank 2016b, IOM 2016). Thus, strategies that enable\n\n\ncommunities to seek these jobs while simultaneously strengthening their ability to benefit from forest\n\n\nresources in a sustainable manner will be key.\n\n\n22\n\nMention: \"Forestry Living Standards Measurement Survey\""}, {"role": "assistant", "content": "{\"role\": \"supporting\", \"usage_action\": \"inform\", \"summary\": \"A newly launched standard instrument for forest-dependent communities.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:007398:15:1", "occurrence_id": "bc0cf83a5202a2778ff75607", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: grammatical gender) is provided in our Data Construction\n\n\nAppendix.\n\n\n**3.1.3** **Identifying** **Gender** **Languages**\n\n\nFor each mother tongue in the _Ethnologue_ database, we attempt to code two variables\n\n\ncharacterizing the language’s grammatical gender structure. First, we create an indicator\n\n\n13Data from the WALS must be used with caution because they were compiled by the linguist Greville\nCorbett; as discussed above, Corbett advocates the use of a non-standard definition of grammatical gender\nthat includes systems of anaphoric pronominal agreement (Corbett 1991). This is particularly problematic\nwhen one combines the WALS with other data sources that do not classify systems of pronominal agreement\nbased on the gender of the referent as examples of grammatical gender. We address this by excluding WALS\ndata on languages that are classified as “strictly semantic” (i.e. agreement class can always be inferred from\nthe meaning of the noun) since Corbett considers pronominal agreement an example of such a system. We\nrely on other sources to classify those languages. Languages that are classified in the WALS as either lacking\na grammatical gender system of having a system that is “semantic and formal” are unambiguous.\n\n\n14\n\nMention: \"_Ethnologue_ database\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"Each mother tongue is coded for grammatical gender structure from this catalogue.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:007398:15:1", "occurrence_id": "957181b3b5cf0411247e4dbb", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: grammatical gender) is provided in our Data Construction\n\n\nAppendix.\n\n\n**3.1.3** **Identifying** **Gender** **Languages**\n\n\nFor each mother tongue in the _Ethnologue_ database, we attempt to code two variables\n\n\ncharacterizing the language’s grammatical gender structure. First, we create an indicator\n\n\n13Data from the WALS must be used with caution because they were compiled by the linguist Greville\nCorbett; as discussed above, Corbett advocates the use of a non-standard definition of grammatical gender\nthat includes systems of anaphoric pronominal agreement (Corbett 1991). This is particularly problematic\nwhen one combines the WALS with other data sources that do not classify systems of pronominal agreement\nbased on the gender of the referent as examples of grammatical gender. We address this by excluding WALS\ndata on languages that are classified as “strictly semantic” (i.e. agreement class can always be inferred from\nthe meaning of the noun) since Corbett considers pronominal agreement an example of such a system. We\nrely on other sources to classify those languages. Languages that are classified in the WALS as either lacking\na grammatical gender system of having a system that is “semantic and formal” are unambiguous.\n\n\n14\n\nMention: \"WALS\""}, {"role": "assistant", "content": "{\"role\": \"supporting\", \"usage_action\": \"validate\", \"summary\": \"Its compiled gender data must be used with caution.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:007417:5:1", "occurrence_id": "387d11e02a4216837be8631a", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: 85 percent of\n\n\nfarmers engage in rice production. Using the spatial distribution of rice production based on\n\n\nthe 2010 SPAM, the latest district-level rice production data for the period of 2013-15 are\n\n\ndisaggregated into 3,198 locations or pixels. This is our dependent variable, _Y_ ( **Figure 3** ).\n\n\n1 It is available on the Internet at MapSpaM.info.\n\nMention: \"2010 SPAM\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"Its spatial distribution of rice production anchors the district allocation.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:007435:54:1", "occurrence_id": "097e079a43c31607b4336664", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: >Boundary 5 km radius 50 km radius\nN 3359370 3359370 689745 689745 688275 688275\nr2 0.95 0.96 0.94 0.95 0.94 0.97\n_∗p <_ 0 _._ 10 _,∗∗_ _p <_ 0 _._ 05 _,∗∗∗_ _p <_ 0 _._ 01\n\nThe table shows difference-in-differences estimates of the impact of new village roads on local forest cover, under\nalternate sample definitions. We define forest cover as log village forest cover; the data source is Vegetation Continuous\nFields. Specifications are identical to those in Table 3 with the following changes. Column 1 includes villages that did\nnot receive PMGSY roads at any time as part of the control group. Column 2 adds village-specific time trends to show\nthat the positive treatment estimate in Column 1 is driven by differential trends in never-treated villages. Columns\n3 and 4 repeat these two specifications with the standard set of villages to show that village-specific time trends do\nnot affect our main estimates. Column 5 estimates the standard specification from Table 3 with treated villages only,\nbut the dependent variable includes forest cover in a 5km radius from the village centroid. Column 6 uses a 50km\ncentroid. Award Period is an indicator variable that takes the value one for years after a road contract was awarded\nand before the\n\nMention: \"Vegetation Continuous\nFields\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"Village forest cover is defined from this satellite product.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:007459:4:0", "occurrence_id": "6a18d79f3c859d6645511929", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: In this paper, use a dataset of publicly listed firms in the United States from the Compustat\n\n\ndatabase to identify star firms and the industries in which these firms are more likely to appear in.\n\n\nWe examine the role of intangible capital, competition (Herfindahl-Hirschman industry concentra\n\ntion index), and market power in influencing star firm status. We use three measures of market\n\n\npower - a firm-level measure of operating markups, firm-level market share, and a raw measure of\n\n\nfirm size. 4 Finally, we examine the persistence of the star firms’ performance and whether they\n\n\ndiffer in their investment and output per unit of capital compared to other firms in the economy.\n\n\nFollowing Furman and Orszag [2015], we define star firms as firms in the top 10% of Return\n\n\non Invested Capital (ROIC) in the US in a particular year. 5 Using conventional ROIC measures,\n\n\nin Figure 1, we find that there has indeed been a run-up in the ROIC of the top decile of large,\n\n\nnon-financial sector, publicly-listed U.S. firms. 6 Over the period 1965-2015, the ratio of the 90 _th_\n\n\npercentile ROIC firm to the median ROIC firm has increased by over 69%. Importantly, we find\n\n\nthat the star firms whose returns are diverging from the rest of the firms are in industries that\n\n\nrequire high cognitive skills and that in these industries average returns are higher. In industries\n\n\nwhere the tasks involve routine manual skills and which score low on non-routine cognitive and\n\n\ncomplex problem solving skills, we see lower returns and don’t see the star firms pulling away from\n\n\nthe rest.\n\n\nHowever, conventional return metrics do not capitalize research and development, brand\n\nMention: \"Compustat\n\n\ndatabase\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"Publicly listed firms in one country are identified from this database.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:007460:31:0", "occurrence_id": "92046a7552be87584ce1a5f7", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: Figure 11: Effect of FV on exchange rate pass-through\n\n\n_Source_ : World Input-Output tables (2013 release), BIS and authors’ calculations.\n\n\n_Note_ : The Figure reports percentiles of _FV_ with respective values in the second row of the x-axis and the corresponding\n\n\nexchange rate elasticity on the vertical axis. Elasticities are computed from the specification in column (6) of Table 2,\n\n\nincluding origin-sector-destination fixed effects and time dummies.\n\n\n**5.2.2** **Export** **volume** **elasticities**\n\n\nTable 3 reports the results for the export volumes regression. 26 The pooled OLS reveals\n\n\na dampening effect of _FV_ on the bilateral exchange rate elasticity and the positive effect\n\n\nof _IV_ on the elasticity of exports to the direct partner’s nominal effective exchange rate\n\n\n(NEER). When we exploit the within sector-destination (second column) or the sector\n\norigin-destination (fourth column) variability and control for common time effects, we\n\n\nobtain a negative and significant coefficient for the interaction terms of the bilateral ex\n\nchange rate with _FV_ and _RDV_ and an insignificant effect of _IV_ on the exchange rate\n\n\nelasticity.\n\n\nInterestingly, the coefficient of the destination’s NEER vis-à-vis its trading partners is\n\n\nnot significant, whereas its interaction with _IV_ is positive and significant, meaning that\n\nsector _s_ _′_ exports are more sensitive to its direct trading partners nominal effective exchange\n\n\nrate the higher is the quantity of exports that are intermediated by the latter. The results\n\n\nare confirmed even when controlling for time-varying characteristics of countries/currencies\n\n\nwith country-time dummies, although the interaction of _IV_ with the NEER of the desti\n\nnation market becomes statistically insignificant, but remains\n\nMention: \"World Input-Output tables (2013 release)\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"Its linkage coefficients give the pass-through exposure.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:007461:20:0", "occurrence_id": "e642d99d57c02ae964138d38", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: 19\n\n\nWe compute, for each country, time paths of childhood stunting and cognition without the\n\n\nnutrition program, to which we apply the program effects 𝑑𝑆��𝑡�𝜕𝐷⁄ ��𝑡� and 𝑑𝐶��𝑡�𝜕𝐷⁄ ��𝑡�. We\n\n\nget the counterfactual childhood stunting time path by setting the 2015 childhood stunting rate equal\n\n\nto the latest JME childhood stunting rate for the country in question, and then assuming that before\n\n\nand after 2015 stunting falls at an annual rate of 1.5% (the rate we computed in section 2 above). For\n\n\nthe counterfactual cognition time path, we assume zero change in the absence of the nutrition\n\n\nprogram, and assume the z-score is initially zero. As in a recent World Bank report (World Bank\n\n\n2016), we assume the program goes to scale gradually over a 10-year period between 2016 and 2025,\n\n\nachieving Bhutta et al.’s estimated 20% reduction (compared to the counterfactual) in 2025. This\n\n\ngives us, after 10 years, a value of 𝑑𝑆��𝑡�𝜕𝐷⁄ ��𝑡� (in terms of year-to-year changes) equal to -3.7%.\n\n\nWe assume the program is maintained at the same scale thereafter, so the stunting rate remains at\n\n\n20% below the counterfactual rate for all periods after 2025.\n\n\nWe estimate the change in the cognition z-score attributable to the nutrition program,\n\n\n𝑑𝐶��𝑡�𝑑𝐷⁄ ��𝑡�, by multiplying, for each intervention in the Bhutta et al. package, the estimated\n\n\ncognition effect of the intervention (obtained from Table 3) by 0.9 minus the fraction of children\n\n\ncurrently covered by the intervention. (The effect size is relevant for going from 0% to 100%,\n\n\nwhereas the program takes intervention coverage from its current rate to 90%.) We use the\n\n\nestimated mean cognition effects from the meta-analyses summarized in Table 3. The current\n\n\nintervention coverage rates are from various sources. We assume the effects\n\nMention: \"JME childhood stunting rate\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"The latest rate for each country sets the model's starting level.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:007480:5:0", "occurrence_id": "ed16cc0686a8793540d72f26", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: perceive that in utility or welfare metrics, its advantages outweigh its drawbacks\n\n\n(Binswanger, Deininger, and Fe 1995). Yet to our knowledge, this has received\n\n\nlittle attention in the literature.\n\n\nIn this article, we contribute to the literature on the economic consequences\n\n\nof land fragmentation, taking these three fundamental issues seriously. Building\n\n\non insights found in Ali, Deininger, and Ronchi (2018) and Veljanoska (2016),\n\n\nwe address issues of endogeneity by exploiting a unique natural experiment,\n\n\nEthiopia’s history of land reform and allocation which we argue represents an\n\n\nexogenous source of household-level land fragmentation. Like Ali, Deininger,\n\n\nand Ronchi (2018), we are able to construct multiple complementary fragmen\n\ntation measures, reflecting number of parcels, size and geographical dispersion.\n\n\nUnlike most studies, however, our data source, Ethiopia’s Living Standards and\n\n\nMeasurement Study-Integrated Survey on Agriculture (LSMS-ISA), contains in\n\nformation on household food security outcomes allowing us to assess the impact\n\n\nof land fragmentation on welfare metrics in terms of food security.\n\n\nWe find that in Ethiopia, land fragmentation reduces food insecurity. To\n\n\nunderstand why, the paper unpacks the risk diversification mechanism. Consis\n\ntent with Shaw’s (1963) conjecture, land fragmentation mitigates the adverse\n\n\neffects of low rainfall on food security. Households with diverse parcel charac\n\nteristics in terms of slope, elevation and wetness can grow a diverse set of crops.\n\n\nBy allowing farmers to create a diverse crop portfolio, land fragmentation helps\n\n\nmitigate weather risks, improving food security outcomes.\n\n##### **The evolution of access to land in Ethiopia**\n\n\nOur identification strategy hinges on our assertion that land access and frag\n\nmentation are exogenous to farmer ability. Justifying this claim first requires\n\n\nunderstanding the evolution of access to land in the diverse regions of Ethiopia.\n\n\n3\n\nMention: \"Living Standards and\n\n\nMeasurement Study-Integrated Survey on Agriculture\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"It carries household food security outcomes alongside plot information.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:007484:21:1", "occurrence_id": "ad8570b76d338c15d28593c8", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: grant) becomes available, if firms are not credit constrained, they should always use the cheaper credit\nto pay o↵more expensive loans. In fact, they should draw down the expensive\nloans to zero if credit is freely available. In Appendix Table E1, we examine\ndata on borrowing for school and household accounts of school owner households.\nWhile there is limited borrowing for investing in the school, over 20% of school\nowner households do borrow (presumably for personal reasons). Yet, we find no\nstatistically significant declines in borrowing at the school or household level as\na result of our intervention.\n\nWe now consider whether these expenditure changes a↵ected school revenues.\nSince schools may not always be able to fully collect fees from students, we use two\nrevenue measures: (i) posted revenues based on posted fees and enrollment (cols\n2-4), calculated as the sum of revenues expected from each grade as given by the\ngrade-specific monthly tuition fee multiplied by the grade-level enrollment; and\n(ii) collected revenues as reported by the school (cols 5-7). 26 To obtain the latter\nmeasure, we inspected the school account books and computed revenues actually\ncollected in the month prior to the survey. 27 While this measure captures revenue\n\n\n26Posted revenues are available for rounds 1,2, and 4, and collected revenues are available from rounds\n2-5. We use baseline posted revenues as the control variable in all revenue regressions.\n27Over 90% of schools have registers for fee payment collection, and for the remainder, we record\n\nMention: \"school account books\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"validate\", \"summary\": \"Inspected directly to compute revenues actually collected before the survey.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:007518:22:1", "occurrence_id": "b1c3586b35eb5d75d59e2a5b", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: by improving\nallocative efficiency, enhancing productive efficiency, and boosting innovation. Aghion, Akcigit\nand Howitt (2014) also provide a compelling framework linking market competition to\nproductivity growth through creative destruction, while Conway et al (2006) and Alesina et al.\n(2005) trace the positive impact of pro-competition product market regulation on productivity, and\nBarone and Cingano (2011) find empirical evidence that pro-competition reforms in input sectors\nbenefit productivity of the overall economy. Furthermore, the introduction of anti-cartel policy is\nalso related to higher labor productivity growth. Symeonidis (2008) records a 20 to 30 p.p. lower\nlabor productivity growth in industries with cartels than in industries without cartels. Some\ngovernment interventions unduly inhibit firm’s ability or incentives to compete. The OECD\nProduct Market Regulation (PMR) indicator measures the degree to which policies or regulatory\nmeasures promote or inhibit competition in areas of the product market where competition is\nviable. PMR data for Brazil in 2013 suggests that policies and regulations in key sectors are less\nconducive to competition than in comparator countries.\n\n\nWhile other BRICS countries have promoted reforms over the last decade, the overall\nrestrictiveness of product market regulation in Brazil remained unchanged between 2008 and 2013.\nThe general degree of restrictiveness of product market regulations in Brazil has not changed since\nbetween 2008 and 2013 and compares less favorably to other economies which on average have\nmoved towards a more pro-competitive regulatory framework (Figure 24). In fact, while others\n\n37 _Competition policy_ encompasses a set of policies and laws that ensure competition in the marketplace is not\nrestricted in such a way as to reduce economic welfare (Motta, 2004).\n38 For more details on what competition policy encompasses, see Kitzmueller and Licetti (2012).\n\n\n21\n\nMention: \"PMR data for Brazil in 2013\""}, {"role": "assistant", "content": "{\"role\": \"supporting\", \"usage_action\": \"source\", \"summary\": \"Its sector regulation scores show policies less conducive to competition.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:007530:36:3", "occurrence_id": "9938d9c1544912e875ef985e", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: -0.374 -0.159 -2.162\n5 - richest -0.373 -0.199 -0.071 -0.643\nTotal -1.678 -0.382 -0.525 -2.579\nPanel C: Share of maize, cassava and rice in food budget across income quintiles\nQuintiles\nItem 1 2 3 4 5\nMaize 18.46 25.29 24.72 19.24 7.92\nCassava 13.75 9.46 6.21 3.38 1.25\nRice 4.19 4.90 4.60 4.33 3.02\n_Source_ : World Bank based on IOF-2014/15 and IAS-2015\n\n\n35\n\nMention: \"IOF-2014/15\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"analyze\", \"summary\": \"The income and expenditure round behind the reported figures.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:007530:36:3", "occurrence_id": "c1cfcb9b49bc0e4ba8cd43d2", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: -0.374 -0.159 -2.162\n5 - richest -0.373 -0.199 -0.071 -0.643\nTotal -1.678 -0.382 -0.525 -2.579\nPanel C: Share of maize, cassava and rice in food budget across income quintiles\nQuintiles\nItem 1 2 3 4 5\nMaize 18.46 25.29 24.72 19.24 7.92\nCassava 13.75 9.46 6.21 3.38 1.25\nRice 4.19 4.90 4.60 4.33 3.02\n_Source_ : World Bank based on IOF-2014/15 and IAS-2015\n\n\n35\n\nMention: \"IAS-2015\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"analyze\", \"summary\": \"The accompanying agricultural round.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:007539:5:0", "occurrence_id": "009a41f5b457d18bfda16bfa", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: following unexpected contingencies and thus bail out efficient exporters that experience\n\n\nfinancial difficulties (Huberman and Kahn, 1988). While differentiating these two channels is\n\n\nnotoriously hard, in the second part of the paper we try to gain intuition into the mechanisms\n\n\nthat drive the baseline results.\n\n\nIn a first set of tests, we build on the prediction of the banking literature that banks’\n\n\nsoft budget constraints are more severe in institutional settings in which banks are more\n\n\nsusceptible to the pressure of external parties (e.g., the government) to rollover credit to\n\n\nbusinesses, and less subject to independent monitoring of bank auditors and supervisors\n\n\non their decisions to grant such rollover. Matching information from our main databases\n\n\nwith data from the World Bank Banking Supervision Survey, we obtain that in countries\n\n\nwhere banks are less independent from the pressures of external parties and where bank\n\n\nmanagers are subject to less rigorous scrutiny of bank auditors and supervisors that prevent\n\n\nthe release of misleading information, domestic banks reduce the dynamism of the export\n\n\nsector relative to stock market investors and to foreign banks (i.e., they reduce exporters’\n\n\nentry, exit and turnover, in line with the soft budget constraint hypothesis).\n\n\nIn a second set of tests, we exploit the prediction of the banking literature that, to\n\n\nthe extent that banks’ behavior instead reflects long-termism, this benefit should manifest\n\n\nitself especially following negative shocks (e.g., crises or recessions) or in settings where\n\n\nex ante it is harder to write detailed contracts that can account for unexpected shocks.\n\n\nHowever, we uncover no evidence that domestic banks moderate the exit of exporters more\n\n\nduring recessions or financial crises than in tranquil times. Moreover, the differential effect\n\n\nof foreign banks is no more pronounced for products characterized by higher informational\n\n\nopacity or contractual complexity (measured according to the methodologies in Rauch,\n\n\n1999, and Nunn, 2007). Overall these findings cast doubts on the benign interpretation that\n\n\ndomestic banks are a buffer against the realization of unforeseen shocks over the\n\nMention: \"World Bank Banking Supervision Survey\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"Matched to the main databases to measure supervisory independence.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:007544:26:2", "occurrence_id": "43147bd36ebdc005c75c524f", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: .12 0.08 0.04\nUpper-bound elasticity 1.24 0.80 0.55 0.44 0.39 0.39 0.30 0.25 0.18 0.09\n\n_Source:_ Estimates based on Russia Longitudinal Monitoring Survey–HSE 2016.\n_Note:_ The table reports the share of total consumption for each decile.\n\n\n**Table D.4 – Years of Working Life Lost (%), by Decile**\n\n\n_Price shock scenario_ _1_ _2_ _3_ _4_ _5_ _6_ _7_ _8_ _9_ _10_\nLow-bound elasticity 0.03 0.01 0.00 -0.01 -0.02 -0.02 -0.02 -0.03 -0.03 -0.04\nMedium elasticity 0.20 0.21 0.17 0.17 0.17 0.21 0.19 0.20 0.18 0.20\nUpper-bound elasticity 0.38 0.41 0.35 0.35 0.36 0.43 0.41 0.42 0.40 0.45\n\n_Source:_ Estimates based on Russia Longitudinal Monitoring Survey–HSE 2016.\n_Note:_ The table reports the share of total individual consumption for each decile. Years of life lost have been estimated using all\ndeaths from tobacco-related diseases.\n\n\n**Table D.5 - Net Effect on Household Expenditures (%), by Decile*\n\nMention: \"Russia Longitudinal Monitoring Survey–HSE 2016\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"analyze\", \"summary\": \"Decile shares of total consumption are estimated from this wave.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:007546:25:0", "occurrence_id": "6aca5f532401628ef99b8a22", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: These results are in stark contrast with those reported in recent studies. Predictions based on different\ncutoffs for population size and population density yield urbanization rates that range from 47.2 to 78.0\npercent (IDFC Institute 2015). A measure based on an agglomeration index that combines population\ndensity, population of the nearby main center, and travel time to that center suggests an urbanization\nrate of 55.3 percent (Uchida and Nelson 2009; World Bank 2015). And measures based on satellite imagery\nand agglomeration criteria produce urbanization rates of from 37.5 to 63.1 percent (Denis and Marius‐\nGnanou 2011). All of these results exceed our highest estimate.\n\n\n_Gaps at the subnational level_\n\n\nAlthough we find no major discrepancy with the official urbanization rate for India as a whole, our results\nsuggest that the 2011 Census of India misclassified large numbers of units and people. Based on the\nbenchmark specification, the misclassification affected 62 million people.\n\n\nThe misclassification is substantial among units falling within three of India’s administrative types (figure\n8). Among statutory urban units, the gap is highest for other towns. According to our assessment, 1,317\nof 2,861 lack sufficient urban characteristics and so should be considered rural. Thus 17 million people are\nincorrectly considered urban residents.\n\n\n**Figure 8. Misclassification of urbanization in India is highest among three administrative types**\n\n\nMisclassification is also substantial among the census towns of India. These units are administratively\nrural, but they meet three criteria to be identified as urban areas according to the 2011 Census of India.\nThey have more than 5,000 inhabitants, a population density exceeding 400 persons per square kilometer,\nand over 75 percent of their male working population is engaged in non‐agricultural activities. We find\n\n\n24\n\nMention: \"the 2011 Census of India\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"validate\", \"summary\": \"Its urbanisation rate suggests large numbers of misclassified units.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:007573:5:0", "occurrence_id": "4f2143816f99a96e5bd8cd26", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: Dolls, Fuest, Peichl (2012) and Dolls, Fuest, Peichl, Wittneben (2018) analyze the capacity of\nEuropean tax benefit systems to act as an automatic stabilizer in times of income changes and how\nthis capacity has been affected by policy changes.\n\n##### 2. Assessing vertical redistribution\n\n\n**2.1 Measuring redistribution**\n\n\nRedistribution is typically measured using the Reynolds-Smolensky index of redistribution as the\ndifference between the Gini coefficients of market income and disposable income:\n\n\n𝑅𝑆��𝐺𝑖𝑛𝑖 ������ �𝐺𝑖𝑛𝑖 ���������� \n\nFigure 1, which is based on the OECD Income Distribution and Poverty Database 3 [^3: Available at http://stats.oecd.org/Index.aspx?DataSetCode=IDD.], shows the\nReynolds-Smolensky index of redistribution for a selection of countries. The European Union’s\naverage level of redistribution equals 21 Gini points. This is almost twice as large as the\nredistribution occurring in the United States, amounting to 11 Gini points.\n\n\nThe Gini difference is a measure of the redistributive effectiveness of taxes and transfers at a given\npoint in time: the larger the difference, the larger the impact of taxes and transfers on reducing\ninequality in market incomes. Market incomes include gross labor incomes and earnings from\nemployment and self-employment (both permanent and temporary jobs), capital income, incomes\nfrom property as well as private pensions. Disposable incomes equal market income minus direct\ntaxes and social insurance contributions (for both employees and self-employed), plus any\nadditional transfers (such as pensions, means tested benefits and non-means tested benefits). Direct\ntaxes include for example personal income taxes, taxes on capital dividends and interests, as well\nas property taxes. 4 Incomes are observed at the household level and weighted with the modified\nOECD equivalence scale. The Gini coefficients for\n\nMention: \"OECD Income Distribution and Poverty Database\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"The inequality figure is built from this compilation.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:007574:39:1", "occurrence_id": "bccddbc050da236e21b1977b", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: ** : 2015 and 2016 waves of the Rural-Urban Migration in China (RUMiC) Survey, and RUMiC Information\nIntervention Survey, 2016.\n**Notes** :An estimated city-level treatment effect is plotted against the relative premium for the urban employee\nhealth insurance and pension programs in the city. The relative premium is calculated as the premium required\nfor self-employed workers to participate divided by the city-wide average monthly earnings of migrants. The citylevel treatment effects are coefficients from the health insurance and pension participation models estimated with\ncity-specific information treatment indicators (city indicators interacted with the information treatment) in models\nthat control for the city fixed effects.\n\n\n38\n\nMention: \"Rural-Urban Migration in China (RUMiC) Survey\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"Two waves plus an information intervention round.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:007589:16:0", "occurrence_id": "38e5f322c4dddb5897ab8030", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: distributing across the cells of the ‘USE’ matrix 3 [^3: The ‘USE’ matrix in a SAM refers to inputs of different goods and services for the production of various goods and\nservices.] the total value of domestically produced goods\n\n\nand services consumed by the productive sectors (intermediate consumption), using technology\n\ncoefficients from the GTAP 4 [^4: GTAP is a global network of researchers who conduct quantitative analysis of international economic policy issues,\nespecially trade policy. A key output of the network is a global economic database, covering many sectors and all\nparts of the world. It is coordinated by the Center for Global Trade Analysis, Department of Agricultural Economics,\nPurdue University, West Lafayette, IN.] 2007 SAM for Bangladesh. The use of 2007 GTAP coefficients\n\n\nmeans ignoring possible structural change between 2007 and 2012 in the Bangladesh economy.\n\n\nAll elasticity parameters are taken from Timilsina and Shrestha (2007). As it is difficult to\n\n\nempirically estimate the elasticity of substitution across commodities for individual countries,\n\n\nusing values from the literature is the norm. Data on government transfers to BPDB were obtained\n\n\nfrom the Medium Term Macroeconomic Policy Statement of the Ministry of Finance, Government\n\n\nof Bangladesh, while quantity forecasts for natural gas and LNG were obtained from Petrobangla\n\n\n(2012), with natural gas price data for 2015 for Bangladesh coming from Petrobangla and LNG\n\n\nprice data for India from Sen (2015).\n\n\n**4.** **Results and Discussion**\n\n\nIn this section, we first discuss results from the CGE model simulations of electricity\n\n\nsubsidy removal followed by results from simulations in which the price of natural gas is increased\n\n\nto its opportunity cost. Under each set of results, aggregate level results, such as impacts on GDP,\n\n\ntotal sectoral outputs, total household demand, total exports, total imports, total investment,\n\n\ndisposable income, the trade balance, and government income are discussed first; this is followed\n\n\nby a discussion\n\nMention: \"GTAP\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"Its technology coefficients give intermediate consumption linkages.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:007590:63:0", "occurrence_id": "c8626407450d828342eb015b", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: must contain at least one metropolitan area of above 300,000 people as defined by the UN\n\n\n(2015); third, the sum of the UN metropolitan area or areas within our polygon must be at\n\n\nleast 800,000 people.\n\n\nWe use the intersection with the UN metropolitan areas data as it provides an external\n\n\ncheck on the Landscan data. One issue we noticed in India and China, in particular, was\n\n\nthat large swathes of seemingly high density rural areas had been combined into gigantic\n\n\nurban areas, which we were certain were not urban areas in reality. Presumably this was\n\n\noccurring because Landscan is smearing people in these regions into agricultural areas.\n\n\nHence, the UN allows us to sense check the data against reported evidence.\n\n\nApplying our initial density-cutoffs to create contiguous polygons, leaves us with a set\n\n\nof 13,638 metropolitan area polygons. After we overlay this with the coordinates of the\n\n\nmetropolitan areas above 300,000 in the 2015 UN data, we get 1,544 polygons which match\n\n\nand we therefore keep. Only 54 of the total 1,692 UN points above 300,000 did not match\n\n\nwith our polygons. In the case that several metropolitan areas fall into one polygon, the\n\n\nUN population is summed and the name of the largest metropolitan area is kept. Once we\n\n\napply the total population threshold of above 800,000, we are finally left with a set of 599\n\n\ncities worldwide, with 451 in the developing world.\n\n\n**B.1.3** **Creating Core, Fringe and Settlement Polygons for Africa**\n\n\nFor separate analyses which we do just on Africa in Sections 4-6, we define urbanized\n\n\nareas using similar but distinct density and population threshold cutoffs. We define three\n\n\nunique urbanized areas: cores, fringes, and LD settlements. A city is the consolidation of\n\n\nan urban core and its surrounding peripheral fringe, whereas a settlement is a unique area.\n\n\nWe define each area as follows:\n\n\n1. Cores are defined\n\nMention: \"UN metropolitan areas data\""}, {"role": "assistant", "content": "{\"role\": \"supporting\", \"usage_action\": \"validate\", \"summary\": \"An external check on the population surface.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:007590:63:0", "occurrence_id": "53d5a0ba4cae15f63562f443", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: must contain at least one metropolitan area of above 300,000 people as defined by the UN\n\n\n(2015); third, the sum of the UN metropolitan area or areas within our polygon must be at\n\n\nleast 800,000 people.\n\n\nWe use the intersection with the UN metropolitan areas data as it provides an external\n\n\ncheck on the Landscan data. One issue we noticed in India and China, in particular, was\n\n\nthat large swathes of seemingly high density rural areas had been combined into gigantic\n\n\nurban areas, which we were certain were not urban areas in reality. Presumably this was\n\n\noccurring because Landscan is smearing people in these regions into agricultural areas.\n\n\nHence, the UN allows us to sense check the data against reported evidence.\n\n\nApplying our initial density-cutoffs to create contiguous polygons, leaves us with a set\n\n\nof 13,638 metropolitan area polygons. After we overlay this with the coordinates of the\n\n\nmetropolitan areas above 300,000 in the 2015 UN data, we get 1,544 polygons which match\n\n\nand we therefore keep. Only 54 of the total 1,692 UN points above 300,000 did not match\n\n\nwith our polygons. In the case that several metropolitan areas fall into one polygon, the\n\n\nUN population is summed and the name of the largest metropolitan area is kept. Once we\n\n\napply the total population threshold of above 800,000, we are finally left with a set of 599\n\n\ncities worldwide, with 451 in the developing world.\n\n\n**B.1.3** **Creating Core, Fringe and Settlement Polygons for Africa**\n\n\nFor separate analyses which we do just on Africa in Sections 4-6, we define urbanized\n\n\nareas using similar but distinct density and population threshold cutoffs. We define three\n\n\nunique urbanized areas: cores, fringes, and LD settlements. A city is the consolidation of\n\n\nan urban core and its surrounding peripheral fringe, whereas a settlement is a unique area.\n\n\nWe define each area as follows:\n\n\n1. Cores are defined\n\nMention: \"Landscan data\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"The population surface whose large gaps are noted in two countries.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:007583:38:0", "occurrence_id": "f4c5d47e6d2165be7916aaad", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: Figure 17. Cumulative tax multiplier evaluated after two years: Linear vs. non-linear multipliers\n\n\nNotes: Country …xed e¤ect panel regression with linear and quadratic trends.\n\n\n6.5 Non-linearities in action III: How do taxes a¤ect incentives to work and invest?\n\n\nIn this subsection, we analyze whether the non-linear distortionary and disincentive-based theoretical\n\n\narguments and the empirical results obtained above are actually re‡ected on the perceived e¤ect of\n\n\ntaxes on incentives to work and invest. Based on a survey of a representative sample of business\n\n\nleaders in 142 countries, the Global Competitiveness Index elaborated by the World Economic Forum\n\n\nincludes speci…c questions such as (i) “[i]n your country, to what extent do taxes reduce the incentive\n\n\nto work?”and (ii) “[i]n your country, to what extent do taxes reduce the incentive to invest?”.\n\n\nFigure 18. Relation between VAT rate and the perceived (survey-based) e¤ect of taxes on the\n\n\nincentives to work and invest\n\n\nPanel A. Relation between VAT rate Panel B. Relation between VAT rate\n\n\nand the perceived e¤ect of taxes and the perceived e¤ect of taxes\n\n\non the incentives to work on the incentives to invest\n\n\nNotes: Regression line includes linear and quadratic terms.\n\n\n37\n\nMention: \"Global Competitiveness Index\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"Survey of business leaders in 142 countries with specific items.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:007601:10:0", "occurrence_id": "a8631d7b25d5a434e27bf790", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: captured in a separate question with a prompt for the respondent describing what constitutes an absent\n\n\nmember.\n\n\n_Figure 1 Five-arm randomized control trial testing various methods of measuring food consumption._\n\n\nBelow, we describe in greater detail the differences between treatment arms, with a focus on how we\n\n\nmeasure FAFH for adults in the household. With the exception of T1, adult FAFH was collected in an\n\n\nentirely separate module specifically designed for each of the experimental arms. Adult FAFH was\n\n\ncollected for nine separate meal events, differentiating main meals (breakfast, lunch and dinner), snacks\n\n\n(morning, afternoon, and evening), and drinks (bottled water, alcohol, other drinks). This structure was\n\n\nmeant to assist the respondent in thinking in more detail about FAFH, and to ensure they did not omit any\n\n\nFAFH consumption. The explicit mention of snacks, for example, is particularly important as most of the\n\n\nsnacking is likely to take place out of the home. The module also asked for the most common place of\n\n\nconsumption, and collected the value of all food consumed, whether purchased or received for free.\n\n\nQuestions were designed so that there was no double-counting of expenditures (e.g. for family meals outside\n\n\nthe home paid for by one member). More information on each of the experimental treatment arms can be\n\n\nfound in Appendix 9.1.\n\n\nUnlike the newly designed modules, treatment arm T1, the 7-day “one-line” recall, followed the current\n\n\nand standard methodology of the VHLSS, where households were asked to recall their food consumption\n\n\nin one question: “How much has your household consumed over the past 7 days of outdoor meals and drinks\n\n\n9\n\nMention: \"VHLSS\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"Its standard single-question food recall is followed here.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:007656:45:1", "occurrence_id": "66e79ac9432f8dec73f3601b", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: 518-50\n\n\n[43] glennerster.r, t.suri and s.bhogale (2016) The Implications of the Ebola Outbreak\n\n\non Markets, Traders, and Food Security in Sierra Leone, IGC Policy Brief.\n\n\n[44] goldin.c and l.f.katz (2002) “The Power of the Pill: Oral Contraceptives and Women’s\n\n\nCareer and Marriage Decisions,” _Journal_ _of_ _Political_ _Economy_ 110: 730-70.\n\n\n[45] gollier.c and j.w.pratt (1996) “Risk Vulnerability and the Tempering Effect of Back\n\nground Risk,” _Econometrica_ 64: 1109-23.\n\n\n[46] guarnieri.e and h.rainer (2018) Female Empowerment and Male Backlash, CESifo\n\n\nWP7009.\n\n\n[47] haushofer.j, j.shapiro, c.ringdal, x.y.wang (2018) Income Changes and Intimate\n\n\nPartner Violence: Evidence from Unconditional Cash Transfers in Kenya, mimeo Princeton.\n\n\n[48] hes.s, d.jaimovich and m.scheundeln (2018) Development Projects and Economic Net\n\nworks: Lessons From Rural Gambia, mimeo Goethe University.\n\n\n[49] himelein.k, m.testaverde, a.turay and s.turay (2015) The Socio-economic Impacts\n\n\nof Ebola in Sierra Leone: Results from a High Frequency Cell Phone Survey (Round Three),\n\n\nWashington DC: The World Bank.\n\n\n43\n\nMention: \"High Frequency Cell Phone Survey\""}, {"role": "assistant", "content": "{\"role\": \"supporting\", \"usage_action\": \"source\", \"summary\": \"Its third round reports the socioeconomic impacts of the epidemic.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:007660:56:0", "occurrence_id": "395aeb0ca8e95285c6da3746", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: Table 10: First stage regressions corresponding to Table 4\n\n\n(1)\nBlack population growth\n\n\n_Panel_ _A:_ _Population_ _growth_ _rates_ _(1991-1996)_\nlog distance -0.940\n(0.593)\n\n\n_Panel_ _B:_ _Population_ _growth_ _rates_ _(1991-2001)_\nlog distance -0.007 _∗∗∗_\n\n(0.001)\n\n\n_Panel_ _C:_ _Population_ _growth_ _rates_ _(1991-2011)_\nlog distance -0.004 _∗∗∗_\n\n(0.001)\n\n\nFixed effects Yes\n\n\nControls Yes\n\n\nObservations 2093\n\n\n_Notes._ This Table displays estimates of equation (1) in the main\ntext. Each cell presents estimates from a separate regression. The\nstandard errors are clustered on the municipality level and presented\nin parentheses. There are 201 clusters. All columns are estimated\nusing OLS where the natural log of distance to the nearest homeland\nis the variable of interest. The outcome variable is absolute black\npopulation growth in the relevant time period divided by the overall\npopulation. The relevant time periods are 1991-1996 in Panel A,\n1991-2001 in Panel B and 1991-2011 in Panel C. Controls include\nvariables on education, income, population group, population density\nand employment in 1991. There are nine provinces for which fixed\neffects are included. Coefficients that are statistically significant at\nthe 90% level of confidence are marked with a *; at the 95% level, a\n**; and at the 99% level, a ***. Standard errors in parentheses.\n_Source_ : Authors’ analysis based on South African census data.\n\n\n55\n\nMention: \"South African census data\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"analyze\", \"summary\": \"Subnational outcomes are analysed from these enumerations.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:007668:16:1", "occurrence_id": "cac2e1cb855f27ddf3e2ba84", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: dollars)_\n\n\n40\n35\n30\n25\n20\n15\n10\n5\n0\n\n\n\n\n\n\n\n\n\n\n\n**Labor productivity**\n_(Median, in thousands of 2009 dollars)_\n\n\n8\n\n6\n\n4\n\n2\n\n0\n\n\n\n\n\n\n\n\n\n\n\n\n\n_Source:_ Calculations using World Bank Enterprise Survey data.\n_Note:_ Labor productivity is the ratio of value added by the number of workers.\n\n\nThese conditions are reflected in lower productivity premia for pioneers in FCS: higher returns are\noffset by important costs and uncertainty. Estimates from the World Bank Enterprise Survey\nsuggest that the productivity of pioneering firms in FCS is lower than that of their peers in nonFCS. As illustrated in Figure 4, the median value added per worker in pioneering firms in FCS\n($6,986) is lower than that of pioneering firms in non-FCS ($11,651).\n\n\n15\n\nMention: \"World Bank Enterprise Survey\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"Its estimates show pioneering firms in fragile settings are less productive.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:007676:12:0", "occurrence_id": "a24f71f6d516952adbce9e1a", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: Figure 1: Cumulative productivity distributions\n\n\nNote: Survey weights are applied in the computation of the data presented above\n\n\nIn section 1, we outlined concerns that have been raised at the macro level that productivity growth has\n\n\nbeen lagging in the region, and the micro data from the WBES provide further justification of these\n\n\nconcerns. Table 3 shows the evolution of labor productivity and total factor productivity across the seven\n\n\ncountries covered in our analysis, for the three rounds of WBES data that are available for these countries.\n\n\nWhile average labor productivity increased from 2006 to 2010, it subsequently declined in 2017; for the\n\n\nmedian establishment, there was a minor increase between 2010 and 2017. Total factor productivity also\n\n\nincreased from 2006 to 2010, but subsequently declined—this holds at both the mean and the median\n\n\nvalues.\n\n\n11\n\nMention: \"micro data from the WBES\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"Firm-level evidence corroborating the regional productivity concern.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:007676:12:0", "occurrence_id": "6a7d349f130043c2d6065009", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: Figure 1: Cumulative productivity distributions\n\n\nNote: Survey weights are applied in the computation of the data presented above\n\n\nIn section 1, we outlined concerns that have been raised at the macro level that productivity growth has\n\n\nbeen lagging in the region, and the micro data from the WBES provide further justification of these\n\n\nconcerns. Table 3 shows the evolution of labor productivity and total factor productivity across the seven\n\n\ncountries covered in our analysis, for the three rounds of WBES data that are available for these countries.\n\n\nWhile average labor productivity increased from 2006 to 2010, it subsequently declined in 2017; for the\n\n\nmedian establishment, there was a minor increase between 2010 and 2017. Total factor productivity also\n\n\nincreased from 2006 to 2010, but subsequently declined—this holds at both the mean and the median\n\n\nvalues.\n\n\n11\n\nMention: \"WBES data\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"analyze\", \"summary\": \"Three rounds across seven countries give the productivity evolution.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "reliefweb", "source_key": "reliefweb:000141:24:1", "occurrence_id": "081cf46b6b67ee6adecdc6b7", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: the decision-making process to end\ndisplacement.\n\n\nLaw 1448/2011 created the Unit for the Attention and\nIntegral Reparation of the Victims (UARIV, Spanish\nacronym), the government agency responsible for\ncoordinating the National System of Attention and\nReparation for Victims regarding the implementation\nof public policy to assist and provide comprehensive\nreparation to victims. The Victims Unit has within its\nmandate the task of guaranteeing the operation of\nthe National Information Network for assistance and\nreparation to Victims, including the interoperability of\nthe various relevant information systems. The Unit also\nmanages the Single Victims Registry, overseeing the\nintegrity of all existing records about displacement and\nhuman rights violations due to armed conflict.\n\n\n\n**22** Contributed by Oscar Iván Rico Valencia (Coordinador Grupo de Atención a Víctimas en el Exterior) as well as Katizza Carvajal and Karen\nChavez from the SDGs Indicators Working Group at DANE (the National Statistics Office in Colombia).\n\n**23** [https://secretariageneral.gov.co/transparencia/control/informaci%C3%B3n-poblaci%C3%B3n-vulnerable/ley-387-1997](https://secretariageneral.gov.co/transparencia/control/informaci%C3%B3n-poblaci%C3%B3n-vulnerable/ley-387-1997)\n\n**24** https://www.unidadvictimas.gov.co/en\n\n\n25 DATA DISAGGREGATION OF SDG INDICATORS BY FORCED DISPLACEMENT\n\nMention: \"Single Victims Registry\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"The unit manages this registry and preserves the integrity of its records.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "reliefweb", "source_key": "reliefweb:000183:5:1", "occurrence_id": "462fc2e175d21ee77c45393c", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: ‘crisis‘ ADCS, 32%\n\nmore than in 2014. The percentage of HHs buying food\n\non credit and reducing essential nonfood expenses such\n\nas health or education was more than double that of\n\n2014 and triple 2013. Spending savings, selling goods\n\nand assets, and withdrawing children from school were\n\nalso more common.\n\n\nThe gap between monthly expenditures and income was\n\nestimated at $300. The percentage of HHs with debts\n\nwas up from 81% in 2014 to 89% in 2015 with HHs\n\nmainly borrowing money to buy food followed by paying\n\nrent and covering health expenses. The amount of\n\nmoney owed rocketed too: on average, HHs with debts\n\nowed $842 compared with $674 in 2014. This national\n\naverage figure has been skewed by that of HHs in BML\n\nregion, where the mean debt average was $1,151. At\n\ndistrict level HHs in El Meten, Beirut, Baabda, Bcharre\nBatroun, Aley and Chouf owed more than $1,000 on\n\naverage.\n\n\n9\n\nMention: \"ADCS\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"Its entries track buying food on credit and reducing meals.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "reliefweb", "source_key": "reliefweb:000215:4:2", "occurrence_id": "02821d4e3348bbb0a92b218d", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: engagement with humanitarian organisations. The analysis of these difficulties forms the\nbasis of key pragmatic recommendations for humanitarian actors.\n\n## **2. Brief methodology**\n\n\nKey informant interviews (KIIs) were conducted with internally displaced persons with disabilities residing in 11 sub\ndistricts in inadequate living situations throughout northwest Syria over the phone by humanitarian staff who have a\nbackground in disability and inclusion. For those key informants who have hearing and communication difficulties, a\nsupport person was present to aid the interaction over the phone and often video call was used.\n\n\nThe KII’s were conducted during the time of severe restrictions on movements to staff and beneficiaries due to COVID19 related safety measures. Inclusion criterion for participants was defined as having significant functional difficulty with\none or more areas of daily functioning congruent with the Washington Group short set domains of functioning which\nare: communication, hearing, cognition, self-care, mobility and vision. 8\n\n\nFor further details related to the methodology, including consent procedures and study limitations, please refer to Annex\nA.\n\n\n2 HNO (2019) Syrian Arab Republic\n3 CCCM Cluster, ISIMM data (September 2020); see also HNAP, October 2020 Mobility and Needs Monitoring NSAG & TBAF controlled areas (November 2020).\n4 HNAP (2020) Summer Report Series – Disability Overview\n5 Ibid\n6 HNAP (2019) IDP insight: Disability\n7 Ibid\n[8 Washington Group on Disability Statistics (2001). Washington Group Short Set of questions. Retrieved from: https://www.washingtongroup-](https://www.washingtongroup-disability.com/question-)\n[disability.com/question-sets/wg-short-set-on-functioning-wg-ss/](https://www.washingtongroup-disability.com/question-)\n\n5\n\nMention: \"ISIMM data\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"Mobility and cluster needs tracking serves as the reference.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "reliefweb", "source_key": "reliefweb:000226:4:3", "occurrence_id": "4c918ad7ad2bd9e55fdb74ac", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: tour-volontaire-des-migrants-137-maliens-de-retour-de-la-libye.html)\n18 and 30, including women with children. One returnee,\nMrs. Ndiaye Aminata Boiré, said: \"I went to Libya since 2007.\nI was really tired there. That's why I decided to go back to my\ncountry to do something else. Even though I was not in jail\nin Libya, what I endured was more than a prison. I'm back.\nMy husband stayed there\". This is the 16th voluntary return\nflight 2018 and was the result of a collaboration between\nthe Malian Ministry of Foreign Affairs and the International\nOrganization for Migration (IOM).\n\n\nMonthly Trends Analysis West Africa 5\n\nMention: \"Monthly Trends Analysis West Africa\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"Monthly analysis produced with the migration organisation.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "reliefweb", "source_key": "reliefweb:000227:6:1", "occurrence_id": "f356020e0cd7b853aee1cd85", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: the flooding due to Hurricane Katrina, in August 2005, necessitated\nthe evacuation of hundreds of thousands inhabitants of New Orleans while tens of\nthousands of others, primarily Afro-Americans, remained trapped in the city due to a\nlack of transport amenities (Cresswell 2006).\n\n\nWhile we know approximately the number of persons affected by flooding worldwide\n(106 million, on average, between 2000 and 2005 according to the _International_\n_Disaster Database_ ), and by hurricanes (38 million), the total number of people\nthreatened by an eventual increase of this kind of disaster is, however, very difficult to\nestimate (EM-DAT). No climate model is able to predict with accuracy whether or not\nthe affected zones will be densely populated and whether the damage will have tragic\nconsequences.\n\n\nApart from this difficulty of forecasting, the studies carried out after such events tend\nto relativize their effects in terms of migration in general, and long-term migration in\nparticular. Living mainly in poor countries, the victims have little mobility (Lonergan\n\n\n5\n\nMention: \"EM-DAT\""}, {"role": "assistant", "content": "{\"role\": \"supporting\", \"usage_action\": \"source\", \"summary\": \"Reference for the difficult estimation of this disaster type.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "reliefweb", "source_key": "reliefweb:000240:3:0", "occurrence_id": "ec50cafa6f84e391f38aaf0c", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: ##### **Outcomes**\n\n\n- More than 63 % of families had enough winter items such as blankets, heaters, mattresses, and cloths\n\n- Most of the households (95.2%) mentioned that they were able to find the items and services needed in the markets\nand shops\n\n- Most of the respondents (87.1%) mentioned that they had spent the full amount received from UNHCR by the time\nof the interview.\n\n- The top three expenditures as rated by respondents were food (1st), rent (2nd), firewood, or fuel for cooking or\nheating (3rd).\n\n- Most of the respondents (98.7%) agreed that the cash assistance improved their living conditions, reduced their\nfinancial burden (98.95%), and reduced feelings of stress (98.7%).\n\n- Most households (72%) were able to meet half or less than half of their basic needs\n\n##### **Socioeconomic conditions and well being**\n\n\n- The top three sources of income were cash assistance through ATM from humanitarian organizations, credit debts,\nand income for work, which was similar to 2019-2020 PDM results\n\n- The majority of families (87.9%) had borrowed money in the last three months, which was similar to 2019-2020 PDM\nresults\n\n- The average overall debt amount that has not been paid back was 1,846,817 LBP which was higher than the average\ndebt for WINCAP only assisted group (1,475,605) in 2019-2020 PDM results\n\n- The majority of interviewed households (63.9%) indicated being dissatisfied or very dissatisfied with their lives, that\nthey feel their standard of living is getting worse (71.7%), and that they worry about the money always or most of the\ntime (88.4%).\n\n- About 99.2% of households had at least one food\n\nMention: \"2019-2020 PDM results\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"analyze\", \"summary\": \"Its results serve as reference for debt and incomes.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "reliefweb", "source_key": "reliefweb:000250:18:0", "occurrence_id": "96176b0254d5bda7f58e2ac7", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: 23\n\n\n\nAn estimated number of persons who entered Serbia exceeds 16,000. 17 According to SCRM, more than 18,000 of new accommodations were provided into asylum\nand reception centres in the same period. 18 [^18: Migration Open House in Obrenovac materials, March 26, the Commissariat for Refugees and Migration of\nthe Republic of Serbia] On the other hand, the number of refugees, migrants and asylum seekers in Serbia in accommodation centres and improvised shelters, hostels and similar, monthly ranged from approximately 3,0004,000 persons (4,500 in December 2018) 19 [^19: UNHCR Inter-Agency Operational updates 2018, https://data2.unhcr.org/], many staying in Serbia for prolonged\nperiod, some over two years.\n\n\n\nWith the coming of spring, the\nnumber of new arrivals increased\nsteadily and peaked during the\nsummer. Influx of Pakistani men\ntravelling from Greece, who had\nstayed a considerable time in\nthis EU country, arrived in Serbia\nthrough North Macedonia. During\nthe second part of the year, a significant influx of unaccompanied\nchildren was observed, entering\nfrom the direction of Bulgaria and\nNorth Macedonia. It is estimated\nthat less than a third of this population remained in the country\nby the end of 2018. 20 [^20: UNHCR, Desperate Journeys, January-December 2018, https://data2.unhcr.org/en/documents/\ndownload/67712#_ga=2.186617261.588054035.1557418235-1885394486.1557155396] Among the\nobserved new arrivals HCIT identified, every third child at exit\npoints was UASC.\n\n\n\n\n\nThroughout the year, CRPC and HCIT, in coordination with UNHCR, observed and\nfocused on new arrivals who had entered Serbia during the past few days or during\nthe past month. The new arrivals were counselled and interviewed, some were assisted on the spot and\n\nMention: \"UNHCR Inter-Agency Operational updates 2018\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"Its updates describe prolonged lengths of stay.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "reliefweb", "source_key": "reliefweb:000261:2:1", "occurrence_id": "944f54af131bd9f93d2e8bb3", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: cash available, they only need\nto make one trip to an ATM to successfully withdraw cash\ncompared to up to 10 trips previously, also saving on\ntransportation costs – up to four times, as reported by some.\n\n\n\n**_“My confidence and security have significantly increased when_**\n**_withdrawing assistance from ATMs. I no longer lose money while_**\n\n\n\n**_exchanging from Lebanese Pound to USD for rent payments.”_**\n\n\n\n**_Female participant in a focus group discussion_**\n\n\n\nSome assisted families reported an increase in discriminatory\nstatements after the introduction of dual currency redemption,\nparticularly on social media, but did not face any serious\nincidents in their daily life as a result. Rather, much of the\ntensions already existed within and between communities,\nwith the common misconception that Syrians had always had\naccess to USD and are better covered than the Lebanese, while\nthe Lebanese allegedly do not receive assistance.\n\n\nThe ATM experience survey covering over 3,000 Syrian refugee\nhouseholds confirmed the results of the focus group\ndiscussions. The number of assisted families reporting facing\nprotection risks further reduced in June to 1.3 percent from 2\npercent in May and 12 percent in February. Similarly, the\nnumber of people reporting paying a commission also reduced\nfrom 3 percent in February to 0.1 percent in May and 0.03\npercent in June. People reporting dignified access to the ATMs\nwas 95 percent in June, in line with May values and up from 85\npercent in April and 74 percent in February.\n\n\n\nIn interviews with governors, mayors, and heads of\nmunicipalities, the local authorities also acknowledged the\nbenefits of dual currency redemption in reducing crowding and\nvisibility and improving operational efficiency. At the same\ntime, many raised concerns about the impact on inflation, the\nsocioeconomic situation of Lebanese communities, and\npotential outflows to Syria, noting that most assisted Syrian\nfamilies are in fact not covering their basic needs with the cash\nprovided, making it unlikely that they will be able\n\nMention: \"ATM experience survey\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"More than three thousand households confirming the focus group results.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "reliefweb", "source_key": "reliefweb:000264:32:0", "occurrence_id": "3de354744b7e823992b5aa32", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: DTM Mali – Juillet 2020\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n|Régions-Cercles-
Communes|Ménages|Enfant ( < 18 ans )|Col4|Col5|Adulte (18 - 59 ans )|Col7|Col8|Personne âgée ( > 59 ans )|Col10|Col11|Total
Femme|Total
Homme|Total
Individus|\n|---|---|---|---|---|---|---|---|---|---|---|---|---|---|\n|**Régions-Cercles-**
**Communes**
|
**Ménages**|**F **|**M **|** Total**
**Enfant**|**F **|**M**|** Total**
**Adulte**|**F **|**M **|** Total**
**Personne**
**âgée**|** Total**
**Personne**
**âgée**|** Total**
**Personne**
**âgée**|** Total**
**Personne**
**âgée**|\n|TOUNA|32|66|61|127|36|17|53|3|1|4\n\nMention: \"DTM Mali – Juillet 2020\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"Dénombre les ménages par âge dans les subdivisions administratives.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "reliefweb", "source_key": "reliefweb:000284:11:1", "occurrence_id": "480de16822fc828e210e6cd1", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: eva which is identifying areas of high restoration](https://unepgrid.ch/en/activity/194E6705)\nand/or protection potential to reduce risk from certain natural hazards (see Figure 4). The spatial\n[data for this project is developed on a global level and can be accessed through a MapX data](https://app.mapx.org/?project=MX-2LD-FBB-58N-ROK-8RH)\n[project. On a national level ACTED, a French NGO, is implementing a project in Rakhine state](https://app.mapx.org/?project=MX-2LD-FBB-58N-ROK-8RH)\nwhich involves planting and conserving mangrove forests.\n\n\n6 OCHA Policy Development and Studies Branch (2016) “Understanding the climate-conflict nexus from a\nhumanitarian perspective: a new quantitative approach”. Available:\n[https://reliefweb.int/sites/reliefweb.int/files/resources/OCHA_OP17_climate%20change_online.p](https://reliefweb.int/sites/reliefweb.int/files/resources/OCHA_OP17_climate%20change_online.pdf)\n[df](https://reliefweb.int/sites/reliefweb.int/files/resources/OCHA_OP17_climate%20change_online.pdf)\n\n\n12\n\nMention: \"MapX data\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"The global project is accessible through this project platform.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "reliefweb", "source_key": "reliefweb:000297:14:0", "occurrence_id": "1378d963845887425651783c", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: Southeast, the second main source is NGOs, it is municipalities in the Aegean, Social Assistance\n\nand Solidarity Foundations in Marmara and UNHCR for Central Anatolia & Other region.\n\n\n**Minimal differences were identified in terms of access to assistance by female versus male**\n\n**heads of households.** Accordingly, 55% of female head of households receive assistance\n\ncompared to 52% of male head of households. After ESSN and CCTE, female heads of\n\nhouseholds receive the most assistance through UNHCR cash programmes.\n\n\nDifferences in distribution of assistance per geographical location were also identified. Assistance\n\nis mostly provided in the Aegean where 68% confirmed receiving support, followed by Southeast\n\n(54%), Central Anatolia & Other (49%) and Marmara (48%).\n\n### Access to Basic Needs and Hygiene Items\n\n##### Access to Basic Needs\n\n\nSurvey findings indicate that **88% of respondents are not fully able cover their monthly**\n\n**expenses and basic household needs.** Only 12% expressed being able to cover their needs in\n\nfull through existing sources of income. The most socio-economically vulnerable populations\n\ngroups are Afghans and Iraqis, with 98% and 93% respectively stating they were either not or\n\nonly partially able to cover their basic needs.\n\n\nFrom a gender perspective, differences in socio-economic vulnerability were identified.\n\nAccordingly, **53% of female headed households, compared to 43% of male headed**\n\n**households, are unable to cover their monthly expenses.** It is also noted that the expenditure\n\nof male headed households is 15% higher compared to female headed households.\n\n\nNotable differences between geographical areas were also identified in terms of respondents’\n\nability to cover monthly expenses. While in the Central Anatolia & Other region, 16% are fully and\n\n49% are partially able to cover their expenses; only 9% are fully and 35% are partially able to\n\ncover expenses in the Marmara region.\n\nMention: \"Access to Basic Needs\n\n\nSurvey\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"Its results give the share unable to cover monthly expenses.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "reliefweb", "source_key": "reliefweb:000324:12:1", "occurrence_id": "ac182820e644c01319cf7030", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: desplazamiento-masivo-y-restricciones-la-movilidad-en-catatumbo-norte-de-santander?_gl=1*10u96yb*_ga*NDIwMjM2MTgyLjE3MjM0NzIyMDc.*_ga_E60ZNX2F68*MTc0MTg3NjEwOS40NC4xLjE3NDE4Nzc0NjcuNTUuMC4w)\n[Santander)](https://reliefweb.int/report/colombia/colombia-reporte-de-situacion-no-02-necesidades-humanitarias-por-desplazamiento-masivo-y-restricciones-la-movilidad-en-catatumbo-norte-de-santander?_gl=1*10u96yb*_ga*NDIwMjM2MTgyLjE3MjM0NzIyMDc.*_ga_E60ZNX2F68*MTc0MTg3NjEwOS40NC4xLjE3NDE4Nzc0NjcuNTUuMC4w)\nviii Ibid.\nix [Governorate of Norte de Santander, PMU Balance Catatumbo, Bulletin N°53 of 17/03/2025.](https://x.com/GoberNorte/status/1901945509239025976/photo/1)\n[x UNODC, Monitoring Report on Territories affected by Coca Cultivation 2022.](https://www.unodc.org/documents/colombia/2023/septiembre-9/INFORME_MONITOREO_DE_TER\n\nMention: \"Monitoring Report on Territories affected by Coca Cultivation 2022\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"Son suivi décrit les territoires affectés par les cultures illicites.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "reliefweb", "source_key": "reliefweb:000327:1:0", "occurrence_id": "a2f409542c636fc6444624d5", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: RECOMMENDATIONS FOR SUSTAINABLE ACCOMMODATION CENTRES IN ROMANIA\n\n## Executive Summary\n\n\n\nFollowing the full-scale invasion of Ukraine by\nthe Russian Federation that began on February\n24, 2022, over 175,000 refugees from Ukraine\nregistered for Temporary Protection in Romania1.\nIn response, the Government of Romania has\nprovided a housing support through various\nprogrammes ensuring the basic needs of refugees\nfrom Ukraine are met, initially through the 50/20\nProgramme (Emergency Ordinance no. 15/2022)\nand then with the transition to established\nprogrammes on 1 May 2023 that differentiated\nlump-sum allowances for holders of temporary\nprotection to cover accommodation and food\ncosts2. On 28 June 2024, a new ordinance3,\nEO No. 96/2024, was adopted, introducing\ntemporary housing support for newly arrived\nrefugees for three to four months and removing\nlegal barriers preventing access to social\nprotection services. Refugees who received\ntemporary protection before July 1, 2024, are\nentitled to social benefits, including child\nallowances and unemployment benefits, while\nthose receiving temporary protection after that\ndate would have access to a one-time,\nfour-month lump-sum allowance before\ntransitioning to the said benefits.\n\n\n\nWhile these programmes aim to support basic\nneeds, findings from the several assessments\nconducted in the past years reveal persistent\nhousing challenges, underscoring the growing\nfinancial strain and increased reliance on\ncollective centres. Thus, the 2023 Multi-Sector\nNeeds Assessment (MSNA)4 and the 2024 Social\nand Economic Insights Survey (SEIS)5 reveal\nsignificant trends and challenges faced by\nUkrainian refugees in Romania regarding the\nhousing situation. In 2023, 4% of refugees lived\nin collective centres, with an additional 8%\nsharing housing or residing in hotels or hostels.\nBy 2024, the percentage of refugees living in\ncollective centres increased to 7%, though the\nmajority (93%) continued to live independently.\nA marked change occurred in refugees' ability to\ncover housing costs. In 2023, 78% could manage\nrent and utilities though many\n\nMention: \"2023 Multi-Sector\nNeeds Assessment\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"Its results describe growing financial pressure.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "reliefweb", "source_key": "reliefweb:000327:1:0", "occurrence_id": "c63b0bf59dbee8f0c3a5f59a", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: RECOMMENDATIONS FOR SUSTAINABLE ACCOMMODATION CENTRES IN ROMANIA\n\n## Executive Summary\n\n\n\nFollowing the full-scale invasion of Ukraine by\nthe Russian Federation that began on February\n24, 2022, over 175,000 refugees from Ukraine\nregistered for Temporary Protection in Romania1.\nIn response, the Government of Romania has\nprovided a housing support through various\nprogrammes ensuring the basic needs of refugees\nfrom Ukraine are met, initially through the 50/20\nProgramme (Emergency Ordinance no. 15/2022)\nand then with the transition to established\nprogrammes on 1 May 2023 that differentiated\nlump-sum allowances for holders of temporary\nprotection to cover accommodation and food\ncosts2. On 28 June 2024, a new ordinance3,\nEO No. 96/2024, was adopted, introducing\ntemporary housing support for newly arrived\nrefugees for three to four months and removing\nlegal barriers preventing access to social\nprotection services. Refugees who received\ntemporary protection before July 1, 2024, are\nentitled to social benefits, including child\nallowances and unemployment benefits, while\nthose receiving temporary protection after that\ndate would have access to a one-time,\nfour-month lump-sum allowance before\ntransitioning to the said benefits.\n\n\n\nWhile these programmes aim to support basic\nneeds, findings from the several assessments\nconducted in the past years reveal persistent\nhousing challenges, underscoring the growing\nfinancial strain and increased reliance on\ncollective centres. Thus, the 2023 Multi-Sector\nNeeds Assessment (MSNA)4 and the 2024 Social\nand Economic Insights Survey (SEIS)5 reveal\nsignificant trends and challenges faced by\nUkrainian refugees in Romania regarding the\nhousing situation. In 2023, 4% of refugees lived\nin collective centres, with an additional 8%\nsharing housing or residing in hotels or hostels.\nBy 2024, the percentage of refugees living in\ncollective centres increased to 7%, though the\nmajority (93%) continued to live independently.\nA marked change occurred in refugees' ability to\ncover housing costs. In 2023, 78% could manage\nrent and utilities though many\n\nMention: \"2024 Social\nand Economic Insights Survey\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"Its trends describe hardships of refugees in collective centres.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "reliefweb", "source_key": "reliefweb:000352:24:0", "occurrence_id": "a49d10dc385966cf7e386b9e", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: con algún tipo de discapacidad.\n\n\n**Atencion Diferencial por tipo de poblacion RENEC**\n\n**UDAPV 2009 - 2010**\n\n|TIPO DE POBLACIÓN|Col2|Col3|Col4|Col5|Col6|\n|---|---|---|---|---|---|\n|**AÑO**|**AFRO**|**INDÍGENA**|**CAMPESINO**|**OTROS**|**POBLACIÓN**
**ATENDIDA**|\n|2009|47,856|40,072|59,450|22,106|169,484|\n|% Participación|28%|24%|35%|13%|100%|\n|2010|50,013|18,078|42,287|45,834|156,212|\n|% Participación|32%|12%|27%|29%|100%|\n|TOTALES
2009 - 2010|97,869|58,150|101,737|67,940|325,696|\n|% Participación|30%|18%|31%|21%|100%|\n\n\n\n**Fuente: Estadísticas UDAPV con corte a diciembre 31 de 2010**\n\n\n5% superan los 60 años.\n\n\n27\n\nMention: \"Estadísticas UDAPV\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"Las cifras de participación provienen de este registro con corte a la fecha.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "reliefweb", "source_key": "reliefweb:000354:8:1", "occurrence_id": "cdc30bfc8f39cd3ce6f2e70a", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: . Restriction of movement for women and girls may limit their\n\n**health services**\n\naccess to health services, while lack of female providers for\nreproductive health services, though improved is also a barrier. HAUS **52% refugees know they**\n2016 11 [^11: Health Access and Utilization Survey, UNHCR 2016] have also shown that refugees have trouble accessing health **can be assisted through**\nservices when only 30% of those who need health services actively **UNHCR partner clinics if**\nsought services. **they can’t access**\n\n**government health services**\n\nRefugees continue to cite lack of **information on health services** as a\nmajor problem. HAUS Survey demonstrated that only 70% of\nrespondents in urban setting aware of subsidized access to public health services while 52% were\naware of free access through UNHCR supported services. Only 47% of urban refugees were able to\ndetect the nearest clinic.\n\n**Secondary and tertiary care** requires a continued high level of funding to ensure access to essential\ncare such as normal and assisted deliveries, caesarean sections, war injuries, congenital\nabnormalities including cardiac abnormalities and renal failure. Costly complex treatments such as\ncertain types of cancer cannot be supported with available resources necessitating difficult choices\nrelating to resource allocation. In particular, access to critical reproductive health services has been\nimpacted by the withdrawal of free services.\n**The MoH** ’s critical role in providing refugee health services needs to be recognized and supported.\nFacilities in areas hosting large numbers of refugees are often overburdened. HAUS survey\nrevealed an increase in percent of Syrians who sought care at MOH facilities in 2016 (28% in first\nfacility and 57% in second facility) compared to 2015 (23.9 in first facility and 42.9 in second\nfacility). This manifests in shortages of medications – especially those for chronic diseases – and\nbeds, overworked staff and short consultation times.\n\nMention: \"HAUS Survey\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"Shows only 70 percent of city dwellers know of subsidised access.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "reliefweb", "source_key": "reliefweb:000364:3:1", "occurrence_id": "8434de38adbd0a62642b52d9", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: men and boys.” 6 “We are appalled by reports of women and girls being sold at slave\nmarkets in areas controlled by RSF forces and other armed groups, including in North Darfur,” UN experts said. 7\nThe experts also expressed concern about the increase in child, early and forced marriage, reportedly a result of\nfamily separation, and gender-based violence, including rape and unwanted pregnancies. 8\n\n\n_3_ [Situation Sudan situation (unhcr.org)](https://data.unhcr.org/en/situations/sudansituation)\n\n_4_ _[Sudan: Disaster before us- GBV situational update as of 1 April 2024](Sudan:%20Disaster%20before%20us-%20GBV%20situational%20update%20as%20of%201%20April%202024)_\n\n_5 The_ Human _Rights Council on 11 October 2023, through resolution A/HRC/RES/54/2 decided to establish an independent international fact-finding mission for_\n_the Sudan,_ [Independent International Fact-Finding Mission for the Sudan | OHCHR](https://www.ohchr.org/en/hr-bodies/hrc/ffm-sudan/index)\n_6_ https://www.ohchr.org/en/hr-bodies/hrc/ffm-sudan/indexInvestigators: Disregard for human rights, law drives crisis in Sudan\n\n_7_ [Sudan: Trafficking for sexual exploitation and recruitment of children\n\nMention: \"Situation Sudan situation\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"The situation page assembles the regional figures.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "reliefweb", "source_key": "reliefweb:000381:9:1", "occurrence_id": "796955188903db0bca6465b5", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: United \nStates of America, France, Germany, Sweden, and Canada), only Sweden features among the top ten \nwhen compared against population size. But all five feature when compared against GDP (PPP) per capita. \nThis may be explained by the relatively large variation in national population size among the industrial-\nized countries. The top five destination countries have a significantly larger population size compared to \nCyprus, Malta, or Liechtenstein. In the case of the GDP (PPP) per capita ratio, the countries included can be \nconsidered as all having highly developed economies and the variation in GDP figures between them is not \nthat significant. With this important difference in mind, the GDP indicator might be more meaningful and \ninteresting when making comparisons among these 44 countries.\n15\tIn order to compare countries, the Purchasing Power Parity (PPP) GDP is considered (Source: International Monetary Fund, World Economic \nOutlook Database, May 2010). Source for national population: United Nations, Population Division, World Population Prospects: The 2008 \nRevision, New York, 2009.\n16\tFor the purposes of this type of analysis, the number of asylum applications registered over a five-year period has been considered to account \nfor some extreme fluctuations in the values.\n17\tAmong the 44 countries included in this report, the number of asylum-seekers per 1 USD GDP (PPP) per capita appears as rather modest when \ncompared to the ‘burden’ developing countries shoulder in receiving asylum-seekers. For instance, Ethiopia and South Africa, two major asylum-\nseeker receiving countries with 22,200 and 222,000 asylum applications respectively registered in 2009, received 26 and 23 asylum-seekers \nrespectively per 1 USD GDP (PPP) per capita during 2009 (Source: 2009 Statistical Yearbook, UNHCR, Geneva).\nCyprus\n24.2\n19.1\n15.2\n14.2\n11.1\n8.8\n7.8\n7.5\n6.8\n5.4\nMalta\nSweden\nLiechtenstein\nNorway\nSwitzerland\nAutria\nGreece\nBelgium\nLuxembourg\n\nMention: \"World Economic \nOutlook Database\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"Its purchasing power parity gross domestic product figures.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "reliefweb", "source_key": "reliefweb:000381:9:1", "occurrence_id": "98616173fb7c0f0a8340ddb0", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: United \nStates of America, France, Germany, Sweden, and Canada), only Sweden features among the top ten \nwhen compared against population size. But all five feature when compared against GDP (PPP) per capita. \nThis may be explained by the relatively large variation in national population size among the industrial-\nized countries. The top five destination countries have a significantly larger population size compared to \nCyprus, Malta, or Liechtenstein. In the case of the GDP (PPP) per capita ratio, the countries included can be \nconsidered as all having highly developed economies and the variation in GDP figures between them is not \nthat significant. With this important difference in mind, the GDP indicator might be more meaningful and \ninteresting when making comparisons among these 44 countries.\n15\tIn order to compare countries, the Purchasing Power Parity (PPP) GDP is considered (Source: International Monetary Fund, World Economic \nOutlook Database, May 2010). Source for national population: United Nations, Population Division, World Population Prospects: The 2008 \nRevision, New York, 2009.\n16\tFor the purposes of this type of analysis, the number of asylum applications registered over a five-year period has been considered to account \nfor some extreme fluctuations in the values.\n17\tAmong the 44 countries included in this report, the number of asylum-seekers per 1 USD GDP (PPP) per capita appears as rather modest when \ncompared to the ‘burden’ developing countries shoulder in receiving asylum-seekers. For instance, Ethiopia and South Africa, two major asylum-\nseeker receiving countries with 22,200 and 222,000 asylum applications respectively registered in 2009, received 26 and 23 asylum-seekers \nrespectively per 1 USD GDP (PPP) per capita during 2009 (Source: 2009 Statistical Yearbook, UNHCR, Geneva).\nCyprus\n24.2\n19.1\n15.2\n14.2\n11.1\n8.8\n7.8\n7.5\n6.8\n5.4\nMalta\nSweden\nLiechtenstein\nNorway\nSwitzerland\nAutria\nGreece\nBelgium\nLuxembourg\n\nMention: \"World Population Prospects\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"The revision of the outlook gives the national populations.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "reliefweb", "source_key": "reliefweb:000386:4:0", "occurrence_id": "cb366faa49688a6a46b9e5d0", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: **SOUTH SUDAN** | March 2025\n\n\n**Threats and Contributing Factors**\n\n\nThe root causes of GBV are deeply embedded in cultural and social norms that\nperpetuate gender inequality and power imbalances. These norms contribute to\npatriarchal structures that often position men as superior, thereby increasing the\nlikelihood of violence. Lasting economic decay perpetuates poverty and insecurity,\nheightening tensions within gender relations and leading to increased instances of\nsexual and physical abuse. Physical violence is the most reported type of GBV accounting\nfor 32% followed by sexual violence (rape and sexual assault) constituting 29% of all\nreported incidents of GBV in South Sudan (2024 GBVIMS).\n\n\nFurthermore, inter/intra-communal violence linked to border disputes, cross-border\nviolence, cyclical and retaliatory attacks, as well as ethnic polarization remained the\nprimary source of subnational violence, accounting for 83% of survivors of gender-based violence. The weak rule of law and\ninadequate access to justice further enable harmful practices, diminishing accountability for perpetrators. Concurrently, seasonal\nfloods as a consequence of climate shocks, contribute to the displacement of communities, further exposing vulnerable populations\nto GBV-related risks.\n\n\nFinally, limited access to education and information perpetuates some of the cultural narratives that undermines women's roles,\nwhile overcrowding inside the IDP camps and settlements further exaggerates the environment for gender-based violence. Longdistance travel for women and girls, driven by essential family responsibilities on fetching firewood and/or water outside of inhabited\nareas, exposes them to heightened risks of attacks, rape, and other physical abuses **,** particularly in areas lacking sufficient resources\nand social infrastructure.\n\n\n**Main Consequences**\nThe main effects of the GBV in South Sudan are profound and far-reaching, impacting individuals and communities alike. Survivors\noften experience severe psychological trauma, which can lead to emotional distress and, in extreme cases, suicide. The physical\nconsequences are equally alarming, with many suffering from injuries\n\nMention: \"GBVIMS\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"Its records give the share of reported incidents.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "reliefweb", "source_key": "reliefweb:000391:3:1", "occurrence_id": "0ced7bfe2d5d0282cb6c002c", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: . UNHCR will continue to periodically survey refugees to understand\ntheir plans, concerns and needs while ensuring that these inform the planning and programming\nprocess for assistance.\n\n### **POSITION ON RETURN AND PROTECTION CONSIDERATIONS**\n\nAll refugees have the fundamental human right to return in safety and dignity to their country of origin\nat a time of their own choosing. This is codified in several international instruments, including the\n_Universal Declaration of Human Rights_ (Art. 13) and the _International Covenant on Civil and Political_\n_Rights_ (Art. 12). Refugee return should be based on a voluntary, free and informed decision. It should\nnot be coerced either overtly through forced return, or indirectly through changes of policies that\nrestrict refugee rights or by limiting assistance to refugees in the country of asylum which in effect\naffects refugees’ ability to take free decisions. 8 [^8: While this document focuses on an operational framework as related to _voluntary_ return of refugees, also recalled is the\nprinciple of _non-refoulement_, a rule of international customary law. The essence of the principle is that a State may not\noblige a person to return to a territory where s/he may be exposed to persecution.]\n\nAligned with the _CPSS_, this operational framework covers two phases of refugee return:\n\n- _Phase 1 - Self-organized/spontaneous return_ : During Phase 1 (current phase), refugees are\nreturning in relatively small numbers in a self-organized manner or in movements not organized\n\n5 See also: UNHCR, _Comprehensive Protection and Solutions Strategy: Resettlement and Complementary Pathways_ (April\n2018).\n~~6~~ UNHCR, _Fifth Refugee Perceptions and Intentions Survey (Nov. 2018 – Jan. 2019)_ . Publication forthcoming.\n7 _Ibid._\n8 While this document focuses on an operational framework as related to _voluntary_ return of refugees, also recalled is the\nprinciple of _non-refoulement_, a rule\n\nMention: \"Refugee Perceptions and Intentions Survey\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"Its fifth round covers this field window.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "reliefweb", "source_key": "reliefweb:000361:4:0", "occurrence_id": "7999cd7080e05e55e5998154", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: Regional Protection Working Group – West and Central Africa\n\n\n**GBV prevention and response** services have been particularly affected across the region. The closure of safe\nspaces, One Stop Centers and mobile clinics, and the interruption of case management services, including\nmedical care and psychosocial support have left over 450,000 people in **Mali** (especially Menaka region) and\nmore than 12,000 people in **Burkina Faso** without support and exposed to negative coping mechanisms. In\n**Niger**, GBVIMS data show a 48% decrease in reported GBV cases during the first quarter of 2025 compared to\n2024 mostly due to the sudden interruption of identification and response services, specifically in the regions\nof Diffa, Maradi, Tillabéri and Tahoua. In **Chad**, where more than 15% of GBV actors had to interrupt or suspend\nGBV programmes due to funding cuts, GBVIMS data show that 59% of identified GBV survivors were unable to\naccess medical services in the first quarter of 2025. In the **Central African Republic**, only 21% of the 65\nlocalities identified as GBV intervention zones retained in the HNRP 2025 are covered by GBV services. In\nrefugee hosting areas like Birao, Sam-Ouandja, Bambouti, where two clinics closed, tens of thousands of\npersons, mainly women and girls, lost access to essential sexual and reproductive health and critical GBV\nsupport, including rape management and psychosocial services.\n\n\nThe impact on children is equally alarming. The disruption in **child protection** **services**, such as **case**\n**management, mental health and psychosocial support** as well as **parenting programs** exposes out-of-school\nchildren, unaccompanied and separated children and children who have experienced human right violations\nto\n\nMention: \"GBVIMS data\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"Its records show a fall in reported cases in the first quarter.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "reliefweb", "source_key": "reliefweb:000434:48:1", "occurrence_id": "e90796488eb0a28e75f0431a", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: is not a term that has an official definition, but is employed in this report to refer to a\nperson who has been living outside his or her country of origin as a refugee for more than 20 years,\nincluding any children born in exile who hold derivative refugee status. The term is used to provide greater\nclarity on the populations of concern for this study, which focuses on those who have held refugee status\nfor much longer than the five-year period employed by UNHCR for statistical purposes in reporting on\n“protracted refugee situations” (see entry below).\n\n##### Protracted refugee situations\n\n\nThere is no definition of protracted refugee situations in international law. UNHCR’s Executive Committee\n(ExCom) adopted a conclusion in 2009 that defined a protracted refugee situation as a situation where\nrefugees have been in exile “for five or more years after their initial displacement, without immediate\nprospects for implementation of durable solutions”. 107 [^107: ‘Conclusion on Protracted Refugee Situations, No. 109 (LXI) – 2009’, UNHCR Executive Committee, 61st session,\nExtraordinary Meeting, 8 December 2009 available with other resources on protracted refugee situations collected\nat [https://www.unhcr.org/research/eval/4a1d43986/protracted-refugee-situations.html. See also discussion in](https://www.unhcr.org/research/eval/4a1d43986/protracted-refugee-situations.html)\nJames Milner, ‘Protracted Refugee Situations’, in _The Oxford Handbook of Refugee and Forced Migration Studies_,] For statistical purposes, UNHCR reports on\n\n\n104 See definition at: [https://unstats.un.org/legal-identity-agenda/, based on Principles and Recommendations for a](https://unstats.un.org/legal-identity-agenda/)\nVital Statistics System, Revision 3, UN Department of Economic and Social Affairs, 2014, para 279.\n[https:/\n\nMention: \"Vital Statistics System\""}, {"role": "assistant", "content": "{\"role\": \"supporting\", \"usage_action\": \"source\", \"summary\": \"Its third-revision principles and recommendations are authoritative.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "reliefweb", "source_key": "reliefweb:000458:2:2", "occurrence_id": "f9fd1cdb9ff8ea598df7a411", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: care services.\n\n\n**783,796** women and girls accessed\nsexual and reproductive health\nservices.\n\n\n\n**76,258** refugees and other people\nof concern provided with mental\nhealth and psychosocial support\nservices.\n\n\n**11** country operations reported all\ngeographic areas inhabited by people\nof concern were reached by COVID-19\ninformation campaigns.\n\n\n\n**88,028** children (6-59 months)\nadmitted for treatment of moderate\nacute malnutrition.\n\n\n**35,359** children (6-59 months)\nadmitted for treatment of severe acute\nmalnutrition.\n\n\n\n**323,770** children and youth\nsupported with distance/home-based\nlearning.\n\n\n**560,339** refugee children and\nyouth out of school due to mandatory\nschool closures.\n\n\n\n**82** UNHCR GLOBAL REPORT 2020 UNHCR GLOBAL REPORT 2020 **83**\n\nMention: \"UNHCR GLOBAL REPORT 2020\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"Ses chiffres décrivent les enfants privés de scolarisation par les fermetures.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "reliefweb", "source_key": "reliefweb:000476:5:1", "occurrence_id": "eccb2ab095f950d867269d27", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: cash assistance and support_\n_for example to cover the costs of prothesis, wheelchairs…”_\n\n\n_Participant of a focus group discussion in Opatovská Nová Ves_ 53 [^53: UNHCR, IOM, WHO, UNICEF (2024), Slovakia: Multi-Sector Needs Assessment 2023 - Annex Report on Persons with Disabilities - June 2024, p.\n4.]\n\n\nThe MSNA indeed confirmed lower levels of employment in refugee households with a member with\ndisability compared to other refugee households. 54 [^54: UNHCR, IOM, WHO, UNICEF (2024), Slovakia: Multi-Sector Needs Assessment 2023 - Annex Report on Persons with Disabilities - June 2024.] Additionally, allowing their access to forms of\nsupport that are currently tied to the possession of a Slovak disability card (which Temporary Protection\nholders cannot obtain) —e.g. discounted transportation fares, access to public services at no or reduced\ncost, or special labor conditions— would also importantly enhance their protection and inclusion.\n\n\nAccording to the Protection Profiling and Monitoring data, 35% of the refugees surveyed between\nJanuary and March 2024 applied for some form of State-provided social protection benefits for\nvulnerable groups. Among those who applied, 90% did not report facing challenges with access. Among\nthe smaller portion (10%) who did, the language barrier was the most reported challenge (49%), followed\nby long waiting times (21%), being considered ineligible (13%), or lack of necessary documents (10%). 55 [^55: UNHCR (2024), Regional Protection Profiling and Monitoring: Protection Risks and Needs of Refugees from Ukraine.]\n\n\nUNHCR, drawing from its partners' counseling and support in numerous individual cases, noted\nchallenges faced by some refugees with disabilities in relation to their access to Disability Allowance for\nRefugees. The Slovak Office of the Commissioner for Persons with Disabilities highlighted several\nsystemic issues, including overly strict eligibility criteria\n\nMention: \"Protection Profiling and Monitoring data\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"Its entries indicate requests for forms of status over the period.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "reliefweb", "source_key": "reliefweb:000526:13:1", "occurrence_id": "1eab2fb74173d8afcd104ce5", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: delivery of humanitarian assistance. Elsewhere across the country intercommunal violence and rising criminality continue to disrupt humanitarian\nactivity. There are also reports that bureaucratic impediments on humanitarian actors are due to interference by local authorities on the ground.\nThere have also been regular demands for jobs by local youth groups in\nBentiu, Renk, Pibor and Melut, which at times have led to protests and\nviolence against humanitarian assets.\n\nIn Afghanistan, data collected by the Humanitarian Access Group (HAG)\nshows that the total number of access related incidents has increased by\n23 %, from 336 incidents in Q4 2020 to at least 436 incidents recorded\nduring Q1 2021. This includes incidents of violence and threats against\nthe humanitarian personnel as well as interference in humanitarian\nprogramming.\n\nWhile in some contexts restrictions on movement, previously in place to\nlimit the spread of Covid-19, have been lifted, in others contexts, movement restrictions remain. For example, in Colombia, certain parts of the\ncountry are only accessible to humanitarian missions considered as\nessential.\nWhile in some contexts restrictions on movement, previously in place to\nlimit the spread of Covid-19, have been lifted, in others contexts, movement restrictions remain. For example in Colombia, certain parts of the\ncountry are only accessible to humanitarian missions considered as\nessential.\n\nMention: \"data collected by the Humanitarian Access Group\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"Its entries show a rise in access incidents.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "reliefweb", "source_key": "reliefweb:000529:1:0", "occurrence_id": "a0c5fe189d22fd4c73d80c3e", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: Based on the results of the first iteration, the project developed a\nstandardized information product that was then tested to\nunderstand perceptions (sentiment) of refugees and migrants\nfollowing the 2016 terrorist attacks in Nice, France (14 July),\nMunich, Germany (22 July), and Berlin, Germany (18 December).\nThis second iteration measured the volume of Tweets that either\nblamed, or defended refugees and migrants in four languages:\nEnglish, French, Greek and German.\n\n\nOverall, findings revealed a low number of tweets that blamed\nrefugees and migrants for the attacks 6% (Nice), 11% (Munich),\nand 5% (Berlin) respectively. In addition, a large number of tweets\nrelated to the terrorist attack in Berlin (7%) expressed explicit\nsupport for refugees and migrants, condemning racism and\nxenophobia.\n\n\n_Figure 2: Expression of xenophobic sentiment after the terrorist attacks in Nice and_\n_Munich_\n\n\nIt is important to note that while the percentage of posts blaming\nrefugees and migrants for the terrorist incidents in the three cities was\nlow, it is still representative of hundreds of thousands, to several\nmillions tweets: 0.2M (Nice), 6.4M(Munich), and 17.6M(Berlin).\n\n## **CONCLUSIONS**\n\n\nFindings demonstrated that data from social media, in this instance\nTwitter data, can be used to monitor protection issues and the safe\naccess to asylum of migrants and refugees in near real-time. This\ninformation was used and continues to be used by UNHCR to develop\ncommunication strategies to mitigate potential correlations between\nattacks and the arrival of migrants and refugees.\n\n\nWorking with social media requires a dynamic mindset, where a\nproject may need to adapt and change its initial scope, as\ndemonstrated above. The limitations of the first iteration and the\nlessons learned throughout the course of the project helped reshape\nits purpose.\n\n\nIn addition, while these results provide interesting insights into the way\npeople perceive issues\n\nMention: \"Twitter data\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"Drawn from social media, it allows protection issues to be tracked.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "reliefweb", "source_key": "reliefweb:000539:17:2", "occurrence_id": "872cf6bfa0e3a39415e2f847", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: Working Group analysis, June 2025.\n\n108 GBV Area of Responsibility trend analysis, December 2024 to May 2025.\n\n109 GBV Area of Responsibility trend analysis, December 2024 to May 2025.\n\n110 ACAPS, Impact of the conflict on mental health and psychosocial needs in Gaza, September 2024.\n\n111 [OPT Protection Cluster Protection Monitoring Snapshot, June 2025. Gaza Protection Cluster Snapshot: Protection Monitoring | 1 April – 10 June](https://reliefweb.int/report/occupied-palestinian-territory/gaza-protection-cluster-snapshot-protection-monitoring-1-april-10-june)\n\n112 Consultation with Gaza Community Mental Health Program, March 2025.\n\n113 [UNICEF, State of Palestine Humanitarian Situation and Needs, June 2024. 2024-HAC-State of Palestine-revised-June.pdf](https://www.unicef.org/media/158391/file/2024-HAC-State%20of%20Palestine-revised-June.pdf)\n\n114 Atfaluna Society for Deaf Children, Gaza Situation Report 2025, March 2025.\n\n115 Key in-field observations shared by HI during structured consultations, June 2025.\n\n116 Key in-field observations shared by HI during structured consultations, June 2025.\n\n117 Key observations shared through surveys with OPDs in Gaza by the Protection Cluster conducted in May and June 2025.\n\n118 [UNRWA, Protection Brief: Situation of Older Persons in Gaza, 24 June, 2025. Protection Brief: Situation of Older Persons in Gaza | UNRWA](https://www.unrwa.org/resources/reports/protection-brief-situation-older-persons-gaza)\n\n119 Key in-field observations shared by HI during structured consultations, June 2025.\n\n120 [HelpAge International, A lifetime of suffering: The challenges faced by older people in Gaza, 20 February 2024. A\n\nMention: \"OPT Protection Cluster Protection Monitoring Snapshot\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"Its snapshots cover the stated period for protection.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "reliefweb", "source_key": "reliefweb:000619:23:0", "occurrence_id": "407911dc822c0e3e0aec272d", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: _only_ marginalized children. For example, differentiated instruction can benefit all children, but the\nimprovements in learning are particularly pronounced in those children who are most left behind\n[by current education systems (Banerjee et al., 2016). In some cases, a combination of interventions](https://www.nber.org/papers/w22746)\ntargeted at specific marginalized groups and more systemic interventions will be required. For\nexample, targeted finance such as cash transfers can help get girls into school, but systemic interventions to improve teaching may be needed to ensure that all children in school (including girls)\n[are learning (DFID, 2018b). It is also important to note that marginalized children are not only in the](https://assets.publishing.service.gov.uk/government/uploads/system/uploads/attachment_data/file/733765/Steps-to-Success.pdf)\npoorest countries. Large numbers of poor children live in middle-income countries.\n\n**■ Poor and rural communities**\n\n**The vast majority of children in learning poverty come from poor and/or rural households** . In\ncountries participating in the Program for International Student Assessment, differences in attainment\n[between rural and urban setting were mainly explained by socioeconomic differences (Echazarra &](https://www.oecd-ilibrary.org/docserver/8b1a5cb9-en.pdf?expires=1601578642&id=id&accname=guest&checksum=373959997E15A832CE87CF5CF3EF94C2)\n[Radinger, 2019](https://www.oecd-ilibrary.org/docserver/8b1a5cb9-en.pdf?expires=1601578642&id\n\nMention: \"Program for International Student Assessment\""}, {"role": "assistant", "content": "{\"role\": \"supporting\", \"usage_action\": \"source\", \"summary\": \"Participating countries show the achievement gap by setting.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "reliefweb", "source_key": "reliefweb:000650:51:1", "occurrence_id": "880a0e53da325a0a10c6e447", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: Convention as a\nresponse to the post-war European refugee crisis.\nThe compassion shown to Europe’s refugees then\nis barely afforded them now. Those who risk their\nlives attempting the journey to Europe today face\nindifference at best, open hostility at worst. At the\nsame time, countries who do look after refugees\nhave been left to shoulder the burden by their\nsupposed European partners.\n\n\nYet no one watching and reading the stories in\nUNHCR’s annual education report could honestly\ndoubt the desire of these youngsters to see their\nstudies through a full educational cycle. We must\nnot be satisfied with merely helping them to\nsurvive the ordeal of displacement; we must give\nthem the tools to thrive, to be independent,\nself-sufficient and fulfilled individuals.\n\n\nThe time has come for decisive, game-changing\nmeasures to end this neglect. That is why I am\nsupporting UNHCR’s new initiative, the Secondary\nYouth Education Programme, as an effort to rally\nthe international community to this cause. If we are\nto give millions of children, refugees and nonrefugees alike, the chance of an education and the\nopportunity to unlock their potential, innovative\nfinancing projects such this programme,\ncombining the know-how and firepower of the\npublic and private sectors, will play a decisive role.\n\n\n\n52 U N H C R > **S T E P P I N G U P :** **R E F U G E E E D U C AT I O N I N C R I S I S**\n\nMention: \"UNHCR’s annual education report\""}, {"role": "assistant", "content": "{\"role\": \"supporting\", \"usage_action\": \"source\", \"summary\": \"Its accounts evidence young people's desire to finish school.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "reliefweb", "source_key": "reliefweb:000652:3:0", "occurrence_id": "3c37e3093bf768c9d93f000d", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: ### **II. Funding for Protection programming in Yemen**\n\nTraditionally, there is already low funding for protection interventions in Yemen.\nAs of July 2024, the Financial Tracking Services indicates that Protection and\nAoRs are funded by a meager 37 percent of required funds. This underscores\na broader failure to recognize protection as a life-saving activity that requires\nappropriate funding for stand-alone protection programming as well as for\nintegrated approaches.\n\n### **III. Banking Crisis, Recent Security Incidents, and Escalating** **Protection Risks**\n\nYemen’s humanitarian situation is heavily impacted by ongoing security\nincidents, which hinder operational effectiveness, coupled with a banking crisis\nthat has led to severe disruptions and in some cases, funding withdrawal.\n\nThe ongoing banking crisis is placing additional strain on households and\nheightening social tensions, which in turn exacerbates protection risks. This is\nparticularly evident in increased tension among the affected population and\ncommunity networks, increase in incidents of abuse and exploitation, limited\naccess to essential services by vulnerable groups, as reported by protection\npartners.\n\n### **IV. Exacerbated Protection Risks**\n\nProtection partners have reported a significant rise in unmet basic protection\nneeds, as a direct consequence of halted and/or reduced protection services.\nThe delay or suspension of these services has heightened risks for vulnerable\ngroups, leaving them more exposed to exploitation, abuse and neglect.\n\n### **V. The Impact on Protection Activities**\n\nThe banking crisis, combined with the associated deterioration in the security\nsituation, have impacted the implementation of protection programming\nthrough:\n\n1. Reduction, delay and Suspension of critical protection services\n2. Authorities’ increased interference in Protection Programs\n3. Freedom of movement restrictions, increased risks to staff safety\nincluding risk of detention and increase of tensions with the\ncommunities.\n\n\n4\n\nMention: \"Financial Tracking Services\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"Its figures indicate the low share of funding for protection.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "reliefweb", "source_key": "reliefweb:000690:4:1", "occurrence_id": "846247c2b5abc7b9ac03bc4c", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: civilian infrastructure and basic\nstructures (such as health care and education), lack of civil documentation, loss of livelihood\nopportunities and property, and human rights and international humanitarian law violations which in\nturn further exacerbate underlying structural vulnerabilities.\n\n\nIn this regard, the Government presented the Annual Contingency Plan and the interventions\nforeseen to provide protection and assistance to affected populations, including (but not limited to)\nfood assistance, delivery of non-food items and dignity kits, and provision of shelters and\nrehabilitation of damaged infrastructures.\n\n\n**2.** D. Eckstein, V. Künzel, L. Schäfer, Global Climate Risk Index 2021, Germanwatch e.V., January 2021. Available at: [Eckstein, V. Künzel, L. Schäfer,](https://www.germanwatch.org/sites/germanwatch.org/files/Global%20Climate%20Risk%20Index%202021_1.pdf)\nGlobal Climate Risk Index 2021, [Germanwatch](https://www.germanwatch.org/sites/germanwatch.org/files/Global%20Climate%20Risk%20Index%202021_1.pdf) e.V., January 2021. Available at:\n[https://www.germanwatch.org/sites/germanwatch.org/files/Global%20Climate%20Risk%20Index%202021_1.pdf. .](https\n\nMention: \"Global Climate Risk Index 2021\""}, {"role": "assistant", "content": "{\"role\": \"supporting\", \"usage_action\": \"source\", \"summary\": \"Its index feeds the thinking on risk reduction.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "reliefweb", "source_key": "reliefweb:000691:4:3", "occurrence_id": "a7f7f84055765a72e885c4c8", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: protection services in 2024 in points of entry and adjacent reception and transit centres, and\nrefugee camps across the country.\n\n\n**1.** **Points of Entry**\n\n\nAs of the end of February 2024, South Sudan has recorded almost 588,000 arrivals at its points of entry, with the majority\n(79%) being South Sudanese returnees. However, reports indicate an increase in Sudanese refugees entering South Sudan\ncompared to the conflict's onset in April. Notably, 97% of all refugees and asylum-seekers in South Sudan originate from Sudan\n(UNHCR population update, 3 March 2024). Furthermore, by the end of 2023, an estimated 70,000 South Sudanese from\nEthiopia have returned to South Sudan due to insecurity in Ethiopia.\n\n\nPage 5\n\nMention: \"UNHCR population update\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"Its updates give the origin of refugees and asylum seekers.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "reliefweb", "source_key": "reliefweb:000692:2:0", "occurrence_id": "ad367a0b881d36909d146e0b", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: **GBV IMS Steering Committee and GBV IMS Task Force Lebanon**\n\n\nviolence, including rape and sexual assault present the third most reported type of GBV incident with 17\npercent of all incidents reported.\n\n\n**_Intimate Partner Violence (IPV)_**\n\n\n**62 percent** of all GBV incidents were perpetrated by the intimate partner of the survivor which is an\nincrease of IPV by 5 percent compared to Q2 2022. Data extracted from the GBVIMS indicate that both\nadults and children are subjected to IPV, with **11 percent** of female children reporting being subjected to\nviolence by their partner, including married children/ adolescent girls exposed to IPV, marking a 4 percent\nincrease compared to the second quarter of 2022.\n\n\n**_Forced/ Early Marriage_**\n\n\nEarly marriage is the most prominent type of GBV perpetrated against children, constituting **84 percent**\nof the forced marriage incidents reported in this quarter. According to the gender findings of UNICEF 's\nrecent report 8 [^8: United Nations Children’s Fund (2022). “Deprived Childhood”. Accessed at:\n[https://www.unicef.org/lebanon/reports/deprived-childhoods](https://www.unicef.org/lebanon/reports/deprived-childhoods)] on multidimensional child poverty, adolescent girls, regardless of their nationality, shared\nexperiences of harassment in public spaces and restriction of their mobility preventing them from accessing\nservices. Additionally, 22 percent of Syrian girls aged 15-18 who do not attend school report marriage as the\nmain reason behind this. The same report reveals that girls’ right to play is further restricted due to harassment\nand gender norms, as they are more likely to be confined to the home\n\nMention: \"GBVIMS\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"Its extracts give the share of affected adults and children.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "reliefweb", "source_key": "reliefweb:000824:9:4", "occurrence_id": "5dca9b2253ee8395da35ba1f", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: of 95% and a margin of error\nof 10% (unless stated otherwise). Data for the mantika of Sirte is indicative only and should not be\ninterpreted with statistical significance.\n10 NB: As outlined, all findings presented on refugees and migrants are based on a qualitative\nmethodology, based on purposive sampling. Hence, any comparison with findings on the Libyan\npopulation originating from the REACH MSNA should be only treated as indicative and cannot be\ngeneralised to represent overall trends between refugees and migrants and Libyans in the country.\n11 REACH/UNHCR, [Access to cash and the impact of the liquidity crisis on refugees and migrants](http://www.reachresourcecentre.info/system/files/resource-documents/reach_lby_brief_refugees_and_migrants_access_to_cash_june2018.pdf)\n[in Libya, June 2018 and REACH/UNHCR,](http://www.reachresourcecentre.info/system/files/resource-documents/reach_lby_brief_refugees_and_migrants_access_to_cash_june2018.pdf) [Refugees and migrants’ access to resources, healthcare](http://www.reachresourcecentre.info/system/files/resource-documents/reach_lby_report_merf_december_2017_0.pdf)\n[and housing in Libya: Key challenges and coping mechanisms, December 2017.](http://www.reachresourcecentre.info/system/files/resource-documents/reach_lby_report_merf_december_2017_0.pdf)\n[12 See REACH/UNHCR, Access to cash and the impact\n\nMention: \"REACH MSNA\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"validate\", \"summary\": \"Any comparison with its results remains indicative and not generalisable.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "reliefweb", "source_key": "reliefweb:000854:16:0", "occurrence_id": "1162713dbfe5b6db677c52ae", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: Kevin, 11, and his brother Jason, 14, Guatemalan refugees, fled to Mexico to escape violence. In their new school in Saltillo, they are able to pursue their \npassion of robotics and science. ©UNHCR/ENCARNI PINDADO\nCASE STUDY\nMACHINE \nLEARNING\nRobot-mad brothers pursue \nlove of science in new school\nJason and Kevin González* are robot crazy. At \nschool in Guatemala, the brothers signed up \nfor robotics workshops and were encouraged \nto take part in science competitions. \nThe two of them even managed to win first prize in \ntheir category in a national robotics contest. For \nthe science-mad duo, life seemed great. “We had \neverything a kid could want,” says Jason, 14.\n“And all of the sudden, we had \nto leave behind the life we \nknew.”\nLike thousands of refugees from the North of \nCentral America region, Jason, his 11-year-old \nsibling and their father fled the gang-related \nviolence in Guatemala and headed north for \nMexico. \nAccording to UNHCR’s Global Trends report, by \nthe end of 2017 the number of asylum-seekers \nand refugees from the region had reached more \nthan 294,000 – up by 58 per cent from the year \nbefore and 16 times more people than at the end \nof 2011.\nOnce over the border to Tapachula, in southern \nMexico’s Chiapas state, the Gonzalez’s applied for \nrefugee status and the boys set about trying to \nrestart their education. \nBut that was not as easy as abc. “The first school \nwe tried did not accept my kids,” says Andres, the \nboys’ father. “They said they had no spaces, but \nwe felt it had more to do with us being foreigners, \nCentral Americans.”\nEventually, with the support of UNHCR partner \nRET International, a humanitarian organization \nfocused on education, the children were enrolled \nin a public boarding school, where they stayed \nduring the week and went back to their father\n\nMention: \"Global Trends report\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"Its figures describe the evolution of the region's asylum seekers.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "reliefweb", "source_key": "reliefweb:000866:5:0", "occurrence_id": "e581c1641a7d018cdd050f92", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: **102 K** people\nbenefited with\n\n**NFI**\n\n\n\n**227 K** people\n\n**Energy**\n\n\nbenefited with **Shelter**\n\n\n\n\n\n\n\n**935 K** people reached\nby shelter, energy and\nNFI activities during\n2021.\n\n\n\n**94** **health centers** were benefited from repairs,\nenergy improvements and NFIs, providing an\nimportant support to the COVID-19 pandemic\nprevention, including the support for triage and\nvaccination areas. **35** **temporary**\n**collective** centers in border areas (including\nPASIs) were benefited by the response, focusing\non supporting vulnerable people on the\nmove. **78** **community** **centers** and **21**\n**schools** providing protection and essential\nservices to population have been benefited\nthrough shelter, energy and NFI response.\n\n\n\n**US$6.7** millions, funding\nreceived during 2021\naccording to Financial\nTracking Service (FTS).\n\n\n**1106 street solar lamps** were installed in public\nplaces, including the surroundings of\ninstitutions benefited by the response, to\nprovide illumination also preventing associated\nprotection risks. **42 electric systems**, including\nphotovoltaic systems for institutions,\norganizations, community centers and\ncollective shelters, were installed allowing\naccess to basic services for the most vulnerable\npopulation.\n\n\n\nBasic NFI distribution was critical in the\n\n**222** **refugee** **housing** **units** **(RHUs)** were assistance of vulnerable people specially those\ninstalled: 104 RHUs in health centres, 24 in affected by flooding and by armed\ncollective temporary shelters and PASIs, 21 in conflicts. NFIs delivered included **14,037**\nmilitary and civil coordination authority spaces, **portable** **solar** **lamps,**\n\nMention: \"Financial\nTracking Service\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"Its records give the amount received during the year.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "reliefweb", "source_key": "reliefweb:000888:3:1", "occurrence_id": "02af440bb6f86bb5c4f97efc", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: in 2018_** **_1_** (Figure 1\nand Table 1). The United States remained the main G20 destination country with around 2.2 million new\nmigrants arriving in 2018. After a peak above 2.3 million in 2016, migration flows to the United States\ndecreased slightly for the second consecutive year. At 1.4 million, new permanent and temporary migration\nflows to Germany were stable in 2018 and remained higher than in any year prior to 2015. About 60% of\nthese new migrants were citizens of another EU country. Labour migration from Asia to Saudi Arabia is\none of the main migration channels in the G20 an account for a large share of the 1.8 million residence\npermits issued annually.\n\n\n**Figure 1. Recent changes in migration flows to selected G20 countries, 2016-2018**\n\n\n2018 or latest year available % change 2017/2016 % change 2018/2017\n\n\n\n**Millions** **%**\n\n\n\n4\n\n\n\n40\n\n\n\n3\n\n\n2\n\n\n1\n\n\n0\n\n\n- 1\n\n\n- 2\n\n\n\n30\n\n\n20\n\n\n10\n\n\n0\n\n\n- 10\n\n\n- 20\n\n\n\nSource: see Table 1 below.\n\n\n1 Data on international migration flows are not available for all G20 countries and are not systematically\ncomparable. The data presented here are compiled from many different sources, notably based on OECD regional\nmonitoring systems, completed with national sources. They include all types of migration ranging from settlement to\ntemporary migration, including students, but exclude visitors.\n\n\n4\n\nMention: \"OECD regional\nmonitoring systems\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"Completed by national sources to cover all migration types.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "reliefweb", "source_key": "reliefweb:000912:11:0", "occurrence_id": "4903bdb1121e97fe51a21432", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: the main country of origin of asylum-seekers to the\nUnited States of America with 8,700 applications,\nfollowed by Guatemala (7,700), Mexico (7,500),\nHonduras (7,400), and China (7,300).\n\nHungary ranked fourth with 65,400 new asylum\napplications registered during the first half of 2015.\nThis constituted a 13-fold increase compared to\nthe first semester of 2014 (4,800 new applications)\nand a 79 per cent increase compared to the second\n(36,500). A large number of those applying for asylum in Hungary move onward to other countries\nin the European Union, where they are typically\nregistered again as asylum-seekers.\n\nA sharp shift in the composition and dynamics of registered asylum applications in Hungary\nwas observed during the reporting period. The\nfirst quarter of 2015 was dominated by asylum\napplicants originating from Serbia and Kosovo\n(S/RES/1244 (1999)), with more than 22,800 persons lodging such a claim, yet this figure dropped\nto less than 500 during the second quarter.\n\nIn contrast, the second quarter in Hungary witnessed a soaring number of asylum applicants from\nAfghanistan (13,600 claims, up from 4,000 during\nthe first quarter) and the Syrian Arab Republic\n(8,400, up from 2,400). These two countries together accounted for two-thirds of all asylum applications in Hungary during the second quarter.\nOverall, Serbia and Kosovo (S/RES/1244 (1999))\nwas the main place of origin for asylum applicants\nin Hungary during the reporting period (23,300\n\n\n**12** UNHCR Mid-Year Trends 2015\n\n\n\napplications), followed by Afghanistan (17,600), the\nSyrian Arab Republic (10,800), and Iraq (3,200).\n\nAs of December 2015, close to 2.2 million registered Syrian refugees in Turkey benefitted from the\nGovernment’s Temporary Protection Regime. In\n\nMention: \"UNHCR Mid-Year Trends 2015\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"Its figures give asylum seeker origins by period.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "reliefweb", "source_key": "reliefweb:000921:24:0", "occurrence_id": "240b2bd18bfc392dfc028c9a", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: **Governorate of Origin**\n\n\nThose from _Baghdad_ represent 84% in the first quarter of 2007 and 62% in the fourth quarter 2008. Those from\n\n_Ninewa_ increases from 3% in the first quarter 2007 to 18% the last quarter of 2008. Those from _Anbar_ are on\n\naverage 3%, _Basrah_ 4%, _Diyala_ 3% throughout the period.\n\nAll other governorates account for 1% or less of the active caseload.\n\n\nTwo Iraqi refugees during an English learning session at the UNHCR community centre in the Southern suburbs of Beirut.\n\n\n. Iraq Refugees Registration Data Comparative Analysis, 2007-2008. - 24\n\nMention: \"Iraq Refugees Registration Data\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"analyze\", \"summary\": \"Its comparative analysis covers the two stated years.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "reliefweb", "source_key": "reliefweb:000981:0:2", "occurrence_id": "ffc6fd696b7322670e44b458", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: :** **18 m2**(3m x 6m)|\n|**SHELTER DENSITY**
**3.6 m2**per person|**SHELTER DENSITY**
**3.6 m2**per person|\n\n\n**DIRECT COST** **USD** **700**\n\n\n**PROJECT COST** **USD** **1,000**\n\n\n[*IOM Nigeria Displacement Report, Round 41, Baseline Assessment in Northeast Nigeria](https://dtm.iom.int/reports/nigeria-north-east-displacement-report-41-june-2022)\n\n[**Humanitarian Response Plan, Nigeria, 2022 (February 2022)](https://reliefweb.int/report/nigeria/nigeria-humanitarian-response-plan-2022-february-2022)\n\n\n\nthrough cash-for-work programs.\n\n\n\nPROJECT\n\n\nCONTEXT\n\n\n\nPLANNING\n\n\n\nCONFLICT\nTIMELINE JUL JAN MAR APR MAY JUN JUL\n\n\n\nDEC\n\n\n\nhttp://www.3rpsyriacrisis.org/wp-\ncontent/uploads/2018/09/3RP-Regional-Quarterly-Dashboards-June ~~-2018.pdf~~\n\n\n\n**PROTECTION**\n\n**33,739**\n\n\n**72,077**\n\n\n**FOOD SECURITY**\n\n**2,332,690**\n\n\n**5,145**\n\n\n**EDUCATION**\n\n**1,202,905**\n\n\n\ngirls and boys who are receiving specialized child\nprotection services\n\npersons receiving Sexual and Gender-Based Violence\n(SGBV) response services\n\n\nindividuals who receive food assistance (cash, voucher\nor in-kind)\n\nindividuals receiving food & agricultural livelihoods\nsupport\n\n\nchildren (5-17 years, girls and boys) enrolled in formal\ngeneral education\n\n\n\n**1,345** classrooms constructed, established or rehabilitated\n\n\n\n\n\n\n\n\n\n\n\n**BASIC NEEDS**\n\n**2,217,095**\n\n**38,628**\n\n\n\nindividuals receiving core relief items in-kind\n\n\nindividuals receiving unconditional, sector-specific or\nemergency cash assistance\n\n\n\n\n\n**WASH**\n\n\n\n**364,769**\n\n\n\npeople with access to adequate quantity of safe water\nthrough temporary provision\n\n\n\n**168,956** people with access to appropriate sanitation facilities\nand services\n\n\n\n**LIVELIHOODS & SOCIAL\n\nMention: \"inter-agency 3RP dashboards\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"Publient les réalisations sectorielles régionales du plan de résilience.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "reliefweb", "source_key": "reliefweb:001030:12:0", "occurrence_id": "cde742fb763f81d541dd8641", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: **2017 ANNUAL REPORT** Regional Refugee & Resilience Plan 2017-2018\n\n\nenhancing the transparency and competitiveness of pricing, reducing barriers to accessing the best deals and making the most\nof every dollar injected into the Lebanese economy.\n\n\nFood for Training and Food for Asset activities targeting and benefiting both Syrian refugees and host communities fostered social\ncohesion and led to a significant improvement in terms of acceptance, integration and cohabitation as well as social solidarity.\nTo monitor the social cohesion effects of projects in Lebanon and Egypt, a Social Cohesion Score (SCS) was developed through\nthe responses of 477 Syrian, Egyptian and Lebanese individuals engaged in livelihood initiatives. Through answering questions\non inter-community relations, competition over resources and trustworthiness in institutions, the index provided a quantifiable\nassessment of the social cohesion effects of programmes. In 2017, SCS was piloted before the start of livelihood activities and\nfollow up measurements will continue in 2018 to identify areas of underlying tension to be addressed.\n\n\n\n\n\n2 JFO Vulnerability assessment data, December 2017\n3 Including PRS and Syrian refugees at King Abdullah Park who were supported through cash assistance.\n\n\n\n13\n\nMention: \"JFO Vulnerability assessment data\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"Its data identify underlying tensions to address.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "reliefweb", "source_key": "reliefweb:001061:2:2", "occurrence_id": "963bd36d9a0a35de109bfa14", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: refugee self-reliance in food security and\nnutrition. This Joint Strategy represents the fulfilment\nof this recommendation.\n\n\n**1.** UNHCR 2015, UNHCR Global Trends 2014.\n**2.** ‘Durable solutions’ refer to the point when refugees no longer need\ninternational protection, generally after voluntary repatriation, local integration, or resettlement to a third country. Complementary pathways to\nprotection and solutions are being expanded, always with consideration\ngiven to durability.\n**3.** The Solutions Alliance aims to improve the lives of displaced persons and\nthe communities that host them by responding more collaboratively to\ndisplacement and contributing to durable solutions. More information is\navailable at www.solutionsalliance.org\n\n\n\n**3**\n\nMention: \"UNHCR Global Trends 2014\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"Its global trends underpin the strategy described.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "reliefweb", "source_key": "reliefweb:001063:51:8", "occurrence_id": "a92600d9b1b0f15a4c8322a4", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: \n[obtaining-asylum-united-states. Individuals apply for asylum defensively](http://www.uscis.gov/humanitarian/refugees-asylum/asylum/obtaining-asylum-united-states)\nwhen he or she requests asylum as a defense against removal from the U.S.\nIndividuals are generally placed into defensive asylum procedures in one of\ntwo ways: (1) “they are referred to an Immigration Judge by USCIS after they\nhave been determined to be ineligible for asylum at the end of the affirmative\nasylum process,” or (2) they are placed in removal proceedings, as discussed\nabove. Id. Immigration judges hear defensive asylum cases and decide\nwhether the individual is eligible for asylum.\n\n**16** _See, e.g.,_ Decree No. 97-96, 24 October 1996, Law to Prevent, Punish,\nand Eradicate Intrafamily Violence (Guatemala); Decree No. 132-97, 29\nSeptember 1997, the Law on Domestic Violence (Honduras); Decree No.\n902, 5 December 1996, the Law on Intrafamily Violence (El Salvador).\n\n**17** All names of women interviewed for this report have been changed to\npreserve their confidentiality.\n\n**18** UNHCR, Population Statistics Database, “Asylum-Seekers (Monthly\nData)”, _available at_ [http://popstats.unhcr.org/en/asylum_seekers](http://popstats.unhcr.org/en/asylum_seekers)\n\n**19** The word “transgender” is “an an umbrella term for people\nwhose gender identity and/or expression is different from cultural\nexpectations based on the sex they were assigned at birth. Being\ntransgender does not imply any specific sexual orientation. Therefore,\ntransgender people\n\nMention: \"Population Statistics Database\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"Its monthly series cover asylum seekers.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "reliefweb", "source_key": "reliefweb:001064:24:0", "occurrence_id": "d3a020f1d6c75790b23b0aef", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: and greater appreciation of UNHCR’s work within Nairobi’s refugee community (a\nloose concept used in this context to encompass areas beyond the city limits and to\ninclude registered and non-registered refugees, people with pending and rejected\nasylum applications, as well as irregular migrants from refugee-producing\ncountries).\n\n\n**National staff and outreach workers**\n\n\n87. UNHCR has appointed a number of national officers to its evolving urban\nrefugee programme, university graduates whose local origins, knowledge of Nairobi\nand interpersonal skills provide the organization with an invaluable means of\ncommunication with refugees and other stakeholders. They deserve significant credit\nfor the increased visibility and credibility that the organization has been able to\nestablish in the city.\n\n\n88. At the same time, UNHCR has worked with an implementing partner, GTZ, to\nestablish a group of 15 community outreach workers, men and women who are\ndrawn from the different national and ethnic groups to be found amongst Nairobi’s\nrefugee population and who are responsible for outreach activities in different parts\nof the city. This initiative was an outcome of the 2006 Participatory Assessment,\nwhen refugees complained that they had to travel to the Branch Office in order to\naccess the information they needed.\n\n\n89. The outreach workers normally have a degree or diploma, are recruited on a\ncompetitive basis and in accordance with AGDM principles. They are paid a modest\nincentive (around 8,000 shillings a month) which does not require them to have a\nwork permit. GTZ convenes monthly meetings to train the outreach workers on a\nvariety of issues, including how to respond to refugee arrests, how to refer survivors\nof SGBV to appropriate services, and how to identify vulnerable individuals who\nneed special support. They are well known to local police stations and play an\nimportant role in negotiating the release of refugees from detention.\n\n\n90. In the course of this review, it became clear that the community outreach\nworkers provide an important link between UNHCR, partner agencies, civil society\nand local officials.\n\nMention: \"2006 Participatory Assessment\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"An initiative follows from its findings on displacement to the office.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "reliefweb", "source_key": "reliefweb:001072:2:0", "occurrence_id": "3d256ffd2a510092eaa0b370", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: # **Shelter Thematic Report**\n\n### **Objective**\n\nThe report aims to analyze the secondary impacts of shelter issues in Sudan and discuss possible solutions\nleveraging existing capacities. Given the large-scale displacement and pre-existing poor shelter conditions, it is\ncritical to understand how these conditions impact populations amidst evolving conflict dynamics and how best\nto address them.\n\n### **Contextual Background**\n\nIn Sudan, humanitarian needs were at record levels even before the outbreak of the conflict in April 2023. The\ncountry has long faced challenges with internal displacement, stemming from various conflicts and\nenvironmental factors. Internally Displaced Persons (IDPs) have consistently faced poor shelter conditions,\nmarked by overcrowding and inferior housing quality, along with widespread issues like limited privacy,\ninadequate lighting, and constrained access to vital household items. Humanitarian organizations' efforts to\nimprove these conditions have been significantly hampered by funding constraints, with the shelter cluster only\n[43% funded on the revised 2023 HRP (FTS](https://fts.unocha.org/plans/1123/summary) 24/01/2023). Findings from the 2023 HNO identified 2.9 million people\nin need of shelter and NFI assistance prior to the conflict, with three in four Sudanese living in damaged shelters\nand many reporting severe damages that compromised the structural safety of their houses or total structural\ncollapse. Even families with more durable housing options struggled with poor living conditions. Inflation and\nsharp increases in the prices of goods have also reduced families’ purchasing power, limiting their ability to invest\nin shelter repair and maintenance. The most commonly reported shelter issues included leaks, cracked roofs, and\npartial roof collapses. Furthermore, findings from the 2022 MSNA showed that only a quarter of assessed\nhouseholds in the country had the security of tenure which protects tenants from forced eviction. For those living\nin camps and informal settlements, 73% of households reported having only collective\n\nMention: \"2023 HRP\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"Its revised amounts and financing are tracked by the monitoring service.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "reliefweb", "source_key": "reliefweb:001072:2:0", "occurrence_id": "46d6a779ad1bd3913e8078e5", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: # **Shelter Thematic Report**\n\n### **Objective**\n\nThe report aims to analyze the secondary impacts of shelter issues in Sudan and discuss possible solutions\nleveraging existing capacities. Given the large-scale displacement and pre-existing poor shelter conditions, it is\ncritical to understand how these conditions impact populations amidst evolving conflict dynamics and how best\nto address them.\n\n### **Contextual Background**\n\nIn Sudan, humanitarian needs were at record levels even before the outbreak of the conflict in April 2023. The\ncountry has long faced challenges with internal displacement, stemming from various conflicts and\nenvironmental factors. Internally Displaced Persons (IDPs) have consistently faced poor shelter conditions,\nmarked by overcrowding and inferior housing quality, along with widespread issues like limited privacy,\ninadequate lighting, and constrained access to vital household items. Humanitarian organizations' efforts to\nimprove these conditions have been significantly hampered by funding constraints, with the shelter cluster only\n[43% funded on the revised 2023 HRP (FTS](https://fts.unocha.org/plans/1123/summary) 24/01/2023). Findings from the 2023 HNO identified 2.9 million people\nin need of shelter and NFI assistance prior to the conflict, with three in four Sudanese living in damaged shelters\nand many reporting severe damages that compromised the structural safety of their houses or total structural\ncollapse. Even families with more durable housing options struggled with poor living conditions. Inflation and\nsharp increases in the prices of goods have also reduced families’ purchasing power, limiting their ability to invest\nin shelter repair and maintenance. The most commonly reported shelter issues included leaks, cracked roofs, and\npartial roof collapses. Furthermore, findings from the 2022 MSNA showed that only a quarter of assessed\nhouseholds in the country had the security of tenure which protects tenants from forced eviction. For those living\nin camps and informal settlements, 73% of households reported having only collective\n\nMention: \"2023 HNO\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"Its findings identify shelter needs before the conflict.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "reliefweb", "source_key": "reliefweb:001174:73:0", "occurrence_id": "d1eac165c8b903a5b8fced89", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: **Jordan Home Visits Report 2014 - Living in the shadows**\n\n\n###### _“The economy of Syrian refugee households is being pushed_\n\n\n###### _to the brink of disaster. In a context of dwindling support_\n\n\n###### _and a lack of alternatives, more funding will be required_\n\n\n###### _in order to ensure refugee protection and assistance.”_\n\n\n\n\n- Andrew Harper, UNHCR Representative, Jordan\n\n\n\n74\n\nMention: \"Jordan Home Visits Report 2014\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"Ses visites domiciliaires décrivent l'économie des ménages réfugiés.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "reliefweb", "source_key": "reliefweb:001216:2:0", "occurrence_id": "406a2b21e247177131bfe9c4", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: REGIONAL SUMMARIES I **SOUTHERN AFRICA** REGIONAL SUMMARIES I **SOUTHERN AFRICA**\n\n### KEY RESULTS AND TRENDS IN 2020\n\n\n\nUNHCR’S **PROGRAMMATIC** RESPONSE\n\n\n\n\n\n**CHILD PROTECTION**\n\n\n\n**WASH**\n\n\n\n**1,651** unaccompanied or separated\nchildren had a best interests assessment\n\n\n**GENDER-BASED VIOLENCE**\n\n\n\n\n\n**TRENDS** IN RESPONSE\n\n**Cash assistance by sector in Africa | 2016-2020**\n\nBasic needs Seasonal grants Life-saving support Solutions\n\n\n2020\n\n\n2019\n\n\n\n\n\n\n\n\n\n**3,390** gender-based violence incidents\nreported for which survivors received\npsychosocial counselling.\n\n\n**CORE RELIEF ITEMS**\n\n**124,164** households provided with core\nrelief items.\n**68,020** women received sanitary\nmaterials.\n\n\n**HEALTH**\n\n**1.05** under-5 mortality rate (per 1,000\nunder-5s per month) in refugee camps.\n\n\n\n\n\n2018\n\n\n2017\n\n\n2016\n\n\n\nUSD millions\n***Including **$8.8 million** in the **Southern Africa** region **.**\n\n\n\n**Individual registration records | 2016-2020**\n\n\nIndividual registration records in PRIMES proGres v4\nindividuals (5 years and above) with biometric records in PRIMES\n\n\nIn millions\n\n\n\n**Resettlement departures | 2016-2020**\n\n\nIndividuals\n\n\n\n4,000\n\n3,500\n\n3,000\n\n\n2,500\n\n2,000\n\n1,500\n\n1,000\n\n\n\n\n\n2016 2017 2018 2019 2020\n\n\n\n2016 2017 2018 2019 2020\n\n\n\n\n\n\n\n**SHELTER**\n\n**76,547** people of concern received\nemergency shelter.\n**62%** of households lived in adequate\ndwellings.\n\n\n\n\n\n\n\n**19** litres of potable water available on\naverage per person per day in refugee\ncamps.\n**62%\n\nMention: \"PRIMES proGres v4\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"Contient les enregistrements individuels et biométriques sur cette période.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "reliefweb", "source_key": "reliefweb:001316:3:2", "occurrence_id": "5f984fa33f990dcbd50f9cfc", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: راطية40،900( )، السودان744،100( السودان\n. ويف هذه 377،700( )، والعراق383،900( )، وأريترييا458،400( )، وميانامر470،600( ((( )\n\n.البلدان أغلبية سكانية مسلمة، فاملسلمون هم جزء كبري من أعداد الالجئني\n\nتعاين هيئات اإلغاثة من حاجة مزمنة إىل مصادر متويل إضافية لتلبية احتياجات الالجئني. وألنّ\nاملسلمني هم اجلزء األكرب من الالجئني يف العامل، فمن املعقول التطلّع إىل املجتمع املسلم باعتباره\nمليار دوالر 200-20 ، قُدِّر ما منحه املسلمون من األموال بني2008 مصدرًا ممكنًا للتمويل. ويف عام\n\n؛ ويشمل هذا التقدير الصدقة والزكاة.(((سنويًّا\n\n\n\n(اجتاهات منتصف سنة2015 Mid-Year Trends ،املفوضية السامية لألمم املتحدة لشؤون الالجئني 1.\n6. اطُّلِع عىل -4 .) ص2015 ،) (جن\n\nMention: \"Mid-Year Trends\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"Ses tendances de milieu d'année fondent les estimations citées.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "reliefweb", "source_key": "reliefweb:001352:41:0", "occurrence_id": "dc6b84b0e9ea9baaa846e58c", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: DTM Mali – Avril 2021\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n|Régions-Cercles
-Communes|Enfant ( < 18 ans )|Col3|Col4|Col5|Adulte (18 - 59 ans )|Col7|Col8|Personne âgée ( > 59 ans )|Col10|Col11|Total
Femme|Total
Homme|Total
Individus|\n|---|---|---|---|---|---|---|---|---|---|---|---|---|---|\n|**Régions-Cercles**
**-Communes**
|**Ménages**|**F **|**M **|**Total**
**Enfant**|**F **|**M **|**Total**
**Adulte**|**F **|**M **|**Total**
**Personne**
**âgée**|**Total**
**Personne**
**âgée**|**Total**
**Personne**
**âgée**|**Total**
**Personne**
**âgée**|\n|OUELESSEBOUGOU|17|119|11|130|43|11|54|6|4|10|168\n\nMention: \"DTM Mali – Avril 2021\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"Dénombre les enfants et adultes par subdivision administrative.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "reliefweb", "source_key": "reliefweb:001384:31:2", "occurrence_id": "b57802c63e075bcd6838df11", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: \n|**Territoire**|**Collectivité**|KARUBA
|KABAYA|4|0,14%|\n|**Territoire**|**Collectivité**|KARUBA
|KALOBA|5|0,18%|\n|**Territoire**|**Collectivité**|KARUBA
|KANIRO|14|0,50%|\n\n\n\nData Center for IDP Population 32\n\nMention: \"Data Center for IDP Population\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"Publie les décomptes de population déplacée par territoire et collectivité.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "reliefweb", "source_key": "reliefweb:001480:3:1", "occurrence_id": "9b7ec046622238a7f35187c9", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: --|---|\n|**0**
**601**
**592**
**242**
**224**
**184**
**COD**
**UGA**
**ZMB**
**MWI**
**MOZ**|**392**
**311**
**244**
**197**
**COD**
**ZMB**
**UGA**
**ZAF**
**MWI**||\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\nData sources: UNHCR PRIMES.\nFor more information or to contribute, please contact\nUNHCR RBSA DIMA (rsarbdima@unhcr.org)\n\n\n|CUMULATIVE CROSS BORDER MOVEMENTS TREND PER YEAR AND PR|OPORTIONS SINCE 2019
Inward
movements
Intra region
25% movements
48%
Outward
movements
28%
shown are restricted only to movements of a minimum group pe
sylum, due to the change of nationality of some PoCs, country of o
the Congo , COG = Republic of the Congo, SSD- South Sudan, KE|\n|---|---|\n|926
3,276
1,777
2,051
4,755
2,554
Before
2019
2019
2020
\n\nMention: \"UNHCR PRIMES\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"Source unique des données présentées pour ce pays.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "reliefweb", "source_key": "reliefweb:001493:4:6", "occurrence_id": "40fdb419884f65ad42e01286", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: نبغو لامنيمأ مراجعأ وتوتتراتاج تذا **د** اع ات **د** )1 ( اأ **د** اا الردام **د** من التوص عدع ا2022عام\n\nؤول الثجئ ن وإ ش **د** اأ ش **د** تراتاجاأ رإلوعفا األعاءا والتزمت ماوت **د** اعاتذا و فيا المجال واتااك مإلا بأ أك.ر ات **د**\n\nةتإلدرا ععا أك.ر عالاأ لادول و الا اتدتجابأ اعا تذا لذيا التإل ااا ويشدمل كلط وتدع اتدتراتاجاأ لممداأ\n\nبشكل تااعل المنيمأ و فيا المجال لثل **دددددد** او الوال مع الدول تش **دددددد** أل تنماأ قد ا الاجوء بالتش **دددددد**\n\nالمنوا الإلاعمأا\n\n\n\n__________\n\nمتاح على UNHCR, “UNHCR Asylum Capacity Development Evaluation” ) 1(\n\n[.https://www.unhcr.org/media/es/2022/01-unhcr-asylum-capacity-development-evaluation](https://www.unhcr\n\nMention: \"UNHCR Asylum Capacity Development Evaluation\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"Son évaluation sur le développement des capacités d'asile est citée.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "umar_pads", "source_key": "umar_pads:004717:41:2", "occurrence_id": "a19d63c4f881e8aa68b952a8", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: Foundational Urban Infrastructure and Climate Resilience|Col2|\n|---|---|\n|**Person-days of jobs created (Days) **|**Person-days of jobs created (Days) **|\n|Description|Measures short-term employment generated through labor-intensive works under drainage, solid waste management,
urban upgrading, and housing reconstruction activities.|\n|Frequency|Quarterly|\n|Data source|Contractor payrolls; site supervision reports|\n\n\n\n32 Andrianirina, Ratsialonana Rivo; Raserijaona, Gaël; Anand, Aanchal; Teyssier, André. Towards an Urban Land Reform in Madagascar? : Support to Urban\nLand Policy (English). Washington, D.C.: World Bank Group. http://documents.worldbank.org/curated/en/517211592452939643.\n\n\nPage 28\n\n\nOfficial Use Only\n\nMention: \"Contractor payrolls; site supervision reports\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"Source trimestrielle pour l'indicateur d'emploi et de reconstruction.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "umar_pads", "source_key": "umar_pads:000214:17:0", "occurrence_id": "39ba3259890f9fa8f994f5a3", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: **The World Bank**\nLao PDR Civil Registration and Vital Statistics Project (P167601)\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n|No.|Province|Region|Districts
(number)|Population
(number)|CMIS
Phase|Health
Facilities
Ready for
DHIS2a
(number)|NT2 with
Health
Database|Intervention
versus
Control|\n|---|---|---|---|---|---|---|---|---|\n|17|Attapeu|Southern|5|139,628|IV|—|—|Control|\n|16|Saravane|Southern|8|396,942|IV|46|—|Control|\n|18|Sekong|Southern|4|113,048|IV|18||Control|\n\n\n_Note:_ a. Number of health care facilities that can directly access DHIS2 (that have computers, Internet connection,\nand staff with basic computer skills), based on the MOH 2017 data.\nb. Provinces for the nutrition convergence approach activities.\n\n\nPage 13 of 54\n\nMention: \"MOH 2017 data\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"Décrit l'équipement et les compétences informatiques du personnel par province.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "umar_pads", "source_key": "umar_pads:001757:13:3", "occurrence_id": "1df1ad7c9ae376cd0df4b7d3", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: .aspx)_\n_[lieu-thong-ke-ve-tinh-trang-dinh-duong-tre-em-qua-cac-nam.aspx](http://viendinhduong.vn/news/vi/106/61/0/a/so-lieu-thong-ke-ve-tinh-trang-dinh-duong-tre-em-qua-cac-nam.aspx)_ .\n11 General Statistics Office and UNICEF. 2015. Vietnam Multiple Indicator Cluster Survey 2014, Final Report. Ha Noi, Vietnam\n12 General Statistics Office and UNICEF. 2015. Vietnam Multiple Indicator Cluster Survey 2014, Final Report. Ha Noi, Vietnam\n13 General Statistics Office and UNICEF. 2015. Vietnam Multiple Indicator Cluster Survey 2014, Final Report. Ha Noi, Vietnam.\n\n\nPage 9 of 31\n\nMention: \"Vietnam Multiple Indicator Cluster Survey 2014\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"Rapport final sur les indicateurs multiples des enfants.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "umar_pads", "source_key": "umar_pads:002248:52:1", "occurrence_id": "7bda715fab0a5e8b7567dadb", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: security and digital
government foundations
designed to strengthen
cybersecurity
(disaggregated by gender)|Annual
|MICT/DTO
|MICT/DTO progress
reports, outlining
attendance at
cybersecurity training
activities
|MICT/DTO
|\n|Of which female|
||
|||\n|Government Enterprise Architecture
Developed|Government Enterprise
Architecture has been
developed and is
operational|Annual
|MICT/DTO
progress
report /
project data
|MICT/DTO to report on
progress
|MICT/DTO
|\n\n\n\nPage 48\n\nMention: \"project data\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"Rapportees annuellement par la division du developpement des technologies.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "umar_pads", "source_key": "umar_pads:002356:2:2", "occurrence_id": "a263c83d8fe1c0903f6610d3", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: and 1.18 million in Tamil Nadu live with some form of disability (Census**\n**2011). However, some recent studies** **1** **in Tamil Nadu estimate that these figures may just have doubled.** As per\n\n\n1 Rakhi Dandona, Anamika Pandey, Sibin George, G. Anil Kumar, Lalit Dandona, India’s disability estimates: Limitations and way forward, 2019\n\n\nSeptember 29, 2021 Page 3 of 10\n\nMention: \"Census**\n**2011\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"Estime le nombre de personnes vivant avec une forme de handicap.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "umar_pads", "source_key": "umar_pads:004507:48:3", "occurrence_id": "53904ae746ed139cdb28070a", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: the sum of all woman-months worked divided by sum of all person-months worked
|\n|Frequency
|Annual
|\n|Data source
|Civil works contractor timesheets|\n|
Methodology for
Data Collection|
DSC will provide spreadsheet-based analysis of timesheets|\n\n\n\nPage 36\n\nMention: \"Civil works contractor timesheets\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"Somme des personnes-mois travaillées pour l'indicateur annuel.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "umar_pads", "source_key": "umar_pads:000016:11:0", "occurrence_id": "70f50a56cb2f2f2c70fa14a6", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: **The World Bank**\nBalochistan Livelihoods and Entrepreneurship Project (P159292)\n\n\n\n\n\n\n\n10. **A ‘double burden’ on resources has affected development outcomes for refugees and host communities in**\n**Balochistan.** Even-though the country has witnessed average growth rates of four percent in the past decade, these have\nnot led to commensurate growth in the province for four main reasons. First, population density in the province is low,\nat 38 persons per square kilometer which falls to 15 in the rural areas. Given the scattered nature of settlements in\nBalochistan, this implies negligible and cost-ineffective service delivery. Second, resource mobilization at the grassroots\nlevel is particularly constrained and this is exacerbated by, amongst others, lack of skills and training, low awareness\nregarding market opportunities, limited access to finance and high cost of doing business 6 [^6: According to the Sub National Doing Business (SNDB) Report 2010, the capital of Balochistan, Quetta is ranked the lowest across 13\nsurveyed districts and cities.] . Resource mobilization capacity\nof the province is restricted given the low tax base. Third, like most traditional and rural societies, even in Balochistan\nthere is a dominance of consumption expenditure and the emphasis on savings for investment purposes is limited.\nFourth, low capacity and a dearth of qualified human resources in Balochistan hinders service delivery to the poor.\n\n\n11. **Agriculture is the backbone of the economy of Pakistan and Balochistan.** A fifth of the national economy is\nagriculture and accounts for nearly half of the jobs. In recent years more jobs have been created in non-farm sectors like\nmanufacturing and service **sectors** than in agriculture. Agriculture remains the main source of income for 64 percent of\nthe households in the province with 43.4 percent employed in the sector in 2017. Female labor force participation rate\nin Balochistan of 11.3 percent in 2014-2015, is less than half of the national average. Climate change exacerbates extreme\nweather events\n\nMention: \"Sub National Doing Business (SNDB) Report 2010\""}, {"role": "assistant", "content": "{\"role\": \"background\", \"usage_action\": \"source\", \"summary\": \"Sub-national ranking cited for the cost of doing business across districts.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "umar_pads", "source_key": "umar_pads:000016:22:1", "occurrence_id": "a4a156a502357d19a68d72e7", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: Plans (RAP) will be developed, as sub-project locations become known, in accordance with the TORs approved by\nthe World Bank.\n\n\n**D. Gender**\n\n\n49. **A gender analysis has been completed and gender action plan has been incorporated in Project design.** The\nresults framework for the Project is fully disaggregated by gender. The Project involves supporting entrepreneurs at the\ncommunity level and data reveals that women are engaged in livelihoods activities (such as handicrafts, kitchen gardening\netc.). Through the LIPs in particular and through training and enterprise development opportunities, the Project will seek\nto elicit this participation and support investment and skills development initiatives for women, thereby improving their\nearnings. And as mentioned above, women voices will be made a part of the overall citizens engagement agenda.\n\n\n**E. Climate**\n\n\n50. **Climate Considerations:** The Project has been screened for climate risk using the WBG’s Climate and Disaster Risk\nScreening Project Level Tool 16 [^16: The tool is available here: _[http://climatescreeningtools.worldbank.org/](http://climatescreeningtools.worldbank.org/)_] . Based on the review of historic and projected data at Project location, risks and potential\nimpacts of exposure to climatic trends and geophysical hazards are rated high for extreme precipitation, flash flooding,\ndrought and earthquake. Climate and geophysical hazards are assessed as Moderate for each operational component for\nthe Project lifetime and beyond. Risk mitigation measures have been incorporated in the project design and include\namong others the promotion of resilience-enhancing technologies (e.g. use of green technologies such as solar, in energy\nand water management; use of climate-resilient materials and design in the construction of transport and storage\ninfrastructures and value-adding facilities. It is expected that increased income of beneficiaries through project\nintervention will increase their resilience to climate-related impacts.\n\n\n51. **GHG Accounting:** The Project used the EX-ACT tool measure\n\nMention: \"historic and projected data\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"analyze\", \"summary\": \"Historic and projected climate data screened at the project location for hazard ratings.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "umar_pads", "source_key": "umar_pads:000032:21:0", "occurrence_id": "1a7738a7b62e6526346a278d", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: **The World Bank**\nDRC Transport and Connectivity Support Project (P161877)\n\n\n39. This subcomponent will finance the operational costs of the _Cellule Infrastructures_ (CI) for\ncoordination and management, including staff costs. It will finance project management and coordination\nactivities, including: (i) salary of key CI personnel proportionately to their involvement in project\nimplementation; (ii) external financial audits; and (iii) acquisition of office furniture, equipment, and\nlogistics. The subcomponent will also support the CI for the monitoring and evaluation of the project,\nincluding use of geo-referencing instruments for monitoring planned and rehabilitated roads, and impact\nevaluations.\n\n40. This subcomponent will also finance innovative supervision tools (for example, drones and social\nmedia monitoring 51 [^51: The objective of social media monitoring is to harness social media analytics and remote‐based geospatial analysis to identify\nand monitor for potentially project‐associated incidents and other social impacts. The real‐time and remote-based social media\nmonitoring has the potential to provide early warning of harm.] ), communication activities, and the development and use of internet-based tools for\nremote supervision (such as through geolocating software like Mapillary and GEMS 52 [^52: GEMS: Geo-Enabling Initiative for Monitoring and Supervision] ) particularly in hardto-reach areas, and zones affected by conflict or unrest. Finally, it will finance in-time analysis and\ninformation on conflict and insecurity dynamics in the project targeted areas to be aware and sensitive of\npossible security challenges and potentially harmful actions to quickly adapt, respond, and ensure staff,\ncommunity beneficiary safety and well-being. This will include accessing information from a variety of\nsources, including existing mechanisms such as Kivu Security Tracker that provide continual data and\ninformation on conflict and insecurity dynamics in Eastern DRC. Should similar arrangements be required\nfor the Kasais (bearing in mind the contextual differences between the provinces), this will be considered\nand resourced accordingly.\n\n**Component 2:\n\nMention: \"Kivu Security Tracker\""}, {"role": "assistant", "content": "{\"role\": \"supporting\", \"usage_action\": \"source\", \"summary\": \"Continual conflict and insecurity data for eastern DRC safety monitoring.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "umar_pads", "source_key": "umar_pads:000053:3:0", "occurrence_id": "09d48386f9192de1a0a731f1", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: **The World Bank**\nHimachal Pradesh State Roads Transformation Program (P163328)\n\n\nspecialized services, including medical tourism, IT and education, as well as renewable energy generation, including hydro\npower. However, ensuring development effectiveness is a challenge in the absence of synergy among development\ninitiatives and institutional efficiency. The World Bank has been supporting agriculture, forestry, public finance, green\ngrowth, sustainable development and transport projects, but implementation has been sluggish due to institutional\ncapacity limitations.\n\n\nSectoral and Institutional Context\n\n4. **HP is endowed with abundant fruit belts and natural tourism potential, which could help the State to be a lead**\n**in green growth, if its transport infrastructure and logistics system are well developed.** The economic growth of the state\nis mainly attributed to agriculture/ horticulture and related activities as it provides employment to about 62 percent of\nthe total workers in the state. However, the roads connecting farm areas to the wholesale markets are substandard\n(narrow mountainous roads) and horticultural products are transported by informal cartels of short-bed truck operators.\nMoreover, the Himalayan mountains and valleys covered with the state record (SoER, HP) of 3,295 species of plants and\n5,721 species of fauna are attracting tourists to HP and make tourism account for seven percent of the State GDP. The\nnatural scenery in the Himalayan mountains, including the Rotana Pass is attracting enormous tourists. The tourism\nindustry is growing fast and the number of tourists in HP has increased from 7 million in 2005 to 13 million in 2010 and 18\nmillion in 2016. Students from all over India join the universities in Solan, which are providing high quality education in\nagriculture, IT and medicine, which makes HP a center for specialized services. Himachal’s hydropower plants generate\n7,000-Megawatt electricity. Recently, manufacturing plants, including pharmaceutical, cement, small steel mills and wool\nfactories are emerging. The absence of physical and digital logistics infrastructure for the\n\nMention: \"state record\""}, {"role": "assistant", "content": "{\"role\": \"background\", \"usage_action\": \"inform\", \"summary\": \"State of environment record cited for species counts attracting tourism.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "fcv", "source_key": "fcv_pads_east_africa:003567:7:0", "occurrence_id": "0e12c94fc4703c74afe653ee", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: legal framework with a view to ensuring coherence with the digital systems, review\nprocesses and development of applicable standard operating procedures; (c) capacity\nbuilding activities including orientation and provision of training for key stakeholders\ninvolved in the reporting, processing, analyses, storage and usage of CRVS data such as\ncivil registrars, health officials, religious and community leaders and different cadres of\nstaff at ICS, MOH and Ethiopian Statistics Service (“ESS”) including Kebeles and refugee\ncamps; (d) designing and rolling out social and behavior change communication activities;\n(e) strengthening CRVS activities in conflict-affected areas including mobile interventions\nfor vulnerable population groups; (f) supporting coordination, monitoring and evaluation\nof associated activities; and (g) supporting management of associated activities.\n\n_3._ _Technical Assistance and Capacity Building_\nProvision of technical assistance and capacity building support to the MOH as well as\ndepartments and agencies for Project implementation and supervision, including:\n(a) strengthening the following functions, namely: financial management and procurement;\ndata and management information systems including MOH vital events notification\nfunctions; monitoring and evaluation; healthcare financing arrangements; strengthening\npublic private partnerships in the sector; emergency obstetric and newborn care services as\nwell as monitoring of fraud and anti-corruption in the healthcare system; and (b) supporting\nthe expansion of comprehensive services in primary healthcare facilities and rolling out of\na new self-care package consistent with the HSTP II.\n\n_4._ _Contingency Emergency Response Component_\n\nProvision of immediate response to an Eligible Crisis or Emergency, as needed.\n\n\n7\n\nMention: \"CRVS data\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"analyze\", \"summary\": \"CRVS data is reported, processed, analyzed, stored, and used within civil-registration and health information-system functions.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "fcv", "source_key": "fcv_pads_east_africa:008738:3:0", "occurrence_id": "d99d9993eb8c30705e3b38b4", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: **The World Bank**\nIntegrated Water Management and Development Project (P163782)\n\n\n**the Northern and Eastern regions.** From 1992 to 2013, the percentage of Ugandan households living in\npoverty nearly halved. **3** [^3: From 1993 to 2013, households living in poverty went from 68.1 percent to 33.2 percent.] However, according to the Uganda Poverty Assessment Report (2016), 4 [^4: World Bank, The Uganda Poverty Assessment Report 2016.] in 2013\nmore than a third of Ugandans lived below the international extreme poverty line of US$1.90 per day.\nMoreover, the risk of Ugandans falling back into poverty is high; for every three Ugandans that moved out\nof poverty, two fell back into poverty. Poverty has become increasingly concentrated in Uganda’s\nNorthern and Eastern regions. Approximately 84 percent of Uganda’s poor (living below US$1.90 per day)\nreside in in the Northern and Eastern regions, where 43 percent of the residents live on less than US$1 a\nday. Economic growth in these regions has been affected by the civil conflict in South Sudan, significant\nland degradation, an influx of refugees, and climate change.\n\n\n3. **Demographic trends and urbanization pose a daunting challenge to Uganda’s economic growth**\n**and underscore the need for better urban planning and basic service provision.** Uganda’s population of\n35 million is expected to reach 80 million by 2040. Uganda’s annual urban growth rate of 5.2 percent is\namong the highest in the world, and the urban population is expected to grow from 6.4 million (2014) to\n22 million by 2040. About 60 percent of the current urban population, however, lacks basic amenities,\nsuch as decent housing and WSS services. In addition, many small towns and rural growth centers\n\nMention: \"Uganda Poverty Assessment Report\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"inform\", \"summary\": \"Report provides poverty estimates and regional concentration figures cited to describe Uganda's poverty context.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "fcv", "source_key": "fcv_pads_east_africa:009106:6:0", "occurrence_id": "600d46a3b1d74a3061446a0d", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: **The World Bank** Implementation Status & Results Report\nEthiopia PFM Project (P150922)\n\n\nValue 90.00 96.00 93.65 95.00\n\n\nDate 30-Dec-2015 18-Dec-2018 28-Jun-2019 08-Apr-2020\n\n\n\nComments **:**\n\n\n\nOut of 1023 Woredas, 983 of them posted the simplified budget and execution reports for citizens on bill\nboards according to the regional BoFEDs report. In 2011 EFY 93.65% woredas are posted simplified\nbudget execution reports to the citizens.\n\n\n\n**Data on Financial Performance**\n\n\n**Disbursements (by loan)**\n\n\nProject Loan/Credit/TF Status Currency Original Revised Cancelled Disbursed Undisbursed % Disbursed\n\n\nP150922 IDA-57660 Effective USD 33.00 33.00 0.00 18.02 15.17 54%\n\n\n**Key Dates (by loan)**\n\n\nProject Loan/Credit/TF Status Approval Date Signing Date Effectiveness Date Orig. Closing Date Rev. Closing Date\n\n\nP150922 IDA-57660 Effective 26-Feb-2016 17-Mar-2016 18-May-2016 07-Apr-2020 07-Apr-2020\n\n\n**Cumulative Disbursements**\n\n\n8/20/2019 Page 7 of 8\n\nMention: \"Data on Financial Performance\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"inform\", \"summary\": \"Loan disbursements, balances, percentages, and key dates report the project's financial performance.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "fcv", "source_key": "fcv_pads_east_africa:009298:8:0", "occurrence_id": "c68d2dfeac12110391d81945", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: **The World Bank**\nEthiopia-Transport Sector Project in Support of RSDP4 (P117731)\n\n\n**I.** **PROJECT CONTEXT AND DEVELOPMENT OBJECTIVES**\n\n\n**A. CONTEXT AT APPRAISAL**\n\n**Context**\n\n1. **In the years leading up to the approval of the Transport Sector Project in Support of RSDP4 (TSP) around**\n**2011-2012, Ethiopia was achieving impressive development results, but the country was still facing a number**\n**of development challenges.** Ethiopia had achieved annual average GDP growth of 11 percent during 20042010 according to the Government of Ethiopia (GoE) estimates (or 7-8 percent according to International\nMonetary Fund estimates), but the inflation was still unstable. Political instability and conflict remained a\npermanent constraint on development in neighboring South Sudan and Somalia. While Ethiopia was making\nthe third fastest improvements of any country towards reaching the Millennium Development Goals (MDGs)\nresulting from a long-term, concerted commitment to pro-poor development, over 80 percent of the\npopulation was living in rural areas. Agriculture, which accounted for about 85 percent of total export earnings,\nwas the main source of livelihood, keeping Ethiopia as one of the world’s poorest countries with a GDP per\ncapita of US$377 in 2009/2010. In 2010 Ethiopia ranked 157 out of 177 nations in the Human Development\nIndex (HDI). Continued investments in infrastructure, including basic road transport connectivity, were\nconsidered a major component of Ethiopia’s program towards improving development outcomes at the\nhousehold, regional, and national levels. Building on the “Sustainable Development and Poverty Reduction\nProgram” 2002-2004/5 (SDPRP), and the “Plan for Accelerated and Sustained Development to End Poverty”\n2005-2010, the GoE’s five-year development plan, the Growth and Transformation Plan\n\nMention: \"Human Development\nIndex\""}, {"role": "assistant", "content": "{\"role\": \"background\", \"usage_action\": \"inform\", \"summary\": \"Ethiopia's HDI ranking provides development context for the transport-project rationale.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:000057:27:1", "occurrence_id": "b6c64c2344f14cf90c74d58c", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: sup>16\n\n\nThe analysis in this study makes use of a programming model designed to produce a consistent\nquantitative framework for the Sierra Leone rice sector in order to simulate the effects of policy\ninterventions as well as the potential impact of technical progress in the sector. The model is largely based\non survey information collected in 2016. Importantly, the model is disaggregated across the five rice\necologies, thereby providing a richer set of simulation results. Furthermore, since the model includes\nboth household as well as hired-in or temporary labor, some sense of the distributional impact of different\ntrade or labor policy can be gleaned from the simulations.\n\n\nSimulation of the base year as a basic validation test showed that the sector model performed well with\nonly minor deviations between the survey data and the simulated results, with the exception of\nemployment, where the simulated level of employment was lower than for the survey. This finding\nsuggests that the sector is not optimal in the use of labor and is entirely consistent with the narrative of\nhigh levels of unemployment and underemployment in Sierra Leone. Over the 10-year period between\n2009 and 2018 the unemployment rate in Sierra Leone has averaged 8.25 percent per year. 17 [^17: World Bank, World Development Indicators.]\n\n\nThe simulation of the base year also suggests that Sierra Leone’s rice sector is operating at a sub-optimal\nlevel in the use of one critical resource—land. The use of two of the most productive ecologies—Mangrove\nSwamp and Riverain are well below their availabilities. The sub-optimal use of these two ecologies is\nreflected in the shadow prices. The shadow prices for a hectare of Mangrove Swamp and Riverain are\n$615.76 and $107.89, respectively. This means that bringing an additional hectare of the former ecology\ninto production would increase producer/consumer surplus by $615.76 and an additional hectare of\n\n\n16 The ‘hunger season’ runs usually from May to December\n\nMention: \"survey information\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"validate\", \"summary\": \"2016 survey information parameterizes the rice-sector model and provides comparison data for base-year validation.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:000079:45:1", "occurrence_id": "4398e0025fc2177508405a65", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: 24\nTajikistan 3.18 3.27 3.27 1.95\nTanzania 0.88 1.06 1.06 2.29\nUganda 1.77 1.90 1.96 2.11\n**Mean** **1.88** **2.02** **2.08** **2.15**\n_Notes_ : Column (1) reproduces national poverty lines from Ferreira et al. (2016). Column (2) updates both PPPs and\nCPIs to the 2017 ICP reference year, while incorporating the revisions to the CPI data used in deriving the $1.90 line.\nColumn (3) updates both PPPs and CPIs to the 2017 ICP reference year, without incorporating the revisions to CPI\ndata used in deriving the $1.90 line. Column (4) takes the $1.90 line as given for all countries and updates the $1.90\nline with both PPPs and updated CPIs to the 2017 reference year. See Appendix E, section 2 for the derivations. If we\nupdated the IPL with US inflation between 2011 and 2017 (i.e., approximately 9%), the new IPL would be $2.07.\n\n\n\n_(3)_\n\n\n\n44\n\nMention: \"CPI data\""}, {"role": "assistant", "content": "{\"role\": \"supporting\", \"usage_action\": \"analyze\", \"summary\": \"CPI data revisions are incorporated when updating the price-based international poverty line to the 2017 reference year.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:000097:11:0", "occurrence_id": "35baa9e1ce2fd17dceee1aa1", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: **c. Average risk-weighted assets over total assets**\n\n\nSource: Archived data from Bureau van Dijk’s Bankscope, BankFocus and staff calculations.\nNote: Off-shore financial centers are excluded from the calculations. Panel A, B and C present country averages across country groups. Banks are\nweighted by total assets within a group (top 20% banks) and country in each year, and countries are equally weighted within a country grouping\n(i.e., a simple average of country-level average ratios for either top 20% banks or the other banks within high-income and developing countries is\ntaken) in each year. A country is included in the calculations in each year if it has data for at least 5 individual banks. Banks are included in the\ncalculations if total assets are larger than USD 10 million.\n\n\nBeyond the levels of the Tier 1 capital ratio, another aspect of the quality of bank capital is the\n\n\nbalance-sheet items allowed in the computation of Tier 1 regulatory capital. As shown in Figure 4, Panels\n\n\nA, B, and C, between BRSS rounds 4 and 5 more countries allowed hybrid debt capital instruments, asset\n\n\nrevaluation gains, and subordinated debt to be used in the computation of Tier 1 capital, although with\n\n\nimportant regional differences. In general, a higher proportion of high-income OECD countries allowed\n\n\nalternative capital instruments to be counted as Tier 1 capital. There was also a notable change between\n\n\nwave 4 and wave 5 in the proportion of countries allowing asset revaluation gains and subordinated debt\n\n\ninto Tier 1 capital, predominantly for high-income OECD countries and developing countries, specifically\n\n\nfor countries in the developing regions EAP, ECA and SSA. Broadening the definition of Tier 1 capital in\n\n\nthis way raises at least three concerns, especially for developing countries. First, a broader definition of\n\n\nbank regulatory capital may increase opacity for private monitors in assessing bank risk, an issue\n\n\nhighlighted by the GFC (see, for instance, Haldane\n\nMention: \"Bankscope\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"analyze\", \"summary\": \"Archived Bankscope data and staff calculations support analysis of bank assets and regulatory-capital ratios across country groups.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:000097:11:0", "occurrence_id": "ad57859bd93bf217e0384e29", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: **c. Average risk-weighted assets over total assets**\n\n\nSource: Archived data from Bureau van Dijk’s Bankscope, BankFocus and staff calculations.\nNote: Off-shore financial centers are excluded from the calculations. Panel A, B and C present country averages across country groups. Banks are\nweighted by total assets within a group (top 20% banks) and country in each year, and countries are equally weighted within a country grouping\n(i.e., a simple average of country-level average ratios for either top 20% banks or the other banks within high-income and developing countries is\ntaken) in each year. A country is included in the calculations in each year if it has data for at least 5 individual banks. Banks are included in the\ncalculations if total assets are larger than USD 10 million.\n\n\nBeyond the levels of the Tier 1 capital ratio, another aspect of the quality of bank capital is the\n\n\nbalance-sheet items allowed in the computation of Tier 1 regulatory capital. As shown in Figure 4, Panels\n\n\nA, B, and C, between BRSS rounds 4 and 5 more countries allowed hybrid debt capital instruments, asset\n\n\nrevaluation gains, and subordinated debt to be used in the computation of Tier 1 capital, although with\n\n\nimportant regional differences. In general, a higher proportion of high-income OECD countries allowed\n\n\nalternative capital instruments to be counted as Tier 1 capital. There was also a notable change between\n\n\nwave 4 and wave 5 in the proportion of countries allowing asset revaluation gains and subordinated debt\n\n\ninto Tier 1 capital, predominantly for high-income OECD countries and developing countries, specifically\n\n\nfor countries in the developing regions EAP, ECA and SSA. Broadening the definition of Tier 1 capital in\n\n\nthis way raises at least three concerns, especially for developing countries. First, a broader definition of\n\n\nbank regulatory capital may increase opacity for private monitors in assessing bank risk, an issue\n\n\nhighlighted by the GFC (see, for instance, Haldane\n\nMention: \"BankFocus\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"analyze\", \"summary\": \"Archived BankFocus data and staff calculations support analysis of bank assets and regulatory-capital ratios across country groups.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:000390:20:1", "occurrence_id": "be4b08bac92077af91b891b5", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: , and inhibit imports of adequate raw materials.\nThe shortage of foreign exchange tends also to fuel the contraband trade through Somaliland because the\nbirr is an unofficial currency there and can more easily be used to purchase products from around the\nworld.\n\n##### 3.5. Underdeveloped and fragile financial system\n\nEthiopia has one of the least developed financial systems in the world. In the 2018 Global Competitiveness\nReport, Ethiopia ranked 126 of 140 countries in terms of financial system development. 76 With total assets\nof 46 percent of GDP, Ethiopia’s financial system is shallow and does not serve well the needs of a\ntransforming economy. Access to finance is identified as the main obstacle to business by 40 percent of\nfirms. 77 While the share of adults having a bank account has increased significantly in recent years, it\nremains at a low 35 percent in 2017 (as compared to 43 percent on average in Sub‐Saharan Africa). The\nnumber of bank branches per capita is low and branches are concentrated in major towns and cities. 78\nNearly one‐third of branches are located in Addis Ababa. The rural poor have little access to formal\nbanking instruments and rely on microfinance institutions (MFIs), informal financing like saving and credit\nassociations, moneylenders and friends. In the absence of formal banking, MFIs have developed and\noperate a network of around 1,900 branches in September 2018. Some of the biggest MFIs outperform\nmost of the banks in the country in terms of branch network and capital. 79\n\n\n75 U.S. Department of State, Bureau of Economic and Business Affairs, Investment Climate Statements for 2018.\n76 World Economic Forum (2018). Global Competitiveness Report 2018.\n77 World Bank Enterprise Survey (2015).\n78 Gashayie, A. and M\n\nMention: \"World Bank Enterprise Survey\""}, {"role": "assistant", "content": "{\"role\": \"supporting\", \"usage_action\": \"inform\", \"summary\": \"Enterprise Survey data support the reported finding that access to finance is a major obstacle for Ethiopian firms.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:000427:7:1", "occurrence_id": "3aed7e9579934dffd1241e28", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: the greatest mitigation effort should\nbe borne by the largest carbon emitters, which are mostly high and middle-income countries that have\n\nalready issued green bonds. 10 And public debt levels are presently a smaller concern in that income\ngroup (Blanchard 2019), suggesting that for countries with sufficient fiscal space, green bonds might\nhelp improve the climate policy mix.\n\nThe relation of green bonds to debt levels also depends on their cost relative to traditional bonds. A\ncritique has been that green bonds may be more expensive than conventional bonds and thus raise debt.\nBut this finding may be driven by sample selection bias. To evaluate climate financing strategies, it is\nimportant to control for the types of investment projects and investor characteristics when comparing\nyields of green and vanilla bonds. The relevant point of comparison for a country which is considering\nthe use of green bonds for financing climate projects is the yield of vanilla bonds that are used in financing\nthese same climate projects, and not the yield of conventional bonds averaged across the broader market.\nWith these controls, green bonds are paying lower yields (Flammer 2018; Baker at al. 2018; Karpf and\nMandel, 2018, Partridge and Medda, 2018). So, given that a country is seeking to finance investments\nin its climate transition, green bonds appear cheaper than vanilla bonds. There is also evidence that the\nact of certifying a green bond through a third party reduces its yield (Bachelet et al. 2019) and that\n\n\ninvested in adaptation projects. The authors also analyze the Bloomberg Green Bonds Database and find that only 2% of the\ncertified issuers (from 2010 to 2018) declared that the volume leveraged should be used only for adaptation projects. The\nexpected use of proceeds of each certified green bond is published by a third-party report at the time of issuance.\n10Among the largest emitters, the Russian Federation was the last country to enter the green bond market in January 2019.\n\n\n6\n\nMention: \"Bloomberg Green Bonds Database\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"analyze\", \"summary\": \"Database analysis identifies certified green-bond issuers' reported use of proceeds for climate adaptation projects.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:000580:0:0", "occurrence_id": "a699bfbfa8776071b4bb1289", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: Policy Research Working Paper\n10502\nHow Prevalent Are Credit-Constrained \nFirms in the Formal Private Sector?\nEvidence Using Global Surveys\nAsif M. Islam\nJorge Rodriguez Meza\nGlobal Indicators Group &\nMiddle East and North Africa Region\nJune 2023\nPublic Disclosure Authorized\nPublic Disclosure Authorized\nPublic Disclosure Authorized\nPublic Disclosure Authorized\n\nMention: \"Global Surveys\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"analyze\", \"summary\": \"The paper identifies global survey evidence as its empirical basis for estimating credit constraints among formal private-sector firms.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:000696:52:0", "occurrence_id": "4250ecf263ded984c64ae464", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: NO2 (LHS) Stringency index (RHS)\n\n\n\n\n\n60\n\n\n40\n\n\n20\n\n\n0\n\n\n−20\n\n\n−40\n\n\n−60\n\n\n60\n\n\n40\n\n\n20\n\n\n0\n\n\n−20\n\n\n−40\n\n\n−60\n\n\n\n**China**\n\n\n\nOct Dec Feb Apr Jun Aug Oct Dec Feb Apr\n2019 2020 2021\n\n\n**United States of America**\n\n\nOct Dec Feb Apr Jun Aug Oct Dec Feb Apr\n2019 2020 2021\n\n\n\n60\n\n\n40\n\n\n20\n\n\n0\n\n\n−20\n\n\n−40\n\n\n−60\n\n\n60\n\n\n40\n\n\n20\n\n\n0\n\n\n−20\n\n\n−40\n\n\n−60\n\n\n\n**Italy**\n\n\n\nOct Dec Feb Apr Jun Aug Oct Dec Feb Apr\n2019 2020 2021\n\n\n**France**\n\n\nOct Dec Feb Apr Jun Aug Oct Dec Feb Apr\n2019 2020 2021\n\n\n\n\n\n\n\n100\n\n\n80\n\n\n60\n\n\n40\n\n\n20\n\n\n0\n\n\n100\n\n\n80\n\n\n60\n\n\n40\n\n\n20\n\n\n0\n\n\n\n100\n\n\n80\n\n\n60\n\n\n40\n\n\n20\n\n\n0\n\n\n100\n\n\n80\n\n\n60\n\n\n40\n\n\n20\n\n\n0\n\n\n\nFigure S5: COVID-19 Lockdown Stringency Index and NO2, by-Country.\n_Notes._ NO2: percentage change in the 91 day rolling. Stringency Index: World Bank, Our World in Data.\n\n\n_N_ = 3 _,_ 073 and _R_ 2 = 0 _._ 01. The constant is negative both due to overall downward trend in\n\nNO2, and overall nationwide decline in NO2 in 2020 due to the pandemic. The effect of the\n\nDemocratic margin is negative, consistent with the collective inaction thesis. While this result\n\nis interesting, there are important robustness checks to this incomplete claim. For instance,\n\nwe make no effort to disentangle whether these differences are due to more lax orders, or more\n\nresistance to orders. These questions are beyond the scope of our analysis.\n\n#### **B Other Results**\n\n###### **B.1 Night Lights Baseline**\n\n\nIn this subsection we show how the incremental introduction of updated data, satellite instru\nments, and technical adjustments (including removal of stray lights and inter\n\nMention: \"Our World in Data\""}, {"role": "assistant", "content": "{\"role\": \"supporting\", \"usage_action\": \"source\", \"summary\": \"Our World in Data supplies lockdown-stringency index values plotted alongside country-level NO2 changes during 2019–2021.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:000850:40:0", "occurrence_id": "a54dd923c1e0b4c780b13a98", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: Table 4: Summary statistics: wealth-related variables of households in host communities\n\n**Variable** **Mean** **Std.** **Dev.** **Min.** **Max.**\nLog(Consumption) 4.4573 0.9797 0.6186 10.7893\nPoorest 0.3082 0.4619 0 1\nQuintiles 3.0187 1.407 1 5\nN 1444\n\n\nThe data is from the World Bank’s cross-sectional data set Profile of Internally Displaced Persons in North-East\nNigeria 2018 that captures households in host communities. _Log(Consumption)_ is continuous and captures householdlevel logarithms of consumption per capita, per day in Nigerian Naira in 2018. _Poorest_ is a binary variable indicating\nwhether a household belongs to the poorest ethnic group in a given LGA. _Quintiles_ divides households into consumption quintiles. _Log(Consumption)_ is employed as a dependent variable in the sensitivity analyses addressing RQ1\n\nMention: \"Profile of Internally Displaced Persons\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"analyze\", \"summary\": \"Cross-sectional host-community household data supply consumption measures used as dependent variables in sensitivity analyses.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:001119:27:0", "occurrence_id": "bc01b2271867a9bca0fd3f3b", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: To assess the potential production and income gains under various frontier attainment scenarios,\nTable 7 presents potential gains in terms of both kilograms and monetary values, for the specific\nplot as well as household level estimates. Household estimates are derived based on total area\ncultivated with maize by the household, which itself is imputed via multiple imputation methods\nto adjust for bias in self-reported area estimates. 18 A key assumption underlying the household\nlevel estimates is that the household experiences the same level of productivity on all maize plots.\nThe reported USD values of potential maize production gains are based on the November 2015\nFamine Early Warning Systems Network (FEWSNET) Uganda Price Bulletin kilogram unit price,\nand do not account for any additional expenditures required to attain the increased level of\nproductivity. 19\n\nIf suitability-class-specific productivity gaps were closed such that all farmers were operating on\ntheir respective MAPS-based productivity frontier, the best-case scenario given soil constraints,\nhouseholds could produce an additional 208 kg, or USD 90, per bi-annual agricultural season, on\naverage. 20 Households classified as S3 under MAPS, assuming the suitability level is the same\nacross all maize plots in the household, only have the potential to earn an additional USD 56 per\nagricultural season, while those in the highly suitable (S1) category can earn USD 171 more.\nReaching this MAPS-based class-specific frontier has asymmetric benefits for female- and maleheaded households, with male-headed households earning USD 99 on average and female-headed\nhouseholds only USD 73.\n\nThe benefits of operating at this frontier also differ across the wealth distribution, with those in the\npoorest tercile having the potential to earn USD 77 per season, USD 28 less than those in the\nrichest tercile. If soil constraints were addressed such that all households were able to operate at\nthe S1\n\nMention: \"Uganda Price Bulletin\""}, {"role": "assistant", "content": "{\"role\": \"supporting\", \"usage_action\": \"analyze\", \"summary\": \"The bulletin's maize-price figure converts projected production gains from kilograms into USD.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:001145:13:0", "occurrence_id": "bb13fef72457c628696b7799", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: expansion as the pandemic is brought under control (Nayyar and Davies 2023;\nCoulibaly and Foda 2020; World Bank 2021c; Zhan et al. 2020).\n\n\nThe four decades prior to the global financial crisis saw a steady increase in global\neconomic integration through trade, assisted partly by falling tariffs (figure 4). Since the\nglobal financial crisis, however, trade integration has stalled, with the COVID-19\npandemic and Russia’s invasion of Ukraine having added further obstacles. With\nRussia’s share of global oil production having increased considerably in recent decades,\nthere is now a material risk that the disruptions caused by Russia’s invasion of Ukraine\ncould lead to a major reconfiguration of global trade and investment networks, as\ncountries look for alternative sources of energy. While this may boost trade in some\nparts of the global economy, it is likely to disrupt trade elsewhere. Since such a\nreconfiguration would be motivated by political and security considerations rather than\neconomic considerations, it is likely to reduce global economic welfare as well as trade in\nthe long term (Ruta 2022).\n\n#### IV. Patterns in trade costs\n\n\nThe fading momentum of global trade growth is diminishing its role as an engine of\noutput and productivity growth. Countries therefore need to find new ways to reap the\nbenefits from trade. One possibility is to cut trade costs to boost exports and encourage\nimports in a manner that is growth-enhancing. A number of studies have documented\nthe negative impact of trade costs on trade growth (Anderson and van Wincoop 2003)\nand the boost to productivity that can result from lowering trade costs (Bernard,\nJensen, and Schott 2006). Trade costs have also been recognized as an important factor\nin firms’ decisions to choose out-sourcing over in-sourcing (Hartman et al. 2017).\n\n\nIV.1 Definition\n\n\nThe analysis in this paper relies on a comprehensive UNESCAP-World Bank dataset of\nbilateral trade costs. Following Novy\n\nMention: \"UNESCAP-World Bank dataset\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"analyze\", \"summary\": \"The dataset supplies bilateral trade-cost measures used as the basis for analysis of trade patterns and costs.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:001183:23:0", "occurrence_id": "661d93922808b89426d512b1", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: ## **Appendices**\n\n**A.** **BPS Data (Sample, Summary Statistics); Sectoral and Country Attributes**\n\n\nTable A1: Number of firms in the BPS data sample per country\nCountry Firm Country Firm Country Firm\nNumber Number Number\nAfghanistan 595 Hungary 706 Poland 1,824\nAlgeria 340 India 2,956 Portugal 853\nArgentina 210 Indonesia 768 Romania 1,373\nBangladesh 899 Italy 487 Senegal 377\nBenin 814 Jordan 48 Sierra Leone 432\nBrazil 1,009 Kenya 1,721 Slovak Republic 346\nBulgaria 1,357 Kosovo 1,663 Slovenia 314\nBurkina Faso 507 Kyrgyzstan 1,248 South Africa 1,760\nChile 214 Latvia 325 Sri Lanka 436\nCóte d’Ivoire 339 Lithuania 229 Sudan 414\nCroatia 381 Madagascar 329 Tajikistan 1,237\nCyprus 201 Malta 39 Tanzania 874\nCzechia 458 Moldova 309 Togo 150\nEl Salvador 474 Mongolia 290 Tunisia 481\nEstonia 297 Morocco 900 Türkiye 1,444\nGabon 110 Mozambique 2 Uzbekistan 1,264\nGeorgia 619 Nepal 1,510 Viet Nam 492\nGhana 3,890 Nicaragua 228 Zambia 564\nGreece 576 Nigeria 296 Zimbabwe 87\nGuatemala 232 Pakistan 508 _Total_ _43,389_\nHonduras 198 Paraguay 385\n\n\n22\n\nMention: \"BPS Data\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"analyze\", \"summary\": \"BPS firm observations define the multinational sample, summarized by country and firm count.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:001308:32:0", "occurrence_id": "36236dbf62b3aeed91e8dafa", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: plants based on the actual construction of major dams across the entire country\n\neach decade. The second step calculates a cost factor that sorts potential\n\nlocations by their geographic suitability. The final step applies the suitability\n\npredictions to the areas where hydropower plants were actually built. Using\n\nthe predictions of the estimated construction site for each hydropower plant,\n\na hypothetical transmission network that depends solely on topological and\n\n\nhydrological characteristics is constructed and used as an instrumental variable.\n\nDetailed description of constructing the instrument can be found in Lipscomb,\n\n\nMobarak, and Barham (2013) and Szerman et al. (2022).\n\n\nWe construct the “natural path” instrumental variable for highways following\n\n\nAli et al. (2015) based on the least amount of time between the 25 existing state\ncapitals in the base period 18 and Bras´ılia. It incorporates local terrain using\n\n\nslope derived from a Digital Elevation Model (NASA’s Shuttle Radar Topography\n\nMission) from Verdin et al. (2007) and a historical land cover dataset (circa\n\n1900) from HYDE (Klein Goldewijk et al., 2011). We use the same walking\n\n\nvelocity from Tobler (1993):\n\n\n_W_ = 6 _∗_ _exp_ ( _−_ 3 _._ 5 _|S_ +0 _._ 05 _|_ ) (A4)\n\n\nwhere _W_ is the hiking velocity (kph) and\n\nMention: \"historical land cover dataset\""}, {"role": "assistant", "content": "{\"role\": \"supporting\", \"usage_action\": \"analyze\", \"summary\": \"Historical land cover from HYDE and terrain data inform the route-cost instrument for modeled highway paths.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:001351:19:1", "occurrence_id": "2c2874671acebc0cdfd63d15", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: 16,880 16,880 16,880\nR-squared 0.772 0.772 0.775 0.764 0.759\nTreatment Obs 9684 9684 9684 9684 9684\nControl Obs 7196 7196 7196 7196 7196\n\nNotes: Robust standard errors in parentheses; *** p<0.01, ** p<0.05, * p<0.1; avg_radBuff05 ranges from 1 st to 99 th percentile\n(0.02 to 2.7 nanoWatts/sr/cm 2 [^2: 0.00639*** 0.00648*** 0.00646*** 0.00634*** 0.00629***\n(0.000899) (0.000926) (0.000887) (0.000863) (0.000860)\nConstant 0.122*** 0.175*** 0.234*** 0.228*** 0.213***\n(0.0129) (0.0129) (0.0128) (0.0126) (0.0128)] )\n\n### Nigeria case study: July 2022 floods\n\n**_2022 flood event_**\n\n\nAccording to EM-DAT & CRED / UCLouvain (2023), Nigeria suffered flooding during the period of July\n1, 2022 to October 31, 2022. The first row of Figure 9 presents the flooded pixel during each month\nand over the whole period, The second row shows flooded pixel during each month but not flooded\nduring the other months. During the first couple of months of the\n\nMention: \"EM-DAT\""}, {"role": "assistant", "content": "{\"role\": \"supporting\", \"usage_action\": \"inform\", \"summary\": \"EM-DAT event records establish the dates and occurrence of Nigeria's 2022 floods for the case study.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:001768:48:6", "occurrence_id": "ad31145dc656d263ff229b07", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: at\nthe 10, 5 and 1 percent level, referring to Romano-Wolf p-values. These are obtained from a step-down procedure to adjust for multiple hypothesis testing\nperforming 1000 bootstrap replications as proposed by Romano and Wolf (2005). Covariates: Toilet ownership at baseline, indicator for presence of a child\naged 0 - 2 at baseline, ratio of number of sampled clients to village size. Data sources: household survey, administrative and credit bureau data.\n\n\n47\n\nMention: \"household survey\""}, {"role": "assistant", "content": "{\"role\": \"supporting\", \"usage_action\": \"source\", \"summary\": \"Household survey records provide toilet, child-presence, and household covariates used in the analysis.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:001768:48:6", "occurrence_id": "336679802240e307836ae9c1", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: at\nthe 10, 5 and 1 percent level, referring to Romano-Wolf p-values. These are obtained from a step-down procedure to adjust for multiple hypothesis testing\nperforming 1000 bootstrap replications as proposed by Romano and Wolf (2005). Covariates: Toilet ownership at baseline, indicator for presence of a child\naged 0 - 2 at baseline, ratio of number of sampled clients to village size. Data sources: household survey, administrative and credit bureau data.\n\n\n47\n\nMention: \"administrative and credit bureau data\""}, {"role": "assistant", "content": "{\"role\": \"supporting\", \"usage_action\": \"source\", \"summary\": \"Administrative and credit-bureau records supplement survey data for the study's covariates and analysis.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:001943:1:0", "occurrence_id": "1a77049e664b62699c651bf1", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: Policy Research Working Paper 9633\n\n### **Abstract**\n\nThis paper provides one of the first comprehensive and\n\nmost updated studies on the effects of firms’ organizational\nresources, country institutions, and national culture on\nthe survival and growth of private firms around the world\nduring the COVID-19 pandemic. Analyzing World Bank\nEnterprise Follow-up Surveys on COVID-19 that cover\n18,770 firms in 36 countries, the paper documents four sets\nof findings. (1) During the pandemic, firms with favorable\norganizational resources (state ownership and affiliation\nwith parent companies) are more likely to survive and grow,\nwhereas firms with foreign ownership or more financial\nobstacles are less likely to survive or grow. Firms in countries with a higher per capita income, a lower COVID-19\n\n\n\nspread, and a less stringent COVID-19 control policy are\nmore likely to survive and grow. (2) Favorable ownership\nand parent-company affiliations help cushion the pandemic\nshock during the pandemic. (3) The relationship between\nfirm characteristics and firm survival/growth is significantly\naffected by the stringency of a country’s COVID-19 policy.\n(4) Firm survival and growth are positively related to a coun\ntry’s cultural tendency in terms of long-term orientation\nand are not significantly related to uncertainty avoidance\nand individualism. The overall quality of country governance is negatively linked to the odds for firm survival as\nwell as revenue and employment growth.\n\n\n\nThis paper is a product of the Development Research Group, Development Economics. It is part of a larger effort by the\nWorld Bank to provide open access to its research and make a contribution to development policy discussions around the\n\nworld. Policy Research Working Papers are also posted on the Web at http://www.worldbank.org/prwp. The authors may\nbe contacted at lxu1@worldbank.org.\n\n\n_The Policy Research Working Paper Series disseminates the findings of work in progress to\n\nMention: \"World Bank\nEnterprise Follow-up Surveys\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"analyze\", \"summary\": \"Enterprise Follow-up Survey responses from firms across 36 countries are analyzed to explain survival, growth, revenues, and employment during COVID-19.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:001973:26:0", "occurrence_id": "fc776f605c64f0523dda1bfb", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: 25\n\n\n\nTable 2: Basic post-harvest indicators and PHL estimates for LSMS-ISA surveys\n\n\n\nStorage and crop protection\nmodalities among maize\nfarmers (national) (%)\n\n\n\nUG 2009-10 TZ 2010-11 TZ 2008-09 MWI 2010-11\n\n\n\nTraditional storage 1.4 24.8 19.2 17.9\nImproved storage 0.6 11.5 5.9 2.0\nCrop protection (spraying or 63.1 49.0 37.2 10.8\nsmoking)\n\n\n\n63.1 49.0 37.2 10.8\n\n\n\nNumber of observations\n(maize-producing households)\n\n\n\n1,853 1,520 1,301 10,331\n\n\n\nNotes: National numbers are household based estimates reweighted by maize harvested quantities. Improved storage refers to\nthe use of airtight drums, modern store or metallic silos, or improved local infrastructures. Traditional and improved storage\ntechniques are contrasted with “poor storage” that comprises in-house or ceiling storage, unprotected piles, and open drums\nand sacks.\n\nSource: LSMS-ISA surveys (authors’ own calculations)\n\nMention: \"LSMS-ISA surveys\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"analyze\", \"summary\": \"LSMS-ISA survey data support country-level estimates of maize-farmer storage and crop-protection practices.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:002014:30:2", "occurrence_id": "dee94fe2b4d1c3a8a85375a3", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: 049 - -.027\n(.057) (.056)\n\n\n\n(.056)\n\n\n\n\n- -.164***\n\n\n\n6 - -.049 - -.027\n(.057) (.056)\n\n7 - -.054 - .028\n(.056) (.055)\n\n\n\n7 - -.054 - .028\n(.056) (.055)\n\nObservations 3416 7637\nSource: EL.STAT, Quarterly Labor Force Survey-LFS (2017 – 2020, 1 st quarter).\nNotes: Reported estimates are average marginal effects drawn from a probit model (interaction effects\nmodel) and correspond to the post 2020Q1 period (additive effect). Based on the ILO definition of\nunemployment, the dependent variable takes the value of 1 if the individual is considered to be\nunemployed and 0 otherwise. Sample includes all individuals (aged 25-54) who have stopped working\nduring the last 8 quarters (2 years). All models include controls for gender, age, country of birth,\neducation, region and sector of economic activity of the last job. In parentheses, white\nheteroskedasticity corrected standard errors are reported. All estimates are weighted using the\nsampling weights provided by the EL.STAT. *** at 1%, ** at 5% and * at 1%.\n\nWe observe (column 2) that, for those who had been laid-off, the probability of\nsearching for work during the first quarter of 2020 was 11.2 percentage points lower\nthan in the first quarter of 2019. For those who were not working because their last\nemployment contract had been terminated, the drop in the probability\n\nMention: \"Quarterly Labor Force Survey-LFS\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"analyze\", \"summary\": \"Quarterly LFS data support weighted estimates of employment transitions and job-search behavior after layoffs.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:002076:58:0", "occurrence_id": "05d0714e01553cf1ab8f86c9", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: First follow-up (2004):\n\n\n_•_ Self-employment: same as baseline.\n\n\n_•_ Migration: defined according to response to survey information, question 2 part\n\nC (“Is household living in the same cluster as 10 years ago; nearby village; else\nwhere in Kagera; elsewhere in Tanzania; neighbouring country; other country”).\n\n\nSecond follow-up (2010):\n\n\n_•_ Self-employment: positive answer to section 2D, question T2dQ16 (“During the\n\npast 12 months, has [NAME] worked for him/herself or his/her household in\n\na non-farm business? For example, as an independent merchant or fisherman,\n\nlawyer, doctor, or other self-employed activity?”) and primary activity is not\n\nfarm/livestock work (section 2D, question T2dQ18).\n\n\n_•_ Migration: same as first follow-up.\n\n###### **B.8 Panel Survey of Income Dynamics (PSID)**\n\n\nThe PSID collects detailed information on occupation and income for the head and (if\n\npresent) for the ”spouse/partner” of each surveyed household.\n\n\nBaseline (2001):\n\n\n_•_ Income: defined as the sum of farm income (ER2042), business income (ER20422\n\nand ER20444), and labor income (ER20443 and ER20447) in the previous year.\n\nLosses are not reported for both farm and business income (i.e. these variables\n\nare truncated at zero).\n\n\n_•_ Occupation type: defined according to status in main job (ER17221 and ER17791;\n\n“On your main job, are you (HEAD) self-employed, are you employed by some\none else, or what?\n\nMention: \"Panel Survey of Income Dynamics\""}, {"role": "assistant", "content": "{\"role\": \"supporting\", \"usage_action\": \"analyze\", \"summary\": \"PSID occupation and income measures support analysis of household employment, migration, and self-employment outcomes.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:002083:36:0", "occurrence_id": "4568222ffcb87f11d323bc6c", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: Table 11: Simulation Employment Upgrading on the basis of education levels and occupational category\n\n\n(1) (2)\nEducation Occupation\nGDP Sim./Baseline GDP Sim./Baseline\n\n\nEcuador 101.9 101.6\n\n\nProvince\nPichincha 103.5 102.8\nGuayas 102.1 101.1\n\n\nNotes: GDP base value indexed to 100. According to the EPEC survey, Venezuelan workers account\nfor 2.9% of employment in Ecuador. Simulated scenario assumes that Venezuelan workers obtain\nthe same monthly earnings as Ecuadoran workers with the same education level (in column 1) or\noccupational category (in column 2) in the same province of residence. The simulation maintains\nwage levels constant at each education level and province. Quito is the capital of the Pichincha\nprovince and Guayaquil is the capital of Guayas.\n\n\n34\n\nMention: \"EPEC survey\""}, {"role": "assistant", "content": "{\"role\": \"supporting\", \"usage_action\": \"inform\", \"summary\": \"EPEC survey estimates the share of Ecuadorian employment held by Venezuelan workers, informing the employment-upgrading simulation.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:002155:60:0", "occurrence_id": "39ba31c96597afcca9d86f47", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: #### **Appendix** **A Other Descriptive Figures and Tables**\n\n‘\n\n\nFigure A1: Share of self-employed workers in Bangladesh and global oil prices\n\n\n_Source:_ Bangladesh Labor Force Surveys 1999-2017 for share of self-employment; OPEC\nReference Basket for crude oil prices.\n_Note:_ The sample is restricted to employed males aged 18-59 in rural or semi-urban areas.\n\n\n59\n\nMention: \"OPEC\nReference Basket\""}, {"role": "assistant", "content": "{\"role\": \"supporting\", \"usage_action\": \"analyze\", \"summary\": \"OPEC crude-oil prices are plotted alongside Bangladesh self-employment rates for comparison over time.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:002190:14:0", "occurrence_id": "1140a1d7049bff9bd8df7e97", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: of pre-treatment survey periods and those surveyed in the immediate aftermath), and consider the\n\n\nthird and fourth quarters to be post-treatment. Thus, while our baseline specification averages\n\n\nthe effects on workers surveyed from 5 weeks to 3 years after the Rana plaza collapse, we also run\n\n\nspecifications where we explicitly consider treatment effect heterogeneity by time duration since\n\n\nthe collapse.\n\n\n**3.3** **Identification** **strategy**\n\n\nOur main identification strategy is a triple-difference that tests for differential outcomes in apparel\n\n\nworkers (vs non-apparel manufacturing workers), in the four districts of Bangladesh that constitute\n\n\nthe vast majority of export apparel factories (vs the rest of the country), pre-vs post Rana Plaza.\n\n\nWe define the apparel industry according to the ISIC-3 classification (ISIC-3 two-digit code 18),\n\n\nwhich we also refer to as the garment industry.\n\n\nOur treated districts are Dhaka, Gazipur, Narayanganj, and Chittagong. As these districts\n\n\nrepresent 3229 of the 3251 (99%) export-oriented ready-made garment factories mapped as of\n\n\nMarch 2021 (Mapped in Bangladesh, 2021), we argue that they were most closely affected by\n\n\nthe Rana Plaza reforms, given the role of international buyers described in section 2.2. Although\n\n\ngarment employment in Bangladesh is disproportionately concentrated in the four treated districts,\n\n\ncontrol districts still host 46% of garment workers in the sample, giving us sufficient control\n\n\nobservations in our triple-difference estimation. Figure 4 shows the distribution of garment workers\n\n\nacross treatment and control districts.\n\n\nWe thus estimate the following specification for an outcome _Y_ for worker _i_ in district _j_ at time\n\n\n13\n\nMention: \"Mapped in Bangladesh\""}, {"role": "assistant", "content": "{\"role\": \"supporting\", \"usage_action\": \"validate\", \"summary\": \"Mapped in Bangladesh factory locations substantiate that treated districts contain nearly all export-oriented garment factories.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:002242:27:0", "occurrence_id": "c7078b4133ae40fad255cf27", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: **Table 1: Variable definitions and Sources**\n\nVariables Definition and source\n\n\n\nCases per 1000\n\nresidents\n\n\nPandemic mortality\n\nrate\n\n\nDelay I\n\n\nDelay D\n\n\n\nDelay in implementing domestic close-down policy, equals to the number of days, divided by 100, from the\n\nday that the economy discloses the first COVID-19 case to the day that the government first announces\ntheir domestic closedown policy, which include school closing, workplace closing, public events\ncancelling, restrictions on gatherings, public transport closing, stay at home requirement and restrictions\non internal movement. Lower number indicates prompt government response. Calculated based on the\ndataset constructed by Hale et al. (2020).\n\n\n\nThe number of confirmed COVID-19 cases per 1,000 residents. Calculated based on original coronavirus data\n\nfrom Johns Hopkins Coronavirus Resource Center. Updated to November 19, 2020. In regressions, we\nuse _Log (1+Cases per 1000 residents)_ as the dependent variable.\n\n\n\nTotal pandemic deaths divided by total confirmed COVID-19 cases. Calculated based on original coronavirus\n\ndata from Johns Hopkins Coronavirus Resource Center. Updated to November 19, 2020.\n\n\n\nDelay in controlling the international travel, equals to the number of days, divided by 100, from the day that\n\nthe economy discloses the first COVID-19 case to the day that the government first announces the policy\nto restrict the international travel. Lower number indicates prompt government response. Calculated based\non the dataset constructed by Hale et al. (2020).\n\n\n\nAvg Temperature Average temperature since the month COVID-19 arrived to November, divided by 100.\n\nMiddle (Top)\n\nThe distance of the country or special region to China is in the middle (top) tercile in the distance to China.\nDistance2China\n\nLongitude, Latitude Geographic coordinate, divided by 100.\n\nGDP per capitai t =\n\n\n\nK\n\n\nk=1\n\n\n\n\naik ∗ tariffst k. (3.3)\n\n\n\nThe information on trade weighted tariffs on products corresponding to the I/O codes comes\n\n\nfrom the World Bank’s WITS database. It should be noted that many industries in China\n\n\nhave access to duty free intermediate inputs through duty drawbacks and hence would not\n\n\nbe affected by tariffs on intermediate inputs. Nonetheless, there are many industries that do\n\n\npay these tariffs and thus it is important to include this variable in the estimation. 10\n\n\n3.4. Market Access\n\n\nWe construct two measures of market access to re fl ect that fi rms can supply other fi rms\n\n\nand households within their own province and in other provinces. The own market access\n\n\nmeasure is de fi ned as\n\n\n\n+ bi\n\n\n\n\n\n\n\nMA_own i p,t =\n\n\n\n\n- kK=1\n\n\n\n\nbik\n\n\n\np,t\nY k\n\n\n\nYp,t k\n\n\n\nGDPp,t\nGDPCHINA,t\n\n\n\n∗ DISTpp −1, (3.4)\n\n\n\nCHINA,t\n\n\n\nwhere Yp,t k\n\nMention: \"the World Bank’s WITS database\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"analyze\", \"summary\": \"WITS tariff data provide trade-weighted measures of restrictions on imported intermediate inputs used in the China model.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:003139:25:1", "occurrence_id": "bc899f6cf7060c892ac11ef0", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: .076
0.905
1.105
0.971
1.078
0.892|\n\n\n\n**Table 16: Money’s Worth Ratios in Selected Countries**\n**Computed with Cohort Annuitant Table and Risk-Free Rate**\n\n|Col1|Australia Canada Switzerl. UK 1 UK UK 2 US 3
(James) (James) (James) (Cannon) (James) (Brown) (Brown)|\n|---|---|\n|**Nominal Annuities**
Male, Age 55
Male, Age 65
Female, Age 55
Female, Age 65
Joint
**Indexed Annuities**
Male, Age 55
Male, Age 65
Female, Age 55
Female, Age 65
Joint|
-
-
-
-
-
0.921
0.934
1.013
0.981
1.046
-
0.977
0.908
0.927
-
-
-
-
-
0.928
0.937
1.002
0.976
1.036
-
0.979
0.907
0.927
0.988
0.980<\n\nMention: \"Cohort Annuitant Table\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"analyze\", \"summary\": \"Cohort annuitant-table inputs are used with risk-free rates to calculate money's-worth ratios for annuities.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:003344:6:0", "occurrence_id": "b86112ea537d2ff322cbfa06", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: strengthening their creditor position. In contrast, the Indian current account balance has\nreturned to negative territory with a deficit of 1.5 percent in 2005 and projected deficits\nof 2.1 and 2.7 percent for 2006 and 2007, respectively, thus deepening their debtor\nposition.\n\nCompared with other developing countries, Figure 2 shows that China and India had at\nthe end of 2004 net foreign asset positions that were less negative than is typically the\ncase for countries at a similar level of development. This remains true today. Although\nsome developing countries have more positive net positions, those typically are resourcerich economies.\n\nIn global terms, the imbalances of China and India are relatively small, as illustrated in\nTable 1. At the end of 2004, the Chinese creditor position amounted to only 7.4 percent\nof the level of Japanese net foreign assets (Japan is the world’s largest creditor nation),\nwhereas Indian net liabilities were only 2.8 percent of U.S. net external liabilities (the\nU.S. is the world’s largest debtor nation). Scaled differently, China’s net creditor position\nof 131 billion dollars at the end of 2004 amounted to only 5 percent of the U.S. negative\nexternal position of $2.65 trillion. 10 [^10: These calculations are based on data drawn from Lane and Milesi-Ferretti (2006). In recent years, the\nmajor oil exporters plus other Asian economies have also run substantial current account surpluses.] However it is increasingly important on a flow basis:\nits projected 2006 current account surplus of $184 billion amounts to more than 20\npercent of the projected U.S. current account deficit of $869 billion (IMF, World\nEconomic Outlook database).\n\nUnderlying these net positions is a significant increase in the scale of China’s and India’s\ninternational balance sheets. Figure 3 shows the sum of foreign assets and liabilities\n(divided by GDP). This indicator of\n\nMention: \"World\nEconomic Outlook database\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"inform\", \"summary\": \"IMF World Economic Outlook projections provide current-account estimates used to compare China's surplus with the U.S. deficit.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:003557:4:0", "occurrence_id": "4e3e44aa41a71b6e27aac371", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: high. Hall’s conclusion is that “small and new innovative firms experience high costs\nof capital that are only partly mitigated by the presence of venture capital,” while\n“evidence for high costs of R&D capital for large firms is mixed”. In more recent work,\nBenfratello et al. (2006) use firm data from Italy to investigate the effect of regional\nbanking development on innovative activities, and find evidence of a stronger positive\neffect for small firms.\n\nPrior research thus suggests that financial development has a disproportionately\npositive affect on innovation by small firms. This innovation channel could be one\nreason behind the heterogenous impact of finance on firm growth. Moreover, the\nobserved higher productivity and lower spending on innovation in small firms suggests\nthat financial growth could lead to a more optimal interfirm allocation of spending\non innovation. This hypothesis implies that as financial markets develop, there is\nrelatively more R&D investment by smaller firms, and that relative R&D productivity\nin larger firms rises. In this paper, I use data on firms from 57 countries to see if this\ndual pattern shows up in cross-country data from developing economies.\n\nI find that within industries, relative R&D spending in smaller firms is more likely\nand sizable in countries at higher levels of financial development. The estimates imply\nthat among firms doing R&D in a country at the 20th percentile of financial development, a one standard deviation decrease in firm size is associated with a decrease of 0.7\nstandard deviation in R&D spending. In contrast, this decrease is only 0.2 if financial\ndevelopment is at the 80th percentile of its distribution across countries. My second\nfinding also supports the hypothesis: small firms report producing more innovations\nper unit R&D than large firms, but this gap is narrower in countries at higher levels\nof financial development.\n\nTo verify further that the observed patterns relate to financing, I exploit the crossindustry dimension of my data, interacting financial\n\nMention: \"data on firms from 57 countries\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"analyze\", \"summary\": \"Cross-country firm data are analyzed to test how financial development relates to R&D spending and innovation.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:003458:2:0", "occurrence_id": "ab7a06dffd1f2dce5de0618b", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: the MDG target of gender parity in primary education by 2005, and the regions with the highest\n\n\ngaps will have to make even greater gains if gender parity is to be achieved as part of universal\n\n\nprimary school completion by 2015. Girls’ exclusion from education in comparison to boys,\n\n\nespecially in South Asia, Sub-Saharan Africa and the Middle East and North Africa, is one of the\n\n\nclearest indicators of gender discrimination (UNICEF 2005).\n\n\nOf those children in developing countries that are in school, most are not learning\n\n\nadequately. The few participating countries in international achievement tests such as TIMSS,\n\n\nPIRLS and PISA usually score near the bottom, especially when compared to middle and high\n\nincome countries. Their levels of comprehension are minimal in important subjects such as\n\n\nmath, science and reading. In fact, 54 percent of Peruvian 15-year-olds are at the lowest level of\n\n\ncomprehension in reading according to the OECD’s PISA assessment; while 23 percent of youth\n\n\nin Argentina and Brazil, 31 percent in Indonesia, and 10 percent in Thailand are at this level. By\n\n\ncontrast only 3 and 4 percent of youth in the United Kingdom and France score at this level.\n\n\nAlthough life expectancy has increased, 10 million children die every year before their\n\n\nfifth birthday (UNICEF 2005), largely from preventable causes, and malnutrition is a\n\n\ncontributing factor in more than half of these. More than 50 percent of the 10 million children\n\n\ndie at home due to poor access to health care. Acute respiratory infections are the biggest single\n\n\nkiller (2 million every year), followed by diarrhoeal diseases, malaria, measles, pertussis,\n\n\ntuberculosis and neonatal tetanus. More than half a million children die of HIV/AIDS each year.\n\n\nMaternal mortality ratios have remained high in some parts of the world, at 1,100 deaths per\n\n\n100,000 live births in Sub-Saharan Africa and 440 in developing countries, compared to 12 for\n\n\ndeveloped countries (Belli and Appaix 2003\n\nMention: \"OECD’s PISA assessment\""}, {"role": "assistant", "content": "{\"role\": \"background\", \"usage_action\": \"inform\", \"summary\": \"PISA assessment results contextualize reading-comprehension differences across countries and education systems.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:003549:17:1", "occurrence_id": "a68bb056ecdb44fbdce9a46c", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: (land values VL). The model in (8) was employed for this\nresearch, as data on land prices for the selected samples were not available. This is the same\napproach followed by Sanghi et al. (1998) and Kumar & Parikh (1998) for India.\n\n\n**_5.2 Data description_**\n\n\nThe household data for this study was based on a sample of 1000 farmers randomly selected from\ndifferent agro-ecological settings of the country, who were believed to be representatives of the\nwhole nation (Table 1). A total of 50 districts (20 farmers from every district) were purposely\nselected, starting from the extreme highlands of the southeastern regions of the Oromia Regional\nState to the lowlands of the Afar Regional States. Yale University and the University of Pretoria\nprovided the questionnaire for this study, which asks about a variety of household attributes. The\ninterviews with the farmers took place during the 2003/2004 production seasons. Almost all were\nsmall-scale farmers with rainfed farms, as more than 95% of Ethiopian farmers are of this type.\n\n\nThe temperature data for this study was derived from the satellite data provided by the US\nDepartment of Defense and the precipitation data from the African Rainfall and Temperature\nEvaluation System (ARTES). The soil data for this study was obtained from the Food and\nAgricultural Organization. The FAO provides information about the major and minor soils in each\nlocation, including the slope and texture. The hydrological data (flow and runoff) was obtained\nfrom the University of Colorado (IWMI/ University of Colorado 2003). The hydrology team\ncalculated flow and runoff for each district using the hydrological model for Africa.\n\n\n16\n\nMention: \"African Rainfall and Temperature\nEvaluation System\""}, {"role": "assistant", "content": "{\"role\": \"supporting\", \"usage_action\": \"analyze\", \"summary\": \"ARTES precipitation data provide climatic inputs for evaluating Ethiopian farm productivity and land-use outcomes.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:003686:5:0", "occurrence_id": "9d18a918230797fd55c508b7", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: having the highest female participation rate at 67 percent. In contrast, the BH female\nparticipation rate is 43 percent. 4 [^4: This is based on a sample of transition economies using the latest available ILO (Key Indicators of the\nLabor Market) data. Data are available from the authors on request. See also Paci (2002) for a comparison\nof gender differentials in labor market outcomes, among other indicators, in the ECA region.]\n\n\nTable 1. Key Labor Market Indicators\n\n(In units as indicated)\n\n\n2001 2002 2004\n\n\nUnemployment rate (in percent of labor force)\n\n\n\n.2\n\n\n\nAll 16.0 21.6 22.2\nFederation 16.9 21.6 20.8\nRepublika Srpska 15.3 21.5 23.8\nMen 15.3 19.6 21.2\nWomen 17.5 25.1 24.1\n\n\n\n.2\n.1\n\n\n\nEmployment rate (in percent of working age population)\n\n\n\nAll 40.4 41.8 45.9\nFederation 34.6 36.4 43.4\nRepublika Srpska 46.4 47.5 47.3\nMen 53.9 55.4 59.1\nWomen 27.2 28.5 32.8\n\n\n\n.9\n\n\n\n.1\n.8\n\n\n\nLabor force participation rate (in percent of working age population)\n\n\n\nAll 48.1 53.3 59.0\nFederation 42.2 47.1 55.8\nRepublika Srpska 55.4 60.9 63.0\nMen 63.6 68.9 75.0\nWomen 32.9 38.0 43.1\n\n\n\n.0\n\n\n\n.0\n.1\n\n\n\nEmployment by sector\n\nFormal sector (in percent of total employment) 63.0 61.0 57.7\nFederation 67.2 68.1 63.7\nRepublika Srpska 59.1 54.6 51.3\n\nInformal sector (in percent of total employment) 1 37.0 39.0 42.3\nFederation 32.8\n\nMention: \"Key Indicators of the\nLabor Market\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"analyze\", \"summary\": \"ILO labor-market indicator data underpin the female participation-rate comparison across transition economies.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:003961:14:0", "occurrence_id": "6309b2e9b89d3f14f1a6d17e", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: direct impact on the MWP decision. Causal effects of migration could be identified by a\n\n\nvariation in the instrumental variables since the effect of this variation is entirely\n\n\nchanneled through the household’s migration decision. We used information from the\n\n\n2001 Nepal Census Data (Central Bureau of Statistics 2003) to construct two\n\n\ninstrumental variables: the proportion of internal and abroad migrants in a ward (village)\n\n\nin 2001. We argued that the women’s decisions to participate in market work in 2004\n\n\nshould not be directly affected by the extent of migration networks in 2001, after\n\n\ncontrolling for the then current conditions on the local labor market. Studies of the Nepali\n\n\nlabor market indicate that female and male labor markets are segmented and the rates of\n\n\nfemale paid employment are only marginally affected by changes in labor market\n\n\nconditions for males (Acharya 2003, Bhatt and Bhattarai 2006).\n\n\nThe proportion of migrants in a ward in 2001 could be interpreted as a proxy for\n\n\nthe ward-level networks that help future migrants to migrate (e.g., Carringon,\n\n\nDetragiache, and Vishwanath 1996; Munshi 2003). When in the host country, Nepali\n\n\nmigrants develop extensive social and information networks that link them with relatives\n\n\nand friends in the home country (Yamanaka 2000). Such networks lower the cost of\n\n\nmigration for the population of a ward. Indeed, in Nepal, migrants tend to follow their co\n\nvillagers and migrate to the same destinations (Thieme 2006). They also are likely to fill\n\n\na similar niche in the labor market. The identification strategies that use migrant networks\n\n\nas instruments for migration decisions were applied by Woodraff and Zenteno (2001) and\n\n\nMcKenzie and Rapoport (2005) in studies of migration in Mexico.\n\n\n_Explanatory variables_\n\n\nOur theoretical model guided us on selecting the explanatory variables for the empirical\n\n\nspecification. Conceptually, these variables can be grouped into four categories. The first\n\n\ngroup of variables contains those characteristics of a woman that determine\n\nMention: \"the\n\n\n2001 Nepal Census Data\""}, {"role": "assistant", "content": "{\"role\": \"supporting\", \"usage_action\": \"analyze\", \"summary\": \"Census data used to construct ward-level migration-network instrumental variables for women’s labor-market participation analysis.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:003999:5:1", "occurrence_id": "57605f84bbca4c3c09c4ae65", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: regional disparities in income and welfare have existed for some time in\n\n\nBrazil, there is not a clear consensus on whether it is mainly due to returns to characteristics or the\n\n\ndistribution of characteristics. Our paper explores these issues in more depth. Aside from the fact that we\n\n\nuse consumption instead of income as a measure of welfare, our approach is different from previous\n\n\nstudies in that we (i) disaggregate urban areas into metropolitan and non-metropolitan areas within\n\n\nregions to obtain a more refined picture, and (ii) analyze both differences in mean welfare and differences\n\n\nbetween distributions, using Oaxaca-Blinder and quantile regression decomposition techniques.\n\n\nThis paper is organized as follows. Section 2 presents the methodology for the decomposition of\n\n\nmean welfare differentials and the quantile regression decomposition along with a brief summary of the\n\n\n2002-03 Pesquisa de Orcamentos Familiares household budget survey and the variables used in the\n\n\nanalysis. Section 3 presents the results of these decompositions, and Section 4 concludes and discusses\n\n\nsome of the implications for policy.\n\n\n3\n\nMention: \"Pesquisa de Orcamentos Familiares\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"analyze\", \"summary\": \"Household budget survey and variables used in analysis of regional welfare differences, consumption, and income.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:004168:10:1", "occurrence_id": "157d301b9a53483a3dba4921", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: with very low poverty rates, but poverty measures then rose sharply in the\n\ntransition. 18 The earliest available surveys pick up these low poverty rates, with a number of\n\n\ncountries having no sampled household living below the poverty lines typical of developing\n\n\ncountries. With the subsequent rise in poverty incidence, this looks like ―convergence,‖ but it has\n\n\nlittle or nothing to do with neoclassical growth processes—rather it is a ―policy convergence‖\n\n\n15 It is known that aggregation can hide the true relationships between the initial distribution and growth,\ngiven the nonlinearities involved at the micro level (Ravallion, 1998); identifying the deeper structural relationships\nwould require micro data, and even then the identification problems can be formidable.\n16 The only exception was that urban surveys were also used (for both the first and last survey) for Uruguay\nwhere over 90% of the population lives in urban areas. Results were robust to dropping these urban surveys.\n17 The data set was constructed from _[PovcalNet](http://econ.worldbank.org/povcalnet)_ in December 2008.\n18 Prior to the global financial crisis there were signs that poverty measures were finally falling in the region,\nsince the later 1990s; see Chen and Ravallion (2010).\n\n\n9\n\nMention: \"povcalnet\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"analyze\", \"summary\": \"The study’s poverty dataset was constructed from PovcalNet in December 2008.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:004170:4:0", "occurrence_id": "09b04948538a3236e5829477", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: 3 \nreach the students who are supposed to benefit from the program. However, parents could \nreact by reallocating food in the household away from these children who are already benefiting \nfrom the program. Food received by the household under THR is more likely to be shared by other \nhousehold members, hence reaching children who may be in need of additional food. Because the \nnutritional benefits would be diluted within the household, the impact on academic performance is \nlikely to be lower for THR than with a school meals program. Which program should be \npreferred is depends both on the policy objectives as well as on the evidence base. The latter \nempirical question is addressed by this paper. \nThe paper uses a randomized experiment to assess the hypothesized relationships between \nSFPs on the one hand, and enrollment, academic performance, cognitive development and preschool \nchildren nutritional status on the other hand. The focus of this study is the Sahel region of northern \nBurkina Faso in West Africa. Northern Burkina Faso is an appropriate context to evaluate the \nimpact of school feeding program for two main reasons. First, the region has some the world’s \nlowest primary school participation. On average 20 percent of school age children (6 to 16 years old) \nattend school, based on recent national surveys (e.g. Institut National de la Statistique et de la \nDémographie & ORC Macro, 2004). Therefore there exists a large scope for increasing enrollment. \nSecond, income levels are very low and severe food shortages are frequent (Zoungrana et al., 1999). \nHence, the value of the food offered should be a sufficient incentive to attract children to school. \nOur analysis adds to the literature on education in low-income countries in two ways. \nFirst, it rigorously evaluates the impact of two alternative school feeding schemes within the same \ncontext. The use of a randomized experiment has the advantage of avoiding the issue of site \nselection that may have limited the causal interpretation of many previous studies. Hence the paper\n\nMention: \"Institut National de la Statistique et de la \nDémographie\""}, {"role": "assistant", "content": "{\"role\": \"supporting\", \"usage_action\": \"inform\", \"summary\": \"National survey evidence for the region’s school-age participation rate.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:004170:4:0", "occurrence_id": "07b962dff4075c4d4eb6c4d5", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: 3 \nreach the students who are supposed to benefit from the program. However, parents could \nreact by reallocating food in the household away from these children who are already benefiting \nfrom the program. Food received by the household under THR is more likely to be shared by other \nhousehold members, hence reaching children who may be in need of additional food. Because the \nnutritional benefits would be diluted within the household, the impact on academic performance is \nlikely to be lower for THR than with a school meals program. Which program should be \npreferred is depends both on the policy objectives as well as on the evidence base. The latter \nempirical question is addressed by this paper. \nThe paper uses a randomized experiment to assess the hypothesized relationships between \nSFPs on the one hand, and enrollment, academic performance, cognitive development and preschool \nchildren nutritional status on the other hand. The focus of this study is the Sahel region of northern \nBurkina Faso in West Africa. Northern Burkina Faso is an appropriate context to evaluate the \nimpact of school feeding program for two main reasons. First, the region has some the world’s \nlowest primary school participation. On average 20 percent of school age children (6 to 16 years old) \nattend school, based on recent national surveys (e.g. Institut National de la Statistique et de la \nDémographie & ORC Macro, 2004). Therefore there exists a large scope for increasing enrollment. \nSecond, income levels are very low and severe food shortages are frequent (Zoungrana et al., 1999). \nHence, the value of the food offered should be a sufficient incentive to attract children to school. \nOur analysis adds to the literature on education in low-income countries in two ways. \nFirst, it rigorously evaluates the impact of two alternative school feeding schemes within the same \ncontext. The use of a randomized experiment has the advantage of avoiding the issue of site \nselection that may have limited the causal interpretation of many previous studies. Hence the paper\n\nMention: \"ORC Macro\""}, {"role": "assistant", "content": "{\"role\": \"supporting\", \"usage_action\": \"inform\", \"summary\": \"Co-cited source for national survey evidence on school participation.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:004279:7:0", "occurrence_id": "9cc9bff172c45bf6ebe8dfc0", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: Economic theory details how problems arising from asymmetric information undermine\n\n\neconomic incentives to such an extent that it may be impossible to serve the under-served\n\n\n(Akerlof 1970 and Stiglitz 1974). The major contribution of microfinance has been to\n\n\ndemonstrate innovative contracts that, both in practice and in theory, can make commercial\n\n\nlending to the poor viable. Gangopadhyay and Lensink (2009), for example, build on previous\n\n\nwork on joint liability borrowing to show how contracts can mitigate adverse selection.\n\n\nArmendáriz and Morduch (2010) show how microfinance contracts reduce moral hazard.\n\n\nIn our 2007 analysis of the MIX data, we investigate the role of contracts empirically\n\n\n(Cull et al. 2007). The study considers lenders that offer different kinds of contracts:\n\n\nconventional bilateral lending agreements, Grameen Bank-style group contracts, and “village\n\n\nbanks” that also use group-based methods. Using one observation per institution from 1999 to\n\n\n2002, we focus on qualitative information on institutions’ lending style, range of services\n\n\noffered, profit status, ownership structure, and source of funds. We include a “lending type”\n\n\nvariable that categorizes institutions, separating individual-based lenders, group-based lenders,\n\n\nand village banks. For our profitability regressions, the primary dependent variable is the\n\n\nfinancial self-sufficiency ratio (FSS), a ratio of revenues and expenses adjusted to account for\n\n\nsubsidies. We also regress two other measures of profitability, the operational self-sufficiency\n\n\nratio (OSS) and return on assets (ROA). A second set of regressions uses “portfolio at risk” as\n\n\nthe dependent variable, and a third investigates mission drift by regressing three outreach\n\n\nvariables. In this third set, the dependent variables are average loan size over GNP, average loan\n\n\nsize relative to the average per capita income of the bottom 20% for the country, and the share of\n\n\nborrowers that are women. While some observers define mission drift narrowly, in terms\n\nMention: \"the MIX data\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"analyze\", \"summary\": \"Institution-level MIX data used to analyze microfinance lenders’ contracts, profitability, portfolio risk, and outreach over 1999–2002.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:004733:8:0", "occurrence_id": "8104db0a602588ebc35573ff", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: the Internet on trade either take a macro or a marketing-business approach which are\n\n\nusually based on small and localized business surveys.\n\n\nAmong the macro studies of the impact of the Internet on international trade,\n\n\nFreund and Weinhold (2004), for example, find that the use of the Internet stimulates\n\n\ntrade. Evidence from time-series and cross-section regressions shows a significant effect\n\n\nof the Internet on trade in recent years. The results suggest that a 10 % increase in the\n\n\ngrowth of web hosts in a country leads to about a 0.2 % increase in export growth. For\n\n\nthe average country in their sample, the Internet contributed to about a 1% increase in\n\n\nannual export growth from 1997 to 1999. Mann et al. (2004) quantify the effects of trade\n\n\nfacilitation by considering four aspects of trade facilitation effort: ports, customs,\n\n\nregulations, and e-business. Based on a specific simulation design, the authors find that\n\n\nan improvement in their measure of e-business of the “below-average” countries\n\n\n“halfway” to the global average yields an increase in global trade of $154 billion. Ferro\n\n\n(2008) finds that a reduction in costs related to creating a website results in an increase in\n\n\nthe proportion of firms that are able to export which in turn results in greater trade flows.\n\n\nMarketing studies have also found positive effects of the Internet on trade. For\n\n\nexample, Prasad et al. (2001) using survey data from a midwestern state in the U.S. find\n\n\nthat firms' integration of Internet technology into marketing activities generally leverages\n\n\nthe influence of market orientation on the firms' marketing competencies (compared with\n\n\ncompetitors), which in turn have a positive impact on their export performance. Daly and\n\n\nMiller (1998) present evidence from a 1998 survey of enterprises in 15 low and middle\n\nincome countries that suggests that firms in these countries use search engines to research\n\n\n7\n\nMention: \"1998 survey of enterprises\""}, {"role": "assistant", "content": "{\"role\": \"supporting\", \"usage_action\": \"inform\", \"summary\": \"Survey evidence from enterprises in 15 low- and middle-income countries on firms’ Internet use and trade-related activities.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:004733:8:0", "occurrence_id": "3d5cc9f37f31b2da5cad6d05", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: the Internet on trade either take a macro or a marketing-business approach which are\n\n\nusually based on small and localized business surveys.\n\n\nAmong the macro studies of the impact of the Internet on international trade,\n\n\nFreund and Weinhold (2004), for example, find that the use of the Internet stimulates\n\n\ntrade. Evidence from time-series and cross-section regressions shows a significant effect\n\n\nof the Internet on trade in recent years. The results suggest that a 10 % increase in the\n\n\ngrowth of web hosts in a country leads to about a 0.2 % increase in export growth. For\n\n\nthe average country in their sample, the Internet contributed to about a 1% increase in\n\n\nannual export growth from 1997 to 1999. Mann et al. (2004) quantify the effects of trade\n\n\nfacilitation by considering four aspects of trade facilitation effort: ports, customs,\n\n\nregulations, and e-business. Based on a specific simulation design, the authors find that\n\n\nan improvement in their measure of e-business of the “below-average” countries\n\n\n“halfway” to the global average yields an increase in global trade of $154 billion. Ferro\n\n\n(2008) finds that a reduction in costs related to creating a website results in an increase in\n\n\nthe proportion of firms that are able to export which in turn results in greater trade flows.\n\n\nMarketing studies have also found positive effects of the Internet on trade. For\n\n\nexample, Prasad et al. (2001) using survey data from a midwestern state in the U.S. find\n\n\nthat firms' integration of Internet technology into marketing activities generally leverages\n\n\nthe influence of market orientation on the firms' marketing competencies (compared with\n\n\ncompetitors), which in turn have a positive impact on their export performance. Daly and\n\n\nMiller (1998) present evidence from a 1998 survey of enterprises in 15 low and middle\n\nincome countries that suggests that firms in these countries use search engines to research\n\n\n7\n\nMention: \"survey data from a midwestern state\""}, {"role": "assistant", "content": "{\"role\": \"supporting\", \"usage_action\": \"inform\", \"summary\": \"Marketing study uses survey data to relate firms’ Internet integration to marketing and export performance.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:004824:9:0", "occurrence_id": "2dcf02575493940da560f726", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: chose loan clients in this age bracket because Partner felt that business and financial education\n\n\ncould have a particularly large impact on this group. Youth unemployment is high in Bosnia,\n\n\nabout 58 percent according to the 2007 Labor Force Survey, and self‐employment provides a\n\n\nviable solution to this problem. In this type of environment, it is particularly important to\n\n\nexplore strategies to promote the entry, survival, and growth of youth‐led businesses.\n\n\nWe limited our study sample geographically to areas around Tuzla, 5 where Partner is\n\n\nheadquartered, to facilitate the logistics of the business training. Moreover, we dropped clients\n\n\nwho had not taken out a loan for business purposes from our sample in order to target clients\n\n\nwho were either running a business or planning to start a business. We also did not include\n\n\nclients who were delinquent on their loan payments according to Partner’s definition. 6\n\n\nAll 2,274 Partner clients meeting these criteria received an initial screening phone call, asking\n\n\nthem whether they would be interested in participating in a business and financial education\n\n\ntraining course. About 500 clients could not be reached over the phone. Among the 1,783\n\n\nclients who were reached, half reported being interested in participating in the course. Table 1\n\n\n5We limited the sample to clients living in the municipalities of Banovici, Gracanica, Gradacac, Kalesija, Lukavac,\nSebrenik, Tuzla, and Živinice.\n6 Partner’s definition of delinquent loans is either being more than 15 days late on the current payment or having a\ncumulative number of late payment days over 15. The reason for not including these clients in the sample is that it\nis Partner’s policy not to offer any programs or new loans to delinquent clients.\n\n\n8\n\nMention: \"the 2007 Labor Force Survey\""}, {"role": "assistant", "content": "{\"role\": \"supporting\", \"usage_action\": \"inform\", \"summary\": \"Labor Force Survey provides context for the high youth-unemployment rate motivating the business-training study.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:004863:39:0", "occurrence_id": "9211cac403c806a70d9d94ed", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: **Table 4. Incidence of Violent Shocks**\n\n**Percentage**\n\n\n\n**Percentage of**\n\n**Communities**\n\n**Affected**\n\n\n\n**Type of shocks**\n\n\n\n**of**\n**households**\n\n**affected**\n\n\n\nMurder 11.22% 13.19%\nCattle Theft 24.88% 31.09%\nLand Expropriations 0.98% 1.04%\nThreats by armed groups 4.39% 4.45%\nKidnappings 1.46% 1.31%\n\n\nAt least one violent shock 36.10% 43.55%\n\n\nN 205 3,754\nTotal number of shocks 74 1,635\n\nSource: CLS-WILL: first wave – community questionnaire.\n\n\n**Table 5. Household Income: Descriptive Statistics**\n\n\n\n**Difference**\n\n**between**\n**means (t-test)**\n\n\n\n**Violent**\n\n**shock**\n\n\n\n**No**\n**Violent**\n\n**Shock**\n\n\n\n**All**\n\n\n\nTotal Income 2,637,983 1,869,390 *** 2,200,207\n(9,286,131) (6,843,082) (7,994,481)\nAgricultural production\nincome 982,511 1,033,592 1,011,606\n(3,493,644) (4,979,059) (4,401,047)\n\n\nLivestock production income 1,223,497 582,002 *** 858,114\n(8,077,275) (4,052,256) (6\n\nMention: \"CLS-WILL\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"analyze\", \"summary\": \"First-wave community questionnaire data used to report incidence of violent shocks; following tables compare household income by shock exposure.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:004899:8:0", "occurrence_id": "315c00158248ff08d7677baf", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: The main strength of the DLM database is that it distinguishes between\nthree levels of education for migrants. High-skilled migrants are those with postsecondary/tertiary education. Medium-skilled migrants are those with uppersecondary education completed. Low-skilled migrants are those with less than\nupper-secondary education, including those with lower-secondary and primary\neducation or those who did not go to school. The main characteristics of the\ndiaspora that we consider in this paper are the following:\n\n\n - The bilateral migration flow for each skill group from origin country - to\ndestination OECD country d is proxied by the change between 1990 and\n2000 in the stock of migrants from - to d.\n\n\n - The bilateral indicator of positive selection is proxied by the log-ratio of\nthe number of high-skilled to low-skilled new migrants from - to d (we\ndisregard medium-skilled migrants for this specification with no impact\non the results)\n\n\n - The bilateral indicator of relative concentration is the ’high-skill minus\nlow-skill’ difference in the squared proportions of migrants from a given\norigin country - to the 30 possible destinations, following equation (4).\n\n\n - The size of the existing diaspora is measured as the immigrant population\nborn in country - and living in the OECD country d (≠ o) in 1990.\n\n\n3.1 Individual vs aggregate data\n\n\nThe use of aggregate macro data has many advantages but also introduces\ncertain complications. In this section, we discuss the pros and cons of using\nthis dataset, and the main econometric issues triggered by our approach. An\nimportant distinction in the empirical analysis of migration data concerns the\nuse of a individual (micro) data as opposed to aggregate (macro) one. Micro\ndata are collected at the household and/or individual level to study the impact\nof networks on the propensity to migrate and the educational composition of\nthe migrants (Massey, 1986; Munshi, 2003, McKenzie and Rapoport, 2010).\nThese datasets\n\nMention: \"DLM database\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"analyze\", \"summary\": \"Database used to construct bilateral migrant-flow, skill-selection, concentration, and diaspora-size measures.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:005212:29:0", "occurrence_id": "5f9d98ac91816b9dd189debe", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: successive primary deficits. The same holds true for the aggregate performance of states; figure 6\n\n\nshows that the fiscal correction phase in states also coincides with a higher GDP growth rate and\n\n\nlower rate of interest paid on state debt. This was also in part the result of fiscal correction,\n\n\nwhich led to a reduction in government dis-savings and debt. This, however, masks the varied\n\n\nfiscal performance of individual states, which has been mixed over the period, causing concern\n\n\nin the context of the global crisis.\n\n\n**Figure 6: Differential between GDP growth rate and interest rate on state debt**\n\n\n\n\n\n\n\nSource: authors‘ calculation with base data from RBI\n\n\n**Section 5: Impact of the Global Financial Crisis and Going Forward**\n\n\nAlthough, the immediate impact of the global financial crisis on state finances was\n\n\nsomewhat subdued, there are implications going forward. The challenges will be more on the\n\n\nresource side through reduced central transfers, accentuated by the low-cost recovery by states.\n\n\nThese may well render difficult the achievement of the Thirteenth FC road map. Going forward,\n\n\nsustainable finances require states to undertake reforms to maintain solvency via, among other\n\n\nthings, increases in own taxes, implementing the goods and services tax (GST), and revising\n\n\ntariffs.\n\n\nAssessing the impact of the crisis on the center, the immediate impact was relatively\n\n―muted‖ (Milan 2011 44 ; RBI 2011). Although there was a setback in the growth of the economy,\n\n\n44 Milan et al. (2011), ―Fiscal Policy for Growth and Development in India: A Review‖ (work in progress).\n\n\n28\n\nMention: \"RBI\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"RBI base data used in authors’ calculation of state-level GDP-growth and debt-interest-rate differences.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:005293:12:0", "occurrence_id": "7daf95977635ec87d60dbbdc", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: **Table 3. External Business Environment Constraints,**\n**Kazakhstan, the Kyrgyz Republic, Tajikistan, and Europe and Central Asia**\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n|BEEPS indicators, various years|Col2|Europe &
Central Asia,
2009|Kazakhstan,
2009|Kyrgyz
Republic,
2009|Tajikistan,
2008|\n|---|---|---|---|---|---|\n|Permits and
Licensing
|Number of days to obtain an
operating license|26|32|18|23|\n|Permits and
Licensing
|Number of days to obtain a
construction-related permit|78|68|65|63|\n|Permits and
Licensing
|Number of days to obtain an
import license|16|23|10|14|\n|Permits and
Licensing
|Percentage of firms identifying
business licensing and permits as
a major constraint|16|25|16|17|\n|Regulation
and tax
issues|Percentage of senior
management time spent on
dealing
with requirements of
government regulations|11|5|5|12|\n|Regulation
and tax
issues|Average number of visits or
required meetings with tax
officials in a typical month|2|3|2|2|\n|Regulation
and tax
issues|Percentage of firms identifying
tax rates as a major constraint|40|46|48\n\nMention: \"BEEPS indicators\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"analyze\", \"summary\": \"Survey indicators compare firms’ business-environment constraints across Central Asia and Europe and Central Asia.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:005317:9:0", "occurrence_id": "4374c381dfb6b9570f34953c", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: consumption expenditures. An important question then is: How do households adjust their\n\n\nconsumption due to higher energy prices? While there is no evidence of price elasticity of\n\n\ndemand for Armenia, as is the case for most transition economies. However, a post gas hike\n\n\nsurvey of residents of multi-apartment buildings shows that the use of gas-based heating declined\n\n\nin 2010 given the sharp increase of gas tariffs for small consumers (EDRC, 2011). According to\n\n\nthis survey, while gas remained the dominant heating source, the share of households relying on\n\n\nit decreased from 72.5% during the 2008-2009 heating season to about 69.8% during the 2010\n\n2011 heating season. There was increased use of electricity and firewood for heating during the\n\n\nsame period. In the following section, the impact of current gas price hike is simulated for\n\n\ndifferent household groups, under a range of assumptions about price elasticity of demand.\n\n##### **3. Welfare Impact of the Gas Price Hike**\n\n\nGas is an important fuel for heating and cooking, as well as an input into the production of many\n\n\ngoods and services (see Table 5). The gas price increase can therefore influence the cost of the\n\n\nbasic consumption basket and the price of other alternative energy sources such as electricity and\n\n\nfuelwood. Ideally the welfare impact should be analyzed in a general equilibrium framework that\n\n\ntakes into account such linkages. However, general equilibrium modeling is data intensive and\n\n\nsensitive to a number of assumptions. In this paper, the analysis is necessarily limited to the\n\n\n_direct_ impact of the gas price increase on household welfare.\n\n###### **_Methodology and data_**\n\n\nThe 2008 ILCS data is used in the simulation of the impact of gasp price hike on April 1, 2010.\n\n\nThe ILCS collects data from nearly 8,000 Armenian households surveyed year round. It is based\n\n\non a representative sample of about 2,000 households surveyed each quarter.\n\nMention: \"2008 ILCS data\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"analyze\", \"summary\": \"Representative Armenian household-survey data used to simulate welfare effects of the 2010 gas-price increase.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:005317:9:0", "occurrence_id": "55f171d306e2341a43a1cc65", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: consumption expenditures. An important question then is: How do households adjust their\n\n\nconsumption due to higher energy prices? While there is no evidence of price elasticity of\n\n\ndemand for Armenia, as is the case for most transition economies. However, a post gas hike\n\n\nsurvey of residents of multi-apartment buildings shows that the use of gas-based heating declined\n\n\nin 2010 given the sharp increase of gas tariffs for small consumers (EDRC, 2011). According to\n\n\nthis survey, while gas remained the dominant heating source, the share of households relying on\n\n\nit decreased from 72.5% during the 2008-2009 heating season to about 69.8% during the 2010\n\n2011 heating season. There was increased use of electricity and firewood for heating during the\n\n\nsame period. In the following section, the impact of current gas price hike is simulated for\n\n\ndifferent household groups, under a range of assumptions about price elasticity of demand.\n\n##### **3. Welfare Impact of the Gas Price Hike**\n\n\nGas is an important fuel for heating and cooking, as well as an input into the production of many\n\n\ngoods and services (see Table 5). The gas price increase can therefore influence the cost of the\n\n\nbasic consumption basket and the price of other alternative energy sources such as electricity and\n\n\nfuelwood. Ideally the welfare impact should be analyzed in a general equilibrium framework that\n\n\ntakes into account such linkages. However, general equilibrium modeling is data intensive and\n\n\nsensitive to a number of assumptions. In this paper, the analysis is necessarily limited to the\n\n\n_direct_ impact of the gas price increase on household welfare.\n\n###### **_Methodology and data_**\n\n\nThe 2008 ILCS data is used in the simulation of the impact of gasp price hike on April 1, 2010.\n\n\nThe ILCS collects data from nearly 8,000 Armenian households surveyed year round. It is based\n\n\non a representative sample of about 2,000 households surveyed each quarter.\n\nMention: \"survey of residents of multi-apartment buildings\""}, {"role": "assistant", "content": "{\"role\": \"supporting\", \"usage_action\": \"inform\", \"summary\": \"Post-price-hike survey documents changes in household heating-source use.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:005388:20:0", "occurrence_id": "d0cf24eab6810f5620e2c05f", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: performance is about 45% larger for parts in components than for final goods. In addition, trade in the\n\n\nAsia-Pacific region—which is where international production networks are most developed—is\n\n\nparticularly sensitive to logistics performance. We also find evidence that South-South trade is more\n\n\nsensitive than average to logistics performance.\n\n\nAt least two important policy implications flow from our results. First, development of the logistics\n\n\nsector can obviously play a key role in promoting greater integration in international production\n\n\nnetworks. There is much that policymakers can do to assist that process. Building logistics competence is\n\n\na many-faceted process, however, involving issues such as regulation of transport and related sectors,\n\n\nborder procedures, infrastructure, and private sector development. Diagnostics exercises using the\n\n\nWorld Bank’s LPI database are a logical place to start for policymakers interested in addressing the key\n\n\nbottlenecks in national logistics performance (Arvis et al. 2010).\n\n\nSecond, developing country policymakers should pay particular note to the importance of logistics\n\n\nperformance in the context of South-South trade flows, particularly in parts and components. With\n\n\nsome degree of global rebalancing possible in the future, South-South trade is likely to assume increased\n\n\nprominence as a driver of worldwide demand (Haddad and Shepherd, 2011). Barriers to further South\n\nSouth economic integration—including those related to logistics performance—should therefore be a\n\n\npriority for policymakers going forward.\n\n\nIn terms of future research, there is considerable scope for confirming and extending our results. First,\n\n\nestimation in a true panel data framework would make it possible to control for an additional array of\n\n\ncountry-specific factors using fixed effects. Such an approach is not currently feasible, however. The LPI\n\n\nis now available for three years—2007, 2010, and 2012—but the lag with which trade data become\n\n\navailable, especially for developing countries, means that a true panel data approach will need to be left\n\n\nfor later versions of the LPI.\n\n\n19\n\nMention: \"LPI database\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"analyze\", \"summary\": \"Logistics Performance Index data support analysis of how logistics quality relates to international and South–South trade; three waves are cited for future panel work.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:005744:17:0", "occurrence_id": "c3d9535ede6e3dd3627248ee", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: **Table 3.1** **Import Substitution Policy Timeline**\n**Date** **Policy actions and Authorities’ declarations**\n\nDecember Resolution 220/2003-SICPME initiated the system on import licensing for\n23, 2003 bicycles. This event was more or less the commencement of Argentina’s\nnew protectionism. The resolution also created the administrative\nprocedures for enforcing the restrictions.\n_Source:_ InfoLEG database website at\nhttp://infoleg.mecon.gov.ar/infolegInternet/anexos/9000094999/91398/norma.htm.\nAugust Argentina limits entry points for certain goods. By virtue of General\n11, 2005 Resolution 1924 of August 11, 2005, and with the purpose of\nstrengthening customs controls, the Federal Public Revenue\nAdministration limited the points of entry for certain categories of goods,\nincluding textiles, shoes and toys.\nOn January 29, 2010, the General Customs Division passed new\nlegislation, adding several new tariff positions to the regime. (Only tariff\npositions added in this new legislation have been included in this reported\nmeasure.)\n_Source:_ Global Trade Alert 2010b.\nAugust President Cristina Fernández de Kirchner and Minister of Economy\n17, 2007 Miguel Peirano announced measures to restrict imports, especially those\nfrom East Asia. The restrictions covered textiles,\n\nMention: \"InfoLEG database\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"Legal database provides the cited import-licensing resolution for the policy timeline.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:005744:17:0", "occurrence_id": "2a87f4ed8bbec1fbd5a509e5", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: **Table 3.1** **Import Substitution Policy Timeline**\n**Date** **Policy actions and Authorities’ declarations**\n\nDecember Resolution 220/2003-SICPME initiated the system on import licensing for\n23, 2003 bicycles. This event was more or less the commencement of Argentina’s\nnew protectionism. The resolution also created the administrative\nprocedures for enforcing the restrictions.\n_Source:_ InfoLEG database website at\nhttp://infoleg.mecon.gov.ar/infolegInternet/anexos/9000094999/91398/norma.htm.\nAugust Argentina limits entry points for certain goods. By virtue of General\n11, 2005 Resolution 1924 of August 11, 2005, and with the purpose of\nstrengthening customs controls, the Federal Public Revenue\nAdministration limited the points of entry for certain categories of goods,\nincluding textiles, shoes and toys.\nOn January 29, 2010, the General Customs Division passed new\nlegislation, adding several new tariff positions to the regime. (Only tariff\npositions added in this new legislation have been included in this reported\nmeasure.)\n_Source:_ Global Trade Alert 2010b.\nAugust President Cristina Fernández de Kirchner and Minister of Economy\n17, 2007 Miguel Peirano announced measures to restrict imports, especially those\nfrom East Asia. The restrictions covered textiles,\n\nMention: \"Global Trade Alert 2010b\""}, {"role": "assistant", "content": "{\"role\": \"supporting\", \"usage_action\": \"source\", \"summary\": \"Global Trade Alert entry sources the reported 2005 import-point restrictions.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:005755:26:0", "occurrence_id": "0f28dca715d562da89957639", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: forecasts using ARIMA or VAR methods overcomes this problem, but raises questions about the validity\n\nof the forecasts. In this paper, forecasts for GDP up to 2015 are provided by Convergence Reports for the\n\n10 European Union countries and IMF WEO projections for non EU countries. We use these estimates,\n\n\nThe choice of lambda in estimating the trend output is important. The lower the value, the more\n\nis the variability of the cyclical component underestimated, and that of the trend output level (or potential\n\noutput) overestimated. For example, with a value of zero, actual and trend outputs would be the same.\n\nHowever, the larger is lambda, the more likely it is that the variability of the cyclical component is\n\noverestimated and the trend component underestimated. For quarterly data, Hodrick and Prescott\n\nrecommend a value of 1600 in their original work. For annual data values from 100-400 have been\n\ncommonly used, though more recent work uses a value of 6 to 8 for annual data. 25 While an ideal value of\n\nlambda is hard to determine, a value of 30 is used in this paper. Too low a value of lambda would\n\nintroduce more variability in the trend and to a certain degree, defeat the purpose of evaluating the fiscal\n\npolicy stance net of short term booms and busts. It would lead to an overly positive assessment of fiscal\n\npolicy in booms. However, a large lambda also comes with disadvantages. For example, by\n\noverestimating gaps in periods of low growth, deterioration in the underlying budgetary position may go\n\nundetected. 26\n\n##### Country Classification and Variable Description for CAB, VAT, and CIT Regressions\n\n\n25 Bouthevillain et al. (ECB 2001)\n26 See Bouthevillain et al. (ECB 2001); it uses a value of 30.\n\n25\n\nMention: \"Convergence Reports\""}, {"role": "assistant", "content": "{\"role\": \"supporting\", \"usage_action\": \"source\", \"summary\": \"Convergence Reports supply GDP forecasts for EU countries in the fiscal projections.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:005755:26:0", "occurrence_id": "b2ff24be0423e84d55eb9eac", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: forecasts using ARIMA or VAR methods overcomes this problem, but raises questions about the validity\n\nof the forecasts. In this paper, forecasts for GDP up to 2015 are provided by Convergence Reports for the\n\n10 European Union countries and IMF WEO projections for non EU countries. We use these estimates,\n\n\nThe choice of lambda in estimating the trend output is important. The lower the value, the more\n\nis the variability of the cyclical component underestimated, and that of the trend output level (or potential\n\noutput) overestimated. For example, with a value of zero, actual and trend outputs would be the same.\n\nHowever, the larger is lambda, the more likely it is that the variability of the cyclical component is\n\noverestimated and the trend component underestimated. For quarterly data, Hodrick and Prescott\n\nrecommend a value of 1600 in their original work. For annual data values from 100-400 have been\n\ncommonly used, though more recent work uses a value of 6 to 8 for annual data. 25 While an ideal value of\n\nlambda is hard to determine, a value of 30 is used in this paper. Too low a value of lambda would\n\nintroduce more variability in the trend and to a certain degree, defeat the purpose of evaluating the fiscal\n\npolicy stance net of short term booms and busts. It would lead to an overly positive assessment of fiscal\n\npolicy in booms. However, a large lambda also comes with disadvantages. For example, by\n\noverestimating gaps in periods of low growth, deterioration in the underlying budgetary position may go\n\nundetected. 26\n\n##### Country Classification and Variable Description for CAB, VAT, and CIT Regressions\n\n\n25 Bouthevillain et al. (ECB 2001)\n26 See Bouthevillain et al. (ECB 2001); it uses a value of 30.\n\n25\n\nMention: \"IMF WEO projections\""}, {"role": "assistant", "content": "{\"role\": \"supporting\", \"usage_action\": \"source\", \"summary\": \"IMF World Economic Outlook projections supply GDP forecasts for non-EU countries.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:005813:35:1", "occurrence_id": "f19edb0486bfe52879d0eb1a", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: .123 0.092\nLogistics regressions; odds ratios reported; p-values in parentheses + p < 0.10, * p < 0.05, **\np < .01, *** p < .001 Programmatic parties and ICRG bureaucratic quality are measured at\nthe project start year; all other variables are averaged over the project period.\n\n\n\nThe base regressions pool all countries, more and less democratic, since our\n\n\nhypotheses apply equally to both. Table 4 shows that the results are robust, however, to\n\n\nrestricting the sample to countries that have exhibited competitive elections and have had at\n\n\nleast one democratic change of government; the definition follows, and the data are taken\n\n\nfrom, ACLP (Alvarez et. al. 1996, Cheibub et. al. 2009). Within democracies and controlling\n\n\nfor IEG quality at entry rating and initial bureaucratic quality, a unit increase in the\n\n\nproportion of programmatic parties is associated with a nine-fold increase (8.68 ) in the odds\n\n\nof a successful institutional development impact rating relative to the odds of an\n\n\nunsuccessful rating, and a similar nine-fold increase (9.37) in the odds of a successful overall\n\n\noutcome rating relative to an unsuccessful rating.\n\n\n34\n\nMention: \"ACLP\""}, {"role": "assistant", "content": "{\"role\": \"supporting\", \"usage_action\": \"validate\", \"summary\": \"ACLP country classifications define the democratic-election subsample used for robustness checks.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:005830:10:0", "occurrence_id": "c2db6635b5207617f320c50d", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: narrow confines of macroeconomic stabilization and an overwhelming focus, in the case of the\nIMF, on inflation and the budget deficit.\n\nTransparency International was soon assisted in its efforts by the international organizations\nthemselves. At the IMF/World Bank meeting in 1996 the Bank president, James Wolfensohn,\ngave a speech in which he did not mince words, saying that there was a collective responsibility\nto deal with “the cancer of corruption.” In country after country—he said—“it is the people who\nare demanding action on this issue. They know that corruption diverts resources from the poor to\nthe rich, increases the cost of running businesses, distorts public expenditures, and deters foreign\ninvestors. They also know that it erodes the constituency for aid programs and humanitarian\nrelief. And we all know that it is a major barrier to sound and equitable development.”\nRecognizing that the Bank “cannot intervene in the political affairs of our member countries,” he\nnevertheless promised that the Bank would “not tolerate corruption in the programs that we\nsupport.” More important, Mr. Wolfensohn invited Transparency International to assist the Bank\nin the development of its anticorruption strategies and gave strong backing to Bank staff efforts\nto develop a broad range of governance indicators, including those specifically capturing the\nextent of corruption. This was an extremely important development because it made it possible\nfor the Bank, through the use of quantified indicators and data, to focus attention on issues of\ngovernance and corruption while at the same time not appearing to interfere in the political\naffairs of its members. The Bank’s Governance Indicators shifted the nature of the debate on\ncorruption, from abstract (and necessarily controversial) discussions about the widespread\nincidence of corruption in, say, Kenya’s public sector, to evidence-based analysis of\ninternationally comparable composite indicators drawn from a large number of credible sources.\n(See Table 1.)\n\n\n7\n\nMention: \"Governance Indicators\""}, {"role": "assistant", "content": "{\"role\": \"background\", \"usage_action\": \"inform\", \"summary\": \"Bank governance indicators are presented as internationally comparable composite evidence for corruption and governance analysis.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:005852:9:0", "occurrence_id": "50414cec7056dd28219cd4d3", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: **_Access to finance_** **:** The share of working capital that is financed by sources other than\n\nretained earnings. These might include banks, non-bank financial institutions such as\n\nmicrofinance institutions, credit cooperatives, credit unions or finance companies,\n\n\n\n8\n\n\n\npurchases on credit from suppliers and advances from customers, and other sources such\n\nas moneylenders, friends, etc.\n\n\n**_Access to Land_** **:** Index of access to land provided by the World Bank’s _Investing Across_\n\n_Borders_ project. This is an un-weighted average of four sub-indices, which measure\n\naccess to land. These sub-indices are described on the project’s website as follows:\n\n_Strength of lease rights index_ (0-100): Compares economies on the security of\n\nlegal rights they offer to investors interested in leasing industrial land—whether\n\nor not foreign and domestic companies are treated differently and whether the\n\nland can be subleased, subdivided, mortgaged, or used as collateral.\n\n_Strength of ownership rights index_ (0-100): Compares economies on the security\n\nof legal rights they offer to investors interested in purchasing industrial land.\n\n_Access to land information index_ (0-100): Compares economies on the ease of\n\naccess to land-related information through the countries’ land administration\n\nsystems including land registries, cadastres and land information systems.\n\n_Availability of land information index_ (0-100): Compares economies on the\n\navailability of key information to interested private parties through land\n\nadministration institutions.\n\n\n**_Skill ratio of the workforce_** **:** Ratio of skilled to unskilled workers in the firm as measured\n\nby the workers’ level of education in the Enterprise Surveys. In addition, the capital\nlabor ratio of the firm is included as a control variable so we can measure the effect of\n\nMention: \"the Enterprise Surveys\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"analyze\", \"summary\": \"Enterprise Survey responses provide workers’ education levels used to construct firm skill-ratio measures.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:006022:24:0", "occurrence_id": "eb89a0a07f1f3f356cfa370e", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: (obtained from World Development Indicators) in 1985 to measure the initial quality of\n\n\nthe transportation infrastructure in each country in the sample. This variable allows us to\n\n\ncontrol for the ease with which resources can move across the cities in a given country.\n\n\nHigher transportation costs associated with poorer infrastructure create incentives for the\n\n\nconcentration of economic activity in a smaller number of cities.\n\n\n_Regime Change Dummy_ **.** This is a dummy variable taking a value of 1 when dictatorship\n\n\nends in a country before 1985. Following Ades and Glaeser (1995), we accept a country\n\n\nas a dictatorship when its Gastil index is higher than 3. Therefore, countries switch from\n\n\na dictatorship to a democracy when their Gastil index decreases from above 3 (in 1970–4)\n\n\nto below 3 (in 1980–4). We use the Gastil index as documented by Barro and Lee (1994).\n\n\nThis variable is important for our purposes because the literature (e.g., Ades and Glaeser\n\n\n1995) has documented a significant and robust positive relationship between the urban\n\n\nconcentration levels and dictatorships.\n\n\nEstimation Results\n\n\nThe regression results for our benchmark case are given in table 1, where the\n\n\nsample is the same across different regressions. The estimates of __ are negative and\n\n\nsignificant using any estimation methodology for all types of tariffs (except for the tariff\n\n\nchange in consumption goods when TSLS using the first instrument is employed). 22 For\n\n\n22Changes in the tariffs for consumption goods would generally be expected to affect urban\n\n\nconcentration differently than changes in the tariffs for intermediate and capital goods. This is because\n\n\naccess to intermediates is more relevant for urban agglomerations where backward and forward linkages\n\n\nbetween firms matter, as in Krugman and Livas (1996).\n\nMention: \"World Development Indicators\""}, {"role": "assistant", "content": "{\"role\": \"supporting\", \"usage_action\": \"source\", \"summary\": \"World Development Indicators supply initial infrastructure-quality measures used as controls.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:006022:24:0", "occurrence_id": "f58b5838282ef0147441c0d3", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: (obtained from World Development Indicators) in 1985 to measure the initial quality of\n\n\nthe transportation infrastructure in each country in the sample. This variable allows us to\n\n\ncontrol for the ease with which resources can move across the cities in a given country.\n\n\nHigher transportation costs associated with poorer infrastructure create incentives for the\n\n\nconcentration of economic activity in a smaller number of cities.\n\n\n_Regime Change Dummy_ **.** This is a dummy variable taking a value of 1 when dictatorship\n\n\nends in a country before 1985. Following Ades and Glaeser (1995), we accept a country\n\n\nas a dictatorship when its Gastil index is higher than 3. Therefore, countries switch from\n\n\na dictatorship to a democracy when their Gastil index decreases from above 3 (in 1970–4)\n\n\nto below 3 (in 1980–4). We use the Gastil index as documented by Barro and Lee (1994).\n\n\nThis variable is important for our purposes because the literature (e.g., Ades and Glaeser\n\n\n1995) has documented a significant and robust positive relationship between the urban\n\n\nconcentration levels and dictatorships.\n\n\nEstimation Results\n\n\nThe regression results for our benchmark case are given in table 1, where the\n\n\nsample is the same across different regressions. The estimates of __ are negative and\n\n\nsignificant using any estimation methodology for all types of tariffs (except for the tariff\n\n\nchange in consumption goods when TSLS using the first instrument is employed). 22 For\n\n\n22Changes in the tariffs for consumption goods would generally be expected to affect urban\n\n\nconcentration differently than changes in the tariffs for intermediate and capital goods. This is because\n\n\naccess to intermediates is more relevant for urban agglomerations where backward and forward linkages\n\n\nbetween firms matter, as in Krugman and Livas (1996).\n\nMention: \"Barro and Lee (1994)\""}, {"role": "assistant", "content": "{\"role\": \"supporting\", \"usage_action\": \"source\", \"summary\": \"Barro and Lee documentation supplies the Gastil-index values used to classify regime changes.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:006358:4:1", "occurrence_id": "6b6f99ff09e395b1e0d03137", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: to the buyer’s name so that the buyer can use the property for expanding its\nbusiness, use the property as collateral in taking new loans or, if necessary, sell the\nproperty to another business are also measured.\n\n - The getting credit indicator covers two areas relevant for access to credit for businesses\n\nand is based on the methodology developed by Djankov _et al._ (2002). The first area\ncovered consists in the legal rights of borrowers and lenders with respect to secured\ntransactions. In particular the indicator measures whether certain features that facilitate\nlending exist within the applicable collateral and bankruptcy laws. The second area\nmeasures the extent to which credit information is shared by looking at the coverage,\nscope and accessibility of credit information available through public credit registries and\nprivate credit bureaus.\n\n - The protecting investors indicator assesses the strength of minority shareholders\n\nprotection against directors’ misuse of corporate assets for personal gain and is based on\n\n2 The Doing Business database is available at www.doingbusiness.org.\n\n\n3\n\nMention: \"Doing Business database\""}, {"role": "assistant", "content": "{\"role\": \"background\", \"usage_action\": \"inform\", \"summary\": \"Doing Business database provides indicator definitions for business-property registration, credit access, and investor protection.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:006446:54:0", "occurrence_id": "09e1bb5c50bcdf90b460562c", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: 0.14\n\n\n0.12\n\n\n0.10\n\n\n0.08\n\n\n0.06\n\n\n0.04\n\n\n0.02\n\n\n0.00\n\n\n‐0.02\n\n\n‐0.04\n\n\n\n**Figure A3.2. Detailed composition effects (2007-2012)**\n\n\nGeographic\n\n\nEducation\n\n\nFirm Size\n\n\nFirm Ownership\n\n\nMin. Wage\n\n\nDemographic\n\n\nOccupation\n\n\nIndustry\n\n\n5 15 25 35 45 55 65 75 85 95\n\n\n\n_Source:_ Own elaboration based on RLMS (Rounds XVI and XXI). _Notes:_ decompositions results are based on the\nsubsample of currently employed wage workers in the age group 18-60, reporting more than 140 worked hours in\nthe last 30 days and with non-missing data in wages. The distribution of hourly wages was trimmed at the bottom\nand top 0.25 percent in each round, to remove outliers.\n\n\n**Figure A3.3. Detailed composition effects (2007-2012)**\n\n\n0.25\n\n\n\n0.20\n\n\n0.15\n\n\n0.10\n\n\n0.05\n\n\n0.00\n\n\n‐0.05\n\n\n‐0.10\n\n\n‐0.15\n\n\n‐0.20\n\n\n‐0.25\n\n\n\nGeographic\n\n\nEducation\n\n\nFirm Size\n\n\nFirm Ownership\n\n\nMin. Wage\n\n\nDemographic\n\n\nOccupation\n\n\nIndustry\n\n\n\n5 15 25 35 45 55 65 75 85 95\n\n\n_Source:_ Own elaboration based on RLMS (Rounds XVI and XXI). _Notes:_ decomposition results are based on the\nsubsample of currently employed wage workers in the 18-60 age group, reporting more than 140 worked hours in\nthe last 30 days and with non-missing data in wages. The distribution of hourly wages was trimmed at the bottom\nand top 0.25 percent in each round, to remove outliers.\n\n\n53\n\nMention: \"RLMS (Rounds XVI and XXI)\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"analyze\", \"summary\": \"RLMS survey rounds underpin wage-decomposition estimates for employed workers across occupation, education, and demographic groups.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:006557:40:1", "occurrence_id": "b9d94869ff1b2decb36112e7", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: 6
.8
1
cumulative proportion: attended births
0
.2
.4
.6
.8
1
cumulative proportion: births in last 5 years
2000
2005
2011
2014
(skilled health personnel)
Skilled Birth Attendant
|\n\n\nSource: Authors' computation from the DHS data.The values are for all regions except Addis Ababa.\n\n\n39\n\nMention: \"the DHS data\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"analyze\", \"summary\": \"DHS data support trends in attended births and skilled birth assistance across Ethiopian regions.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:006726:7:0", "occurrence_id": "8fd8d7cee215dc91f42823f4", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: averaged 0.81 in 2000-2013. Even by SSA standard (which has an average index of 0.60), DRC’s\n\n\nproduct concentration is very high.\n\n\n\n**Figure 4. Export Market Concentration Index**\n\n\n\n**Figure 4. Export Market Concentration Index** **Figure 5. Export Product Concentration Index**\n\n**2000-2013** **2000-2013**\n\n\n\n**2000-2013**\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\nSource: calculated using data from UNCTAD database. Source: calculated using data from UNCTAD database.\n\n**III-** **Export Concentration, Exogenous Shocks, and Volatility in DRC**\n\n\n9. **As the 2007–2008 crisis hit the world and global demand and international prices**\n\n\n**collapsed, export receipts in DRC declined sharply.** In 2009, DRC’s export earnings declined\n\n\nby more than 28 percent, which is equivalent to US$933 million or 6.4 percent of GDP and led to\n\n\na quick deterioration in the trade-in-goods balance which decreased from a 5.4 percent of GDP\n\n\nsurplus in 2007 to a 3.5 percent deficit in 2009. DRC was much more impacted than other SSA\n\n\ncountries. Indeed, for SSA as a whole, export receipts fell by 15 percent, but DRC was among the\n\n\nfew countries that registered the biggest losses (see Figure 6). Without the diversification away\n\n\nfrom the EU27 towards China, the impact of the financial crisis on DRC would have been harder.\n\n\nIn fact, as a consequence of the global turmoil, DRC’s exports to the EU27 declined from 47\n\n\npercent of total exports to 29 percent in 2009, while exports to China increased from 22 percent to\n\n\n42 percent. However, DRC is now much more exposed to the fluctuations of China’s economy.\n\n\n6\n\nMention: \"UNCTAD database\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"UNCTAD database provides export data used to calculate market and product concentration indexes.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:006756:23:0", "occurrence_id": "3eb3c5db104ea7bb1388dc4c", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: **Figure 6: Sundarbans** **_upazila_** **s: poverty status (lower poverty line)**\n\n\nWe assess the implication of projected mangrove migration for poor communities by\n\n\ncomputing changes at the _upazila_ level for 27 climate scenarios. Table 5 summarizes the results\n\n\nfor five dominant mangrove species. Here it is worth recalling that all five _upazila_ s are poor by\n\n\nnational standards, but Shyamnagar and Koyra are the poorest and most populous (Table 4). For\n\n\n_Heritiera fomes_ (Sundri), the most valuable 16 species overall, the negative impact is concentrated\n\n\nin Koyra, with a median decline of 58.0%. However, this is at least partly offset by significant\n\n\nincreases in _Avicennia alba, marina, officinalis_ (Baen) (45.6%), _Excoecaria agallocha_ (Gewa)\n\n\n(20.0%) and _Ceriops decandra_ (Goran) (20.0%). In contrast, Shyamnagar has very large declines\n\n\n16 The estimated price of Sundri-equivalent-timber BDT 41,890/ m3, and the price of other species is BDT.2,375/m3\n(Data Source: Economic and Financial Analysis of the Ganges Barrages Study Project).\n\n\n22\n\nMention: \"Ganges Barrages Study Project\""}, {"role": "assistant", "content": "{\"role\": \"supporting\", \"usage_action\": \"source\", \"summary\": \"Economic and Financial Analysis of the Ganges Barrages Study Project supplies timber-price data used to value mangrove changes.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:006845:9:0", "occurrence_id": "56058674df34dede7ee78aac", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: Nonetheless, the ES include rich information about the business environment, firms’ characteristics and\n\n\nowner’s characteristics. The data were gathered from interviews with top managers and CEOs in the\n\n\nformally registered non-agricultural private sector; firms that are fully state-owned are excluded from\n\neligibility for the study. 8 As such they notably omit informal businesses, a sector known to comprise a\n\n\npredominant share of employment in Ghana. Another notable point in the case of Ghana is that the global\n\n\nEnterprise Survey methodology excludes extractive industries. Firms eligible for interviews operate in the\n\nmanufacturing, construction, retail, wholesale, hospitality, and transport sectors (as well as IT firms). 9\n\n\nAdditionally, in the case of Ghana, firms with between one and four full-time workers (so-called ‘micro’\n\n\nfirms) were interviewed, and the data used here include this supplementary source of data.\n\n\nThe study was conducted using a stratified survey design, along dimensions of firm size (micro\n\n\n[1–4 employees], small [5–19], medium [20–99], and large [100+]), sector of activity within industry and\n\n\nservices (food, chemicals/plastics/rubber, metals, other manufacturing, construction; retail, other\n\nservices 10 ), and in four of the most active economic cities in Ghana: Accra Metropolitan Area and Tema\n\n\n(Accra), Kumasi (Ashanti), Tamale (Northern) and Takoradi (Western). In all, interviews were completed\n\n\nwith 1,324 firms. Table 1 provides basic descriptive statistics of the sample.\n\n\nThe sample consisted of 720 small, medium and large registered establishments and 604 registered\n\n\nmicroenterprises with the Ghana Registrar’s General Department. These establishments were located from\n\n\nlists compiled from the following: firm registry, list of firms paying value added tax (VAT\n\nMention: \"the global\n\n\nEnterprise Survey\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"analyze\", \"summary\": \"Enterprise Survey firm data measure business conditions, firm performance, workforce skills, and owner characteristics.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:006895:24:0", "occurrence_id": "51c4498c79cf1e8fcc6dfd17", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: **Table 1. Distribution of IHDS sample of rural households by region**\n\n\n**Region** **States and union territories** **2005** **2012**\nNorth Haryana, Himachal Pradesh, Jammu and 7,589 9,334\nKashmir, Punjab, Rajasthan,\nUttarakhand, Uttar Pradesh\n\nWest Goa, Gujarat, Maharashtra 3,046 3,448\nSouth Andhra Pradesh, Karnataka, Kerala, 5,366 5,985\nTamil Nadu\n\nEast Bihar, Jharkhand, Orissa, West Bengal 3,865 4,530\nCentral Chhattisgarh, Madhya Pradesh 2,852 3,572\nNortheast Arunachal Pradesh, Assam, Manipur, 1,255 1,335\nMeghalaya, Mizoram, Nagaland, Sikkim,\nTripura\n\n\n\nUnion territories and\nthe capital a\n\n\n\nDadra and Nagar Haveli, Daman and Diu,\nDelhi, Pondicherry\n\n\n\n218 242\n\n\n\n_No. of Observations_ 24,191 28,446\n_Note:_ While this is a panel sample, the number of surveyed households in 2012 exceeds that in 2005 because\nmany of the original 2005 households split during the seven years between the two surveys.\na. Union territories are administrative divisions that differ from the states. While each state is ruled by its own\nelected government, union territories are ruled by the central government.\n\n\n**Table 2. Electrification rate among sample households by region (percent)**\n**Region** **2005** **2012**\n\nMention: \"IHDS\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"analyze\", \"summary\": \"Panel household-survey rounds provide the sample for regional electrification and household-outcome analysis.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:006901:5:0", "occurrence_id": "53ac37396fa7482041985a17", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: support the idea that policies oriented to reduce inequality have a positive effect on growth (“pro\n\ngrowth equity”) is more scarce and limited.\n\n\n_Pro-growth equity_\n\n\nConceptually, income inequality should have a strong contemporaneous correlation with growth, as\n\n\ngrowth and inequality are jointly determined (Chenery, et al, 1974; Ferreira, 2010). As Chenery, et al.\n\n\n(1974) show 40 years ago, overall growth can be decomposed as the weighted sum of the income\n\n\ngrowth of different groups in society, where the weights are determined by those groups’ initial share\n\n\nin total income.\n\n\n**Figure 1. Growth and equity are jointly determined**\n\n\nStudies looking into the inequality-growth relationship have found ambiguous results (Marrero and\n\n\nRodriguez, 2013). In a recent study, Ferreira et al. (2014) use two new data sets, consisting of 118\n\n\nhousehold surveys and 134 Demographic and Health Surveys, to show that inequality is negative for\n\n\n4\n\nMention: \"Demographic and Health Surveys\""}, {"role": "assistant", "content": "{\"role\": \"background\", \"usage_action\": \"inform\", \"summary\": \"Demographic and Health Survey datasets underpin cited research linking inequality and growth across countries.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:006901:5:0", "occurrence_id": "ce71d9205f277633c321e1f5", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: support the idea that policies oriented to reduce inequality have a positive effect on growth (“pro\n\ngrowth equity”) is more scarce and limited.\n\n\n_Pro-growth equity_\n\n\nConceptually, income inequality should have a strong contemporaneous correlation with growth, as\n\n\ngrowth and inequality are jointly determined (Chenery, et al, 1974; Ferreira, 2010). As Chenery, et al.\n\n\n(1974) show 40 years ago, overall growth can be decomposed as the weighted sum of the income\n\n\ngrowth of different groups in society, where the weights are determined by those groups’ initial share\n\n\nin total income.\n\n\n**Figure 1. Growth and equity are jointly determined**\n\n\nStudies looking into the inequality-growth relationship have found ambiguous results (Marrero and\n\n\nRodriguez, 2013). In a recent study, Ferreira et al. (2014) use two new data sets, consisting of 118\n\n\nhousehold surveys and 134 Demographic and Health Surveys, to show that inequality is negative for\n\n\n4\n\nMention: \"118\n\n\nhousehold surveys\""}, {"role": "assistant", "content": "{\"role\": \"background\", \"usage_action\": \"inform\", \"summary\": \"Household-survey datasets form the other cited source base for the inequality-growth study.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:006937:24:4", "occurrence_id": "20a11c0fa83b3a204640429d", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: >2,045 1,946\nSource: Staff calculations using UNPS. Notes: Household fixed effects estimation with robust standard errors\nin parentheses. *** p<0.01, ** p<0.05, * p<0.1\n\n\n\n**Table 10: Impact of weather, prices and peace on income and consumption: bottom 40**\n\n**percent**\n\n\n\n23\n\nMention: \"UNPS\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"analyze\", \"summary\": \"UNPS household survey data underpin estimates of weather, price, and peace effects on income and consumption among the bottom 40 percent.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:007071:18:2", "occurrence_id": "87ff8d8aef246b0c681d2698", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: .52|1.21|35.73|26.38|9.35***|\n||Pre-Treatment|Post-Treatment|Diff|Pre-Treatment|Post-Treatment|Diff|\n|Became Single-Shift in 2011|29.40|24.97|4.43|35.34|24.88|10.47***|\n|Became Single-Shift in 2012/2013|20.93|16.52|4.41***|40.80|26.38|14.42***|\n\n\n\nT-test: * significant at 10%; ** significant at 5%; *** significant at 1%\n\nNotes: Items in the house refers to the sum of major household goods in the house of 5th and 9th grade students. The household goods\nconsidered are: TV, stereo, DVD, refrigerator, freezer, car, washing machine and the total number of bathrooms and bedrooms. Mother\neducation refers to % of 5th/9th grade students of which their mother has Tertiary Education. The age-grade distortion is the proportion of\nstudents with more than 2 years of school delay.\n\n\nData sources: Brazilian Ministry of Education.\n\n\n17\n\nMention: \"Brazilian Ministry of Education\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"Education-ministry data supply student and school measures used in the single-shift policy table.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:007112:6:0", "occurrence_id": "b946fddd7236f9b4fcae9fa7", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: skew their portfolios to liquid and other short-term instruments, the full benefits from pension savings on\ndomestic capital market development could be limited.\n\n\nThis paper documents differences in regulation on switching in a number of countries operating DC\npension systems. The paper also studies the extent to which switching between pension providers and\nacross different portfolios affect asset allocation. More precisely, the paper analyses whether pension\nfunds’ holdings in short-term assets is related to outflows resulting from transfers within and across\npension fund providers. Data on pension funds’ portfolios were provided by the regulatory authorities in\nChile; Colombia; Costa Rica; Estonia; Hong Kong SAR, China; Mexico; Peru; Poland; and Romania. 9 [^9: IOPS members from Nigeria and Slovak Republic also kindly provided information for this paper, but as no data\nwere available on switching, it was not possible to include these countries in the paper.]\n\n\nThe remainder of the paper is organized as follows. Section 1 presents the aggregate trends in pension\nfunds’ holdings at different maturities. Section 2 documents outflows from benefit payments and\nswitching. Section 3 studies the relation between switching and portfolio allocations. In addition to\nanalyzing the relation between fund transfers and short-term holdings for the group of countries, the\nsection also presents two empirical exercises for Colombia and Chile where recent events in switching\nprovide two quasi-natural experiments to study the causal effects on portfolio strategies and liquidity\nmanagement. Section 4 concludes and presents several policy recommendations.\n\n\n1. Holdings of short-term assets\n\n\nHoldings of short-term and medium-term assets have declined in all Latin American countries over the\npast decade, with similar trends witnessed in the Central and Eastern Europe region. For the purpose of\nthis paper, short-term assets have been defined as local government treasuries securities < 1-year\nmaturity, local bank term deposits, foreign treasury securities < 1-year maturity and foreign term deposits.\nMedium term assets are defined as those with between 1-5 years maturity. For example, in Chile, while\nshort-term investments accounted for 19% of AUM in\n\nMention: \"the regulatory authorities in\nChile\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"analyze\", \"summary\": \"Regulatory-authority data on pension-fund portfolios and transfers support analysis of switching and asset allocation.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:007154:18:2", "occurrence_id": "31ed1bf5424d9bbf518de2df", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: >89.8% 10.2%\n**50%** 0.67 0.11 0.78 50.10 93.1% 6.9%\n**0%** 0.00 0.00 1.00 69.18\nSource: Authors’ estimations based on Jordan UNHCR data.\n\n\n\n**budget**\n\n\n\n**rate**\n\n\n\n**rate**\n\n\n\n**threshold**\n\n\n\n17\n\nMention: \"Jordan UNHCR data\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"UNHCR administrative data underpin the authors’ Jordan estimates in the table.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:007189:44:3", "occurrence_id": "2ab6e856721444167c73bae3", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: *** 26.7***\nDivorced 46.5*** 70.3*** 50.9*** 4.9*** 59.6*** 38.1*** 21.4* 38.3*** 36.4*** 15.5***\n\nNote: The table shows the % of women in each marital status answering positively to each question. “Has no say” is defined as answering that each decision is\ntaken by either the husband/partner alone or by someone else. Divorced includes separated women. Significance tests are relative to once-married women, where\n*** p<0.01, ** p<0.05, * p<0.1.\nSample: ever-married women, aged 15-49\nSource: Authors’ calculations using Senegal’s 2005 DHS.\n\n\n43\n\nMention: \"Senegal’s 2005 DHS\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"analyze\", \"summary\": \"DHS household survey supports analysis of women’s decision-making by marital status.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:007441:5:0", "occurrence_id": "f729c460e33614505eb8c4eb", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: and performing tax reforms can affect entrepreneurship, formalization rate, output,\nand productivity.\n\nWe first test the implications of the model using reduced form estimations techniques, based on a cross-section of micro-enterprises from the Business census and the\nNational Survey on Employment and the Informal Sector. This allows us to test the\ntheory by investigating empirically the importance of location and sector of activity\non the extent of informality and firm performance. Our cross-sectional results show\nthat firm profits increase with agglomeration and informal agricultural activities are\nthe least profitable, whereas the least profitable formal activities are in the service\nsector. In addition, informal entrepreneurs operating in manufacturing, commerce\nand services are more likely to formalize than their counterpart in the agriculture\nsector. Second, we perform specification tests and provide structural estimates of\nthe model using the Generalized Method of Moments and micro-data (firm-level and\nhousehold-level) from Cameroon. We find that the return to capital and labor is not\nuniform across sectors and cities in Cameroon. Manufacturing industries are highly\nconstrained in capital and the elasticity of capital is higher in Yaoundé and Douala,\nwhile labor elasticity is higher in Kribi, reflecting a low availability of workforce. One\nof the main advantages of using a structural econometric approach is that it allows\none to generate counterfactual samples on the basis of a well-tested theoretical model\nthat is consistent with the data. The counterfactual policy simulations that we perform\nbased on the estimated model are then used to quantify the effects of several policy\nmeasures on informality and productivity. In particular, by identifying prominent sectors of activities (and/or strategic locations) and constraints faced by agents operating\nin these sectors (and/or locations), we provide a quantitative assessment of the impact\nthat a targeted policy design such as improved infrastructure, access to finance or adjusted tax rates would have on aggregate productivity, job creation, formalization of\ninformal firms, and government revenues. The results show that an increase in\n\nMention: \"Business census\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"analyze\", \"summary\": \"Business-census and employment/informal-sector survey data support cross-sectional analysis of microenterprise performance.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:007441:5:0", "occurrence_id": "3e6b1d0018c9aca88f6376bd", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: and performing tax reforms can affect entrepreneurship, formalization rate, output,\nand productivity.\n\nWe first test the implications of the model using reduced form estimations techniques, based on a cross-section of micro-enterprises from the Business census and the\nNational Survey on Employment and the Informal Sector. This allows us to test the\ntheory by investigating empirically the importance of location and sector of activity\non the extent of informality and firm performance. Our cross-sectional results show\nthat firm profits increase with agglomeration and informal agricultural activities are\nthe least profitable, whereas the least profitable formal activities are in the service\nsector. In addition, informal entrepreneurs operating in manufacturing, commerce\nand services are more likely to formalize than their counterpart in the agriculture\nsector. Second, we perform specification tests and provide structural estimates of\nthe model using the Generalized Method of Moments and micro-data (firm-level and\nhousehold-level) from Cameroon. We find that the return to capital and labor is not\nuniform across sectors and cities in Cameroon. Manufacturing industries are highly\nconstrained in capital and the elasticity of capital is higher in Yaoundé and Douala,\nwhile labor elasticity is higher in Kribi, reflecting a low availability of workforce. One\nof the main advantages of using a structural econometric approach is that it allows\none to generate counterfactual samples on the basis of a well-tested theoretical model\nthat is consistent with the data. The counterfactual policy simulations that we perform\nbased on the estimated model are then used to quantify the effects of several policy\nmeasures on informality and productivity. In particular, by identifying prominent sectors of activities (and/or strategic locations) and constraints faced by agents operating\nin these sectors (and/or locations), we provide a quantitative assessment of the impact\nthat a targeted policy design such as improved infrastructure, access to finance or adjusted tax rates would have on aggregate productivity, job creation, formalization of\ninformal firms, and government revenues. The results show that an increase in\n\nMention: \"National Survey on Employment and the Informal Sector\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"analyze\", \"summary\": \"Employment and informal-sector survey provides information on microenterprise status and performance.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:007474:5:1", "occurrence_id": "618420e58b124d65308c69a6", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: formality and informality. Businesses with\n\n\nan incorporated legal status (as opposed to unincorporated or natural persons) are more likely\n\n\nto acquire municipal licenses and keep them. In contrast, young firms (less than age four years)\n\n\nare more likely to de-formalize by not renewing municipal licenses. These findings are\n\n\nconsistent with the view that young entrepreneurs learn about their productivity in the formal\n\n\nand informal sectors and act upon it. Similarly, firms with greater value added per worker and\n\n\nfrom regions with larger proportions of firms registering with the Electronic Payroll Registry\n\n\nare more likely to register their workers and keep them registered. These findings suggest that\n\n\nenforcement matters, and—everything else being equal—firms must reach a certain level of\n\n\nproductivity before they have the necessary potential to formalize their labor force.\n\n\nNext, we attempt to infer the extent to which business formalization affects labor formalization\n\n\nand vice versa. Are firms that initiated the process of formalization more likely to conclude it?\n\n\n4\n\nMention: \"the Electronic Payroll Registry\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"analyze\", \"summary\": \"Electronic Payroll Registry tracks whether firms register workers and keep them registered.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:007521:19:2", "occurrence_id": "7378780a6a2af4b65387aaf5", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: u> 5226 5226 5226 5226\n\n\nfirm and year FE Yes Yes Yes Yes Yes\nlog employment No Yes Yes Yes Yes\nindustry-specific trends No No Yes Yes Yes\nfirm-specific trends No No No Yes Yes\nimported inputs No No No No Yes\n\n\nNOTES: IV-FE regressions of (log) employment on export intensity (exports/sales). The instruments are the weighted\naverage the real exchange rate of a firm export partners and the weighted average of the real gdp of a firm export destinations.\nColumn (1): firm fixed-effects and year fixed-effects; column (2): adds log total employment (firm size); column (3): adds\ncontrols for industry-specific trends (i.e., interactions between year dummies and industry dummies); column (4): adds initial\nconditions to control for firm-specific trends; column (5): adds the share of imported inputs. Data are from the Encuesta\nNacional Industrial Anual (National Annual Industrial Survey), Chile 2001-2005.\n\n\n18\n\nMention: \"Encuesta\nNacional Industrial Anual\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"analyze\", \"summary\": \"Industrial survey data measure firm-level employment responses to export intensity.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:007521:19:2", "occurrence_id": "47beab0b3bdc89ff082134ee", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: u> 5226 5226 5226 5226\n\n\nfirm and year FE Yes Yes Yes Yes Yes\nlog employment No Yes Yes Yes Yes\nindustry-specific trends No No Yes Yes Yes\nfirm-specific trends No No No Yes Yes\nimported inputs No No No No Yes\n\n\nNOTES: IV-FE regressions of (log) employment on export intensity (exports/sales). The instruments are the weighted\naverage the real exchange rate of a firm export partners and the weighted average of the real gdp of a firm export destinations.\nColumn (1): firm fixed-effects and year fixed-effects; column (2): adds log total employment (firm size); column (3): adds\ncontrols for industry-specific trends (i.e., interactions between year dummies and industry dummies); column (4): adds initial\nconditions to control for firm-specific trends; column (5): adds the share of imported inputs. Data are from the Encuesta\nNacional Industrial Anual (National Annual Industrial Survey), Chile 2001-2005.\n\n\n18\n\nMention: \"National Annual Industrial Survey\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"analyze\", \"summary\": \"National Annual Industrial Survey is the English name for the source of the firm-employment estimates.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:007628:37:1", "occurrence_id": "0923006dfcbde9ecf1719ccd", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: ]\n\n\nAdults with only primary education (18+) 0.242 0.233 0.009\n\n\n[0.008] [0.007]\n\n\nHousehold head practices polygamy 0.333 0.338 ‐0.005\n\n\n[0.015] [0.012]\n\nHousehold head is male 0.579 0.603 ‐0.024\n\n\n[0.016] [0.013]\n\nHousehold head is employed 0.732 0.715 0.018\n\n\n[0.014] [0.012]\n\nAverage age 19.311 19.026 0.285\n\n\n[0.217] [0.186]\n\n\n_** and * indicate significance at the 1 and 5 percent level._\n\n\n**Source: Authors’ own calculations based on HFS 2016‐2017 data.**\n\n\n36\n\nMention: \"HFS 2016‐2017 data\""}, {"role": "assistant", "content": "{\"role\": \"supporting\", \"usage_action\": \"analyze\", \"summary\": \"Household survey data support the table’s comparison of household-head characteristics and outcomes.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:007655:23:2", "occurrence_id": "552052d2f774e448fc67d07f", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: .746* -0.066 -0.339 -0.041\n(0.217) (0.345) (0.279)\nUbudehe 4 or higher (=1) -0.861*** -0.170 -0.679* -0.082\n(0.305) (0.363)\nConstant -0.224 0.297 -0.744 -0.137 -0.946 -0.534\n(0.577) (0.566) (0.697) (0.747) (0.606) (0.595)\n\nN 615 615 583 490 615 615\nPseudo-R2 0.108 0.127 0.331 0.331 0.085 0.096\n_Notes:_ Robust, clustered standard errors in parenthesis. * p<0.10; ** p<0.05; *** p<0.01.\n_Source:_ VUP household survey, 2009, 2011, 2014.\n\n\n\n22\n\nMention: \"VUP household survey, 2009, 2011, 2014\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"analyze\", \"summary\": \"VUP household-survey waves underpin table estimates of Ubudehe poverty status.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:007680:10:0", "occurrence_id": "36aa7db5ada85a21301b2a47", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: **Cost-benefit estimates**\n\n\nWe use a subsample of 97,050 workers aged 15-65 years who had positive earnings from\ndependent employment. Annual earnings were converted to $US using the 2017 exchange rate in\nJune, which was equal to 3.52 TL. Table 4 gives their mean earnings by level of education.\n\n\n**Table 4: Mean Annual Earnings by Educational Level**\nEducational level Mean annual Number of\nearnings ($US) observations\n\nNone 3,714 1,528\nPrimary 5,278 24,850\nSecondary 5,974 38,567\nHigher 10,756 32,105\nAll 7342 97,050\nSource: 2017 HLFS\n\nWe observe a sharp rise in mean annual earnings for those with higher education. This is consistent\nwith the very high demand for university education as well as the restriction on the university\nadmissions by the highly competitive university entrance examination. There is very high demand\nfor university education for several reasons. First, in addition to high income, the university degree\nconfers a prestigious position in Turkish society. Secondly, men with university education serve\nin the army with a higher rank. These factors are behind the high demand for higher education.\nThe age-earnings profiles by level of education show a very sharp earnings premium for higher\neducation graduates.\n\n\n\n\n\n\n\nThe discounting formula presented above was applied to the earnings profiles to estimate the\nreturns assuming a 6-6-4 duration of primary, secondary and higher education, and two years of\n\n\n9\n\nMention: \"2017 HLFS\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"analyze\", \"summary\": \"Labor-force survey provides earnings by educational level for dependent employees.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "reliefweb", "source_key": "reliefweb:000132:2:1", "occurrence_id": "cb4b1dae3d7043a32b9a75ca", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: than JODs 750 per person per\nyear, the case has to be approved by the UNHCR health unit (for emergency cases) and/or\nExceptional Care Committee (ECC) for non-emergency cases before the referral takes place.\n\n\n**Data Collection and Analysis**\n\n\nReferral care is considered an essential part of access to comprehensive health services, thus\nUNHCR since 2014 has maintained a medical referral database in order to monitor trends in\nurban and camp settings in Jordan.\n\n\n - This report includes all referrals data for the period January to December 2016\n\n - Data was collected from 11 sites; 6 Urban (Amman, Zarqa, Mafraq, Irbid, Ramtha,\nand south Mobile Medical Unit), 4 camps (Zaatri, Azraq, Cyber City and King\nAbdullah Park), and Ruwaishid.\n\n - Data was captured on-site daily then compiled and shared on a monthly basis with\nJHAS referral hub, where the initial data compilation and cleaning was done.\nCompiled and cleaned data was then shared with the UNHCR Public Health Unit,\nwhere secondary data cleaning and analysis was carried out.\n\n - Descriptive analysis carried out using Microsoft Excel 2013.\n\n\n**3 |** P a g e\n\nMention: \"medical referral database\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"analyze\", \"summary\": \"UNHCR medical-referral records monitor referral trends across urban and camp settings in Jordan.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "reliefweb", "source_key": "reliefweb:000177:0:0", "occurrence_id": "3779cd486e6678758c186617", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: **Response to the main protection concerns in the aftermath of the February 2023 earthquakes**\n\n\n**Introduction**\n\n\nThis paper outlines **the main protection concerns** in the aftermath of the 6 February earthquakes and\n**actions taken by the Protection Sector** to prevent, mitigate and respond to them in the first two months\nfollowing the earthquake.\n\n\nThe following key protection concerns are highlighted due to their frequency and severity:\n\n\n1. Gender-based violence (GBV)\n2. Limited accountability to affected populations (AAP)\n3. Sexual exploitation and abuse (SEA)\n4. Psychological distress\n5. Protection concerns affecting children\n6. Limited response to the needs of older people and people with disabilities\n7. Challenges to access housing, land and property (HLP) rights\n\n\n**Overall context**\n\n\nIn response to the 6 February earthquakes, local authorities in directly impacted areas established\ntemporary shelters to host affected populations. As of 7 March, it is estimated that 265 collective shelters\n(schools, mosques and other community infrastructure) host people affected by the earthquakes in\nAleppo, Hama, Latakia, Homs and Idleb.\n\nMost people in shelters are reported to be women and children (82% in Aleppo governorate). 1 Children\nwho are either unaccompanied or staying with relatives were reported in 30 shelters. 2 76% of key\ninformants who participated in a Rapid Protection Assessment (RPA) 3 conducted in the early days after\nthe earthquake reported the presence of destitute older persons. Female-headed households (74% of key\ninformants), persons with disabilities (72%), and older persons providing care to a household (61%) were\nalso frequently reported among the most affected population groups.\n\nPartners engaged in\n\nMention: \"Rapid Protection Assessment\""}, {"role": "assistant", "content": "{\"role\": \"supporting\", \"usage_action\": \"inform\", \"summary\": \"Rapid Protection Assessment records key-informant reports of protection needs after the earthquakes.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "reliefweb", "source_key": "reliefweb:000311:9:0", "occurrence_id": "599479a92ee57eeb1cd82e04", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: Periodic Analysis of Syrian Workers September 2018\n\n\n_Chart 12: Reasons why refugees prefer not to have a work permit_\n\n\nThe majority of refugee workers (87 %) pay the work permit issuance fees themselves to get their work permits. This situation is\nmostly prevailing in the construction sector followed by the agricultural sector.\n\n\nThe refugees self-reported costs associated with the work permits issuance varied between the three sectors (Construction,\nAgriculture, and public/private sectors). It is worth mentioning that the cost get higher if the employer was a Private/public\nemployer, with an average of 85 JOD, while the averages is 64 JOD if it was GFJTU.\n\n\n\n1000\n\n\n900\n\n\n800\n\n\n700\n\n\n600\n\n\n500\n\n\n400\n\n\n300\n\n\n200\n\n\n100\n\n\n0\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\nGFJTU Private/public employer\n\n\n_Chart 13: Costs Associated with Work Permit Issuance_\n\n\n\n10\n\nMention: \"Periodic Analysis of Syrian Workers\""}, {"role": "assistant", "content": "{\"role\": \"supporting\", \"usage_action\": \"inform\", \"summary\": \"Periodic analysis reports refugee workers’ work-permit costs by employment sector.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "reliefweb", "source_key": "reliefweb:000465:12:2", "occurrence_id": "5c1e3d6f3416a8251c83e8fb", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: opportunities\n\n\nLack childcare\n\n\nEducation\nrecognition\n\nNot staying\n\n\n\n33%\n\n\n27%\n\n\n11%\n\n\n7%\n\n\n7%\n\n\n\n11%\n\n\n9%\n\n\n5%\n\n\n\n*Due to rounding, some percent totals do not add up to 100%\n** Multiple responses were possible, so percentages can go over 100% when added.\n\n\n10. UNHCR, Education on hold: almost half of school-aged children from Ukraine missing out on formal education available at [https://www.unhcr.org/](https://www.unhcr.org/news/briefing-notes/education-hold-almost-half-school-aged-refugee-children-uk)\n[news/briefing-notes/education-hold-almost-half-school-aged-refugee-children-ukraine-missing-out](https://www.unhcr.org/news/briefing-notes/education-hold-almost-half-school-aged-refugee-children-uk)\n11. [UNHCR’s fourth intentions survey Micro-data available at Survey of intentions and perspectives of refugees from Ukraine #4 - June 2023 (unhcr.](https://microdata.unhcr.org/index.php/catalog/934)\n[org)](https://microdata.unhcr.org/index.php/catalog/934)\n\n\n**U N H C R R E G I O N A L B U R E A U F O R E U R O P E,** N O V E M B E R 2 0 2 3 13\n\nMention: \"Survey of intentions and perspectives of refugees from Ukraine\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"analyze\", \"summary\": \"Refugee-intentions survey data inform education-access findings for displaced children from Ukraine.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "reliefweb", "source_key": "reliefweb:000465:12:2", "occurrence_id": "9f249b3a60bbe7d130ea2928", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: opportunities\n\n\nLack childcare\n\n\nEducation\nrecognition\n\nNot staying\n\n\n\n33%\n\n\n27%\n\n\n11%\n\n\n7%\n\n\n7%\n\n\n\n11%\n\n\n9%\n\n\n5%\n\n\n\n*Due to rounding, some percent totals do not add up to 100%\n** Multiple responses were possible, so percentages can go over 100% when added.\n\n\n10. UNHCR, Education on hold: almost half of school-aged children from Ukraine missing out on formal education available at [https://www.unhcr.org/](https://www.unhcr.org/news/briefing-notes/education-hold-almost-half-school-aged-refugee-children-uk)\n[news/briefing-notes/education-hold-almost-half-school-aged-refugee-children-ukraine-missing-out](https://www.unhcr.org/news/briefing-notes/education-hold-almost-half-school-aged-refugee-children-uk)\n11. [UNHCR’s fourth intentions survey Micro-data available at Survey of intentions and perspectives of refugees from Ukraine #4 - June 2023 (unhcr.](https://microdata.unhcr.org/index.php/catalog/934)\n[org)](https://microdata.unhcr.org/index.php/catalog/934)\n\n\n**U N H C R R E G I O N A L B U R E A U F O R E U R O P E,** N O V E M B E R 2 0 2 3 13\n\nMention: \"Education on hold: almost half of school-aged children from Ukraine missing out on formal education\""}, {"role": "assistant", "content": "{\"role\": \"supporting\", \"usage_action\": \"inform\", \"summary\": \"UNHCR report cites global education exclusion affecting school-aged children from Ukraine.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "reliefweb", "source_key": "reliefweb:000563:2:1", "occurrence_id": "fb2db53720871a6b26f22243", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: 5 of\n\nthese were schools, while 11 were incidents impacting on Al-Hudaydah\n\nUniversity medical and engineering faculties, which have been\n\ncommandeered by military forces as defensive and firing positions.\n\n\n**Case study 2: Fishing communities in Al-Hudaydah**\n\n\nAl-Hudaydah’s fishing community saw a significantly reduced impact from\n\nincidents of armed violence since the ceasefire commenced. In 2018, 77\n\nfishermen were reportedly killed, 37 injured, and another 17 reported\n\nmissing as a result of incidents of armed violence, the majority of which\n\nwere as a result of airstrikes, along with three instances of naval shelling\n\nand three seamine incidents. Over 25 boats were reportedly destroyed.\n\nFishing ports in Al-Hawak and Al-Tuhayat, fishing huts on Kamaran island,\n\nand the Ministry of Fisheries in Al-Luheyah were also reportedly hit by\n\nairstrikes last year. The Al-Hawak fish market was also hit by shellfire on 2\n\nAugust 2018 which, together with a follow-up attack outside the Al-Thawra\n\nhospital gates, was reported to have resulted in 55 civilian fatalities and\n\n170 civilian injuries. Since the ceasefire entered into force, airstrikes are\n\nreported to have hit 5 fishing boats, killing 9 fishermen and injuring 6.\n\n\n\nOn the whole, the introduction of the cease�re resulted in a decrease in\nincidents impacting on civilian infrastructure in Al-Hudaydah. In the 12 months\nprior to the cease�re, 139 incidents impacted on civilian infrastructure, while in\nthe 12 months after, this almost halved, dropping to 73. The most frequently\nimpacted types of infrastructure are shown in the chart below by number of\nincidents. The 2 infrastructure types to have seen an increase in the past 12\nmonths were education and food, explained in case study 1, to the left.\n\n\n\nThe Civilian Impact Monitoring Project is a service under the United Nations Protection\n\nCluster for the collection, analysis and dissemination of open source data on the civilian\n\nMention: \"Civilian Impact Monitoring Project\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"analyze\", \"summary\": \"Civilian Impact Monitoring Project collects open-source incident data used to track violence and impacts on civilian infrastructure.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "reliefweb", "source_key": "reliefweb:000556:15:1", "occurrence_id": "b5df8d1bf878f2b110573f00", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: \nthan Syrian children. As with small groups of displaced children of Somali and Sudanese\norigin and stateless Palestinians, and Palestinian refugees from Gaza, the realisation of their\nrights is evidently not a matter of principle but contingent upon a range of factors, including\nmaterial circumstances and political consideration.\n\n**_Access to Services_**\n\nThe UNCRC identifies State Party responsibility for provision of services to children in a\nnumber of areas. The most obvious of these are education (Article 28), and healthcare\n(Article 24). In addition, assistance should be offered to children with physical or mental\ndisabilities (Article 23) and, of special relevance to a population exposed to extreme violence,\nsupport for psychological recovery (Article 39).\n\n_Education_\nExamination of Iraqi children’s access to the Jordanian public school system reveals a\nchequered history. Until 2007 only private schools were accessible to the majority of this\npopulation (Nelems, 2008). In August of that year King Abdullah II issued a decree opening\nthe public school system to Iraqi children for ‘humanitarian reasons’. This decree timed in\nwith the provision of funds from the European Union and the US Government. Iraqi children\nwere thus admitted from the 2007-2008 school year onwards. The funding made available\nwas generous: new schools were built and the costs for each individual child’s participation\ncovered.\n\nAt the time of our research free access to primary and secondary education was offered to\nIraqi children within Jordanian public institutions. However, take-up was far from universal.\nThe 2013 CARE survey indicated a non-enrolment rate of 37.5%, and a non-attendance rate\n\n\n14\n\nMention: \"2013 CARE survey\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"analyze\", \"summary\": \"CARE survey measures school non-enrolment and non-attendance among Iraqi children in Jordan.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "reliefweb", "source_key": "reliefweb:000857:10:1", "occurrence_id": "ffa287d1949fce8289cccf9e", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: For the first time, Germany hosted more\nUkrainians (876,300 or 39 per cent) than any other\nnationality, including Syrians (664,200 or 30 per cent).\n\n\n\nOther countries hosting more than 1 million refugees\nby mid-2022 were Pakistan, Poland, the Russian\nFederation, **29** Sudan and Uganda.\n\n\n\n**28** By 19 October 2022, the number of Ukrainian refugees had grown to 7.7 million. In addition, a number of third country nationals as well as\nrefugees and asylum seekers hosted in Ukraine before the invasion were also forced to leave the country.\n**29** As of 30 June, registration and formal recognition of Ukrainians in the Russian Federation were still ongoing and therefore not all those\nreported had the formal status of refugees.\n\n\nUNHCR > **MID-YEAR TRENDS 2022** 11\n\nMention: \"MID-YEAR TRENDS 2022\""}, {"role": "assistant", "content": "{\"role\": \"background\", \"usage_action\": \"inform\", \"summary\": \"UNHCR Mid-Year Trends report provides global refugee-registration and hosting statistics.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "reliefweb", "source_key": "reliefweb:001026:0:1", "occurrence_id": "6904705e885ef946640cf5bf", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: behind a number\nof active workstreams. 3 [^3: Localisation, resourcing, communications, capacity building and the QCCF] That said, a significant amount of work is still required over the coming years,\nparticularly in IASC/mixed settings, where adequately resourcing the new model and effectively\npromoting local engagement and leadership represent the main challenges. Efforts are also needed at\nfield, regional and global level to untangle the roles and responsibilities of various stakeholders and\ndevelop strategic working relationships; to strengthen approaches to capacity building and ensure all\nrelevant partners throughout the system have the skills and knowledge they need; and for the CAG to\nenhance its relationship with the field. Notably, the standards and guidance issued thus far by the CAG\nhave been well received and contributed to more consistent approaches to cash coordination. The\nbelow sections will go through each of these topics in more detail.\n\nOver the course of the transition efforts have been made to advance **localisation** commitments mainly\nthrough local actor representation on the CAG and as CWG co-chairs. This has brought a welcome\nincrease in focus to the issue overall, with 83% of CWGs in refugee settings now having a local cochair. UNHCR’s considerable cash programming and coordination experience was identified as an\nimportant contributing factor to this achievement. Effectively promoting sustainable local engagement\nand leadership has been more challenging in IASC/mixed settings, and for the CAG itself. Some of the\nmain barriers for local actors include a lack of funding, technical capacity and experience in\nimplementing cash programming. 4 [^4: Local Engagement Online Survey, Zebs, March 2024] Also, a need to ensure local actors feel confident in raising their\nvoice amongst international partners. That said, the CAG has recently launched a Local Leadership\nInitiative to identify sustainable arrangements for CWG co-leadership and is planning to increase the\nnumber of local observers to the forum itself.\n\nThe issue of **resourcing*\n\nMention: \"Local Engagement Online Survey\""}, {"role": "assistant", "content": "{\"role\": \"supporting\", \"usage_action\": \"inform\", \"summary\": \"Online survey informs analysis of local actors’ roles and representation in refugee-response coordination.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "reliefweb", "source_key": "reliefweb:001017:1:1", "occurrence_id": "f6b2a31112fbf028463abc0a", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: refugees who arrived by boat in recent years and who are residing primarily in temporary\nshelters in Aceh and North Sumatra.\n\n\nIndonesia’s National Refugee Task Force, established in 2019, remains an important Government entity\nin the management of refugee affairs. Deputy V in POLHUKAM is the head of the National Refugee\nTask Force and members include the Ministry of Foreign Affairs and a wide range of security-focused\nactors. Several local refugee task forces operate in provinces hosting refugees and remain active and\nimportant counterparts. UNHCR also works with a range of partners in Indonesia, particularly IOM,\nYCWS, and YKMI in several areas of protection and assistance. In addition, UNHCR works with nongovernmental, civil society and refugee-led organizations, as well as other UN agencies working with\nand advocating for the rights of the refugee population in Indonesia.\n\n\n**Locations of Persons Registered with UNHCR**\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n1 The Government of Indonesia-UNHCR host country agreement has been in place since 1979.\n\n\nUNHCR / 1 November 2024 2\n\nMention: \"Locations of Persons Registered with UNHCR\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"UNHCR registration records are mapped to show locations of persons registered in Indonesia.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "reliefweb", "source_key": "reliefweb:001303:14:1", "occurrence_id": "b241dd7d72067e3701b639b7", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: \non need, not mandates or artificial legal categorizations‟.\n52 See further Alice Edwards, 'Overview of International Standards and Policy on Gender Violence and\nRefugees: Progress, Gaps and Continuing Challenges for NGO Advocacy and Campaigning'. Paper\ndelivered at the Canadian Refugee Council International Refugee Rights Conference, Toronto, Canada, 1719 June 2006. Amnesty International, AI Index: POL/33/004/2006.\n\n13\n\nMention: \"AI Index\""}, {"role": "assistant", "content": "{\"role\": \"background\", \"usage_action\": \"inform\", \"summary\": \"Amnesty International reference on gender violence and refugee rights standards.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "reliefweb", "source_key": "reliefweb:001462:34:0", "occurrence_id": "b6b07702b6caf9a1c319a185", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: TABLE 12 **Origin of asylum applicants in Australia and New Zealand \u0003** | 2013 **(1)**\n\n\n\n\n\n\n\nUNHCR Asylum Trends 2013 **35**\n\nMention: \"UNHCR Asylum Trends 2013\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"UNHCR asylum trends provide applicant-origin data presented in the table.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "reliefweb", "source_key": "reliefweb:001494:7:0", "occurrence_id": "f87a2e2bd6c9e6fd166ad679", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: In conflict areas, almost no response services are available to survivors. Due to the limited\naccess to medical care, psychosocial support, and other specialized protection services,\nincluding cash and dignity kits, that humanitarian partners are unable to deliver in the\nabsence of credible guarantees from the authorities, survivors remain unattended,\nsuffering severe physical and emotional consequences with no care or redress.\n\nOn 24 May, the United Nations Special Representative of the Secretary-General on Sexual\nViolence in Conflict Pramila Patten, expressed grave concerns about reports of sexual\nviolence against women and girls, including allegations of rape, in the context of the\nhostilities.\n\n\n**Violations against children.** Children, who were already among those most in need\nbefore the crisis (57% of the 15.2 estimated in needs based on the HRP 2023), have had\ntheir situation further exacerbated due to the ongoing conflict. Actors on the ground 8 have\nidentified grave violations affecting children, including killing, maiming, and recruitment into\narmed forces. The disruption of national child-care systems affects particularly those\nchildren who were already unaccompanied or living in institutional care. Even those\nrefugees and IDP children who reached safe locations have seen their well-being severely\naffected by the interruption of education and health services; suffer from the exposure to\nconflict-related distress and trauma; experience neglect and deteriorated family\nenvironment due to severe destitution; and may experience involuntary family separation\nwhile on the move.\n\n\nThe lived experience of the conflict and the flight has had a severe impact on the mental\nhealth and psychological wellbeing of children, with signs of acute emotional distress widely\nreported amongst children as well as caregivers. The interruption of children’s access to\nschool due to the halting of education and the sudden displacement around final exam time\nhas hindered thousands of children from completing their course of study. Attendance rate\nat existing Child-Friendly Spaces has dropped, due to fleeing, as well as due to children\nbeing\n\nMention: \"HRP 2023\""}, {"role": "assistant", "content": "{\"role\": \"supporting\", \"usage_action\": \"inform\", \"summary\": \"Humanitarian Response Plan provides needs estimates for children in conflict-affected communities.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "reliefweb", "source_key": "reliefweb:001554:2:0", "occurrence_id": "f8af0400f3fa6c24bd0f93d4", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: **Figure 3. Have you personally experienced any of these types of**\n**incidents on your journey?**\n\n\n\nWomen consistently reported slightly more abuses than men for the top four protection\n\nincidents, highlighting the specific vulnerability of women in this conflict (Figure 3). The\n\nwidest gap pertains to sexual violence, faced by 75% of women and 54% of men – high\n\nrates, given that much sexual violence generally goes unreported. Men slightly more\n\noften reported kidnapping, which may be linked to forced conscription by parties to\n\nthe conflict. 8 [^8: UNHCR (14 October 2024). [Afflux des Réfugiés du Soudan](https://data.unhcr.org/en/documents/details/111905)] Older respondents (above 60 years old) also more often reported abuses\n\nthan respondents from other age groups, particularly for physical violence (90%), sexual\n\nviolence (76%), detention (71%), and kidnapping (58%), showcasing the existence of\n\nage-specific vulnerabilities in the conflict and calling for protection programming that is\n\nage-sensitive.\n\n## **Children perceived as particularly exposed to** **abuse during the journey**\n\nA vast majority of respondents (95%) noted that children were particularly vulnerable\n\nduring the journey. Death (94%), physical and sexual violence (83% each), robbery (72%),\n\ndetention (63%), and kidnapping (38%) were the most prominent risks for children (Figure\n\n4). According to UNHCR registration data, 88% of new Sudanese refugees in Chad are\n\nwomen and children, underlining the large protection challenges for this age group. 9 [^9: UNHCR, _op. cit._]\n\nAlthough no children were interviewed, 68% of respondents were travelling with children\n\nin their care, with more than a third of\n\nMention: \"UNHCR registration data\""}, {"role": "assistant", "content": "{\"role\": \"supporting\", \"usage_action\": \"validate\", \"summary\": \"UNHCR registration data corroborate the reported share of new Sudanese refugees who are women and children.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "reliefweb", "source_key": "reliefweb:001571:1:0", "occurrence_id": "239aadbb382c38f6b29263d5", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: - **Recommendation 3: Strengthening partnerships and build the capabilities** of actors that can contribute to expanding\nresettlement; engaging actors not traditionally involved in resettlement; strengthening the efficiency of processes and\nimproving data collection to inform evidence-based advocacy.\n\n## II. GLOBAL RESETTLEMENT NEEDS 2021 AND KEY PRIORITY SITUATIONS\n\n\n- **Recommendation 4: Priority situations:** As per the 2021 Projected Global Resettlement Needs (PGRN) more than 1.445\nmillion refugees are in need of resettlement. UNHCR urges EU Member States to focus efforts on refugees along the\n**Central Mediterranean Route,** as well as **in the Comprehensive Refugee Response Framework (CRRF) countries,** and **in**\n**the Middle East, with a focus on Syrian refugees.** Additionally, UNHCR calls for **unallocated quotas** that can be used in a\nflexible way for urgent and emergency cases across the globe.\n\n## III. KEY POLICY CONSIDERATIONS AND RECOMMENDATIONS\n\n\n- **Recommendation 5: Towards a predictable and sustainable European program:** The EU has taken encouraging steps\nto solidify a predictable and sustainable European programme for providing refugees third country solutions – with the\ndraft regulation proposing the **_Union Resettlement and Humanitarian Admission Framework_** . UNHCR looks forward to the\nopportunity to consult with the EU and Member States and provide input as the Framework comes closer to becoming a\nreality. The Pact and discussions ahead are also an opportunity to recall the importance of resettlement, and its function\nas a tool to provide protection and a durable solution to refugees.\n\n\n- **Recommendation 6: Enhance collaboration among actors and EASO engagement:** UNHCR welcomes ongoing close\ncollaboration with EASO and the opportunity to participate in EASO’s recent Resettlement and Humanitarian Admissions\nNetwork meetings to maximize information-sharing and coordination among all stakeholders involved.\n\n## IV. COMPLEMENT\n\nMention: \"2021 Projected Global Resettlement Needs\""}, {"role": "assistant", "content": "{\"role\": \"supporting\", \"usage_action\": \"inform\", \"summary\": \"Projected Global Resettlement Needs report estimates the number of refugees requiring resettlement and identifies priority situations.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "umar_pads", "source_key": "umar_pads:000229:2:1", "occurrence_id": "5e28f6c38ec44074ed063b75", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: I) per capita 2 was estimated at US$320 in 2017. Malawi\nis ranked 170 out of 188 countries on the United Nations Human Development Index, and 125 out of 157 on the World\nBank’s Human Capital Index. Almost half (47 percent) of the children under age five in Malawi are short for their age\ndue to long-term effects of malnutrition and 20 percent are severely stunted. Malawi’s economic growth rates have\nfallen below the average of 2.8 percent in non-resource rich African economies during the last twenty years. Real per\ncapita Gross Domestic Product (GDP) has grown at an average of just above 1.5 percent per year between 1995 and\n2014. With these persistent low growth rates, successive governments in Malawi have struggled to lift people out of\npoverty. Wealth accounting data 3 shows that more than half of Malawi’s wealth (estimated at US$10,442 per capita in\n2014) is renewable natural capital, mainly cropland with smaller shares contributed by pastureland, forests and\nprotected areas. The natural capital base however is under extreme pressure due population growth, agricultural\nexpansion and climate change. There is also a strong correlation between areas with highly degraded land and those\nwith a high incidence of poverty, although there is currently insufficient evidence to point to a causal link 4 .\n\n\n1 World Bank (2017). Malawi Economic Monitor – Unleashing the Urban Economy, Macroeconomics and Fiscal Management Global\nPractice, Washington, DC: The World Bank.\n2 GNI _per capita_ - atlas method (current US$)\n3 Lange et al. (2018). The Changing Wealth of Nations 2018: Building a Sustainable Future. Washington, DC: World Bank\n4 World Bank (2018). Malawi Country Environmental Analysis. October 2018 (under preparation)\n\n\nNov 27, 2018 Page 3 of\n\nMention: \"Wealth accounting data\""}, {"role": "assistant", "content": "{\"role\": \"supporting\", \"usage_action\": \"inform\", \"summary\": \"Wealth-accounting data quantify renewable natural capital and forest contributions to Malawi’s GDP and poverty context.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "umar_pads", "source_key": "umar_pads:000347:6:1", "occurrence_id": "ef6513893a5a74220bba26ad", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: storage reservoir\nin the “Kike-Kremenata” hydro-System, not currently ready to be appraised, and the first phase project\nwill finance the technical, social and environmental studies to allow a more detailed appraisal for the\nsecond phase project.\n\n\n**Component 1: Foundational measures for water security (IDA €6.2 million)**\n\n\n16. **This component will build the foundations for water security in the country, thereby increasing**\n**targeted communities’ resilience to the climate change–induced threat of droughts and build readiness**\n**for major investments that duly consider current and foreseen climate change impacts.** It will support:\n1) national level water resources investment preparation; 2) enhancement of water information system\nfor decision making; and 3) dam operations improvement and safety regulations and measures. These\nactivities will also enable improved implementation of Kosovo’s Climate Change Framework Strategy.\n\n\n**Component 2: Addressing water crisis with catalytic investments (IDA €19.1 million** **and WBIF** **4**\n**grant €1 million)**\n\n\n17. **This component aims to catalyze water security investments in the Morava e Binces Basin that**\n**address the immediate challenges of water shortage and other risks exacerbated by climate change**\n\n\n4 Western Balkans Investment Framework (WBIF) is a joint facility of the EU, financial institutions, bilateral donors and the\ngovernments of the Western Balkans. It supports socio-economic development and EU accession across the Western Balkans\nthrough the provision of finance and technical assistance for strategic investments in the energy, environment, social, transport\nand digital infrastructure sectors. The World Bank became a full member of WBIF in June 2019. A recipient executed trust fund\nwill be established.\n\n\nFeb 24, 2020 Page 7 of 13\n\nMention: \"water information system\""}, {"role": "assistant", "content": "{\"role\": \"supporting\", \"usage_action\": \"curate\", \"summary\": \"Water information system supports decisions on water security and climate-resilient watershed investments.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "umar_pads", "source_key": "umar_pads:000482:69:0", "occurrence_id": "d0efa075389505a5885e9635", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: **The World Bank**\nAgriculture Governance, Growth and Resilience Investment Project (P170035)\n\n\nexpectancy of the investment works justify the time considered for analysis. The prices were projected to increase by 6%\nper year in the first few years 47 [^47: The current Russia’s invasion of Ukraine has put tremendous pressure on food prices, exceeding the projected rates, and such upward price pressure is\nexpected to continue for years to come.] and then continue a price increase of 3% per year over the other 25 years of project\nperiod.\n\n25. **Financial analysis is done for investments in farms, looking at the small farm sector and larger agricultural**\n**enterprises.** Although much of the agricultural data is available in aggregate level, due to lack of detailed farm data,\nanalysis used assumptions on the farming trends following the irrigation improvements, as experienced in other countries\nwith irrigation projects supported by the bank in recent years. 48 [^48: Water Resource and Irrigation Project in Albania was one of those examples used.]\n\n26. **Expansion on higher value crops at cost of lover value cereals and field crops is expected.** The main fruits\ncurrently cultivated are apples, peaches, and plumbs, which are foreseen to expand further. But the project also expects\nother fruits such as Pears and berries to come to picture following improved irrigation systems. Wine grapes dominate\ncurrently and are expected to further expand but also table grapes are foreseen too. The major changes are expected\nfrom vegetables in both open fields and especially in greenhouses as they rely totally on irrigation and can yield much\nhigher productivity. A presentation of the anticipated changes in increased irrigated land and shifting from low value\ncrops (cereals and field crops) to high value crops (fruits and vegetables) and expected yield improvements are presented\nin table 1.1 below.\n\n\n**Table 1.1. Expected changes in areas\n\nMention: \"agricultural data\""}, {"role": "assistant", "content": "{\"role\": \"supporting\", \"usage_action\": \"inform\", \"summary\": \"Aggregate agricultural data inform assumptions about irrigation-driven farm production and crop shifts.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "umar_pads", "source_key": "umar_pads:000482:70:2", "occurrence_id": "bf31f76f1d97dfcb09d3d628", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: , and\nvineyards. The actual data support those changes. 49\n\n30. **Positive economic spillover effects are expected to be generated from higher income generated and boosted**\n\n\n49 The actual data are mainly those published by the Moldova Institute of Statistics, in specific agriculture reports and agriculture data series. These\nstatements are also supported by interviews and discussions with farmers .\n\n\nPage 67 of 75\n\nMention: \"agriculture data series\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"Agricultural reports and data series supply evidence on crop changes and farm-sector conditions.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "umar_pads", "source_key": "umar_pads:000498:3:2", "occurrence_id": "4ce04d8d2cd5d6653a9401e4", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: direct investments);\n\n\n2 World Bank (2018) “Country Private Sector Diagnostics”\n3 The World Bank’s Enterprise Survey (2012) indicated that informal enterprises are predominantly micro firms, while their downstream linkages\nto other firms (formal or informal) are limited, hindering the sector’s ability to play a role in the supply chain for the formal sector.\n4 Rural based value chains are those value chains where primary production is based in rural areas.\n\n\nMay 27, 2020 Page 4 of 9\n\nMention: \"Enterprise Survey\""}, {"role": "assistant", "content": "{\"role\": \"supporting\", \"usage_action\": \"inform\", \"summary\": \"Enterprise Survey evidence describes informal firms’ size and limited supply-chain links.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "umar_pads", "source_key": "umar_pads:000861:3:2", "occurrence_id": "4be11a8ca1cde0cb3dbc4d93", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: \nand (c) management of two employment centers, one in Majuro and one in Ebeye, which aim to connect job-seekers with\nemployers and training/work-related opportunities. The Scholarships Board offers education scholarships and loans to\nMarshallese citizen to pursue tertiary education abroad and in RMI. Scholarships are conditional on performance and\nreturning to RMI for work after graduation. 8 Scholars who return to RMI are eligible for some support in finding\nemployment (they are referred to the public service commission (PSC), put on lists shared with the private sectors, or\naccompanied to potential employers’ offices).\n\n\n5 The last Household Income and Expenditure Survey in the RMI was carried out in 2002, limiting the extent to which trends in poverty and other\nquality-of-life indicators can be accurately examined. The term ‘hardship’ relates specifically to national poverty measures. Incidence of ‘hardship’ is\ndefined as the proportion of the population whose expenditure is below a threshold that includes an allowance for minimum food and non-food\nneeds.\n6 US Graduate School (2018).\n7 Job corps is a US run training institution in Hawaii offering 2-years TVET courses targeting 18-25 years old high school graduate.\n8 It requires to maintain a GPA of 2.5 or higher and one year of scholarship equals one year of service. From latest cohort (2018 and 2017), 67% and\n86% of students having completed their program came back.\n\n\nMar 10, 2020 Page 4 of 14\n\nMention: \"Household Income and Expenditure Survey\""}, {"role": "assistant", "content": "{\"role\": \"background\", \"usage_action\": \"validate\", \"summary\": \"Cited as the last national household survey, whose 2002 date limits how far poverty trends can be examined.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "umar_pads", "source_key": "umar_pads:000908:33:0", "occurrence_id": "a5c11e72d13ec77c42e83937", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: **The World Bank**\nHUBEI SMART AND SUSTAINABLE AGRICULTURE PROJECT (P172224)\n\n\naccess to inspection reports have increased consumer confidence in food quality and safety in both New Zealand and\nDenmark.\n\n\n58. The Ag Observatory concept has been successfully implemented by the World Bank in collaboration with client\ngovernments in the Africa Region, providing near real-time and high-resolution agricultural weather information that\nallows Governments to proactively monitor the weather-related performance factors of agricultural production\nsystems. The Ag Observatory's insight is based on 1.5 million “virtual weather stations” (VWS) generated on demand\nfrom a combination of data from ground stations, and satellite platforms. The application of Big Data and Machine\nLearning (using published algorithms) then allows the generation of a contiguous 9km x 9km weather dataset that is\nused for advanced analytics linking agricultural meteorology, crop and livestock performance, and a variety of\nsocioeconomic and socio-political metrics for decision support. By harnessing the remote sensing and high-resolution\nreal-time weather data with local cropping calendars, it is possible to make early projections of crop yield anomalies\nfrom sub national to global scales and thus provide early warning of potential food shocks several months in advance of\nnormal harvest periods. The design of Component 1 of this project draws on that experience.\n\n\n**III.** **IMPLEMENTATION ARRANGEMENTS**\n\n\n**A. Institutional and Implementation Arrangements**\n\n\n59. Institutional arrangements for project implementation have been established at the provincial level and at the\nfive project counties, and will be further detailed in the Project Operations Manual (POM), which must be to the Bank’s\nsatisfaction. _Project Leading Groups (PLGs)_ of high-level decision-makers from relevant key agencies are needed to\nprovide oversight, strategic guidance, and inter-agency coordination for the project at province and county levels. In\naddition to DARA and its relevant departments,\n\nMention: \"contiguous 9km x 9km weather dataset\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"analyze\", \"summary\": \"Gridded weather surface built from ground stations, satellites and machine learning, used for crop and food-security analytics.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "umar_pads", "source_key": "umar_pads:000908:33:0", "occurrence_id": "76761edaae7d7693efc22fad", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: **The World Bank**\nHUBEI SMART AND SUSTAINABLE AGRICULTURE PROJECT (P172224)\n\n\naccess to inspection reports have increased consumer confidence in food quality and safety in both New Zealand and\nDenmark.\n\n\n58. The Ag Observatory concept has been successfully implemented by the World Bank in collaboration with client\ngovernments in the Africa Region, providing near real-time and high-resolution agricultural weather information that\nallows Governments to proactively monitor the weather-related performance factors of agricultural production\nsystems. The Ag Observatory's insight is based on 1.5 million “virtual weather stations” (VWS) generated on demand\nfrom a combination of data from ground stations, and satellite platforms. The application of Big Data and Machine\nLearning (using published algorithms) then allows the generation of a contiguous 9km x 9km weather dataset that is\nused for advanced analytics linking agricultural meteorology, crop and livestock performance, and a variety of\nsocioeconomic and socio-political metrics for decision support. By harnessing the remote sensing and high-resolution\nreal-time weather data with local cropping calendars, it is possible to make early projections of crop yield anomalies\nfrom sub national to global scales and thus provide early warning of potential food shocks several months in advance of\nnormal harvest periods. The design of Component 1 of this project draws on that experience.\n\n\n**III.** **IMPLEMENTATION ARRANGEMENTS**\n\n\n**A. Institutional and Implementation Arrangements**\n\n\n59. Institutional arrangements for project implementation have been established at the provincial level and at the\nfive project counties, and will be further detailed in the Project Operations Manual (POM), which must be to the Bank’s\nsatisfaction. _Project Leading Groups (PLGs)_ of high-level decision-makers from relevant key agencies are needed to\nprovide oversight, strategic guidance, and inter-agency coordination for the project at province and county levels. In\naddition to DARA and its relevant departments,\n\nMention: \"high-resolution\nreal-time weather data\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"analyze\", \"summary\": \"Remote-sensing weather inputs combined with local cropping calendars to project yield anomalies and warn of food shocks.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "umar_pads", "source_key": "umar_pads:000934:3:0", "occurrence_id": "f6990a16cda3f815c9cb8331", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: **The World Bank**\nEastern Ukraine: Reconnect, Recover, Revitalize (3R Project) (P172348)\n\n\nline separating Government-Controlled Areas (GCAs) and Non-Governmental Controlled areas (NGCAs) in\nEastern Ukraine.\n\n\n4. **The conflict has severely impacted socioeconomic activity in Ukraine’s eastern industrial heartland of**\n**Donetsk and Luhansk Oblasts.** Prior to the conflict, these areas (referred to as “the Donbas”) accounted for 12.5\npercent of Ukraine’s population and generated 15.7 percent of the country’s total GDP and a quarter of its\nexports. Because of the conflict, an estimated 70 percent of enterprises in the Donbas have reported decreased\ninvestment and revenues, disrupted trade relationships, lack of demand for products, and shrinking\nworkforces. 2 [^2: REACH. 2017. _Thematic Assessment of Livelihoods in Donbas_ [. http://www.reachresourcecentre.info.](http://www.reachresourcecentre.info/)] A World Bank survey of the socioeconomic impacts of the conflict in 2017 highlighted the welfare\nand socioeconomic challenges facing IDPs, veterans, and host communities. 3 [^3: World Bank. 2017. _Ukraine: Socio-Economic Impacts of Internal Displacement and Veteran Return_ .]\n\n\n5. **Since taking office in May 2019, Ukrainian President Volodymyr Zelenskyy has made outreach and**\n**development support to Eastern Ukraine a key policy priority, emphasizing socioeconomic integration of the**\n**region.** This policy shift represents a window of opportunity for the World Bank to support the GoU in promoting\nthe recovery and development of conflict-affected areas. Luhansk Oblast GCAs are proposed as the geographic\nfocus for initial World Bank investment because of their acute lack of connectivity and economic opportunity\ncompared to other areas of Eastern Ukraine, to complement and leverage other international partner funding\nmore heavily concentrated in Donetsk Oblast, and to promote economic recovery of the region\n\nMention: \"World Bank survey of the socioeconomic impacts of the conflict\""}, {"role": "assistant", "content": "{\"role\": \"supporting\", \"usage_action\": \"source\", \"summary\": \"Survey highlighting welfare and socioeconomic challenges facing IDPs, veterans and host communities in 2017.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "umar_pads", "source_key": "umar_pads:001063:2:1", "occurrence_id": "d07806b6b2baad4858b8c2c8", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: majority foreign-owned firms closed their doors. Only\n0.6 percent of companies reported revenue growth, and the increases were generally small. 2 [^2: Ibid]\n\n\n3. **The global pandemic has also led to significant household income losses and especially for those in the informal**\n**sector.** Household survey results indicate that 71 percent households saw their income decrease and were unable to meet\ntheir basic living expenses. Only three out of every ten households have enough savings to pay for regular expenses such\nas rent, water and electricity bills, and food. The survey data clearly show that the impact has been greater and more\nwidespread than anticipated and has worsened the living conditions of already vulnerable households. In the short term,\nmany households will have trouble covering this income gap, and the government’s support program will therefore be\nessential to mitigate the shock. 3 [^3: Ibid]\n\n\n**4.** **If the pandemic remains under control locally, Côte d’Ivoire could resume its strong economic performance in**\n**2021.** The economy is expected to gradually recover in 2021–2022, with a rebound in services and renewed productivity\nin industry and agriculture. Should investment rebound, it would help restore productivity growth in the manufacturing\nand food industries. This could subsequently boost exports and fuel private consumption, which could return to prepandemic levels and push GDP growth to 5 percent in 2021. A potential recovery in 2021 will depend on many factors\nincluding: the availability and distribution of vaccine; the speed of government aid disbursements; the management of\ndomestic budget pressures; and the uncertainties related to the current political situation and new exogenous shocks,\nsuch as a deterioration in key commodity prices and a global recession. 4\n\n\n1 World Bank. 2020. Cote d’Ivoire 10th Economic Update : Cote d’Ivoire and the COVID-19\n\nMention: \"Household survey results\""}, {"role": "assistant", "content": "{\"role\": \"supporting\", \"usage_action\": \"source\", \"summary\": \"Survey showing 71 percent of households saw income fall and could not meet basic living expenses.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "umar_pads", "source_key": "umar_pads:001063:2:0", "occurrence_id": "f79ff978f511067a1e1b7c52", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: **The World Bank**\nCote d'Ivoire Youth Employment and Skills Development Project - Phase 3 (P172800)\n\n\nOther Decision (as needed)\n\n\n**B. Introduction and Context**\n\nCountry Context\n\n\n1. **With GDP growth estimated at 6.9 percent in 2019 (or 4.2 percent in per capita terms), Côte d'Ivoire continued**\n**to be one of the best performing economies in Sub-Saharan Africa (Figure 1), driven in particular by the expansion of**\n**the middle class, which supported demand across all sectors.** The outlook for 2020 was favorable, with projected growth\nof about 7 percent, but the COVID-19 health situation has driven this projection downward to reflect the slowdown in\nexports and the introduction of COVID-19 containment measures, both of which have slowed economic activity. 1 [^1: World Bank. 2020. Cote d’Ivoire 10th Economic Update : Cote d’Ivoire and the COVID-19 Pandemic. World Bank, Washington, DC. © World Bank.\nhttps://openknowledge.worldbank.org/handle/10986/34559 License: CC BY 3.0 IGO.]\n\n\n2. **GDP growth for Côte d'Ivoire is now expected to be around 1.8 percent for 2020 due to COVID-19’s impact on**\n**businesses and households.** According to data collected in April 2020, COVID-19 has had direct repercussions on Côte\nd'Ivoire’s businesses: reduced working hours, lower sales and revenue, and even partial or total shutdown. Overall, 37.7\npercent of businesses were forced to close (2.4 percent permanently and 35.3 percent temporarily). The business closure\nrate was higher among microenterprises (43 percent), however, than among small and medium-sized enterprises (about\n30 percent). Nearly 35 percent of export firms and 54 percent of majority foreign-owned firms closed their doors. Only\n0.\n\nMention: \"data collected in April 2020\""}, {"role": "assistant", "content": "{\"role\": \"supporting\", \"usage_action\": \"source\", \"summary\": \"April 2020 firm data behind the closure, working-hours and revenue-loss figures under COVID-19.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "umar_pads", "source_key": "umar_pads:001142:5:1", "occurrence_id": "125a57b669f6421764c84ddf", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: their operations, this would enable ESPs to attract increased commercial financing in addition to\ncreating an enabling environment for private sector led investments in grid scale generation as there would be credible\ndownstream off-takers. Further, the proposed Institutional and regulatory enhancement will support to re-establish\ntransparency, trust, effectiveness, and legitimacy in the government institutions to provide an enabling operating\nframework for the private sector.\n\n20. **The proposed MPA establishes the blueprint for other financiers to collaborate on Somalia’s energy sector**\n**recovery** . Major development partners active in the energy sector include Africa Development Bank (AfDB), Department\nfor International Development (UK) (DFID), United States Agency for International Development (USAID), Swedish\nInternational Development Agency (SIDA), Kreditanstalt fur Wiederaufbau (KfW), Norway and United Nations\nDevelopment Program (UNDP).\n\n21. **Finally, the proposed MPA is a COVID 19 economic recovery response** . Over the past few months, the COVID-19\npandemic has caused an unprecedented global economic and social crisis, significantly affecting all aspects of life. The\nproposed project will also address the growing need to fight contagious diseases such as COVID by availing reliable\nelectricity supply to health institutions to reduce the cost of operations in addition to the specific targeting to water supply\nsystems. IFC implemented a rapid survey among electricity service providers (ESP) to better understand the impact that\nthe COVID 19 pandemic on Somali electricity operations. Investments to respond to post COVID 19 socio-economic\nrecovery will be identified and prioritized during project preparation.\n\n\nRelationship to CPF\n\n22. **The proposed MPA contributes to the World Bank Group (WBG) twin goals of eliminating extreme poverty and**\n**boosting shared prosperity** . The program is aligned with the Country Partnership Framework for the Federal Republic of\nSomalia for the Period FY19 – 22, which explicitly identifies energy access\n\nMention: \"rapid survey among electricity service providers\""}, {"role": "assistant", "content": "{\"role\": \"supporting\", \"usage_action\": \"analyze\", \"summary\": \"IFC provider survey used to understand pandemic impacts on Somali electricity operations.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "umar_pads", "source_key": "umar_pads:001183:5:2", "occurrence_id": "8e018e9657accc69fd14e44b", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: interventions with Ecuador’s IPAMs continue to rely on exogenous intervention models that\nfail to define the design of the investment and its delivery in a way that adequately reflects the specific cultural\nidentities 22 and development priorities of IPAMs. In this vein, the PRODEPINE model 23 in which the IPAMs serve\n\n\n20 ENEMDU, 2019.\n21 The December 2011 Employment Survey.\n22These include the unique ways of living, self-governing, attachment to land and natural resources, traditional knowledge and specific IPAM rights\nthat are protected by various laws and policies (i.e. the country’s constitution, ILO 169, UN Declaration for IP Rights, the International Convention\nto Eliminate All Forms of Racial Discrimination, and the Durban Action Plan).\n23 PRODEPINE, as it is commonly referred to, is the World Bank-financed Indigenous and Afro-Ecuadorian Development Project (P040086) operation,\nthat was satisfactorily implemented between 1998 and 2003, and was structured in a way that allowed for local IPAM communities to plan and\nimplement investments and sub-projects aimed at improving their quality of life.\n\n\nFeb 19, 2020 Page 6 of 12\n\nMention: \"December 2011 Employment Survey\""}, {"role": "assistant", "content": "{\"role\": \"supporting\", \"usage_action\": \"source\", \"summary\": \"Footnoted employment survey behind an Indigenous-population labour figure cited in the discussion of IPAMs.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "umar_pads", "source_key": "umar_pads:001176:6:1", "occurrence_id": "4a23d01ce8ae2e26e4704c87", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: from GoG. One of the primary initiatives of the ESRP is that sector arrears are to be netted out\nand a funding plan be adopted to clear the remaining balance. An audit of the sector has to be updated annually, and\nonce completed, GoG will implement a process to net out the cross arrears. It will also consider what refinancing options\nare available for public sector SOEs to clear their remaining arrears and curtail further accumulation of these shortfalls.\nMeasures to implement a financing plan to help redress the sector will play a key role in the Program.\n\nESRP measures to improve performance and financial viability of the distribution utilities will be supported by the\nProgram. This will include supporting the PURC to establish a new tariff methodology in order to project a tariff\ntrajectory, implement a new tariff for street lighting and install prepaid meters for MDAs to ensure that utilities are\npaying their dues. The Program will also support the establishment and enforcement of performance improvement plans\nby ECG and NEDCo that will help improve both technical and commercial performance. Finally, the Program will support\nkey activities to improve corporate governance at ECG to improve transparence and accountability.\n\nThe Program will include the results of ESRP actions related to generation cost reduction and increase revenues of the\ndistribution companies. The Program will also support ESRP activities aimed to reduce current generation costs (ensuring\ntransparent implementation of the merit order dispatch and optimization of hydropower generation for the regulated\nmarket) as well as ensure that new power plants will be procured competitively and are consistent with the least-cost\npower expansion plan. On the revenue side, the Program will support activities of the ESRP that are expected to reduce\nelectricity losses and increase collection rates of the distribution utilities.\n\nThe clean cooking component of the program will support GoG’s commitment to LPG becoming the primary cooking fuel\nfor 50 percent of households. GoG intends to utilize market-based approaches in the delivery of cooking solutions by\nproviding the necessary conditions for sustainable innovation\n\nMention: \"audit of the sector\""}, {"role": "assistant", "content": "{\"role\": \"supporting\", \"usage_action\": \"validate\", \"summary\": \"Annually updated sector arrears audit whose completion gates the netting-out and refinancing process.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "umar_pads", "source_key": "umar_pads:001197:2:0", "occurrence_id": "b2310deb5ab8e25a1eccc0d0", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: **The World Bank**\nGEF China Sustainable Cities - Supporting Green and Low Carbon Urban Development (P173316)\n\n\n\n\n\nOther Decision (as needed)\n\n\n**B. Introduction and Context**\n\nCountry Context\n\n1. **China’s successful transformation into the world’s second largest economy has come with high**\n**environmental costs.** Urbanization and infrastructure expansion amid rapid economic growth has led to a huge\nconsumption of natural resources, aggressive land conversion to urban and industrial uses and insufficient\nwaste management, among others. Heavy consequences including spikes in greenhouse gas (GHG) emissions 1,\nbiodiversity loss 2 and environmental and land degradation have followed. As a result, Chinese cities where\nmost people and economic activities concentrate are becoming less livable and sustainable.\n\n\n2. **To address its environmental and ecological challenges, China has shifted focus from high** - **rate GDP growth**\n**to high quality.** The Chinese leadership has explicitly emphasized preserving ecological resources as an\nessential part of the new modality of growth. 3 The government has made some efforts to actualize this\ndeclaration. In the case of urban development, China’s newly initiated territorial and spatial planning system 4\noperationalizes ecological preservation and environmental protection by requiring all urban planning maps to\nclearly demarcate three areas: “red lines” are mandated to be drawn to show the boundaries of ecological\nprotection, farmland preservation and city expansion.\n\n\nSectoral and Institutional Context\n\n\n1 China is the largest emitter in the world with CO2 emissions at 7.5 metric tons per capita in 2014 (Euro Area: 6.5) and total\n[greenhouse gas emissions 12,454,711 kt of CO2 equivalent in 2012. Source: World Bank Data](https://\n\nMention: \"World Bank Data\""}, {"role": "assistant", "content": "{\"role\": \"supporting\", \"usage_action\": \"source\", \"summary\": \"Cited source for China's 2014 per-capita CO2 and 2012 total greenhouse-gas emissions figures.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "umar_pads", "source_key": "umar_pads:001183:8:1", "occurrence_id": "4dfbed8741c7a39e95e34aaf", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: sup> (GBV), with IPs, AEs and Montubians citing higher incidence levels (67.8\npercent, 66.7 percent and 62.9 percent respectively) 29 [^29: IBID.], aggravated by discrimination based on ethnic, cultural,\neconomic, social or age status. Persistent and traditional social norms can often fuel and/or mask this pervasive\nviolence: indeed, a quarter of all women surveyed justified domestic violence. 30 [^30: OECD (2019), Gender, Institutions and Development Database, https://oe.cd/ds/GIDDB2019.] The proposed Project presents an\nopportunity to not only increase the skills and agency of women through capacity building, education initiatives\nand financial support, but also to address and shape community attitudes towards GBV by utilizing the community\nspaces to host sensitization events and safe spaces for women.\n\n\n**21.** **Climate Change.** The Project would contribute to national climate change objectives by employing climate resilient\nand green building designs, standards, and construction techniques for infrastructure investments. It would also\nbe achieved through strengthening of territorial governance of relevant aspects of disaster risk management and\nclimate change mitigation and adaptation, to be integrated into the technical assistance and design of targeted\ntraining programs. Furthermore, the menu of investments and technical assistance will take into account ecofriendly approaches and will include eligibility criteria that is aligned with climate resilient activities.\n\n\n**22.** **Citizen Engagement.** The project will be designed in a fully participatory manner. The list of potential technical\nassistance and investment activities will be prepared in close consultation with representative IPAM organizations.\nFurthermore, the specific activities and investments to be carried out at the local level will be activated based on|**Frequency **|**Datasource **|**Methodology for Data**
**Collection **|**Responsibility for Data**
**Collection **|\n|Suspected cases of COVID-19 reported
and investigated per approved protocol|Percentage of suspected
cases of COVID-19 cases
reported and investigated
per approved protocol
|Monthly
|HMIS
|
Collected by the Ministry
of Health (MOH)
|
MOH
|\n|Health facilities with trained staff in
Covid-19 infection prevention control per
MoH approved protocol|
Numerator: Health facilities
with trained staff in Covid-
19 infection prevention
control per MoH approved
protocols
Denominator: Total
number of health facilities.
|
Semi-
annual
|Project
reports
|Data collected by MOH
|MOH
|\n|Reference and district hospitals with
personal protective equipment and
infection control products and supplies,
without\n\nMention: \"Data collected by MOH\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"Ministry-collected data named as the source for the trained-staff indicator's numerator and denominator.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "umar_pads", "source_key": "umar_pads:001457:3:1", "occurrence_id": "4a2ca7e072dbf5979294f954", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: Saharan Africa (0.40).\n\n\n6. **The economic impacts of a COVID-19 outbreak are expected to be large underscoring the need for an urgent**\n**response.** PNG’s heavy reliance on natural resources makes the country vulnerable to global market shocks in\ncommodity prices and weaker external demand – the close economic ties with China, the epicenter of COVID-19, will\nhave significant ramifications on the PNG economy. Limited fiscal space and a rigid exchange rate regime constitute\nconstraints for the authorities to react to these shocks, requiring an urgent mobilization of external financial support\nfrom the development partners. External assistance could play a key role in ensuring that service delivery can be\nstrengthened to meet the challenge of COVID-19 and increase the health system’s preparedness to manage future\npandemics.\n\n\nSectoral and Institutional Context\n\n\n7. **PNG has been buffeted by a number of health crises in recent years** . A cholera outbreak in 2009 infected\n15,500 people with 500 deaths, a chikunguniya outbreak in 2012-13 affected all 22 provinces, a measles\noutbreak in 2014 resulted in nearly 5,000 cases and 365 deaths and polio re-emerged in 2018 with an outbreak\nof vaccine-derived polio virus type 1 (cVDPV1). Tuberculosis (TB) is at public health emergency levels and PNG\nhas one of the highest rates of Multi Drug Resistant TB in the world with an incidence of 23 per 100,000\npopulation 5 [^5: Global Tuberculosis Report 2019\n[https://www.who.int/tb/publications/global_report/tb19_Report_country_profiles_15October2019.pdf](https://www.who.int/tb/publications/global_report/tb19_Report_country_profiles_15October2019.pdf)] .\n\n\n8. **A COVID-19 outbreak will further strain a health system that struggles to deliver basic health services** . PNG\nfaces a shortage in health workers – there are fewer than 500 registered medical officers in\n\nMention: \"Global Tuberculosis Report 2019\""}, {"role": "assistant", "content": "{\"role\": \"supporting\", \"usage_action\": \"source\", \"summary\": \"Footnoted source for the MDR-TB incidence of 23 per 100,000 used to flag TB emergency levels.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "umar_pads", "source_key": "umar_pads:001293:59:1", "occurrence_id": "4459ea2202bcfd0427d08b0c", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: part of
project implementation
|Consortium of Service
Providers
|\n|Strategy and capacity-building plan
established for monitoring, evaluation,
accountability and learning (MEAL) and
sex-disaggregated data generation|The indicator captures the
establishment of a need-
based strategy and capacity
building plan to ensure
enhanced monitoring,
evaluation, accountability
and learning, uptake and
generation of sex
disaggregated data by public
institutions.|
End-Term
|Evidence
from
ministerial
documents
|Evidence collected from
ministerial records,
validation and
discussion meeting
minutes.
|PMU
|\n|Qualitative agriculture survey conducted|This indicator will track
successful launch of the
agriculture survey to|Once at
end of year
three|Survey
conducted
|Ministerial publications
|PMU
|\n\n\nPage 55 of 71\n\nMention: \"ministerial records\""}, {"role": "assistant", "content": "{\"role\": \"supporting\", \"usage_action\": \"validate\", \"summary\": \"Ministry records and documents, validated in discussion meetings, evidencing the sex-disaggregation indicator.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "umar_pads", "source_key": "umar_pads:001775:2:1", "occurrence_id": "fc2bb634ecaae460836df20e", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: and\ngeological and socio-economic characteristics, and consequently the multiple effects of climate change pose\nsignificant threats to infrastructure, resources and human health. 2 This, coupled with its susceptibility to\nnatural hazards and adverse weather events such as tropical cyclones, sea level rise, storm surges, drought,\nflooding and volcanic eruptions make the country vulnerable to current and future climate change events.\nEach of these hazards, bar volcanic eruptions, are being compounded by the impacts of climate change,\nresulting in the higher frequency and intensity of adverse events. Catastrophic risk modeling by the World\nBank 3 indicates Tonga is expected to incur, on average, US$15.5 million per year in losses due to earthquakes\nand tropical cyclones and losses of up to 14 percent of GDP in years affected by specific disasters. In the next\n50 years, Tonga has a 50 percent chance of experiencing a loss exceeding US$175 million and casualties higher\nthan 440 people, and a 10 percent chance of experiencing a loss exceeding US$430 million and casualties\n\n\n1 United Nations Development Programme, Human Development Report 2020; The Next Frontier: Human Development and the\nAnthropocene – Tonga, 2020.\n2 World Bank Climate Change Knowledge Portal, Tonga Dashboard.\n3 Pacific Catastrophe Risk Assessment and Financing Initiative (PCRAFI) Country Risk Profiles, September 2011.\n\n\nOct 05, 2021 Page 3 of 16\n\nMention: \"Tonga Dashboard\""}, {"role": "assistant", "content": "{\"role\": \"supporting\", \"usage_action\": \"analyze\", \"summary\": \"Climate portal dashboard supplying Tonga's climate trend and hazard profile.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "umar_pads", "source_key": "umar_pads:001775:3:1", "occurrence_id": "87aa44cec6d51fa7761ab244", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: FY20-FY21 as TC Gita reconstruction activity picked up and the tourism\nand agriculture sectors continued to recover. The Government of Tonga (GoT) had successfully consolidated\nits fiscal position over the previous few years, with debt to GDP declining. However, the dual shocks have\nresulted in an economic contraction in FY20, and a projected 6.1 percent contraction in FY21. This is due\nmainly to the reduction in international tourism arrivals and delays in public construction.\n\n\n7. **Extreme poverty (consumption of less than US$1.90 in purchasing power parity terms per person per**\n**day) was less than 1 percent in FY16, among the lowest in the Pacific region. However, a quarter of the**\n**population suffer from hardship.** Many of these people will face significant additional hardship due to the\nimpacts of the dual shocks. Around 30 percent of households have at least one member working in tourismlinked sectors—the sectors hardest hit by the border closure and strict social distancing measures. Business\nsurveys indicate that over 60 percent of firms have reduced staff and/or reduced workers’ hours in response\nto the economic downturn. Moreover, four out of every five households receive remittances from abroad.\nRemittances are projected to decline by 15 percent due to COVID-19. A decline of this size would have a\nsignificant negative impact on the poorest and most vulnerable households, for whom remittances tend to\naccount for a higher share of income.\n\n\n8. **Tonga is focused on accelerating its gender commitments under its revised National Policy on Gender**\n**and Development (RNPGAD) 2014 and the Sustainable Development Goal 5: Gender Equality** . Based on the\n2019 Gender Inequality Index (GII) 4, the Kingdom of Tonga ranked 79 out of 162 countries on the index with\na GII score of 0.354. This is a substantial improvement\n\nMention: \"Business\nsurveys\""}, {"role": "assistant", "content": "{\"role\": \"supporting\", \"usage_action\": \"source\", \"summary\": \"Firm surveys showing over 60 percent reduced staff or hours in response to the downturn.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "umar_pads", "source_key": "umar_pads:002053:2:0", "occurrence_id": "7876f44e5432cce853969585", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: **The World Bank**\nPathways towards Decarbonizing Transport in Diverse Regions in China (P175561)\n\n\n\n\n\n**B. Introduction and Context**\n\nCountry Context\n\n\n**China’s rapid economic growth took place alongside its structural and spatial transformation** : from primary to\nmanufacturing and service economies, from agrarian to urbanized society, and from a closed economy to a major\nparticipant in global trade and value chains. The share of primary sectors of the GDP decreased from 28.2 percent in 1978\nto 9.8 percent in 2018, while that of service sector increased from 23.9 percent to 52.2 percent during the same period.\nAs of 2018, 59.6 percent of the total population lived in urban areas in China, a dramatic increase from 17.9 percent in\n1978 when the reform and opening policy initiated. International trade increased from US$20.64 billion in 1978 to\nUS$4.62 trillion in 2018. 1 [^1: Ministry of Finance (http://zhs.mofcom.gov.cn) and WITS (https://wits.worldbank.org/)] Such transformation has had a profound impact on the people’s lives, with 770 million people\nlifted out of poverty over the last 40 years.\n\n\n**_Figure 1. China’s carbon emission alongside GDP growth, industrialization and motorization_**\n\n\nSources: National Bureau of Statistics, Global Carbon Budget 2019; *industrialization is calculated as share of\n\nmanufacturing and service of GDP\n\n\n**On the other hand, the increasingly urbanized and industrialized China meant a sharp rise in energy use and emissions**\n**of greenhouse gases (GHG) and other pollutants** . According to the International Energy Agency (IEA), China’s total\nCarbon Dioxide (CO2) emissions grew from 3,540 Mt in 2002 to 9,574 Mt in 2018, at an annual growth rate of 6.4 percent.\nWith about\n\nMention: \"Global Carbon Budget 2019\""}, {"role": "assistant", "content": "{\"role\": \"supporting\", \"usage_action\": \"source\", \"summary\": \"Emissions series plotted with national statistics in the figure on China's emissions and growth.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "umar_pads", "source_key": "umar_pads:002148:16:0", "occurrence_id": "248b71580612dd9ca31fb69b", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: **The World Bank**\n\n\nCabo Verde Human Capital Project (P175828)\n\n\n**Strengthening the shock-responsiveness of the CSU.** The proposed Project intends to increase the ability of\nthe Government to rapidly expand its safety net to protect households negatively affected from shocks, such\nas drought and floods, by strengthening the shock-responsiveness of the CSU by expanding the coverage to\nhouseholds that are particularly exposed to climate-related shocks and introducing risk related data into the\nCSU (including climate-related maps).The proposed Project would support technical assistance for the CSU\nunit.\n\n\n**Strengthening the system and storage function of the CSU.** To ensure that the CSU system is up-to-date, safe\nand efficient, support would be provided for: (i) system modifications needed to accommodate the revised\nPMT and the “ _Bilhete de Identidade”_ and “ _Cartão Nacional de Identidade_ ” transition; (ii) adjustments to the\nconsultation application, existing modules (i.e., data analysis, reporting, programs, etc.) and training to use\nthe new modules; (iii) system changes required to ensure the interoperability with key programs and efficient\nflow of information; (iv) support for software updates in the short-run and software upgrades in the mediumterm; and (v) storage of existing data, as well as exploring options for future solutions for MFIDS to host the\ndata. Special attention will also be given to enhancing data recovery and backup systems for the CSU, in order\nto prevent data loss in the event of expected climate change-exacerbated natural disasters.This would include\nsystem maintenance costs of the current system (i.e., licensing fees and data storage) and then technical\nassistance to make\n\nMention: \"risk related data\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"curate\", \"summary\": \"Risk data to be introduced into the social registry so it can flag shock-exposed households.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "umar_pads", "source_key": "umar_pads:002148:16:0", "occurrence_id": "615dcfeafac0d693b9c23bea", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: **The World Bank**\n\n\nCabo Verde Human Capital Project (P175828)\n\n\n**Strengthening the shock-responsiveness of the CSU.** The proposed Project intends to increase the ability of\nthe Government to rapidly expand its safety net to protect households negatively affected from shocks, such\nas drought and floods, by strengthening the shock-responsiveness of the CSU by expanding the coverage to\nhouseholds that are particularly exposed to climate-related shocks and introducing risk related data into the\nCSU (including climate-related maps).The proposed Project would support technical assistance for the CSU\nunit.\n\n\n**Strengthening the system and storage function of the CSU.** To ensure that the CSU system is up-to-date, safe\nand efficient, support would be provided for: (i) system modifications needed to accommodate the revised\nPMT and the “ _Bilhete de Identidade”_ and “ _Cartão Nacional de Identidade_ ” transition; (ii) adjustments to the\nconsultation application, existing modules (i.e., data analysis, reporting, programs, etc.) and training to use\nthe new modules; (iii) system changes required to ensure the interoperability with key programs and efficient\nflow of information; (iv) support for software updates in the short-run and software upgrades in the mediumterm; and (v) storage of existing data, as well as exploring options for future solutions for MFIDS to host the\ndata. Special attention will also be given to enhancing data recovery and backup systems for the CSU, in order\nto prevent data loss in the event of expected climate change-exacerbated natural disasters.This would include\nsystem maintenance costs of the current system (i.e., licensing fees and data storage) and then technical\nassistance to make\n\nMention: \"climate-related maps\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"curate\", \"summary\": \"Hazard maps named as an example of the risk layers to be integrated into the registry.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "umar_pads", "source_key": "umar_pads:002176:4:0", "occurrence_id": "7d2ddf0ac1044c1434bd397b", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: **The World Bank**\nMozambique COVID-19 Strategic Preparedness and Response Project (P175884)\n\n\n8. **The Government of Mozambique’s COVID-19 vaccine coverage and purchase plan is a national priority to tackle**\n**the health and socio-economic impact of the pandemic. Still under development, Mozambique’s vaccine strategy aims**\n**to primarily tackle the acute health crisis and reduce mortality by targeting the most vulnerable groups.** In the longerterm the strategy also considers scaling coverage up to reduce transmission, which should also serve as economic stimulus.\nBased on the available evidence, the theoretical herd immunity threshold for SARS-CoV-2 — the virus that causes\ncoronavirus disease — is about 60 percent6. Considering limited vaccine supplies and financing, the government has\nplanned to cover 20 percent of the population targeting vulnerable groups and frontline workers, covering the remaining\n40 percent incrementally as more resources become available. The proposed strategy to ensure the vaccination of 20\npercent of the population as part of Phase 1 follows a two-step approach for prioritized groups. COVAX AMC will provide\nvaccine doses to cover 16-20 percent of the population. Other sources may also support additional acquisition, including\nthe African Union (AU) and the private sector. This project aims to support Phase 1 and 2, focusing on deployment and\nrelated systems to cover these initial allocations, with financing for additional vaccine acquisition available depending on\nthe extent of operational costs\n\n\nRelationship to CPF\n\n9. **The proposed project is aligned with the World Bank’s Country Partnership Framework (CPF) for**\n**Mozambique,** **as revised in the recently concluded Performance and Learning Review (PLR) that includes adjustments**\n**to the CPF for COVID-19.** The FY 17-21 WBG CPF for Mozambique draws on the 2016 Systematic Country Diagnostic (SCD)\nwhich identified\n\nMention: \"2016 Systematic Country Diagnostic\""}, {"role": "assistant", "content": "{\"role\": \"supporting\", \"usage_action\": \"inform\", \"summary\": \"Diagnostic that informed the country partnership framework guiding this health response.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "umar_pads", "source_key": "umar_pads:002185:7:1", "occurrence_id": "06dfc4552563a4883ce4df3a", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: \nThe community-based monitoring system is expected to supplement the hydro-meteorological data collected by\nthe official agencies, i.e. MoIWR and SMA. The activity will engage with civil society such as women’s groups and\nschools. A set of capacity building and awareness program will be conducted in selected pilot sites and the link\nbetween the local government and the civil society will be strengthened.\n\n\nThe technical assistance and pilot implementation consultancies will be complemented by capacity building of\nthe Nile Water Directorate, the GWWD, the SMA and related stakeholders on operation and maintenance of\nFEWS, including the use of earth observation data for flood forecasting. This activity will also be aligned with the\ninstitutional and policy reforms which the GoS is currently implementing in the DRM sector.\n\n\n**_Component 2: Improving the Maintenance of Small-scale Water Storage Structures (USD 0.90million)_**\nThis component will support the Water Harvesting Directorate of MoIWR in their endeavor to reduce the failure\nrisk of small dams and water harvesting structures (haffirs) and asset management procedures for other flood\nmanagement structures, such as retarding basins and river embankments. Special attention will be paid to the\nmanagement of haffirs as an entry point for the MoIWR and local government to enhance the asset\nmanagement procedures for other larger-scale infrastructures. Activities under this component aim to address\ncommunity level adaptive capacities to mitigate the risk of floods and effectively harness flood waters in haffirs\nfor productive livelihood activities. This component will finance: (i) baseline survey and update the inventory of\nsmall dams and haffirs that will include the key dimensions and development of failure risk index; (ii)\ndevelopment of guidelines, standard operating procedure (SOP), and emergency operation plan (EOP) for\nhaffirs, small dams and flood management structures; (iii) minor rehabilitation of damaged haffirs; and (iv)\n\n\nMar 27, 2021 Page 8\n\nMention: \"earth observation data\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"curate\", \"summary\": \"Satellite data whose use for flood forecasting will be built into water-directorate capacity.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "umar_pads", "source_key": "umar_pads:002243:8:1", "occurrence_id": "a3d902ca4d3b21b405467c6c", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: agricultural production in Northern Laos 16 [^16: World Bank (2021). Lao Transport Corridor Connectivity Assessment Report.] . In addition, more consolidation activities could\nreduce logistics costs, especially for smallholders. The improved regional connectivity along the economic\ncorridor is already attracting more tourists, which will, in turn, promote the local economy and employment.\n\n24. **Dry ports and logistics parks are a key component of the national logistics development strategy and**\n**action plan, which was approved in 2015.** In August 2021, the government approved the dry port decree,\ndefining principles, regulations, and measures for the management of dry ports. However, there remains a gap\nin the legal framework and implementing capacity. Out of nine locations for international logistics parks and\ndry ports, three dry ports have been developed through a PPP approach by the Government: Savannakhet dry\nport (in operation since 2016), Thanalaeng Dry Port (expected operation in 2022), and Pakse Dry Port (expected\noperation in 2022). Future dry port locations along the railway are in Luang Prabang, Muangxai, and Natuey.\nPrivate sector developers have shown interest in the development of dry ports and logistics parks, but there is\na need to ensure competitive and transparent PPP transactions\n\n25. **Road accidents are high and increasing, because of infrastructure characteristics, driving practices,**\n**alcohol use, weak enforcement, and limited capacity for post-crash response.** In 2019, the reported road\ntraffic crash deaths in Lao PDR were 1,020, or approximately 2.4 percent of total deaths. The Global Status\nReport on Road Safety 17 [^17: WHO 2018.] reports 1,120 road crash deaths, which is 16.6 fatalities per 100,000 people in Lao PDR\nand rising. Road crashes in Lao PDR are the number one cause of death for 5-14-year-olds, the number two\ncause of\n\nMention: \"Global Status\nReport on Road Safety\""}, {"role": "assistant", "content": "{\"role\": \"supporting\", \"usage_action\": \"source\", \"summary\": \"Reports 1,120 road crash deaths and 16.6 fatalities per 100,000 in Lao PDR.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "umar_pads", "source_key": "umar_pads:002243:4:0", "occurrence_id": "b3d61e9795126697d1d1bbea", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: **The World Bank**\nSoutheast Asia Regional Economic Corridor and Connectivity Project (P176088)\n\n\nconcessions to foreign investors. Laotian agricultural exports reportedly reached close to $1 billion in 2020,\ncorresponding to a 67% increase since 2018, with China accounting for approximately 80% of these exports 2 [^2: https://www.producereport.com/article/laotian-banana-exports-hit-china-border-closure] .\n\n\n8. **The inclusion of smallholders in export-driven supply chains, particularly women farmers and farmers**\n**from ethnic minority groups, has therefore become an urgent policy priority.** Promoting agricultural trade\nthrough investment in improving sanitary and phytosanitary standard (SPS) management capacity and export\nbusiness processes will help not only leverage local smallholders and traders to integrate into regional and\nglobal value chains but also help reduce documentary transaction time and costs, and improve their capacity\nto upgrade product quality and standard to meet market requirements of neighboring countries such as China,\nThailand and Vietnam. At production level, producer organizations and associations need be strengthened and\nlinked to economic opportunities in export-oriented production. Through provisions of equal access to farm\ninputs and agricultural services (i.e. through matching grants), small farmers, including women, would be able\nto adopt faster new agricultural technologies such as organic farming, good agricultural practices (GAP) and\nclimate-resilient production techniques and, therefore, allowing them to increase agricultural productivity and\nproduct quality for exports.\n\n9. **The Lao PDR’s road network is highly susceptible to climate change induced natural hazards, particularly**\n**floods and landslides.** Approximately 80 percent of the country’s land area is mountainous, while the\nremaining 20 percent is low lying plains along the Mekong River. This topography makes Laos very vulnerable\nto increasing heavy rainfalls, flooding, and landslides. The observed annual rainfall has already been on raise\n(Figure 1.2). Fifteen major floods have occurred in Lao PDR from 1970 to 2010. Based on\n\nMention: \"observed annual rainfall\""}, {"role": "assistant", "content": "{\"role\": \"supporting\", \"usage_action\": \"analyze\", \"summary\": \"Observed rainfall series shown rising in the figure, establishing flood and landslide exposure.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "umar_pads", "source_key": "umar_pads:002272:3:2", "occurrence_id": "ee99ae980173146e6b5b2e70", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: losses.\n\n\n1 Economic and Social Statistics of Sri Lanka 2020, Central Bank of Sri Lanka [https://www.cbsl.gov.lk/sites/default/files/cbslweb_documents/statistics/otherpub/ess_2020_e1.pdf](https://www.cbsl.gov.lk/sites/default/files/cbslweb_documents/statistics/otherpub/ess_2020_e1.pdf)\n2 Economic and Social Statistics of Sri Lanka 2020, Central Bank of Sri Lanka [https://www.cbsl.gov.lk/sites/default/files/cbslweb_documents/statistics/otherpub/ess_2020_e1.pdf](https://www.cbsl.gov.lk/sites/default/files/cbslweb_documents/statistics/otherpub/ess_2020_e1.pdf)\n[3http://www.statistics.gov.lk/GenderStatistics/StaticalInformation/ContributiontoEconomy/EconomicallyActivePopulationbySectorAndSex2017](http://www.statistics.gov.lk/GenderStatistics/StaticalInformation/ContributiontoEconomy/EconomicallyActivePopulationbySectorAndSex2017-2019)\n[-2019](http://www.statistics.gov.lk/GenderStatistics/StaticalInformation/ContributiontoEconomy/EconomicallyActivePopulationbySectorAndSex2017-2019) (Accessed 25th March 2021)\n4 Aging population of Sri Lanka – A thematic Report based on Census of Population and Housing 2020, Department of Census and Statistics [https://srilanka.unfpa\n\nMention: \"Economic and Social Statistics of Sri Lanka 2020\""}, {"role": "assistant", "content": "{\"role\": \"supporting\", \"usage_action\": \"source\", \"summary\": \"Central Bank statistical compendium cited for the macroeconomic and sector figures.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "umar_pads", "source_key": "umar_pads:002272:3:2", "occurrence_id": "68b186a02d92038ab808ba95", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: losses.\n\n\n1 Economic and Social Statistics of Sri Lanka 2020, Central Bank of Sri Lanka [https://www.cbsl.gov.lk/sites/default/files/cbslweb_documents/statistics/otherpub/ess_2020_e1.pdf](https://www.cbsl.gov.lk/sites/default/files/cbslweb_documents/statistics/otherpub/ess_2020_e1.pdf)\n2 Economic and Social Statistics of Sri Lanka 2020, Central Bank of Sri Lanka [https://www.cbsl.gov.lk/sites/default/files/cbslweb_documents/statistics/otherpub/ess_2020_e1.pdf](https://www.cbsl.gov.lk/sites/default/files/cbslweb_documents/statistics/otherpub/ess_2020_e1.pdf)\n[3http://www.statistics.gov.lk/GenderStatistics/StaticalInformation/ContributiontoEconomy/EconomicallyActivePopulationbySectorAndSex2017](http://www.statistics.gov.lk/GenderStatistics/StaticalInformation/ContributiontoEconomy/EconomicallyActivePopulationbySectorAndSex2017-2019)\n[-2019](http://www.statistics.gov.lk/GenderStatistics/StaticalInformation/ContributiontoEconomy/EconomicallyActivePopulationbySectorAndSex2017-2019) (Accessed 25th March 2021)\n4 Aging population of Sri Lanka – A thematic Report based on Census of Population and Housing 2020, Department of Census and Statistics [https://srilanka.unfpa\n\nMention: \"Census of Population and Housing 2020\""}, {"role": "assistant", "content": "{\"role\": \"supporting\", \"usage_action\": \"source\", \"summary\": \"Census underlying the thematic report on the ageing population.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "umar_pads", "source_key": "umar_pads:002352:36:3", "occurrence_id": "c9fe84dc9e13fb79a08962f9", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: كة المجتمعية|صياغة وتنفيذ إستراتيجية التوعية بالمخاطر والتواصل
بشأنها|صياغة وتنفيذ إستراتيجية التوعية بالمخاطر والتواصل
بشأنها|\n|إدارة الصحة العامة
بوزارة الصحة
|التحقق من خلل الزيارات
الميدانية/البيانات الدارية
|البيانات الدارية لوزارة
الصحة
|6
شهور
|البسط: عدد المختبرات المعينة
المجهزة تجهيزا كامل بالمعدات
والجهزة والكواشف والمستلزمات
.اللزمة لختبارات فيروس كورونا
المقام: العدد الجمالي للمختبرات
المعينة|نسبة المختبرات المعينة والمزودة بأجهزة التشخيص
الخاصة بفيروس كورونا وأدواتلختبار والكواشف|نسبة المختبرات المعينة والمزودة بأجهزة التشخيص
الخاصة بفيروس كورونا وأدواتلختبار والكواشف|\n\nMention: \"البيانات الدارية\""}, {"role": "assistant", "content": "{\"role\": \"supporting\", \"usage_action\": \"validate\", \"summary\": \"Ministry of Health administrative data used to verify results from field visits.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "umar_pads", "source_key": "umar_pads:002440:4:0", "occurrence_id": "b493c52f2cbd512c5d244000", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: **The World Bank**\nGEF SUSTAINABLE GROUNDWATER MANAGEMENT IN SADC MEMBER STATES PROJECT PHASE 2\n(P176607)\n\n\nComponent 1 (capacity building) is to support groundwater management institutions to be effective in planning and\nregulating groundwater uses at the local, national and regional level. Outputs will include development of a capacity\nbuilding strategy, establishment and training of National Focus Groups, strategic partnerships, groundwater assessments,\nbasin plans and GESI capacity developed.\n\nComponent 2 (knowledge development and dissemination) is expected to enable evidence-based decision making on\nsustainable groundwater management using an accessible and up-to-date knowledge base from SADC member states.\nOutputs under this component include expansion of SADC-GIP, SADC-GLA groundwater studies disseminated and\nknowledge sharing.\n\nComponent 3 (grants to member states) will promote sustainable and innovative groundwater solutions to improve public\nhealth and climate resilience consciousness in the communities for both women and men. Outputs include men and\nwomen on groundwater management, expansion of groundwater monitoring networks and awareness raising events.\n\n\n**D. Project Description**\n**Component 1** - Capacity building for sustainable groundwater management, will focus on capacity building and strengthening\ninstitutions through a range of technical assistance, knowledge exchanges, workshops, and training activities. Capacity-building\nefforts will seek to be inclusive by considering the special needs and challenges of women and other vulnerable populations.\nThe component will strengthen SADC-GMI to fulfil its core functions as a center of excellence for groundwater in the region.\nThis component will also support project management activities\n\n\n**Component 2 –** Knowledge development, dissemination and advocacy will support the generation and dissemination of\nknowledge on groundwater resources in the SADC-region. The knowledge products will promote inputs from women who\nhave accumulated considerable knowledge about water resources, including location quality and storage methods. Results of\nthe activities under this component will be compiled at the national level in National Groundwater Assessments that assess\nthe status of groundwater resources, their\n\nMention: \"groundwater monitoring networks\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"curate\", \"summary\": \"Monitoring networks to be expanded as an output for sustainable groundwater management.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "umar_pads", "source_key": "umar_pads:002478:10:1", "occurrence_id": "690a7b4401f2e09cebf9153d", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: as providing technical assistance for enabling LATRA to perform its regulatory function under\nopen-access arrangements.\n\n34. **The development of an asset management system for railway tracks is key for the sustainability of**\n**operations.** The project will support the operationalization of the track recording car for effective network data\ncollection, provide capacity strengthening for data analysis, and prepare maintenance strategies and programs.\nThe support will enable TRC to switch to condition-based maintenance (from currently force account maintenance\nmethods) as part of their enterprise-wide asset management transformation.\n\n35. **The project will contribute to addressing the identified barriers to women’s participation in the railways**\n**sub-sector with the aim of achieving safe, decent, and equal employment opportunities in both technical and**\n**nontechnical positions.** There are several barriers that restrict women’s participation in the railway industry and\nthese manifest at multiple levels. A gender survey of TRC that was conducted in 2022 confirmed that unequal\naccess to education, and in particular, STEM between girls/women and boys/men is a key entry-level barrier in\nformal employment and is reported by 72.4% of the respondents. The project will enhance women’s participation\nin the sector by (a) building a pipeline of young experts through providing three-year financial support to graduate\nengineers, at least half of whom will be women, to participate in the structured engineers apprenticeship program\n(SEAP) to enable them to register as professional engineers and thus expand their employment opportunities in\nthe sector and in the market ( including TRC, TAZARA, and private sector consultants and contractors); (b)\nsupporting the training and certification 24 of women as locomotive drivers; (c) supporting the development and\nimplementation of a resource- and time-bound institutional gender equality policy with an action plan\n\nMention: \"gender survey of TRC\""}, {"role": "assistant", "content": "{\"role\": \"supporting\", \"usage_action\": \"analyze\", \"summary\": \"Survey confirming unequal education access as an entry barrier, reported by 72.4 percent of respondents.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "umar_pads", "source_key": "umar_pads:002545:4:1", "occurrence_id": "8fcabade3df8d2a926766ecf", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: profit and provides\nonly short-term seasonal loans oftentimes associated with pre-harvest purchase of the farmer’s production at an undermarket price.\n\n6. **Women farmers have assumed a growing share of responsibility for agriculture in Punjab and their position in**\n**agriculture production could be strengthened.** In Punjab, approximately 74 percent of women depend on agriculture as\na source of livelihood. However, the low participation of women in the farming-related decision-making process deprives\nwomen farmers (especially smallholder women farmers) from accessing innovations, extension services,\nentrepreneurship training, and technologies, which ultimately limits their potential to grow and increase their incomes\nin agriculture and livestock. Their participation in marketing activities faces cultural barriers that expose them to the risk\nof exploitation, which further reduces their profitability. Social factors have also led to a lack of voice and agency among\nwomen farmers regarding access to natural as well as financial resources. For example, a majority of the loans provided\nto women are used by male heads of households, making it difficult for women to enter agribusiness activities and to\nconnect with formal value chains. Finally, the lack of sex disaggregated data within the agriculture sector contributes to\nthe lack of practical recommendations and policies promoting gender equality in agriculture. This results in higher\npoverty prevalence, along with an increasing ratio of stunting in rural children in Punjab.\n\n7. **Punjab has recently improved the policy environment for the processing and marketing of agricultural products.**\nWith the support of the Punjab Agriculture and Rural Transformation P4R program (SMART, P162446), the Punjab\nAgricultural Marketing Regulatory Authority (PAMRA) Act 2020 lifted some of the regulatory constraints that had been\nencumbering the agricultural marketing system for the past 80 years, notably by (a) mitigating the role of middlemen and\nchanging the power structure of the market by reducing government intervention that had benefited vested interests at\nthe expense of small and medium producers; (b) confining the role\n\nMention: \"sex disaggregated data\""}, {"role": "assistant", "content": "{\"role\": \"supporting\", \"usage_action\": \"inform\", \"summary\": \"Absence of disaggregated agriculture statistics blocks practical gender-equality policy recommendations.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "umar_pads", "source_key": "umar_pads:002609:72:0", "occurrence_id": "6003ff3892b4736743393c11", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: **The World Bank**\nResilient Tourism and Blue Economy Development in Cabo Verde Project (P176981)\n\n\n - **Additional growth rate.** A steady state revenue growth rate of 3 percent for entrepreneurs\nwithout the project investments is estimated, with additional revenue growth of 10 percent for\nbeneficiaries receiving project support.\n\n\n13. The above assumptions are supported by a wide range of studies in different regions on the\nimpact of different types of support services for SMEs:\n\n - A series of studies finds significant impacts from training programs on profits or sales in\ndeveloping countries based on evidence from rural Mexico, 34 Colombia, 35 and other economies. 36\nThis impact applies across various types of beneficiaries, including microenterprises. 37\n\n - Supporting climate-related upgrades in fisheries SMEs, such as fisheries and aquaculture, can\nincrease revenues and boost adaptive capacity and resilience of communities and the\necosystems on which they depend. 38\n\n - The Sarder et al. (1997) 39 study, “The Importance of Support Services to Small Enterprises in\nBangladesh,” finds 5–16 percent increase in employment, sales, and productivity with\ntechnology adoption support provided to SMEs.\n\n - Tan and Lopez-Acevedo (2005) 40 look at the impact of SME programs in Mexico using panel firm\ndata and find that 9–14 percent improvement in training and 9 percent improvement in\ntechnology absorption have been achieved. Various SME programs in Chile presented similar\nresults.\n\n - Lopez-Acevedo and Tan (2010), “Impact Evaluation of SME Programs in Latin America and\nCaribbean,” finds an 8 percent increase in wages and 9 percent increase in productivity as a result\nof these programs\n\nMention: \"panel firm\ndata\""}, {"role": "assistant", "content": "{\"role\": \"supporting\", \"usage_action\": \"analyze\", \"summary\": \"Firm panel behind the Mexican SME programme evaluation finding 9–14 percent improvements.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "umar_pads", "source_key": "umar_pads:002943:4:1", "occurrence_id": "fcd2b445299b2bead67d5999", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: Johnson & Johnson vaccine. The First AF to The Togo COVID-19 Emergency Response and System\nPreparedness Strengthening Project (P173880) will be used to purchase 1,950,000 of these doses through\nAVAT. This second AF will finance the procurement of 2,050,000 doses of Johnson & Johnson vaccine.\n\n**5.** **Togo is experiencing a third wave of the COVID-19 pandemic, with around 900 new cases per**\n**week, since the end of June 2021 (Annex 2).** As of November 1, 2021, the country has confirmed 26,086\ncases of COVID-19; 25,632 (98 percent) have recovered, with 242 deaths (0.9 percent). Although Togo is\nconsidered as one of the leading countries in the region in terms of response to the pandemic, the\nperception about the vaccine’s safety is negative. The communication on COVID-19 vaccination and the\nmeasures taken by the government are addressing this negative perception as evidenced by the high\nproportion of priority targeted population vaccinated during Phase 1 of the campaign. As of October 17,\n2021, 5 percent (425,501 people) of the population were reported to be fully vaccinated and 881,567\npeople vaccinated with the first dose are waiting for the second one. Of the Knowledge, Attitudes, and\nPerceptions (KAP) survey 2 [^2: Report on Knowledge, Attitudes and Perceptions of the population in the context the introduction of the vaccine against COVID-19\nIn Togo; WHO; GAVI; September 2021] respondents, only 6.4 percent mentioned vaccination as a means of preventing\nCOVID-19. The survey showed, however, that perceptions of the vaccine's effectiveness were positive,\nwith 63 percent of respondents indicating that the vaccine protects against COVID-19. Challenges\nidentified under the first AF remain the same, such as managing persistent rumors related to vaccination\nagainst COVID-19, as well as strengthening coordination, management of database, and protection of\npersonal data\n\nMention: \"Knowledge, Attitudes, and\nPerceptions (KAP) survey\""}, {"role": "assistant", "content": "{\"role\": \"supporting\", \"usage_action\": \"analyze\", \"summary\": \"Survey in which only 6.4 percent of respondents mentioned vaccination concerns.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "umar_pads", "source_key": "umar_pads:003047:3:0", "occurrence_id": "000278f8c9bd07243a006c93", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: **The World Bank**\nMongolia Third Energy Sector Project (P178190)\n\n\n_Source: IEA World Energy Balance Mongolia (https://www.iea.org/countries/mongolia)_\n\n\n3. **As the economy is on its path to recover from the recent economic slowdown, the supply of reliable and green**\n**power is indispensable.** The COVID-19 pandemic caused economic slowdown, but the impact has been gradually eased\ntoday. In 2022 the economy is expected to expand at 1 percent and domestic activity is expected to gradually normalize,\nwhile in the medium term (2023-2025) it is expected that growth will be accelerated to above 6 percent **3** [^3: According to the IMF, this forecast is conditional on resolution of border disruptions and geopolitical shocks by the end of 2022. Source:\nhttps://www.imf.org/en/News/Articles/2022/05/12/mongolia-concluding-statement-2022-imf-staff-visit] . To sustain the\ngrowth of the economy and the inclusive socio-economic development of the country, reliable and efficient electricity\nsupply to consumers is one of the important groundworks. The energy sector’s support for economic recovery was\nhighlighted in the recently adopted New Recovery Policy (NRP). NRP is a 10-year strategy adopted by the Parliament of\nMongolia in December 2021 for the effective implementation of the long-term Vision 2050 policy and aims to strengthen\nMongolia's economic independence and promptly address development barriers. As NRP highlights in two of its six pillars\nthe importance of energy sector recovery and green development, it is necessary to take action and support the GoM in\nstrengthening the green energy infrastructure for the economic recovery of the country.\n\n\nSectoral and Institutional Context\n\n\n4. **The power sector is of crucial importance to Mongolia’s economy and social development.** However, the power\nsystem has been running out of sufficient generation capacity reserve, and many transmission and distribution facilities\nare obsoleted. On the generation side,\n\nMention: \"IEA World Energy Balance Mongolia\""}, {"role": "assistant", "content": "{\"role\": \"supporting\", \"usage_action\": \"source\", \"summary\": \"Energy balance data cited with a URL as the figure's source.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "umar_pads", "source_key": "umar_pads:003047:5:0", "occurrence_id": "b68a032d49acf8ad3e6801f0", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: **The World Bank**\nMongolia Third Energy Sector Project (P178190)\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n_Source: ERC Statistics booklet 2022_\n\n\n7. **Although Mongolia has abundant solar and wind resource potential, only a few projects have been developed.**\nPrevious study estimated the exploitable potential to be at least 400 GW wind and 700 GW solar. 19 Most of the solar and\nwind energy resources are located far south and east of Ulaanbaatar as shown in Figure 6. Future development of\nabundant solar and wind generations could contribute to bridging the supply-demand gap for the whole grid, and\nadditionally, offers an important potential for the future export of renewable energy to neighboring countries. Despite of\nsuch rich resources, only few projects have been developed as of 2022, mainly due to a lack of access to high voltage\npower transmission links for power evacuation to the load center in Ulaanbaatar in the CES.\n\n\n**_Figure 7: Mongolia’s solar and wind resource potential_**\n\n\n_Source: Everoze Mongolia Site ID report, 2020_\n\n\n8. **The current generation fleet is dominated by inefficient CHP plants, which makes the system inflexible.** CHPs\nhave been developed as an important source in meeting the demand for heating service, especially in winter seasons.\nMost of the CHP units are quite old and inefficient, producing local pollution and greenhouse gas emission. The CHP plants\nare also inflexible with limited ramping capability, making the power system less flexible and dispatchable than what are\nneeded to enable the integration of variable renewal energy, such as solar and wind energy. The aging of the CHP plants\nalso poses a major risk to the whole power system in terms of the reliability of the power supply. Increasing the flexibility\nof the system has been taken care of by the government through other projects, including installation of 125MW scale\n\n\nSep 07, 2022 Page 6 of 12\n\nMention: \"ERC Statistics\""}, {"role": "assistant", "content": "{\"role\": \"supporting\", \"usage_action\": \"source\", \"summary\": \"Regulator's statistics booklet cited as the figure's source for sector structure.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "umar_pads", "source_key": "umar_pads:003039:5:2", "occurrence_id": "b7b737025798439e60b68959", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: the SME sector conducted as part of the discussions with the Ministry of Small and Medium\nEnterprises and Entrepreneurship (Ministry of SMEs) and reflects various legislations and charters signed with business\nassociations in DRC. Based on this definition and available statistics, MSMEs constitute the bulk of economic activity, but\ntheir formalization, growth, and competitiveness face severe constraints. 1 Over 90 percent of firms are micro (1–10\nemployees), and nearly half of them have been on the market for less than five years. However, firms six years and older\ncontribute to 60 percent of employment in DRC. Young firms created in the last two years account for over 35 percent of\ntotal employment. The share of young firms in DRC is large even in the context of fragility. SMEs demonstrate the strongest\ndynamic in creating new jobs compared to large firms. However, the growth rate of existing SMEs is sluggish. The improved\nperformance of SMEs would enable them to better serve as an important engine of growth and job opportunities.\n\n\n1 World Bank Enterprise Survey 2013; SME Ecosystem Survey 2019.\n\n\nPage 4\n\nMention: \"World Bank Enterprise Survey\""}, {"role": "assistant", "content": "{\"role\": \"supporting\", \"usage_action\": \"source\", \"summary\": \"Enterprise survey cited with the ecosystem survey as the SME evidence base.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "umar_pads", "source_key": "umar_pads:003039:5:2", "occurrence_id": "d3f866e412ba21a6305c0563", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: the SME sector conducted as part of the discussions with the Ministry of Small and Medium\nEnterprises and Entrepreneurship (Ministry of SMEs) and reflects various legislations and charters signed with business\nassociations in DRC. Based on this definition and available statistics, MSMEs constitute the bulk of economic activity, but\ntheir formalization, growth, and competitiveness face severe constraints. 1 Over 90 percent of firms are micro (1–10\nemployees), and nearly half of them have been on the market for less than five years. However, firms six years and older\ncontribute to 60 percent of employment in DRC. Young firms created in the last two years account for over 35 percent of\ntotal employment. The share of young firms in DRC is large even in the context of fragility. SMEs demonstrate the strongest\ndynamic in creating new jobs compared to large firms. However, the growth rate of existing SMEs is sluggish. The improved\nperformance of SMEs would enable them to better serve as an important engine of growth and job opportunities.\n\n\n1 World Bank Enterprise Survey 2013; SME Ecosystem Survey 2019.\n\n\nPage 4\n\nMention: \"SME Ecosystem Survey 2019\""}, {"role": "assistant", "content": "{\"role\": \"supporting\", \"usage_action\": \"source\", \"summary\": \"More recent ecosystem survey underpinning the SME diagnosis.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "umar_pads", "source_key": "umar_pads:003199:2:0", "occurrence_id": "5aa9e0e4de3c6763eb0792df", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: **The World Bank**\nBurkina Faso Emergency Local Development Project-Additional Financing (P178650)\n\n\n\n\n\n\n|World Bank Group Financing|Col2|\n|---|---|\n|International Development Association (IDA)|123.00|\n|IDA Credit|123.00
|\n\n\n\n\n\n\n\nOther Decision (as needed)\n\n\n**B. Introduction and Context**\n\n\nCountry Context\n\n\n1. **Burkina Faso has one of the fastest growing, poorest, and most vulnerable populations in the world** . With\nan annual growth rate of 3.1 percent, the population is expected to reach 42 million by 2050. But limited\nopportunities for youth and gender‐related inequalities prevent Burkina Faso from reaping the demographic\ndividend. The Covid-19 shock and associated economic downturn have reversed recent progress made in\npoverty reduction. Economic growth was resilient over 2016-2019, averaging 6.1 percent. In the wake of the\nCovid-19 shock, real Gross Domestic Product (GDP) only rose by 1.9 percent (-1 percent in per capita terms)\nin 2020. The extreme poverty rate measured by the US$1.9 a day (2011 PPP) poverty line was 38 percent in\n2019 with an upward trend. This increase in the poverty rate combined with the fast population growth\npushed an additional 330,000 people into extreme poverty. Findings from eight waves of high frequency\nsurveys conducted between 2020 and 2021 suggest that the pandemic negatively impacted economic\nactivities and led to an increase in unemployment and a sharp reduction in household incomes. With fewer\nor no sources of income, many households were not able to make ends meet, and about 50 percent of the\ninterviewees reported that they could no longer meet their dietary needs.\n\n2. **Burkina Faso is experiencing a multi-dimensional crisis driven by climate change, rising food prices, political**\n**instability, and conflict, leading to a deterioration in food and nutrition\n\nMention: \"high frequency\nsurveys\""}, {"role": "assistant", "content": "{\"role\": \"supporting\", \"usage_action\": \"analyze\", \"summary\": \"Eight survey waves showing pandemic effects on activity, unemployment and household income.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "umar_pads", "source_key": "umar_pads:003205:27:2", "occurrence_id": "6a911e81503fc833929c43d3", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: will be tailored to specific sectors (for example, agribusiness, tourism, and\ntransport).\n69 These include the joint World Bank-IFC CPSD, which provides analysis on key sectors with demonstrated catalyst potential for\ngrowth; World Bank Group Enterprise Surveys, including on the informal sector and two rounds of follow-up surveys during COVID-19\nto understand the main constraints to productivity; Subnational Doing Business; Investment Policy and Promotion Assessment and\nplanned Investment Promotion Strategy; the Recovery and Peace Building Assessment to identify sources of fragility and possible\n\n\nPage 23 of 71\n\nMention: \"joint World Bank-IFC CPSD\""}, {"role": "assistant", "content": "{\"role\": \"supporting\", \"usage_action\": \"inform\", \"summary\": \"Diagnostic analysing sectors with catalyst potential for growth.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "umar_pads", "source_key": "umar_pads:003205:27:2", "occurrence_id": "8d5e7e3e4afa95b1a99702e2", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: will be tailored to specific sectors (for example, agribusiness, tourism, and\ntransport).\n69 These include the joint World Bank-IFC CPSD, which provides analysis on key sectors with demonstrated catalyst potential for\ngrowth; World Bank Group Enterprise Surveys, including on the informal sector and two rounds of follow-up surveys during COVID-19\nto understand the main constraints to productivity; Subnational Doing Business; Investment Policy and Promotion Assessment and\nplanned Investment Promotion Strategy; the Recovery and Peace Building Assessment to identify sources of fragility and possible\n\n\nPage 23 of 71\n\nMention: \"World Bank Group Enterprise Surveys\""}, {"role": "assistant", "content": "{\"role\": \"supporting\", \"usage_action\": \"source\", \"summary\": \"Enterprise surveys including informal sector and COVID follow-ups on productivity constraints.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "umar_pads", "source_key": "umar_pads:003316:2:1", "occurrence_id": "3b418c6a0defea80258e7e12", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: services, and inadequate provision of opportunities for youth and the female labor force. Based on the\nHuman Capital Index (HCI), a child born in Morocco today will only be 50 percent as productive when she grows up as\nshe could be if she enjoyed complete education and full health, lower than the average for the Middle East and North\nAfrica (MENA) region, but higher than other lower middle-income countries. Between 2010 and 2020, Morocco’s HCI\nincreased from 0.47 to 0.50, but learning poverty is high. Though Morocco is benefitting from a demographic dividend\n(42 percent of the population was below age 25 in 2022), 4 the quality of the labor force is relatively low. To offer more\nquality jobs for youth and increase female labor force participation, Morocco will need to accelerate economic growth\nand job creation and build the human capital required to grow and compete in the 21st century.\n\n\n_1 WB, 2022, Morocco Economic Update April 2022._\n_2_ [WB, Country Economic Memorandum Morocco 2040: Emerging by Investing in Intangible Capital](https://openknowledge.worldbank.org/bitstream/handle/10986/28442/9781464810664.pdf?sequence=2&isAllowed=y) _. Poverty measurement is based on the national poverty line._\n_3_ [WB, 2023, Morocco Economic Update: Responding to Supply Shocks, Winter 2022/2023, February 2023](https://documents1.worldbank.org/curated/en/099332002132325417/pdf/IDU0e3742c55010a3044730a80a0ad6062acd9db.pdf) _._\n_4 HCP,_ [Annuaire statistique du Maroc 2022](https://www.hcp.\n\nMention: \"Annuaire statistique du Maroc 2022\""}, {"role": "assistant", "content": "{\"role\": \"supporting\", \"usage_action\": \"source\", \"summary\": \"Official statistical yearbook cited with a URL for the demographic and labour figures.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "umar_pads", "source_key": "umar_pads:003674:21:1", "occurrence_id": "d8c3725ff8526457a53763e9", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: forage seed production and multiplication centers (in collaboration with research\ncenters) and the provision of matching grants in coordination with Subcomponent 3.2, (iii) the\ndevelopment of productive alliances between fodder producers (such as MSEs) and traders, (iv) the\nfacilitation of local and cross-border market links for the offtake of excess forage, and (v) support to pilot\nof joint management of feed stores through public-private partnerships. The subcomponent will target\nproduction of high yielding, nutritive and highly digestible forage species with a potential to lower carbon\nintensity per unit of livestock product, meat, or milk, produced. The project will not encourage\ngovernment-led mass production and free distribution of fodder, as this would impede the sector’s\ncommercialization. However, in the event of a drought emergency (forecast with the support of\nSubcomponents 1.1 and 2.1), the project may facilitate and support fodder production and marketing in\ndrought hotspot areas in collaboration with MSEs through the provision of inputs and advisory services.\nThe subcomponent will be closely coordinated with Subcomponent 1.2, which may finance the\nconstruction of feed stores and processing plants, as well as Subcomponent 4.2, under which the project\nwill support the development or updating of policies and strategies on the privatization and\ncommercialization of fodder and feed production in PAP areas.\n\n\n_Subcomponent 2.3: Resource-Related Conflict Management and Mitigation (US$7.63 million, including US$6.18_\n_million IDA equivalent and US$1.45 million IFAD)_\n\n\n29. This subcomponent will equip PAP stakeholders with tools and capacities to address root causes of\nresource-related community-level conflict in PAP areas. Strong conflict management governance systems are\ncritical to ensure peace and cohesion in face of climate change related events, amongst others. The project will\napproach this by updating conflict assessments conducted during LLRP I and assessing new project areas, with\n\nMention: \"conflict assessments conducted during LLRP I\""}, {"role": "assistant", "content": "{\"role\": \"supporting\", \"usage_action\": \"analyze\", \"summary\": \"Phase-one conflict assessments to be updated and extended to new project areas.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "umar_pads", "source_key": "umar_pads:003988:3:0", "occurrence_id": "1ecb8ca3d5556f630584b649", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: **The World Bank**\nAdditional Financing to West Africa Food Systems Resilience Program, Phase 1 (P181139)\n\n\nSectoral and Institutional Context\n\n**3.** **Togo’s food and nutrition security situation has significantly worsened over the past few years** . According\nto Cadre Harmonisé analyses, 487,319 individuals (7 percent of the population) face Integrated Food Security\nPhase Classification (IPC) 3+ crisis or emergency level food insecurity, and 1,344,729 people (19 percent of\nthe population) are at risk of falling into a food crisis (IPC 2) between June and September 2023. Over the\nsame period in 2022 and 2021, the incidence of food insecurity was much lower, with 390,000 people and\n200,000 people, respectively, experiencing crisis levels of food insecurity (IPC 3+). 3 [^3: https://www.food-security.net/datas/togo/] Trends related to the\npopulation’s nutrition are equally alarming. The food and nutrition security survey carried out in September\n2022 showed that the nutritional situation is particularly critical in the country's northern regions, notably in\nthe Kara and Savanes where 73.5 percent of women were found to consume less than three of the five\nrecommended food groups. According to the Cadre Harmonisé analyses from November 2022, there is an\nupward trend in the number of children admitted to Nutritional Recovery and Education Centers, rising from\n28 percent in 2021 to 35 percent in 2022.\n\n\n**4.** **The recent rise in food and nutrition insecurity stems from food supply gaps driven by a combination of**\n**longer-term trends and recent shocks.** First, productivity of the mainly rain-fed agricultural sector has\nremained stagnant over the past years amid continued food demand growth and growing climate change\nimpacts. More irregular rainy seasons, along with more frequent drought spells and rising temperatures\nincreasingly affect crop yields, especially in the\n\nMention: \"food and nutrition security survey\""}, {"role": "assistant", "content": "{\"role\": \"supporting\", \"usage_action\": \"analyze\", \"summary\": \"September 2022 survey showing 73.5 percent of women in Kara and Savanes consume fewer than three food groups.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "umar_pads", "source_key": "umar_pads:004028:2:1", "occurrence_id": "6cb178aaccc35ca793867a94", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: (GoP) remains committed to transition to a decarbonized economy and strengthen CC**\n**adaptation.** This is particularly important since in the absence of Climate Change (CC) mitigation actions, Peru’s\ndevelopment will lead to a significant increase of its contribution to global greenhouse gas (GHG) emissions by 2050. 2 [^2: Net emissions from the energy, transport, land use, land-use change, and forestry (LULUCF) sectors expected to increase by 83 percent over the next 30 years. World\nBank staff calculations using the World Bank Macro-Fiscal Model (MFMoD) with climate change module.] In\naddition, close to half of the national territory is classified as having high to very high vulnerability to natural hazards, 3 [^3: MINAM (Ministerio del Ambiente). 2016. El Perú y el Cambio Climático: Tercera Comunicación Nacional del Perú a la Convención Marco de las Naciones Unidas\nsobre Cambio Climático (Peru and Climate Change: Third National Communication of Peru to the United Nations Framework Convention on Climate Change).]\nwhich are expected to increase in frequency, severity, and impact due to CC. In the last two decades, the economic losses\nlinked to natural events reached more than US$ 4 billion dollars with the damages caused by ENSO exceeding US$ 3.1\nbillion, equivalent to 1.6 percent of the country’s GDP in 2017. 4,5 [^4: RPP Noticias. 2017. “El Niño costero: Daños ya suman $3,124 millones según Macroconsult” (March 24).] [^5: World Bank. 2022. Peru Country Climate and Development Report.] Recognizing the challenge, in 2020, Peru reinforced its\nclimate commitments with the updated NDC, which was followed by the adoption of the Law on Climate Change (Law No.\n30754, 2021). The country’s Strategic Plan\n\nMention: \"Macroconsult\""}, {"role": "assistant", "content": "{\"role\": \"supporting\", \"usage_action\": \"source\", \"summary\": \"Private consultancy estimate of El Niño damages reported in the press.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "umar_pads", "source_key": "umar_pads:004137:5:1", "occurrence_id": "2a179e9ea5e7435de68a1fee", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: \n**vulnerability to drought exacerbated by climate change.** The severe drought in 2021 resulted in the loss of 225,000 ha of\ncultivated fields 12 [^12: GTPA, October 2021] affecting more than 3 million people mainly in Mopti, Segou, and Timbuktu. 13 [^13: https://reliefweb.int/report/mali/mali-alarming-food-crisis-leaves-12-million-hungry] Moreover, the shortening\nof the rainy season has prevented the renewal of pastures in many parts of the country, increasing competition for the\nfew remaining grazing resources. Against this backdrop, Mali’s rivers (Niger, Senegal, Volta) are lifelines for most of its\npopulation and irrigation is fundamental to increase and stabilize food output and incomes, and to reduce the need to\nmigrate.\n\n\n15. **Although Mali does not face physical water scarcity in average terms, variability** **14** [^14: Temporal and spatial variability] **, and mismanagement**\n**contribute to significant economic water scarcity.** With annual renewable water resources of 6,290 m 3 per capita, 15 [^15: FAO Aquastat. 2018. https://www.fao.org/aquastat/statistics/query/index.html;jsessionid=E357A9D3F72DC9F3EDAA5F11C57E6CBD] Mali’s\ncurrent water consumption levels do not exceed sustainable water resources at the country level. However, extreme\nvariability in water availability in time and space (particularly between riparian and Saharan populations), coupled with\nunderdeveloped knowledge and infrastructure bases and poor service delivery and water quality management, lead to\ndifferentiated water access and exacerbate water insecurity. Violence has also led to significant restrictions on movement,\ndisrupting economic activities and limiting access to fields and grazing areas and resulting in the abandonment of cropped\nlands. Because of an increasingly unpredictable climate, insecurity, and\n\nMention: \"FAO Aquastat\""}, {"role": "assistant", "content": "{\"role\": \"supporting\", \"usage_action\": \"source\", \"summary\": \"Reports annual renewable water resources per capita, cited with URL.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "umar_pads", "source_key": "umar_pads:004151:3:2", "occurrence_id": "9e0af0a8a45b1dea33e88d26", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: 87 total PMCIs nationwide,\n550 now meet the minimum criteria for basic capacities, including improved availability of essential medicines\nand equipment, however periodic spells of shortages still remains a challenge; access to basic testing, and\navailability of trained staff has also shown improvement. The Project also included introduction of laboratory\nnetworks and implementation of new human resource strategies to facilitate service availability. The Project,\nhowever, attempted to introduce the concept of quality of care at PMCIs, this necessitates further reinforcement\nto enhance the utilization of services at PMCIs. Where the Project has been rolled out, local health seeking\nbehavior has shifted in favour of using PMCIs as the first point of care, and service utilization outcomes have\n\n\n1 Hapangama A, Kuruppuarachchi KALA. Maternal mental health services in Sri Lanka: challenges and solutions. BJPsych Int. 2021 Nov;18(4):100-102. doi:\n10.1192/bji.2020.52. PMID: 34747934; PMCID: PMC8554894 and Neupane S, Scott S, Piwoz E, Kim SS, Menon P, Nguyen PH (2023) More is not enough: High\nquantity and high quality antenatal care are both needed to prevent low birthweight in South Asia. PLOS Glob Public Health 3(6): e0001991.\n[https://doi.org/10.1371/journal.pgph.0001991](https://doi.org/10.1371/journal.pgph.0001991)\n[2 Sri Lanka Demographic and Health Survey 2016. http://www.statistics.gov.lk/Resource/en/Health/DemographicAndHealthSurveyReport-2016-Contents.pdf](http://www.statistics.gov.lk/Resource/en/Health/DemographicAndHealthSurveyReport-2016-Content\n\nMention: \"Sri Lanka Demographic and Health Survey 2016\""}, {"role": "assistant", "content": "{\"role\": \"supporting\", \"usage_action\": \"source\", \"summary\": \"DHS cited with a direct report link for maternal and child health indicators.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "umar_pads", "source_key": "umar_pads:004151:3:3", "occurrence_id": "efd40f13f0d9ffac6ba62bdb", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: /Resource/en/Health/DemographicAndHealthSurveyReport-2016-Contents.pdf](http://www.statistics.gov.lk/Resource/en/Health/DemographicAndHealthSurveyReport-2016-Contents.pdf)\n3 Sri Lanka: Health System Review. 2021 _. Health Systems in Transition_ . [https://iris.who.int/bitstream/handle/10665/342323/9789290228530-](https://iris.who.int/bitstream/handle/10665/342323/9789290228530-eng.pdf?sequence=1)\n[eng.pdf?sequence=1](https://iris.who.int/bitstream/handle/10665/342323/9789290228530-eng.pdf?sequence=1)\n4 Early results from Sri Lanka Health and Ageing Survey\n5 Addressing mental health in Sri Lanka. New Delhi: World Health Organization, Regional Office for South-East Asia; 2022. Licence: CC BY-NC-SA 3.0 IGO.\n\n\nDec.22, 2023 Page 4 of 9\n\nMention: \"Sri Lanka Health and Ageing Survey\""}, {"role": "assistant", "content": "{\"role\": \"supporting\", \"usage_action\": \"source\", \"summary\": \"Early results cited on ageing and health in later life.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "umar_pads", "source_key": "umar_pads:004209:5:0", "occurrence_id": "4bba93040b98463e5da9504b", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: **The World Bank**\nSouth Sudan Resilient Livestock Sector Project(P500553)\n\n\nproduction, processing, and trading. A total of 3 to 5 new dipping tanks per county of intervention will be\nconstructed based on pre-identified priority needs.\n\n\n**(ii)** **Sub-component 1.2: Strengthening the delivery of animal health services.** The component will support the\n\ntraining of CAHWs. Training of CAHWs is a cost-efficient and locally available option to offer access to quality\nanimal health services. There is a network of more than 2,000 CAHWs across the country (database and mapping\navailable). Training will cover GAHP and basic animal health (with a One Health approach) and welfare care.\nCAHWs will be critical in the delivery and sustainability over time of activities under sub-component 1.1. This subcomponent will be conducted in collaboration with technical partners with experience and a successful track\nrecord in delivery of CAHWs training in underserved and at-risk areas of South Sudan and in coordination with\nand under the supervision of local veterinary authorities in the public sector. The project will also support the\nimplementation of small veterinary health centers (VHC) and adequate community slaughterhouses on a pilot\nbasis at the sub-district level to supply Veterinary Medicinal Products (VMP), basic animal health services, and\ntraining for CAHWs. It will also support a pilot privatization model for access to animal health services\nthrough the establishment of Veterinary Field Units (VFU) for the delivery of demand – driven animal\nhealth services. The sub-component will train 1,000 new CAHWs (with special emphasis on women herds).\n\n\n**11.** **Component 2: Sustainable management of natural resources for livestock systems, with focus on rangeland and**\n**water management (US$20 million).** The proposed project will introduce\n\nMention: \"database and mapping\navailable\""}, {"role": "assistant", "content": "{\"role\": \"supporting\", \"usage_action\": \"analyze\", \"summary\": \"Existing register and map of the community animal health worker network.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "umar_pads", "source_key": "umar_pads:004240:16:0", "occurrence_id": "8e2c1142ae1bf65f02ca07fe", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: **The World Bank**\nRajasthan Highway Modernization Project (P501071)\n\n\nsuch as entrenched social norms, limited access to skilled jobs, and challenging workplace conditions. Furthermore,\nwomen are vastly underrepresented in transport-related industries, averaging only 17 percent of the transport workforce\nacross 46 countries. Specifically, in Rajasthan, female employment in the transport and storage sector is alarmingly low at\njust 1.3 percent, according to PLFS for 2023-2024. Granular statistics on women's waged employment within India's\ntransport sector are scarce; nonetheless, PLFS 2021-2022 indicates that only 5.3 percent of women in India overall are\nregular wage/salaried employees. Various barriers restrict women’s entry into and retention in the labor market, including\ncultural norms, workplace safety concerns, and a lack of training and mentorship.\n\n\n13. **Rajasthan is prioritizing the decarbonization and digitalization of its passenger transport services to build a**\n**more sustainable and efficient transportation network** . In August 2022, the DTRS introduced the Electric Vehicle (EV)\nPolicy, aimed at promoting eco-friendly transport, reducing emissions, and enhancing energy security. The policy includes\nfinancial incentives for EV buyers, such as subsidies and registration fee exemptions, alongside plans for a comprehensive\ncharging infrastructure across the state. However, progress has been slow, and further streamlined measures are needed.\nThe GoR is also advancing digitalization initiatives in transport services, such as implementing intelligent transportation\nsystems (ITS), real-time passenger information, automated fare collection, and smart mobility solutions, including\nintegrated travel card across different transport modes. While challenges remain, particularly in infrastructure investment\nand technology adoption, Rajasthan aims to address these through PPPs, government grants, and collaboration with local\ncommunities and technology providers, fostering innovation and economic growth.\n\n\n**II.** **PROJECT DESCRIPTION**\n\n\n14. **This Project builds on the foundational achievements\n\nMention: \"PLFS\""}, {"role": "assistant", "content": "{\"role\": \"supporting\", \"usage_action\": \"analyze\", \"summary\": \"Female employment in transport and storage just 1.3 percent in 2023-24.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "umar_pads", "source_key": "umar_pads:004283:44:2", "occurrence_id": "619d1b3f17cdbb8e79d23407", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: beneficiaries benefiting from improved access to
electric bus infrastructure and services. This is the number of female users who will ride the electric buses introduced
through the project from the start of the services to the date of project closure.|\n|Frequency|Once at project closure|\n|Data source|Ridership data reported by DTCA during the project implementation period.|\n|Methodology for Data
Collection|The ridership data will be collected from ticketing information reported and verified by DTCA through different sources
including the technology tools and verification measures. Youth segregation is to be made from the total ridership
number by using the male/female ratio reported in the most recent census data.|\n|Responsibility for Data
Collection|PIU - DTCA|\n|**Vehicle inspection centers in operation (Number) **|**Vehicle inspection centers in operation (Number) **|\n|Description|Number of vehicle inspection centers are in proper operation.|\n|Frequency|Semi-annual|\n|Data source|Progress reports of BRTA PIU and supporting documents.|\n|Methodology for Data
Collection|Document review, site visits and interviews.|\n|Responsibility for Data
Collection|PIU-BRTA|\n\n\n\nPage 32\n\nMention: \"census data\""}, {"role": "assistant", "content": "{\"role\": \"supporting\", \"usage_action\": \"analyze\", \"summary\": \"Latest census male/female ratio used to split ridership for the youth and gender indicator.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "umar_pads", "source_key": "umar_pads:004574:35:1", "occurrence_id": "8c7381500efe9fdb64aa492f", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: transport
(excluding BRT corridors) are selected based on their geographic location within the total catchment area.
2. Population Estimation
Using geoprocessing techniques, the population within the total catchment area in Salvador is calculated based on
data from the 2022 IBGE Census. Data for Salvador’s project are disaggregated by gender and by youth (ages 15–
24).|\n|Responsibility for Data
Collection|PMU (SEMOB)|\n|**PDO Indicator 2: Users satisfied with the quality of public transport service in the BRT Corridor, disaggregated by gender and income**
**(percentage)**|**PDO Indicator 2: Users satisfied with the quality of public transport service in the BRT Corridor, disaggregated by gender and income**
**(percentage)**|\n|Description|The satisfaction survey will focus on services provided by the BRT Corridor. This indicator measures beneficiary
satisfaction with the quality of public transport services before and after the implementation of e-buses. Results
will be disaggregated by gender and income level, with low-income defined as a maximum of two minimum wages.|\n|Frequency|Once the e-buses become operational|\n|Data source|Annual user satisfaction survey –_QualiÔnibus._|\n|Methodology for data
collection|The methodology will be based on the_QualiÔnibus_survey that solicits the views of users of the service in the BRT
Corridor, deliberately excluding periods of atypical demand (such as school and public holidays) and weekends to
ensure accurate representation. The sample distribution will follow the demand curve to maintain proportionality
throughout the day. Heavy loaded lines will be assured in the sample, while the other ones will be\n\nMention: \"2022 IBGE Census\""}, {"role": "assistant", "content": "{\"role\": \"supporting\", \"usage_action\": \"analyze\", \"summary\": \"Census counts geoprocessed to estimate catchment population by gender and youth.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "umar_pads", "source_key": "umar_pads:004801:5:0", "occurrence_id": "d95fe5b44283f1c49250de16", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: **The World Bank**\nDRC Urban Flood Resilience Project (P508410)\n\n\n9. **Climate risk is a threat multiplier, keeping communities across DRC in a vicious cycle of fragility and vulnerability to**\n**poverty, resource-driven conflicts, displacement and livelihood insecurity.** The 2021 Risk and Resilience Assessment\n(RRA) 5 [^5: World Bank (2021). Democratic Republic of Congo Risk and Resilience Assessment (June 2021).] for the DRC identified a fragmented conflict landscape, coupled with pervasive governance challenges and\nresource exploitation, as the key drivers of fragility, conflict, and violence. The co-location of multiple hazards with\narmed conflict, violence against civilians, and violent discontent shows clear coexistence in the east of the country.\nThis region is particularly prone to both natural hazards and various forms of violence, making it a critical area for\ntargeted interventions. Increasing frequency and intensity of climate shocks, such as floods, droughts and extreme\nweather events, exacerbate economic disparities, particularly in urban and conflict-affected regions where rapid\npopulation growth and unregulated resource extraction strain already limited infrastructure and services. Climate\nrisks further undermine the sustainability of livelihoods by aggravating land disputes, intensifying poverty, and driving\nlarge-scale displacement, creating immense challenges for social cohesion and resilience across communities.\n\n10. **The DRM system in DRC is fragmented with over 40 Ministries, Departments, and Agencies (MDAs) involved in**\n**emergency preparedness and response without clear roles and overlapping mandates.** Currently, there is no\nadopted DRM Law or Policy that regulates the sector. The Government has developed a Disaster Risk Reduction\nStrategy and Action Plan (2024) which has been validated by the relevant sector ministries and is pending formal\napproval by the Council of Ministers. The Ministry of Interior, Security, Decentralization and Traditional Affairs (MoI),\nunder which lies Civil Protection, has the mandate for coordination in emergency response and chair the national DRM\nplatform, which is intended to be\n\nMention: \"2021 Risk and Resilience Assessment\""}, {"role": "assistant", "content": "{\"role\": \"supporting\", \"usage_action\": \"analyze\", \"summary\": \"Identified fragmented conflict landscape and governance as fragility drivers.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "umar_pads", "source_key": "umar_pads:004801:5:0", "occurrence_id": "9aa014bddf543213506759eb", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: **The World Bank**\nDRC Urban Flood Resilience Project (P508410)\n\n\n9. **Climate risk is a threat multiplier, keeping communities across DRC in a vicious cycle of fragility and vulnerability to**\n**poverty, resource-driven conflicts, displacement and livelihood insecurity.** The 2021 Risk and Resilience Assessment\n(RRA) 5 [^5: World Bank (2021). Democratic Republic of Congo Risk and Resilience Assessment (June 2021).] for the DRC identified a fragmented conflict landscape, coupled with pervasive governance challenges and\nresource exploitation, as the key drivers of fragility, conflict, and violence. The co-location of multiple hazards with\narmed conflict, violence against civilians, and violent discontent shows clear coexistence in the east of the country.\nThis region is particularly prone to both natural hazards and various forms of violence, making it a critical area for\ntargeted interventions. Increasing frequency and intensity of climate shocks, such as floods, droughts and extreme\nweather events, exacerbate economic disparities, particularly in urban and conflict-affected regions where rapid\npopulation growth and unregulated resource extraction strain already limited infrastructure and services. Climate\nrisks further undermine the sustainability of livelihoods by aggravating land disputes, intensifying poverty, and driving\nlarge-scale displacement, creating immense challenges for social cohesion and resilience across communities.\n\n10. **The DRM system in DRC is fragmented with over 40 Ministries, Departments, and Agencies (MDAs) involved in**\n**emergency preparedness and response without clear roles and overlapping mandates.** Currently, there is no\nadopted DRM Law or Policy that regulates the sector. The Government has developed a Disaster Risk Reduction\nStrategy and Action Plan (2024) which has been validated by the relevant sector ministries and is pending formal\napproval by the Council of Ministers. The Ministry of Interior, Security, Decentralization and Traditional Affairs (MoI),\nunder which lies Civil Protection, has the mandate for coordination in emergency response and chair the national DRM\nplatform, which is intended to be\n\nMention: \"Democratic Republic of Congo Risk and Resilience Assessment\""}, {"role": "assistant", "content": "{\"role\": \"supporting\", \"usage_action\": \"analyze\", \"summary\": \"Full assessment title and date cited in the footnote.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "umar_pads", "source_key": "umar_pads:004810:30:0", "occurrence_id": "8a5a7809a2acc559ef5306f1", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: **The World Bank**\nAccelerating Trade Facilitation in the Pacific (P508537) PROJECT APPRAISAL DOCUMENT\n\n\nand final result), and other data sources covering the region including the World Bank’s Business-Ready assessment. Each\ncountry PMU will be responsible for (a) collecting and compiling relevant data for project results indicators, (b) evaluating\nresults, and (c) providing the relevant performance information to be consolidated and reported to the World Bank on a\nsemiannual basis. The PDO indicators are disaggregated at the country level. Intermediate results indicators are\naggregated across all project countries. The World Bank task team will be responsible for aggregating these country-level\nresults. IAs and the World Bank will undertake a midterm review three years following the effectiveness date, to assess\nthe status of project implementation and the need for adjustments.\n\n\n**C. Disbursement Arrangements**\n\n39. **All the participating countries and the PIF through their PMUs will access funding from the World Bank using**\n**the disbursement methods described in the World Bank Disbursement Handbook, that is, advance, direct payment,**\n**reimbursement, and special commitments.** Detailed disbursement procedures will be documented in the Financial\nManagement chapter of Project Operations Manual. Upon credit/grant effectiveness, each entity will be required to\nsubmit a withdrawal application for an initial deposit to the DA, drawn from the IDA credit/grant, in an amount to be\nagreed to in the Disbursement and Financial Information Letter (DFIL). Due to the lapse loan in Solomon Islands and Fiji,\nthe advance method will not be available for the Solomon Islands Ministry of Finance and Treasury and the FRCS until the\nlapse loan is resolved. The World Bank will offer access to FundsChain to all participating countries starting FY2026.\nThis is an innovative, user-friendly blockchain-based platform that will enhance the participating countries\n\nMention: \"Business-Ready assessment\""}, {"role": "assistant", "content": "{\"role\": \"supporting\", \"usage_action\": \"analyze\", \"summary\": \"Regional comparative assessment used alongside project data.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "umar_pads", "source_key": "umar_pads:005127:3:1", "occurrence_id": "d9ee9e079714e994c0324a7c", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: the population are estimated to have made or received a digital\npayment (2024). On digital government, Nepal ranked 119th out of 193 countries on the UN e-Government Development\nIndex (EGDI) in 2024, an improvement of 4 positions from 2022 6 [^6: https://publicadministration.un.org/egovkb/en-us/Data/Country-Information/id/120-Nepal] . A key component of the EGDI is the Online Service Index\n(OSI) where Nepal scores at 0.45, below the regional and global averages.\n\n\n**In September 2025, Nepal experienced political upheaval with a Gen Z led protest** . This protest was triggered by the\nGovernment’s decision to ban 26 social media services on September 9, 2025. The protests were not only about\nrestrictions on social media but also about deep frustrations with unequal access to services, corruption, and weak\naccountability. They underscored the urgent need for government to restore trust by delivering inclusive, transparent,\nand equitable services. Certain government services such as driving license are no longer being delivered as the servers\nand digital infrastructure were damaged. The Prime Minister and other key Ministers also resigned. An interim\ngovernment has been established and a Prime Minister appointed. Elections are expected to take place by March 2026.\n\n\nSectoral and Institutional Context\n\n**The Government of Nepal (GoN) needs to rebuild public trust by demonstrating transparency and inclusive public**\n**service delivery** . The aftermath of the protests has exposed the fragility of the country’s trust in government, exacerbated\nby weak data infrastructure and poor digital platforms. As such, it is essential that they invest in digital public infrastructure\n(DPI) and citizen facing service portals to reinforce social contracts with citizens by developing inclusive, user centric\nsystems with good governance and strong data protection. Historically, many of these systems, both in Nepal and other\ncountries, have suffered from poor adoption and low levels of trust. Adoption and trust will require\n\nMention: \"Online Service Index\""}, {"role": "assistant", "content": "{\"role\": \"supporting\", \"usage_action\": \"analyze\", \"summary\": \"Score below regional and global averages.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "umar_pads", "source_key": "umar_pads:005229:21:0", "occurrence_id": "98b0a43b2a1cb08d1f74a33f", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: **The World Bank**\nFinancial Sector Strengthening and Modernization (P513308)\n\n\nreduce already low climate risks, and advance adaptation and Paris-alignment objectives. Detailed operational\nguidelines will ensure compliance and effectiveness.\n\n**49.** **By enhancing access to finance, the project is expected to strengthen the climate resilience of MSMEs and**\n**individuals over time, contributing meaningfully to both mitigation and adaptation outcomes in line with the**\n**Paris Agreement.** None of the supported FIs will commit to new financing to universally non-aligned activities.\nWith this the material residual risk is expected to be reduced to a low/acceptable level given the due diligence\nincorporated to manage adaptation risks\n\n**50.** **The Palestinian microfinance sector's direct contribution to carbon emissions is negligible by any measure, as**\n**the CCDR confirms, the West Bank and Gaza’s total GHG footprint is already far below the global average, and**\n**the portfolio composition of MFIs operating in the West Bank and Gaza reinforces this picture clearly.** With a\ngross loan portfolio of approximately USD 265 million, the sector is heavily concentrated in General Trade (29.3%),\nHousing (30.3%), and Services (11.9%), which together account for over 70% of total loans. While the PMA\nSustainable Finance Roadmap 11 [^11: Sustainability Finance Roadmap and Acton Plan, PMA, 2024 i] identifies housing as a sector warranting climate risk attention due to exposure\nto flooding and landslides, lending in this category at microfinance ticket sizes is more likely to support incremental\nhousing improvements and basic infrastructure upgrades for vulnerable households than carbon-intensive largescale construction, making it a channel for climate resilience rather than a source of transition risk. Agriculture, at\n10.5% of the portfolio, is the sector with the highest physical climate exposure, but it is also where MFI lending\nmost directly\n\nMention: \"CCDR\""}, {"role": "assistant", "content": "{\"role\": \"supporting\", \"usage_action\": \"source\", \"summary\": \"Confirms emissions footprint far below the global average.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "umar_pads", "source_key": "umar_pads:000611:70:1", "occurrence_id": "7f901c9e14f7c50e51dcefc7", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: \ntourism sector and adversely affected domestic production, as business activity has been curtailed to combat the\nspread of the disease. More specifically, COVID-19 has affected growth through several channels, including: the\nsudden total stop in tourism; declining remittances, as global growth slows; lower foreign direct investment; and\nfalling Citizenship by Investment (CBI) revenues. 48 . Tourism receipts approximate 20 percent of Dominica’s GDP in a\ntypical year. This fell to 8 percent in 2020 and 7.5 percent in 2021, although is slowly rebounding with projected\ndoubling (to 15 percent) in 2022 and rising closer to pre-2020 levels by 2023.\n\n2. There are no recent official poverty data, but poverty remains a cause for concern. The official poverty data are\noutdated (2008) with indicated poverty rates of 28.8 percent. Estimates after Hurricane Maria projected that poverty\ncould increase to 43 percent if consumption impacts were not addressed. Economic recovery in 2018 and 2019 are\nexpected to have reduced poverty levels but the extent of this potential poverty reduction cannot be confirmed. With\ngrowth decelerating markedly in 2020 due to the COVID-19 pandemic, poverty rates are expected to increase in 2020.\nIndicative data from a rapid survey for the Caribbean 49 revealed that impacts of the COVID-19 pandemic seem to be\ntaking an increasing toll on household income. As of June 2020, 70 percent of households reported a loss in\nemployment or reduced salaries, 12 percentage points higher than in April 2020 50 . Additionally, 70 percent of those\nwhose income comes from informal sources and 66 percent of those in petty trades reported livelihood disruptions,\ncompared to 50 percent for salaried workers. Based on the 2008 Dominica Country Poverty Assessment, most of the\npoor work in services and agriculture, sectors that are directly linked to tourism. Given the high negative impact\n\nMention: \"poverty data\""}, {"role": "assistant", "content": "{\"role\": \"supporting\", \"usage_action\": \"analyze\", \"summary\": \"No recent official data; the outdated round indicated high poverty.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "umar_pads", "source_key": "umar_pads:000611:70:1", "occurrence_id": "171896882fcd0ea6830f1290", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: \ntourism sector and adversely affected domestic production, as business activity has been curtailed to combat the\nspread of the disease. More specifically, COVID-19 has affected growth through several channels, including: the\nsudden total stop in tourism; declining remittances, as global growth slows; lower foreign direct investment; and\nfalling Citizenship by Investment (CBI) revenues. 48 . Tourism receipts approximate 20 percent of Dominica’s GDP in a\ntypical year. This fell to 8 percent in 2020 and 7.5 percent in 2021, although is slowly rebounding with projected\ndoubling (to 15 percent) in 2022 and rising closer to pre-2020 levels by 2023.\n\n2. There are no recent official poverty data, but poverty remains a cause for concern. The official poverty data are\noutdated (2008) with indicated poverty rates of 28.8 percent. Estimates after Hurricane Maria projected that poverty\ncould increase to 43 percent if consumption impacts were not addressed. Economic recovery in 2018 and 2019 are\nexpected to have reduced poverty levels but the extent of this potential poverty reduction cannot be confirmed. With\ngrowth decelerating markedly in 2020 due to the COVID-19 pandemic, poverty rates are expected to increase in 2020.\nIndicative data from a rapid survey for the Caribbean 49 revealed that impacts of the COVID-19 pandemic seem to be\ntaking an increasing toll on household income. As of June 2020, 70 percent of households reported a loss in\nemployment or reduced salaries, 12 percentage points higher than in April 2020 50 . Additionally, 70 percent of those\nwhose income comes from informal sources and 66 percent of those in petty trades reported livelihood disruptions,\ncompared to 50 percent for salaried workers. Based on the 2008 Dominica Country Poverty Assessment, most of the\npoor work in services and agriculture, sectors that are directly linked to tourism. Given the high negative impact\n\nMention: \"rapid survey for the Caribbean\""}, {"role": "assistant", "content": "{\"role\": \"supporting\", \"usage_action\": \"analyze\", \"summary\": \"Rapid survey shows a large share of households lost employment or pay.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "fcv", "source_key": "fcv_pads_east_africa:000314:44:0", "occurrence_id": "11dc45f6f7a1b80f60a17891", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: |Project Phase|Key Activities|Frequency|Responsibility|\n|---|---|---|---|\n|Long‑Term
(Years 3+)|Reduced‑frequency
surveys
in
hotspots; remote monitoring via
UAVs and sensors; annual trend
analysis|Bi‑annual / Annual|UETCL E&S Directorate /
ERA (Electricity Regulatory
Authority)|\n\n\n\nActual details of the monitoring activities need to be developed to suit the field conditions in\nwhich they will be implemented and to meet the capacity and equipment availability of persons\ninvolved in their implementation. A detailed monitoring program therefore needs to be\ndeveloped by the implementing partners, although the following methodology, use of citizen\nscience and data analysis points provide an initial brief overview of the expected structure.\n\nMethodology\n1. Sampling Design: Stratified - random design selecting representative spans across risk strata\n(wetlands, ridges, plains).\n2. Data Collection: Standardized mobile phone-based datasheets that record GPS, species ID,\ncarcass condition, cause of mortality, tower ID, and photo evidence.\n3. Bias Correction: Application of carcass persistence and searcher - efficiency factors to adjust\nraw mortality estimates.\n4. Species Identification: Verification by NU/WCS ornithologists; voucher photos archived in\nUETCL’s biodiversity database.\n5. Data Storage: All records entered into a UETCL BNG monitoring database, that is GIS-linked\nwith data analysis that supports dashboard presentation.\n6. Adaptive Feedback: Results to be reviewed quarterly to adjust diverter density, maintenance\nintervals, or routing where high collision clusters occur.\n\nCitizen Science and Community Participation\nRegular routine monitoring is required which can be facilitated through community participation.\nUETCL will train and engage community monitors living near sensitive areas, such as wetlands,\nroost\n\nMention: \"UETCL’s biodiversity database\""}, {"role": "assistant", "content": "{\"role\": \"supporting\", \"usage_action\": \"curate\", \"summary\": \"UETCL and WCS ornithologists archive bird-mortality voucher photos and monitoring records in this database for project impact monitoring.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "fcv", "source_key": "fcv_pads_east_africa:002183:17:0", "occurrence_id": "3ed37032e7d77a2003edad7f", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: **The World Bank** Implementation Status & Results Report\nEthiopia Program for Results (Hybrid) for Strengthening Primary Health Care Services. (P175167)\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n|PHCU facilities having all
drugs from the MOH list of
essential drugs (Percentage)
(Percentage)|Comments on
achieving targets|Col3|The result achieved could not be verified due to absence of SARA/SPA survey. Currently,
based on the administrative report, this DLI continues to show consistent progress and is
expected to meet the closing period target. Despite this achievement, the result is not yet
verified.
Once the Bank receives the independent verification report from MOH, the team will update
the result/target accordingly.|Col5|Col6|Col7|Col8|Col9|\n|---|---|---|---|---|---|---|---|---|\n|Hospitals providing clinical
mentorship to Health Centers
on the 7 signals of Basic
Emergency Obstetric and
Newborn Care (
BEmONC)(Number)
(Number)|100.00|Jun/2022|164.00|24-Jul-2025|156.00|09-Jan-2026|120.00|Jun/2026|\n|Hospitals providing clinical
mentorship to Health Centers
on the 7 signals of Basic
Emergency Obstetric and
Newborn Care (
BEmONC)(Number)
(Number)|Comments on
achieving targets|Comments on
achieving targets|This DLI surpassed the end of Program\n\nMention: \"SARA/SPA survey\""}, {"role": "assistant", "content": "{\"role\": \"supporting\", \"usage_action\": \"validate\", \"summary\": \"Implementation team would verify the essential-drugs DLI indicator against SARA/SPA survey results; absent, administrative reports stand in.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "fcv", "source_key": "fcv_pads_east_africa:010012:7:1", "occurrence_id": "19e4d2baeab7ad97c2fec942", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: system. Clear reporting procedures and systems\nwere also designed for key public sector entities. Project indicators focused primarily on outputs, which was in\nline with the project’s objectives, though two behavior change indicators were also included that intended to\nmeasure behavioral outcomes (proportion of sexually active youth aged 15-24 who report having had sex with a\nnon-regular partner in the past 12 months, and proportion of sexually active youth aged 15-24 who report having\nused a condom during their last sexual encounter with a non-regular partner), even though these outcomes were\nnot embedded in the objectives. An impact evaluation was planned on behavior change communication among\nyouth in two provinces. More than half of the project's indicators lacked baseline values or targets, including\nindicators for most key populations (MSMs, sex workers, and drug users). According to the ICR (p. 15), the\nframework in some instances used outdated (2003 or 2007) baseline values that could have been updated by the\ntime the M&E plan was implemented.\n\n\n**b. M&E Implementation:**\n\n\nThe NACC implemented almost all M&E activities in the project’s original first-year work plan on schedule using\nalternative funding sources to compensate for delays in project effectiveness (these delays stemmed from\npost-election violence in early 2008 and time needed to recruit fiduciary consultants). An M&E Coordination\nSpecialist, database administrator, and analyst/programmer were recruited and trained. A new NACC local area\nnetwork/wide area network hosted the COBPAR system. Monitoring and Coordination Groups (MCGs) were set\nup for each priority area of the project, and formal linkages were established with entities responsible for other\nsources of data. An M&E Technical Working Group actively coordinated M&E activities, standards, and essential\nfunding. The project funded the HIV testing modules of the Kenya Demographic and Health Survey (KDHS) in\n2007, and part\n\nMention: \"Kenya Demographic and Health Survey\""}, {"role": "assistant", "content": "{\"role\": \"supporting\", \"usage_action\": \"source\", \"summary\": \"The project financed the HIV testing modules of this survey so its results could supply national HIV prevalence and behavior indicators.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:000023:22:0", "occurrence_id": "f065eb7f62d7eb7c13b3c27b", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: Source: Authors’ calculations based on data from the High Frequency Surveys of Ethiopia (2017), Nigeria (2018),\nSomalia (2017), South Sudan (2017) and Sudan (2017).\n\n\nConsidering the relative contribution of each indicator to multidimensional poverty between\nthe two types of households, we see that being deprived in the indicators of bank account and\nschool attendance in Ethiopia; bank account and years of schooling in Sudan; years of\nschooling and school attendance in Nigeria; and legal identification and school attendance in\nSouth Sudan are the main contributors of poverty to both types of households. In South Sudan,\nearly marriage contributes more to poverty in female-headed households, while school\nattendance contributes more to poverty in male-headed households. In Nigeria, the relative\ncontributions of early marriage and lack of legal identification are greater in female-headed\nhouseholds. The source of deprivation is slightly different for male- and female-headed\nhouseholds in Ethiopia, where lack of physical safety, early marriage, and lack of legal\nidentification contribute more to female-headed households, while years of schooling and\nschool attendance are much larger contributors to poverty in households headed by men.\n\n\nTable 6 refines the above analysis by looking within displaced households, and presenting data\nat the individual level for selected indicators. This is important as household level deprivations\ncan mask inequalities within the household unit (for instance, a household where four children\nare attending school and one is not would be considered deprived, similar to households where\nno children are in school). Looking at the three countries, years of schooling and early marriage\nare key indicators in analyzing the gender differences in poverty among forcibly displaced\nindividuals. with a significantly higher percentage of displaced females deprived in years of\nschooling compared to males. In terms of marriage, females are significantly more likely to get\nmarried at early age compared to males. The prevalence of child marriage in South Sudan and\nSudan is particularly high with 75% and 50% of displaced female individuals getting married\nbefore\n\nMention: \"High Frequency Surveys\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"analyze\", \"summary\": \"Authors compute multidimensional poverty contributions and gender gaps among displaced households directly from these country surveys.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:000076:13:0", "occurrence_id": "619be4d73c031de5d8f5a9bd", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: Together, this information allows obtaining a reliable estimate of taxes and contributions to\nFONASA paid by workers, capital earners and pensioners using the schedular rates. In this\nestimation we assume that workers who do not contribute to the social security system do not pay\ndirect taxes and do not contribute to the Health System Fund. Besides, we assume that workers\nwho contribute do not evade taxes and contributions. Finally, we assume no evasion in the case of\ncapital income and pensions. We estimate the individual’s pre-fiscal income adding taxes and\ncontributions to reported income. 14,15 [^14: Nevertheless, this is still an estimation, and might differ from other calculations. Please refer to Appendix\nII.] [^15: The estimation of taxes and contributions made by workers are based on the procedure followed by OPP\n(Simulador de Políticas Públicas versión 2016.0.0, Oficina de Planeamiento y Presupuesto, Presidencia de la\nRepública) for 2016. The estimation was adapted to 2017, and this was made with invaluable support from\nthe OPP team.] Pre-fiscal income also contains contributions to the health\nsystem paid by employees, private transfers and imputed rent (see Figure 1).\n\n\nFigure 2 provides a schematic of the different income concepts. It shows pre-fiscal income (market\nincome plus pensions), disposable income, consumable income (although it is not used in this\nanalysis), and adjusted income.\n\n\nWe define Net Market Income as Pre-Fiscal Income less direct taxes and contributions to the\nhealth system. Next, we estimate Disposable Income as the sum of Net Market Income and public\ndirect transfers. Information of the ECH on social programs receipt and household composition\nallows the direct identification of public transfers’ beneficiaries. Besides, the survey also provides\nthe amount of the benefit. Finally, we define Adjusted Income as the sum of Disposable Income\nand public educational and health transfers. As for in-kind benefits, school attendance, type of\nschool and access to health services allow for the imputation of monetary\n\nMention: \"ECH\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"analyze\", \"summary\": \"Provides program receipt, household composition and benefit amounts used to identify transfer beneficiaries and construct income concepts.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:000128:47:2", "occurrence_id": "d06b590e9cdf70488a695c14", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: *\n0-25% 0.78 0.60 0.50 0.33 0.21 0.050\n26%-50% 0.75 0.51 0.49 0.45 0.27 0.060\n51%-75% 0.73 0.43 0.51 0.55 0.31 0.070\n76%-100% 0.69 0.30 0.56 0.73 0.47 0.100\n\n_Data sources: National Surveys of Privately-Owned Enterprises in China_\n\n\n46\n\nMention: \"National Surveys of Privately-Owned Enterprises in China_\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"analyze\", \"summary\": \"Named in the table source line as the data behind the reported estimates by enterprise ownership-size class.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:000162:13:0", "occurrence_id": "24d11bb7ee854a2cc74f57a7", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: **Definition** **1** **_Equilibrium_** **_Definition._**\n\n_An_ _equilibrium_ _in_ _this_ _model_ _specifies_ _the_ _set_ _of_ _child_ _care_ _providers_ _available_ _to_ _households_\n_as_ _well_ _as_ _their_ _prices_ _and_ _qualities,_ _and_ _the_ _decisions_ _made_ _by_ _households_ _with_ _respect_ _to_\n_work_ _and_ _child_ _care,_ _such_ _that:_ _(1)_ _the_ _child_ _care_ _providers_ _in_ _parental_ _choice_ _sets_ _are_ _indeed_\n_available in the market; (2) every child care provider in the market makes non-negative profits,_\n_and_ _(3)_ _neither_ _parents_ _nor_ _child_ _care_ _providers_ _wish_ _to_ _alter_ _their_ _decisions._\n\n\nDue to the discreteness of household and firm choices, as well as the finite number of\nhousehold types and potential firms, the equilibrium does not have a closed-form solution and\nmust be solved numerically for a given set of parameter values. Appendix B.1 describes the\nquantitative version of our model, and Appendix B.2 describes the equilibrium computation.\n\n#### **3 Data**\n\n###### **3.1 Sources**\n\n\nWe estimate the model with data from the US Early Childhood Longitudinal Study birth\ncohort (ECLS-B), which follows individuals from birth through kindergarten for a nationally\nrepresentative sample of children born in 2001\n\nMention: \"US Early Childhood Longitudinal Study birth\ncohort\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"analyze\", \"summary\": \"The structural child-care and maternal employment model is estimated on this nationally representative birth-to-kindergarten cohort.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:000193:58:0", "occurrence_id": "99e144ac4d92483d2c5fc005", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: **Table C.4. Robustness check with additional telephone survey round**\n\n\nEvent type Perpetrator type\n(1) (2) (3) (4) (5) (6) (7) (8)\nVARIABLES\n\nConflict events 0.071*** 0.045** 0.052***\n(0.026) (0.020) (0.016)\nConflict events property 0.091***\n(0.026)\nConflict events violence 0.046\n(0.038)\nInsurgents 0.081***\n(0.020)\nBandits/criminals 0.202**\n(0.089)\nPastoralists/nomads 0.018*\n(0.009)\n\nObservations 3,458 2,802 2,802 2,802 2,802 2,802 2,802 2,802\nR-squared 0.323 0.023 0.045 0.043 0.042 0.045 0.044 0.042\nNumber of households 581 581 581 581 581 581 581 581\nControls NO YES YES YES YES YES YES YES\nYear FE YES YES NO NO NO NO NO NO\nHH FE YES YES YES YES YES YES YES YES\nRegion-round FE NO NO YES YES YES YES YES YES\n_Note_ : Dependent variable is the standardized CSI. Data used are from the six visits of the GHS and telephone survey for conflict and an additional telephone survey with the\nCSI administered to 581 households in 2017. All regressions\n\nMention: \"GHS\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"analyze\", \"summary\": \"Robustness regressions on the standardized distress index are estimated from six panel visits of this household survey plus telephone rounds.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:000224:5:0", "occurrence_id": "0e12c0994518fbec6d86babf", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: significantly related in LICs. This paper builds on those results by identifying the specific shortcomings in\nDeM in LICs and providing the basis for targeted reform programs to increase their DeM performance.\nMuch literature exists on the importance of DeM in developing countries as well as the links between\nDeM and financial crises. 9 [^9: Notably, see World Bank (2003), World Bank (2009), Anderson and Togo (2009), Melecky (2007), Jaimovich and\nPanizza (2006), and Panizza (2008)] This paper builds on this literature by introducing new data on DeM in LICs\nthat identifies vulnerabilities and highlights areas for improvement. The structure of the paper is as\nfollows: Section II gives a brief overview of the current crisis, with particular attention paid to its effects\non LICs. Section III looks at the unique challenges developing countries, and LICs in particular, face with\nregard to DeM. Section IV focuses on the results of the DeMPA and MTDS tools and what they tell us\nabout the current state of DeM in LICs. This section identifies priority areas for improvement and\nhighlights potential pitfalls in the current environment. Section V concludes.\n\n\n**II.** **Setting the Stage: The Global Financial Crisis and Developing Countries**\n\nThe global financial and economic crisis of 2008‐09 has significantly altered the economic landscape for\ndeveloping countries. The effects of the crisis on developing countries and regions were diverse and a\nfunction of both developmental and structural factors. Many Eastern European economies, which were\nhighly integrated with and reliant upon Western European capital markets, most notably, were hard hit\nby financial contagion and the sudden stop in capital flows. LIC’s on the other hand, with financial\nsectors that were largely not integrated with the global markets, were insulated from the financial\nmarket contagion that spread from advanced economies. LICs, however, were severely affected by the\ndecline in exports and falling commodity prices. In either case, developing countries as\n\nMention: \"new data on DeM in LICs\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"curate\", \"summary\": \"The authors introduce this newly compiled debt-management dataset for low-income countries to identify vulnerabilities and reform priorities.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:000337:15:0", "occurrence_id": "2b1895cfb3bfb5052fc67d0c", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: **SKILLS AND INDUSTRIAL EMISSIONS**\n\nTo test whether higher cognitive skills are associated with production technology that relies less\n\non emissions for production, several linear regression models were estimated using our individual\nlevel skills and industrial emissions data sets. Two outcome variables were examined: emissions\n\nper output in 2012 and annualized growth in emissions per output between 2010 and 2019. These\n\nmodels were estimated using pooled data for all countries (see descriptive statistics above); models\n\nwere estimated following OECD (2013) using plausible value estimates for cognitive skills and\n\nthe Jackknife 2 method. Jackknife replicate weights were provided for each country by the OECD\n\nbased on either the “delete-one” Jackknife or “paired” Jackknife method; however, the paired\n\nJackknife method was applied because the data was pooled (using the paired Jackknife aggregation\n\nformula with delete-one jackknife weights results in an overestimate of the standard error). Stata\n\nroutines by Macdonald (2008) were used in implementing the estimation method.\n\n\nTable 3 presents estimates from the first set of models, looking at the association between cognitive\n\nskills and emissions per output in 2012 and annualized growth in emissions per output from 2010\n\nto 2019 within a Mincerian type model. All three measures of cognitive skills, literacy, numeracy,\n\nand problem solving, are negatively associated with the level of emissions per output in 2012 as\n\nwell as growth between 2010 and 2019. Country fixed effects were added to this model and\n\npresented in Table 4 showing that cognitive skills negatively associate with emissions and growth\n\nin emissions per output within countries, across industries. Table 5 presents the same model with\n\nhighest level of education added; higher levels of education generally associate with lower\n\nemissions and growth in emissions per output. Finally, Table 6 introduces an interaction term\n\nbetween whether the individual was employed in a managerial or professional occupation (ISCO\n08 categories 1 and 2). The association between cognitive skills and lower emissions per output\n\nand lower growth in emission per output is strong for\n\nMention: \"individual\nlevel skills and industrial emissions data sets\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"analyze\", \"summary\": \"The authors own individual-level skills and industrial emissions datasets are pooled and regressed on emissions per output and its growth.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:000550:9:0", "occurrence_id": "0ed2e8563e2db2c04f666c4f", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: In early 2021, the predominant reason for refusing vaccines was that the respondent did not trust vaccine\nproducers. Although this remained a significant concern in all three countries, much more striking is the\nrising prevalence of the response that “counterindication” was the reason a respondent did not plan to\nbe vaccinated. By August 2021 this accounted for the plurality of vaccine hesitant people in all three\ncountries. The rise of counterindication is not solely an effect of composition, it also continuously rose in\nabsolute terms in Uzbekistan and Kazakhstan. See annex 2 for more details on counterindication patterns\nin Central Asia.\n\nAmong those saying they will not vaccinate in Kazakhstan and Tajikistan, those who cited\ncounterindication were the “stickiest” in their responses, in the sense that they were consistently the least\nlikely to change their response. In Uzbekistan only the “other” category is stickier, and in Uzbekistan, many\npeople providing “other” responses describe ineligibility due to various health criteria that are not\nformally counterindication restrictions on vaccination. For instance, a common response in the other\ncategory was the (mistaken) impression that vaccines were unsafe for people over age 60 or 65.\n\nThe prevalence of counterindication as a reason for vaccine hesitancy in Central Asia is likely linked to\nofficial guidance (please see annex 2 for more details). In Kazakhstan, Uzbekistan, and to a limited extent\nTajikistan, vaccination programs explicitly excluded some at-risk groups, with public communications\ncampaigns often listing these conditions explicitly. Eligibility restrictions were primarily based on\nperceived risk arising due to pre-existing health conditions. However, the guidance in some cases strongly\ncontrasted with conventional practice elsewhere in the world where members of these same at-risk\ngroups are often targeted for early vaccination with the same vaccines. 8\n\n#### Methods\n\n\nOur survey experiment was embedded in the Listening to Central Asia series of surveys in Tajikistan,\nUzbekistan, and Kazakhstan, surveys that are designed to continuously\n\nMention: \"Listening to Central Asia\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"analyze\", \"summary\": \"The vaccine hesitancy experiment is embedded in this continuous country survey series, which supplies its respondents.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:000692:6:1", "occurrence_id": "1ffb21f301787dbd3df26aa5", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: IPUMS International (Integrated Public Use Microdata Series, IPUMS, 2019), hosted\n\n\nat the University of Minnesota Population Center, which reports harmonized representative\n\n\nsamples (typically 10%) of full census micro data sets for a large number of countries. In\n\n\nparticular, I use 91 samples of population and housing censuses from 24 countries, which are\n\n\nrun to compute the total population and contain an educational attainment question in their\n\n\nquestionnaire. 4 The key advantage of this data set is that it contains the entire population\n\n\n4Because the individuals are not organized into households, I do not use Chile 1960, Colombia 1964,\n\n\n5\n\nMention: \"population and housing censuses\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"analyze\", \"summary\": \"91 harmonized census samples across 24 countries supply population totals and educational attainment for the analysis.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:000760:9:1", "occurrence_id": "f2c50c4c59fee2fcac6e5ae1", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: on a 0.5 _◦_ _×_ 0.625 _◦_ grid. 8 We collect the daily aggregate mean of temperature for\n\nthe first 19 levels of the atmosphere. This roughly corresponds to the levels beginning at the\nsurface and extending 5km into the atmosphere. 9 Because MERRA indexes layers based on\n\npressure levels, rather than consistent elevation thresholds we calculate surface temperature\n\nindividually for each grid-point _×_ day based on the temperature reported at the lowest level\n\nfor that grid-point _×_ day. We set this layer as the surface and calculate temperatures in the\n\nlayers counting up from the surface layer.\n\n\nWe aggregate our grid-point _×_ day temperatures to the district level by taking the weighted\n\naverage across grid-points for each day with weights defined as the total population in each\ngrid-point’s unique catchment area. 10 We assign grid-points to the districts that contain\n\nthem. For districts that do not contain any grid-points we use the nearest grid-point to the\n\ncenter of the district. We then calculate whether a district experiences an inversion on a\n\ngiven day based on the district _×_ day temperature at each atmospheric level.\n\n\nWe use two different measures of inversions. The first considers the difference between\n\n\n8Data available here: `[https://disc.gsfc.nasa.gov/datasets/M2I3NPASM_5.12.4/summary?](https://disc.gsfc.nasa.gov/datasets/M2I3NPASM_5.12.4/summary?keywords=M2I3NPASM)`\n```\nkeywords=M2\n\nMention: \"M2I3NPASM\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"analyze\", \"summary\": \"Gridded daily atmospheric temperature levels from this reanalysis product are aggregated to districts to detect temperature inversions.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:000788:16:0", "occurrence_id": "9911c65aea6befc453186d79", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: #### **Supplementary files**\n\n**Table A1: Sample Size**\n**Burkina Faso** **Kenya (KIHBS)** **Kenya (RDD)** **Malawi** **Nigeria** **Tanzania**\n\nPre-COVID F2F Survey / RDD frame 7,010 92,999,970 3,181 4,976 12,812\n\nWith phone numbers 6,877 9,007 92,999,970 2,337 4,934\n\nAttempted to contact 2,199 9,007 5,000 2,337 4,440 5,750\n\nReached 1,951 4,075 1,729 3,152 2,251\n\nPhone interviews completed 1,847 4,561 1,075 1,447 2,922 2,193\n\n\nNote: Sampling frame in Kenya consisted of re-contact sample from the Kenya Integrated Household Budget\nSurvey 2015/16 (KIHBS) and a sample obtained from random digit dialing (RDD).\n\n\n**Table A2: Estimated vaccine acceptance**\n\nBurkina Faso Kenya Malawi Nigeria Tanzania<\n\nMention: \"Kenya Integrated Household Budget\nSurvey 2015/16\""}, {"role": "assistant", "content": "{\"role\": \"supporting\", \"usage_action\": \"curate\", \"summary\": \"Provides the re-contact sample used as one arm of the Kenya phone-survey sampling frame.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:000855:7:0", "occurrence_id": "26f3ab1d6138457a39bf5519", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: Another important debate concerns how labor is measured and what really matters. Discussion centers\n\n\non explaining if what matters is whether the child works or the actual number of hours spent working (i.e.,\n\n\nwork intensity). Goulart and Bedi (2008) assessed economic work both inside and outside the household\n\n\nand found that while economic work negatively affects school success, household chores are unrelated\n\n\nto schooling outcomes. Guarcello, Lyon and Rosati (2006) present contrasting evidence, however. Their\n\n\nstudy, looking at children aged 7 to 14 years across 60 developing countries, suggests that the negative\n\n\neffects on schooling are not limited to economic activity but also extend to household chores, and that\n\n\nintensity of work matters. They report that hours of economic work as well as household chores are\n\n\nrelated to the probability of attending school in Bolivia, Cambodia, Mali and Senegal. Edmonds (2007) and\n\n\nAllais (2009) also suggest that intensity matters most. Edmonds (2007) finds that the difference in school\n\n\nattendance rates for children working inside and outside the household appears to owe more to\n\n\ndifferences in the total hours worked rather than something else intrinsic to work outside home. Allais\n\n\n(2009), in a study looking at 16 countries, reports that engaging in 28 or more hours of economic work\n\n\nresulted in 30 percent lower school enrollment compared to working fewer than 14 hours. He also looks\n\n\nat work intensity related to household chores and finds that doing household chores for 28 or more hours\n\n\nis associated with almost 20 percent lower school enrollment for girls and 10 percent lower enrollment\n\n\nfor boys, when compared to working fewer than 14 hours.\n\n##### 3. Data and methodology\n\n\nThe present analysis uses data from the 2015 Myanmar Labour Force, Child Labour and School-to-Work\n\n\nTransition Survey (LFS). Conducted by the Department of Labour (DOL) at the Ministry of Labour,\n\n\nImmigration and Population (MOLIP), this unique countrywide survey collected detailed information on\n\n\nthe\n\nMention: \"School-to-Work\n\n\nTransition Survey\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"analyze\", \"summary\": \"The countrywide survey supplying the child labour, work-intensity and schooling data this analysis estimates on.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:000857:6:0", "occurrence_id": "cd31afa5ab9c494a49572dee", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: and storms.\n\n\nTheoretical literature on the economic effects of natural disasters has been gradually\n\nevolving. Marto et al. (2018) develop a model that explores the macroeconomic im\npact of a major natural disaster. Their study focuses on debt sustainability concerns\n\nthat arise from the need to fully rebuild public infrastructure over the medium term and\n\ncompares policies, such as building adaptation infrastructure and fiscal buffers, with the\n\npost-disaster support provided by donors. Burns et al. (2021) develop a macrostructural\n\nmodel for Jamaica that embeds climate damages from natural disasters and considers\n\ndifferent risk management strategies to address them. When it comes to DSGE models,\n\nKeen and Pakko (2011) develop a model to investigate the appropriate monetary policy\n\nresponse to natural disasters like Hurricane Katrina. Fern´andez-Villaverde and Levintal\n\n(2018) compare different solution methods for computing the equilibrium of DSGE mod\nels with rare disasters, given large nonlinearities that could be triggered by these events.\n\nStrulik and Trimborn (2019) examine the welfare effects in the aftermath of natural dis\nasters. Similarly, Cantelmo et al. (2019) study the macroeconomic outcomes and welfare\n\nimplications in disaster-prone countries and policies to mitigate them. Most of the pa\npers focus on the channel in which disasters destroy durable goods or productive capital.\n\nGallic and Vermandel (2020), on the other hand, build and estimate a DSGE model with\n\na weather-dependent agriculture sector to investigate the adverse weather implications in\n\nNew Zealand.\n\n\nThe contribution of this paper is twofold. First, it provides evidence of the fiscal im\nplications of natural disasters in a broad sample of countries using different specifications\n\nand the disaster measure that is based on physical intensity. As pointed out in Felbermayr\n\nand Groeschl (2014), EM-DAT and similar databases comprise disaster intensity measures\n\nthat are a function of economic development. Reported monetary damages of disasters are\n\nhigher in richer\n\nMention: \"EM-DAT\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"analyze\", \"summary\": \"Source of disaster intensity and damage records used for the fiscal impact analysis, with its development-dependent measures discussed as a caveat.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:000882:23:1", "occurrence_id": "2a666813a6a97bc38cf6aaad", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: ad trans ort\nesiden al services and construc on ndustries and other ener\nood forestry et chan e\n\n_Note_ : Graphs use different y-axis scales to account for and visualize the different magnitudes of sectoral impacts.\n\n\nFFS reforms save lives\nThe relationship between particle concentrations of different pollutants and the incidence of disease has\nbeen documented extensively in the medical literature. Air pollution can cause multiple severe health\nconditions, depending on concentration levels and the chemical composition of particulate matter. For\nexample, heightened PM2.5 exposure has been shown to increase the risk of chronic obstructive\npulmonary disease, ischemic heart disease, lung cancer, stroke, and chronic and acute respiratory\ndiseases such as asthma (Cohen et al. 2017; WHO 2018). There is also growing evidence of the role of\nPM2.5 exposure in increasing the risk of type 2 ia etes an neurological iseases such as Al heimer’s\n(Peters et al. 2019; GBD 2019 Risk Factors Collaborators 2020). The Global Burden of Disease Study 2019\nestimates that 2.3 million and 4.5 million premature deaths result from exposure to indoor and outdoor\nair pollution, respectively (IHME 2021).\n\n\nThis means that, by reducing fossil fuel consumption and associated particle emissions, FFS can directly\nhelp reduce a country’s air pollution eaths Yet, it can only be considered a first step toward wider actions\nto reduce air pollution. Based on estimated reductions in particle emissions and ambient concentrations,\nit is possible to distinguish the health impacts associated with different air pollutants and their originating\n\n\n22\n\nMention: \"Global Burden of Disease Study 2019\""}, {"role": "assistant", "content": "{\"role\": \"supporting\", \"usage_action\": \"inform\", \"summary\": \"Cited for the premature-death estimates from indoor and outdoor air pollution supporting the health-mortality argument.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:000883:7:1", "occurrence_id": "ea5d1797e3190eb5f15667bd", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: T estimates household per capita consumption;\nb. VM estimates income to earnings ratio (initially estimated $2 a day poverty status).\n\n\n2. They vary in how they do this:\na. PMT uses a continuous regression with variable selection (stepwise in 2012, Lasso in\n\n2017);\nb. VM uses a binary regression with variable selection (stepwise).\n\n\n3. They vary in the number of geographical models:\na. PMT produces regional models;\nb. VM produces a single model for all regions.\n\n\nThe CLCI revised the models using the 2018 Multi Cluster Needs Assessment (MCNA) survey, which\nresulted in the 2019 Socio-Economic Vulnerability Assessment Tool (SEVAT). 7 [^7: Reverification:\na. By law, households file an annual report on the MOLSA website;\nb. Social workers also revisit the households each year to maintain rapport and support case] The new models are closer\n\n\n7 https://www.humanitarianresponse.info/en/operations/iraq/document/iraq-mpca-vulnerability-model-review\n\n\n6\n\nMention: \"2018 Multi Cluster Needs Assessment (MCNA) survey\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"analyze\", \"summary\": \"Used to re-estimate the proxy and vulnerability targeting models, producing the 2019 SEVAT tool.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:001151:13:0", "occurrence_id": "4b052db938bc3976ac7970db", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: **Figure 1. Sectoral CO2 and non-CO2 Emissions per Value Added across Sectors (metric/million USD).**\n\n\n\n4,000 **CO2 Emissions per VA**\n\n\n\n20,000 **Non-CO2 Emissions per VA**\n\n15,000\n\n10,000\n\n5,000\n\n \n\n\n2,000\n\n\n \n\n\n\n\nSource: Authors’ computations using GTAP data. Utilities are removed from Figure 1 for CO2 emissions for presentational\npurpose, as they have nearly five times higher emissions per value added (on average) compared to transportation and\ncommunication.\n\n\nFigure 1 clearly shows that transportation and communication, mining, and manufacturing are among the\n\nhighest contributors to CO2 emissions per value added, while other services, finance, and trade have the\n\nlowest levels of CO2 emissions per value added. It is important to note that utilities are intentionally\n\nremoved from the graph as they have nearly five times higher emissions per value added (on average)\n\ncompared to transportation and communication. There is also a large dispersion within these broad\n\nsectors indicating that production structures within industries could be diverse differing among\n\ndeveloping countries relative to the different stages of sophistication and the choice of technology. At\n\nthe same time, the CO2 emissions per value added vary substantially across the different country income\n\ngroups. Finally, non-CO2 emissions in terms of CO2 equivalent are multiple times higher for agriculture,\n\nmining, and utilities with a large variation across income groups. These non-CO2 emissions include\n\nmethane (CH4), nitrous oxide (N2O) and the group of fluorinated gases (F-gases).\n\n\n**5.** **Estimation Results**\n\n\nThe paper estimates the impact of the share of informal workers on emissions per value added using cross\n\ncountry and industry data in the following regressions: OLS, OLS with control variables, industry fixed\n\neffects, country fixed effects, and industry and country fixed effects as shown in\n\nMention: \"GTAP data\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"analyze\", \"summary\": \"Supplies cross-country industry emissions and value-added data used for the sectoral figures and the informality-emissions regressions.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:001365:5:2", "occurrence_id": "c3e5f6d1f6ed5b110e54d762", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: 20th century, it was clear that incoming transfers of funds reached high\nproportions compared to the size of the economy. Figure 3 shows the composition of the income of\nMount Lebanon in 1914. Table 2 is drawn based on data on what is called in the early 20th century\nlanguage “Income of the Mountain.” This data covers an unspecified year between 1910 and 1914,\nmost likely 1912. I calculated a proxy of the equivalent of today’s GDP and Gross National Disposable\nIncome (GNDI). According to this calculation, silk industry provided 48 percent of Mount Lebanon’s\nGDP, while Net Transfers from the Americas amounted to 54 percent, and GNDI reached 154 percent\n\n\n4\n\nMention: \"Income of the Mountain\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"analyze\", \"summary\": \"Early twentieth-century income compilation used to draw Table 2 and compute proxy GDP and gross national disposable income.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:001557:41:0", "occurrence_id": "a010591e3b3d4035413f8c43", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: **Annex A. Methodology to capture procyclicality**\n\n\nThe purpose of the analysis is to see how the fiscal authority is conducting fiscal policy over the business\ncycle. Accordingly, the initial step is to have historical data both on GDP and fiscal accounts. In\nparticular, the methodology consists in the following:\n\n\n1. Define any fiscal instrument/variable we want to analyze (e.g. government spending)\n2. Put together the historical series of both the fiscal instrument and the GDP, in real terms.\n3. Get the trend series of both variables by applying HP filter or similar methods in order to\ndecompose the cyclical and the trend components of the series.\n4. The difference between the original series and its trend is the cyclical component of each\nvariable. For instance, if real GDP (at any given point in time) is above its (HP) trend, the\neconomy is in “good times” and the cyclical component would be positive (see Example Figure\nbelow).\n\nCyclical component i: Original Series i – HP Trend i\n\n\n5. Once we have the cycle of both series (fiscal instrument and GDP), we calculate the correlation\nof both cyclical components.\n6. If the correlation is positive, then we define the fiscal instrument as procyclical as it increases\nin good times and decreases in bad times, and vice versa.\n\n\n**Figure 26. Country A Real GDP vs HP Filter Trend** **Figure 27. Country A GDP Cycle (Real GDP-HP**\n**Trend)**\n\n\n1.0\n30\n\n\n0.5\n25\n\n\n0.0\n\n\n20\n-0.5\n\n\n15\n-1.0\n\n\n_Source:_ IMF Database _Source:_ IMF Database\n\nMention: \"IMF Database\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"analyze\", \"summary\": \"Supplies the historical real GDP and fiscal series behind the HP-filter illustrations of the procyclicality method.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:001638:19:2", "occurrence_id": "910dfb648d952c34a8b6eac3", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: * 𝑝𝑝,𝑌𝑌�𝑝 **𝑝** 𝑝𝑝� × 𝑃𝑃� 𝑝 **𝑝** 𝑝𝑝\n\n\n\n𝑌𝑌𝑝 **𝑝** 𝑝𝑝 = 𝛽𝛽 × 𝐿𝐿�𝐶 𝐶𝐶�𝑃𝑃 � 𝑝 **𝑝** 𝑝𝑝, 3�, 𝑘𝑘�\n\n\n\n( 3 )\n\n\n\n𝑝 **𝑝** 𝑝𝑝|𝐼 **𝐼** �𝐼𝐼4+ = 𝛽𝛽̂ arg min𝑘𝑘∈1,…12 𝑀 **𝑀** 𝑀𝑀�𝑌𝑌𝑝 **𝑝** 𝑝𝑝,𝑌𝑌�𝑝 **𝑝** 𝑝𝑝� × 𝑃𝑃� 𝑝 **𝑝** 𝑝𝑝\n\n\n\n( 4 )\n\n\n\n**Figure 7: availability of IPC assessments**\n\n\n\n**Figure 7: availability of IPC assessments**\n\nIPC assessments are contingent on suf�icient evidence for high-con�idence declarations, with no phases declared when\ninformation availability does not meet con�idence criteria. The graph therefore highlights the likely access issues that may have\n\n\n\nutilized 𝑌𝑌𝑝 **𝑝** 𝑝𝑝, incorporating data from both FEWS NET (starting from 2014) and IPC data (from 2019\nonwards). The data integration was performed due to several challenges with the underlying assessment\n\n18\n\nMention: \"FEWS NET\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"analyze\", \"summary\": \"Supplies food security assessments from 2014 that are merged with IPC evidence to build the outcome variable.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:001638:19:2", "occurrence_id": "c31e16d391dc90fbc34a9758", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: * 𝑝𝑝,𝑌𝑌�𝑝 **𝑝** 𝑝𝑝� × 𝑃𝑃� 𝑝 **𝑝** 𝑝𝑝\n\n\n\n𝑌𝑌𝑝 **𝑝** 𝑝𝑝 = 𝛽𝛽 × 𝐿𝐿�𝐶 𝐶𝐶�𝑃𝑃 � 𝑝 **𝑝** 𝑝𝑝, 3�, 𝑘𝑘�\n\n\n\n( 3 )\n\n\n\n𝑝 **𝑝** 𝑝𝑝|𝐼 **𝐼** �𝐼𝐼4+ = 𝛽𝛽̂ arg min𝑘𝑘∈1,…12 𝑀 **𝑀** 𝑀𝑀�𝑌𝑌𝑝 **𝑝** 𝑝𝑝,𝑌𝑌�𝑝 **𝑝** 𝑝𝑝� × 𝑃𝑃� 𝑝 **𝑝** 𝑝𝑝\n\n\n\n( 4 )\n\n\n\n**Figure 7: availability of IPC assessments**\n\n\n\n**Figure 7: availability of IPC assessments**\n\nIPC assessments are contingent on suf�icient evidence for high-con�idence declarations, with no phases declared when\ninformation availability does not meet con�idence criteria. The graph therefore highlights the likely access issues that may have\n\n\n\nutilized 𝑌𝑌𝑝 **𝑝** 𝑝𝑝, incorporating data from both FEWS NET (starting from 2014) and IPC data (from 2019\nonwards). The data integration was performed due to several challenges with the underlying assessment\n\n18\n\nMention: \"IPC data\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"analyze\", \"summary\": \"Provides IPC phase classifications from 2019 onwards used alongside FEWS NET in the composite measure.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:001654:15:0", "occurrence_id": "db2a3739e04c4f240ba9f95b", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: **Figure 2: National median maize price in Malawi and its neighbors (2006–2017)**\n\n_(during periods with and without export bans)_\n\n\n_Source:_ Authors’ calculations based on price data from markets in each country and official exchange rates. _Note_ :\n\nMOZ = Mozambique; MW = Malawi; TZ = Tanzania; ZM = Zambia. The prices are converted from local currency\nunits to US$ per kg using the official exchange rate for each country.\n\n\n**Figure 3: Median price dispersion between market pairs within Malawi and across the border**\n\n\n\n_Source_ : Authors’ calculations based on price data from individual markets within countries; distance and travel time\n\n𝑃𝑀𝑃 ,𝑖𝑖,𝑡𝑡 −𝑃 𝑛 𝑃 **𝑛** 𝑛𝑛−𝑀 ,𝑗𝑗,𝑡\n\nthe market in Malawi, that is, dispersion is defined as ~~�~~ ~~𝑃𝑀~~ 𝑃 ~~,𝑗~~ 𝑗 ~~,𝑡~~ ~~�~~ × 100.\n\n\n\nthe market in Malawi, that is, dispersion is defined as ~~�~~ 𝑃\n\n\n\n𝑃𝑀𝑃 ,𝑖𝑖,𝑡𝑡 −𝑃 𝑛 𝑃 **𝑛** 𝑛𝑛−𝑀 ,𝑗𝑗,𝑡\n~~𝑃𝑀~~ 𝑃 ~~,𝑗~~ 𝑗 ~~,𝑡~\n\nMention: \"price data from markets in each country\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"analyze\", \"summary\": \"Compiled market maize prices converted at official exchange rates underpin the median price and dispersion figures.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:001710:13:1", "occurrence_id": "ee4e4d26970e17c822e374c3", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: resemblance to_\n\n\n\n_formal enterprises_\nReasons for not Percentage Percentage Percentage\nregistering answering “yes” selecting as main answering “yes”\n\n\n\nPercentage\nanswering “yes”\n\n\n\nPercentage\nselecting as main\n\n\n\nreason\n\n\n\nPercentage\nanswering “yes”\n\n\n\nPercentage\nselecting as main\n\n\n\nreason reason\n\nTime, fees and 33.4 26.1 50.4 68.7\npaperwork\n\n\n\n33.4 26.1 50.4 68.7\n\n\n\nTaxation 27.5 10.9 42.2 2.9\nInspections 13.6 1.4 24.4 4.3\nBribes 12.9 1.8 22.2 0.0\nNo benefit for business 45.3 33.5 22.3 14.6\nLack of information 43.0 18.6 37.2 8.7\nSource: WB Enterprise Survey.\n\n\n\nAs presented in Table 2, firms indicate as the main reason for not registering that they do not see\n\na benefit of registering for the business (33\n\nMention: \"WB Enterprise Survey\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"analyze\", \"summary\": \"Supplies firm-level responses on registration costs, taxation and perceived benefits used in the informality discussion.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:001711:5:0", "occurrence_id": "a91e4e38be1f21dca5ce77d4", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: the de facto exemption of the informal sector achieves on average as much inequality re\nduction as the actual direct tax policies (income taxes and social security) in developing\n\ncountries. Equally remarkable is that this policy achieves 75% of the inequality reduction\n\nobtained in a counterfactual world with perfect enforcement in which governments can\n\ntax both formal and informal varieties (thereby taxing a much larger base) and optimally\n\ndifferentiates rates between food and non-food goods. In the realistic world in which\n\ninformal varieties cannot be taxed, the inequality reduction obtained by the de jure op\ntimal rate differentiation is half that obtained by the de facto exemption of the informal\n\nsector.\n\n\nWe investigate the robustness of our results to changing our main assumptions. First,\n\nwe obtain similar results when changing how we assign places of purchases to the formal\n\n(informal) sector. This is because the association between budget shares and household\n\nincome is strongest for places of purchase which are clearly informal (non-market con\nsumption) or clearly formal (large supermarkets). Second, we assume at baseline a zero\n\npass-through of taxes to prices in informal stores. This assumption may not hold if, for\n\nexample, informal retailers buy inputs from formal suppliers. We relax this assumption\n\nby combining our model with microdata from Mexico on formal input purchases of in\nformal retailers. We find a slightly smaller redistributive effect of the de facto exemption\n\nof the informal sector, but our main results remain unchanged. Third, due to data limitations, we use total household expenditure to proxy for household income. 2 We relax\n\nthis assumption by using estimates of saving rates across the income distribution and\n\nfind similar results. Finally, we discuss the implications of our modeling assumption\n\nthat no direct tax instrument is available to the government. An important theoretical\n\nresult in public finance is that redistribution is better achieved through direct rather than\n\nindirect taxes (Atkinson and Stiglitz 1976). This result, however,\n\nMention: \"microdata from Mexico\""}, {"role": "assistant", "content": "{\"role\": \"supporting\", \"usage_action\": \"analyze\", \"summary\": \"Records on formal input purchases by informal retailers are merged with the model to relax the zero pass-through assumption.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:001785:15:0", "occurrence_id": "43f24722ff7bfb618217003c", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: internationally competitive tenders in most cases. While procurement is usually carried out through\ncompetitive bidding, some large plants procured in the period 2010-2015 were through direct negotiations.\n\n\nIt is worth noting that part of the government resistance to procurement of private investment stemmed\nfrom the belief that reserve margins in the sector were not sufficient to tolerate the uncertainty about\ntiming that is intrinsic to negotiating with the private sector – that can be seen as an inadequacy in the\nplanning process (i.e. private sector procurements should have been initiated early enough). However,\nafter initial teething troubles, this belief may have been overcome by the recent renewable energy\nprocurements, which have successfully involved private investment.\n\n\nEgypt scores relatively high when it comes to the procurement and planning index developed for the\nrethinking power sector reform project (table 2). The country scores higher than the international average\nfor the various indicators used in the index.\n\n\nTable 2: Benchmarking institutional arrangements for power sector planning, 2015 11 [^11: For the detailed planning and procurement index, see the annex.]\n\n|Col1|Egypt|India|Morocco|Pakistan|International
benchmark|\n|---|---|---|---|---|---|\n|Planning and Procurement|82%|78%|61%|63%|71%|\n|Generation Planning|71%|57%|43%|29%|56%|\n|Procurement of Generation|100%|95%|100%|100%|85%|\n|Transmission Planning|75%|75%|50%|25%|74%|\n|Transmission Procurement|83%|83%|50%|100%|68%|\n\n\n\nNote: Scores based on index developed for the Rethinking Power Sector Reform Project.\n\n\nNonetheless two aspects can usefully be emphasized. First, sector institutions have not yet demonstrated\nthat they can sustain their effectiveness\n\nMention: \"the procurement and planning index\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"analyze\", \"summary\": \"Provides the 2015 planning and procurement scores used to benchmark Egypt against India, Morocco, Pakistan and the international average.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:001795:6:0", "occurrence_id": "e94840b85d24954a032dd2d0", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: The remainder of the paper is organized as follows. Section II presents the data used in our analysis. Section\nIII shows the results from our empirical analysis. Section IV concludes.\n\n**II. Data**\n\nThis section describes the construction of a new indicator of country rankings of technology adoption in\ntelecom. The section also presents other measures including telecom sector liberalization, foreign\nparticipation and quality of regulatory authority. Appendix Table 1 presents the list of variables used in our\nempirical analysis as well as sources. Appendix Table 2 presents basic descriptive statistics.\n\n**_Technology adoption ranking_**\n\nWe construct an index of the pace of technology adoption by ranking each country on how quickly it adopts\neach telecom technology standard. This constructed data set of ranking is a balanced data set for 198\ncountries for 40 years since 1980 3 [^3: Not all countries have been stable in the world telecom history. Take Croatia for example, which was part of\nYugoslavia (1945-1991), and became Republic of Croatia since 1991. Croatia has not been added in World Bank\nincome groups until 1992. However, its 1G technology was first launched in 1990, before it was formally Republic\nof Croatia. Similarly, Czech Republic claimed independence in 1993, not added to World Bank’s income groups\nuntil 1992, but with 1G technology first launched in 1990, before its independence. Hence, we ranked all countries\nfor all years since 1980, regardless of its political/constitutional independence.] . We construct the indicator based on the ranking of the speed in\ntechnology adoption from 1G through 5G. The source of data is based on Telegeography’s Spectrum\nLaunched Timeline, which lists the date at which each country has adopted a given technology standard.\n\nConsidering the balanced nature of the panel, the indicator precisely gives the ranking of any given country\nin the adoption of the telecom technology standard. Appendix Figure 1 shows the evolution of ranking for\neach country over the past decades.\n\nIn the following we illustrate\n\nMention: \"Spectrum\nLaunched Timeline\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"analyze\", \"summary\": \"Supplies per-country launch dates for each telecom standard used to construct the balanced technology adoption ranking.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:001857:4:1", "occurrence_id": "56afd4bf06e296216e12141a", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: jobs. Relatedly, a World Bank Group (WBG) study estimated that the costs of collusion\nand cartels in the road sector were between 8% and 60% of the contract value (World Bank 2011).\n\nBandiera et al. (2009) analyze purchases of standardized goods by Italian public bodies and find that some\npublic bodies pay systematically more than others for equivalent goods, and differences are correlated with\nthe governance structure. Several papers focus on common pitfalls in infrastructure procurement. Most\nnotably, Flyvbjerg et al. (2003) find that average cost overruns for roads are about 20% for projects in\nEurope and North America. The paper shows that cost estimates used in decision making are inaccurate,\nand that substantial cost escalation is the rule rather than the exception. Along the same line, Alexeeva et\nal. (2008, 2011a, 2011b) estimate cost overruns in the road sector in developing economies using the Roads\nCost Knowledge System (ROCKS) database. 7 [^7: In 1999, the Transport Unit of the World Bank Group (WBG) first developed ROCKS, an empirical study of road-related projects\ncompleted by the WBG. The study was designed to obtain average and range of unit costs based on historical data that could\nimprove the reliability of new cost estimates and reduce the risks generated by cost overruns. The database was updated in 2018\nwith WBG-financed projects between 2000 and 2017.]\n\nAnother branch of the literature tries to assess whether some features of the public procurement framework\nenhance desired outcomes. In this area, transparency plays a leading role. De Silva and others (2008)\nexamine the impact of a policy change by the Oklahoma Department of Transportation that led to the release\nof the state’s internal estimate of the costs to complete highway construction projects, and compare it with\nbidding in Texas, a state that had a uniform policy of revealing the same information during the same period.\nThe results show that, in comparison to Texas auctions, the average bid in\n\nMention: \"Roads\nCost Knowledge System\""}, {"role": "assistant", "content": "{\"role\": \"supporting\", \"usage_action\": \"inform\", \"summary\": \"Historical WBG road project unit-cost database cited as the basis for prior cost-overrun estimates in developing economies.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:001896:30:10", "occurrence_id": "e4343ca3d77a7796bb6c06e6", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: is slightly different to data from Op.Cit.|Total education expenditure and distribution by education level by World Bank staff using data from Ministry of Finance. (total is slightly different to data from Op.Cit.|Total education expenditure and distribution by education level by World Bank staff using data from Ministry of Finance. (total is slightly different to data from Op.Cit.|Total education expenditure and distribution by education level by World Bank staff using data from Ministry of Finance. (total is slightly different to data from Op.Cit.|Total education expenditure and distribution by education level by World Bank staff using data from Ministry of Finance. (total is slightly different to data from Op.Cit.|Total education expenditure and distribution by education level by World Bank staff using data from Ministry of Finance. (total is slightly different to data from Op.Cit.||\n\n\nMONGOLIA Distributional impact of taxes and transfers / November 2018 27\n\nMention: \"Ministry of Finance\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"analyze\", \"summary\": \"World Bank staff used these budget records to compute total education expenditure and its distribution by education level.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:002080:10:0", "occurrence_id": "d9d29a11a9efeb2c1b562ffe", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: _Source_ : Author’s tabulations using the Encuesta de Hogares de Propósitos Múltiples 2015 (EHPM).\n_Notes:_ Numbers represent the distribution of women's employment outcomes conditional on their spouse's (column\npercentage). The category \"Other\" includes wage employment, domestic work, and unemployment. The following\noutcomes for men were not included due to small sample size: public sector wage employment, unpaid status,\nunemployment, and inactive. This analysis is limited to households with a male head and a female spouse present.\nThey represent 67 percent of households and 73 percent of working-age individuals in the rural sector.\n\nThe use of proxy respondents can also elicit biased responses since they do not always provide accurate\ninformation for the other household members, which can result in an underestimation of women’s\nparticipation in work activities (Dixon 1982; Shah 1985; Rives and Yousefi 1997; Franck and Olsson 2014;\nBardasi et al 2011). In the case of the 2015 household survey in Honduras, however, men and women\nreport female participation at the same rates.\n\nIn 2015 few Honduran women in the rural sector reported being employed with most reporting being out\nof the labor force. From analyzing the household survey, several hypotheses can be drawn to explain this.\nFirst, intensity of household tasks is likely very high limiting the extent to which women can engage in\nactivities outside the home. Second, it is likely that agricultural activities performed by women are not\nbeing accurately captured by the survey. In fact, some of these may be considered household tasks. This\nis further supported by the observation that women are particularly unlikely to report being in the labor\nforce if they live with a husband who has an agricultural enterprise. Third, the lack of difference by gender\nof respondent suggests that both men and women are inaccurately reporting activities of women.\n\n#\n\nMention: \"Encuesta de Hogares de Propósitos Múltiples 2015\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"analyze\", \"summary\": \"Author tabulations from this survey give rural women employment outcomes conditional on spouse status and test proxy-response bias.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:002092:16:0", "occurrence_id": "8ba1b8bdb67d9732d59f9138", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: World Development Indicators of the World Bank. We also take trading partners’ GDP from\n\n\nWorld Development Indicators.\n\n\nTo test our hypothesis, we collect additional information at sector and product level. First, we use\n\n\nRauch’s (1999) classification of export products into differentiated and homogenous products.\n\n\nSecond, we use data on outstanding loans by sector, for the period 2015-2017 from the two largest\n\n\nexport finance schemes run on a concessional basis by the SBP: Export Finance Scheme (EFS)\n\n\nand Long-Term Finance Facility (LTFF), to proxy sectoral access to finance. Because these\n\n\nschemes target specific sectors and are by far the country’s largest export financing schemes, the\n\n\noutstanding loans by sector is a good indicator of the sectoral access to finance. 10 Third, we use\n\n\nsectoral measures of finance dependence as presented in Rajan and Zingales (1998). The indicators\n\n\nsignal the reliance on external funds to cover long-term investments and dependence from banks,\n\n\nas the fraction of capital expenditures not funded by internal funds. Fourth, we use data on labor\n\n\nintensity estimated for 63 sectors of the economy, based on a Social Accounting Matrix for 2013\n\n14, constructed by the International Food Policy Research Institute (IFPRI) for Pakistan. Fifth, we\n\n\nproxy dollar export prices with unit values, by calculating the ratio of export values and quantities\n\n\nat a six-digit disaggregation of the HS classification, from UN Comtrade.\n\n\n_Empirical Strategy_\n\n\nWe start analyzing the link between exports and the RER at aggregate levels. We model exports\n\n\nas a function of the RER and global income and use an error correction model (ECM) to analyze\n\n\n10 The EFS was put in motion in 1973 and provides short-term financing to exporters. The LTFF started in 2008 and\nprovides long-term financing for investments in plant and machinery for export purposes.\n\n\n15\n\nMention: \"World Development Indicators\""}, {"role": "assistant", "content": "{\"role\": \"supporting\", \"usage_action\": \"analyze\", \"summary\": \"Supplies domestic and trading-partner GDP series used as income controls in the export regressions.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:002125:27:0", "occurrence_id": "c62a36223da1c7fe2276459c", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: Figure 9. Policies to Stem Declining Potential Growth\nA. Global potential growth under reform\nscenarios scenarios\n\n\n\nPercent Pension reforms\n\n3.5 Labor market reforms\n\nEducation and health improvements\n\n3.0 Fill investment needs\n\nBaseline\n\n2.5\n\n\n\nB. EMDE potential growth under reform\nscenarios\n\nPercent Pension reforms\n\n5.5 Labor market reforms\n\nEducation and health improvements\n\n\n\n3.5\n\n3.0\n\n2.5\n\n2.0\n\n1.5\n\n1.0\n\n0.5\n\n0.0\n\n\n\n2013-17 2018-27 Reform impact\n\n\n\n2013-17 2018-27 Reform impact\n\n\n\n5.5\n\n5.0\n\n4.5\n\n4.0\n\n3.5\n\n3.0\n\n2.5\n\n2.0\n\n\n\nD. EMDE potential growth under reform\nscenarios\n\n\n\nC. EMDE potential growth under reform\nscenarios\n\n\n\nPercent Pension reforms\n\n10 Labor market reforms\n\nEducation and health improvements\n\n\n6\n\n\n\nPercent Pension reforms\n\n12 Labor market reforms\n\nEducation and health improvements\n\n10\n\nFill investment needs\n\n\n\n8\n\n6\n\n\n\n12\n\n10\n\n\n\n10\n\n\n\n8\n\n6\n\n4\n\n2\n\n0\n\n\n\nSource: World Bank estimates.\nNote: GDP-weighted averages.\n\n\n\n4\n\n2\n\n0\n\n\n26\n\nMention: \"World Bank estimates\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"analyze\", \"summary\": \"Model-based potential growth projections under pension, labour, education-health and investment reform scenarios plotted in the figures.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:002136:15:0", "occurrence_id": "0c071d802c1011edfadf99c2", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: As of September 1, 2020 the mean FPRAI stood at around 20 measures, but the variability is relatively high\n\n(standard deviation equals approximately 21 measures). The box plot in Figure 3 offers a closer look at the\n\ndistribution of the FPRAI across country groupings. High income and SAR are the country groupings that\n\nexhibit the highest group median FPRAI (around 32 measures). The group median FPRAI is under 10 in\n\nLAC, MENA, and SSA. The box plot further shows that variability within regions is significant in several\n\ngroups.\n\n\nFigure 4 presents scatter plots of the FPRAI against selected country characteristics. While these simple\n\ncorrelations show considerable noise, they suggest a positive association between the FPRAI and the\n\ncumulative number of COVID-19 cases per capita, population size, and economic development. The\n\ncorrelation between the FPRAI and the stringency of containment measures such as lockdown restrictions\n\nand restrictions on internal and external mobility appears limited. We will explore these correlations more\n\nclosely using Poisson regression in Section 4.3.\n\n\n**Figure 2. Financial Policy Response Activity Index (September 1** **st** **, 2020)**\n\n\nSource: World Bank COVID-19 Financial Sector Policy Response Database.\nNote: Colors in the map reflect the sorting of countries into quartiles of the distribution of FPRAI: from the highest activity (the darkest blue)\nto the lowest activity (the lighter blue).\n\n\n14\n\nMention: \"COVID-19 Financial Sector Policy Response Database\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"analyze\", \"summary\": \"Counts of national financial-sector policy measures from this database are used to compute the FPRAI mapped and correlated with country features.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:002310:2:0", "occurrence_id": "78d14747e0cfe8421076ee2f", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: ### **The Welfare Effects of Mobile Broadband Internet: Evidence from** **Nigeria 1**\n\n\n\nKalvin Bahia 2 [^2: GSMA]\n\n\n\nPau Castells 3 [^3: GSMA] Genaro Cruz 4 [^4: GSMA] Takaaki Masaki 5 [^5: World Bank]\n\n\n\nXavier Pedrós 6 [^6: GSMA] Tobias Pfutze 7 [^7: Florida International University] Carlos Rodríguez-Castelán 8 [^8: World Bank and IZA] Hernan Winkler 9 [^9: World Bank]\n\n\n.\n\n**Keywords:** Poverty, Household consumption, Mobile broadband, Africa, Nigeria\n**JEL codes:** D12, F63, I31, L86, O12\n\n\n1 The authors wish to thank Shubham Chaudhuri, Andrew Dabalen, Mark Dutz, Jonas Hjort, Samantha Lach, David\nMcKenzie, Chandni Raja, Viviane Sanfelice, Emmanuel Skoufias, Daniel Valderrama and Tara Vishwanath for their\ncomments and suggestions. The authors would also like to thank participants of the World Bank seminar organized by the\nPoverty and Equity and Digital Development Global Practices. The authors are also thankful to Gero Carletto and Siobhan\nMurray from the World Bank LSMS team for their support with data integration, as well as Aibek Baibagysh and Abul\nAzad from the World Bank Poverty and Equity Global Practice for their support on building the consumption aggregate\nfor Nigeria GHS. The authors would also like to thank Mobile Network Operators in Nigeria for sharing their mobile\nnetwork infrastructure data. This study received funding from the Digital Development Partnership and from UK aid.\nThe findings, interpretations, and conclusions expressed in this paper are entirely those of the authors. They do not\nnecessarily represent the views of the International Bank for Reconstruction and Development\n\nMention: \"Mobile Network Operators in Nigeria\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"Shared mobile network infrastructure data used to characterise broadband internet coverage in the study area.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:002334:30:7", "occurrence_id": "a404745d2c060f8e8cd5e516", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: , we calculate implied changes in the values **V** ¨ as in equation (35).\n\nAt the end of the labor loop, we calculate **L** which updates the guess for **L** . Using the updated labor\n\n\n\nallocation **L**, the initial guess of\n\n\n\n\n- **w** �� 1 _,_ **w** �� _−_ 1 _,_ - **b**, and the solved **P** �, we calculate the excess demand\n\n\n\nof each factor following Equations (37)-(39). We update the guess of\n\n\n\n\n- **w** �� 1 _,_ **w** �� _−_ 1 _,_ - **b** and repeat the\n\n\n\nalgorithm until all excess demands of factors become close to zero at every period.\n\n\n**5.3** **Taking** **the** **Model** **to** **the** **Data**\n\n\nWe calibrate the model to the base year 2003 before solving for changes. The model is quantified for\n\n21 countries including Brazil, plus the rest of the world, thus, _N_ ¯ = 22. 44 Taking advantage of the\n\n\ndetailed data, RAIS, we assume that country 1 is Brazil where there are multiple regions. We use\n\n\nthe same definition of the labor market as before, with three sectors—agricultural, manufacturing,\n\n\n\nand services—and 558 microregions. We use the average of estimates for _C_ � _t_ 1\n\n\n\n_t_ 1\n\nMention: \"RAIS\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"analyze\", \"summary\": \"Detailed sectoral and microregion labor records used to calibrate the model for Brazil in the 2003 base year.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:002401:55:2", "occurrence_id": "9f9744133c484ddfde9cdb3d", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: EAs 433 290 143 433 290 143 433 290 143\nN 12937 9337 3600 12937 9337 3600 12937 9337 3600\n_Notes:_ This table provides estimates of the impacts of logarithm of refugee intensity on logarithm (first three columns) or “started log” (last six columns) of the components of\ntotal household consumption expenditure per adult equivalent. Household sample weights from ESS2 applied. The first, middle, and last three columns report results for food,\neducation, and other non-food per adult equivalent consumption expenditures, respectively. Columns labeled (1), (2), and (3) report results for all, rural, and urban households,\nrespectively. All columns control for household (HH) FEs, round FEs, and 12 time-varying characteristics. The coefficient estimates for these 12 characteristics variables are\nnot reported here, but can be available on request. Robust standard errors clustered at EA level are given in parenthesis. Asterisks: *, **, and *** indicate statistical significance\nat 10%, 5%, and 1% levels, respectively.\n\n\n54\n\nMention: \"ESS2\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"analyze\", \"summary\": \"Supplies the household consumption expenditure panels and sample weights used to estimate effects of refugee intensity.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:002405:25:0", "occurrence_id": "db2064197d64aa15262913b0", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: **Figure 25: Instagram posts:** 01/2016 - 10/2018\n\n\n\n**Figure 26: Protected areas:** 2016\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\nSource: Author´s calculations using World Bank data. Source: Author´s calculations using UNWTO and WDI.\n\n**Figure 27: Protected area and other measures from Baldi et al. (2017)**\n\n\n\n24\n\nMention: \"World Bank data\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"analyze\", \"summary\": \"Cited in a figure source line as the data behind one of the authors calculations in the appendix exhibits.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:002487:3:4", "occurrence_id": "f71db7a1f9bb8e772b12599e", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: PNADs are a series of\nnationally representative household surveys conducted more or less annually since 1976,\nusing a consistent methodology by the Instituto Brasileiro de Geografia e Estastistica (IBGE).\nAll members of each household over ten years in age are asked detailed questions concerning\ntheir labor market activity during one week in September. Each survey covers a nationally\nrepresentative sample of households. The sample size has risen progressively from 69,066\nhouseholds in 1988, to 94,171 in 1992 and 112,434 in 1998. The present paper draws from\nthese households the sample of employed men between the ages of 18 and 65, who report\nearnings and hours of work data and information on human capital and the other controls\nused for estimation purposes. This results in a sample of 65,002 in 1988, 67,880 in 1992 and\n74,003 in 1998. The 63% increase in the number of households sampled over the decade\n\nMention: \"PNADs\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"analyze\", \"summary\": \"Provides the nationally representative household samples from which employed men aged 18-65 with earnings and hours data are drawn.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:002512:25:0", "occurrence_id": "6eda23b525ab22ca89f7f34d", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: the network needed to serve a given community, costs are further reduced by relying on community\nvolunteer labor to construct the systems.\n\n**3.5** **Obstacles to expanding coverage** **20** [^20: See Annex D for an explanation of the definitions of coverage, take-up, and availability.]\n\nIn order to develop a strategy for reaching unserved households, it is important to understand the reasons\nwhy these households remain unconnected at present. Broadly speaking, there are two possible\nexplanations. The first explanation is that the service is simply not available in the communities where\nthey live; this is essentially a supply-side problem that requires increased investment in infrastructure\nexpansion. The second explanation is that the households fail to take-up the service even when it is\navailable in the community; this is essentially a demand-side problem that may be less costly to\novercome in investment terms, but is perhaps more complex to deal with requiring a careful diagnosis\nand considered policy response.\n\nIt is possible to capture this difference by comparing two indices (Table 3.12). The availability index\ngives the percentage of households that live in communities where the service is available, while the\nuptake index shows the percentage of households who live in communities where the service is available\n_who actually connect to the service_ _21_ [^21: It is important to clarify the definition of ‘community’. The sampling frame of the ENCOVI 2000 was based on ‘unidades\nprimarias de muestro’, which are blocks of 50 contiguous households from which 10-12 households were sampled by the\nsurvey.] . The results show that electricity has the highest uptake index of\nany of the services at 88%, followed by water, sewerage and fixed telephone. Not only are services more\nlikely to be available in urban areas, but urban households are substantially more likely to take-up these\nservices when they are available.\n\n\n**Table 3.12: Comparison of availability and uptake\n\nMention: \"ENCOVI 2000\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"analyze\", \"summary\": \"Its primary sampling units define the communities used to compute service availability and uptake indices.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:002556:17:0", "occurrence_id": "5c6dbf3f63d18903fc400c85", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: 16\n\n\nsignificance. Variables that remain are GDP per capita, secondary school enrolment ratio\n\n\n(or human capital investment), annual population growth and gross capital formation as\n\n\nratio of GDP (which is considered as investment).\n\n\nIn their study, Davoodi and Zou used five-year and ten-year average data to smooth over\n\n\nshort-term effects. Here, with a limited sample that covers only three years for each\n\n\ncross-section, no such average could be used. However, centred three-year moving\n\naverages * have been applied on dependent and control variables to minimize any short\n\nterm effects. What is estimated here is not the relation between decentralization and\n\n\ngrowth on a short-term or year-to-year basis. It is the relation between decentralization\n\n\nand growth on an average medium-term basis.\n\n\nIn the Oates model, the dependent variable ( _Yit_ ) is the public sector size measured as total\n\n\naggregate government current expenditure as a share of GDP. In the original model, two\n\nproxies for decentralization (θ _it_ ) were used: revenue share and expenditure share. Again,\n\n\nmeasures of decentralization of Ebel and Yilmaz and the new measures of this study will\n\nbe added as θ _it_ . In this model, only countries fixed effects (α _i_ ) will be considered. Joint\n\n\nF-test on fixed effects reveals that time dummy coefficients are not significant, while\n\n\ncountry dummies are significant. The set of control variables ( _X_ _it_ ) will be the same as in\n\n\nthe original study, including urban population ratio, GDP per capita and total population.\n\n\nBecause the dependent variable in this model is computed from the OECD data, which\n\n\nare available for only three-year period, it is impossible to use three-year moving\n\n\naverages to smoothen for short-term effects. It must be notice dough that no average data\n\n\nwas used in the Oates study.\n\nMention: \"OECD data\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"analyze\", \"summary\": \"Supplies government current expenditure as a share of GDP, the dependent variable in the Oates-type model.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:002614:8:0", "occurrence_id": "380c477d5e4ced27ce175059", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: directly. 13 [^13: The 54th round of National Sample Survey of India included two household questionnaire modules that\nwere asked to different households.] Instead, we proxy education by a literacy indicator about whether or not a\nmember of the household reads the newspaper.\n\nAppendix tables A1 and A2 present data on the differences in various village and\nhousehold characteristics between participants in community forestry and non-participants.\nThe typical participant in community forestry is a poor household that lives on the fringes\nof forests (see Table A.2). Over half the participating households are agricultural laborers,\nwhile only 3% are headed by females. Eleven percent of these households have at least 1\nliterate member. Some 38% of participants belong to scheduled tribes, 7% to scheduled\ncastes and another 39% to other backward classes. Participant households, on average,\nown less than 1 ha of land, but 22% own an asset such as a radio or TV or telephone.\n\n#### **4. Methodology**\n\nOur paper seeks to answer two key questions: a) What are the determinants of participation\nat the village and household levels in community forestry? and, b) What are the impacts of\nparticipation on household fuelwood consumption?\n\nWe treat domestic consumption of fuelwood as an indicator of dependence on forest\nresources for subsistence as well as a measure of household welfare. Household and\nvillage participation in CF affect fuelwood use. This relationship exists because in some\ncases community forestry restricts forest use, and, in other cases, it results in forest\nmanagement activities that increase access to fuelwood. Further, households that are\ndependent on scarce fuelwood are more likely to participate. Thus, we model jointly\nhousehold fuelwood consumption and participation in CF.\n\nIn the following paragraphs, we first discuss the determinants of village level participation\nin community forestry. This is followed by a discussion of household participation and\nimpacts on fuelwood consumption. We use three methods to assess impacts – simple\ncomparison of means, maximum\n\nMention: \"National Sample Survey of India\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"analyze\", \"summary\": \"Supplies the village and household characteristics, literacy proxy and fuelwood consumption used in the community forestry analysis.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:002712:2:1", "occurrence_id": "12c2081ab28cdb47ef6c562f", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: rate, e.o.p., % 10.3 10.7 13.8 16.3 19.4 20.0 20.0\nPoverty headcount, % of population 14.7 13.1 14.3 14,8 15.6 16.6 . .\n\nGeneral gov’t expenditures, % of GDP 43.5 41.9 42.7 40.5 43.3 44.0 46.3\nGeneral gov’t budget balance, % of GDP -2.8 -2.4 -3.1 -3.0 -4.9 -5.9 -6.6\nConsumer price inflation, % y/y 13.2 8.6 7.3 10.1 5.5 1.9 0.8\nNBP refinancing rate, % 28.0 21.0 21.5 24.0 16.5 9.75 6.0\nCurrent account deficit, % of GDP -3.7 -4.1 -7.6 -6.0 -2.9 -2.6 -2.0\nExternal debt, % of GDP 34.6 35.2 41.6 39.8 37.7 41.7 47.6\n**e.o.p – end of period, 2003 – forecast or latest available**\n\n_Source_ : GUS data.\n\n\n**The Factors Behind the Trends in Growth**\n\n\nWhile many factors can account for Poland’s growth record - including consistent economic\npolicies despite frequent changes of government - the main economic factor has been that Poland\nmanaged the macro-micro policy linkages well.\n\nMention: \"GUS data\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"analyze\", \"summary\": \"Official national statistics supplying the growth, poverty, fiscal and external accounts series in the table.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:002942:26:0", "occurrence_id": "27a86340158c0f0f6dc78828", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: **Table 1: Descriptive Statistics**\n\nMean Std Deviation P25 P50 P75\n\n\nEmployment Growth 0.17 0.91 -0.34 0.14 0.69\nConcentration 0.10 0.16 0.01 0.03 0.10\nCompetition 28.2 44.0 6.5 15.1 33.4\nDiversity 4.8 2.9 2.6 4.1 6.1\nAverage cost of labor 7.18 0.36 7.01 7.17 7.37\nEmployment in the region 6,974 10,986 566 2,313 9,943\nEstimated Productivity Growth 2.9 2.0 2.1 2.6 3.2\n\n\nSource: \"Quadros de Pessoal\"\n\nNotes: All the variables except Employment in the region, are averages for the region-sector, where region stands for \"concelho\" and sector for the two-digit ISIC\nsectors. Growth rates are computed between 1985 and 1994 and the other variables are for 1985. All the statistics are computed excluding the region-sectors with\nemployment growth rates smaller than 3 standard deviations from the average. Concentration is the employment's share in the total employment of the region,\nCompetition is the Hirschman-Herfindhal index, Diversity is the Hirschman-Herfindhal index for diversity, Average cost of labor is the log of average labor costs\nper employee (in Euros), Employment in the region is the total number of employees in the region and Estimated Productivity Growth is the estimated\nproductivity using the formula derived in Section 2.3.\n\nMention: \"Quadros de Pessoal\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"analyze\", \"summary\": \"Employer records behind the region-sector descriptive statistics on employment growth, concentration, diversity and labor cost.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:002951:28:0", "occurrence_id": "f5b02da0e911a409c92f1624", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: Aside from information on antidumping revocations (if any exist), there is nothing systematically missing\n\n\nfrom the Indian data for all investigations. Nevertheless, for any given investigation there may some\n\n\nmissing elements such as dates, decisions or even product codes.\n\n\n**3.8** **South Korea (KOR)**\n\n\nIn South Korea, the Korean Trade Commission is wholly responsible for anti-dumping investigations.\n\n\nThis quasi-judicial agency determines if dumping and/or injury has occurred for each case. The initiation\n\n\nand outcomes of each investigation are published in the Korean Official Gazette (Gwanbo). The Korean\n\n\nTrade Commission also publishes information about ongoing antidumping cases online at its website.\n\n\nThe source of the data was hard-copies of antidumping documents in Korean provided by the Korean\n\n\nTrade Commission. Summary information about Korea’s antidumping process is available on the Korean\n\n\nTrade Commission’s website.\n\n\nIn addition to the standard data described in section 2, the Korean file contains additional data\n\n\ndescribed in the table below.\n\n\n**Table 3.8.1 : Additional Korean Data Included in AD-KOR-v1.0.xls**\n**Column** **Variable Name** **Description**\n**In AD-KOR-Master :**\n\nThe maximum (or range) of preliminary anti-dumping duty (duties)\n**U.** **P_AD_DUTY**\nimposed\n**V.** **F_AD_DUTY** The maximum (or range) of final anti-dumping duty (duties) imposed\n\nThe range and schedule of anti-dumping duties maintained after a sunset\n**W.** **REVIEW_DUTY**\nreview\n**X\n\nMention: \"Korean file\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"curate\", \"summary\": \"Compiled antidumping file containing extra columns on preliminary, final and sunset-review duties beyond the standard variables.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:003253:33:4", "occurrence_id": "8e06d2f107eb4349e1ccdeee", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: .60\n29.44\n4.96\n\n\n\n\n - Employed 69.28 94.27 47.26\n - Employed with secondary education 78.82 93.03 64.20\n\n - Out of LF/unemployed 30.72 5.73 52.74\n\n - Share of wage employment 48.72 53.61 40.14\n\n - Share of self-employed 44.16 42.81 46.54\n\n - Share of unpaid employment/other 7.12 3.58 13.32\nWith secondary education:\n\n - Share of wage employment 62.73 65.60 58.46\n\n - Share of self-employment 29.88 29.44 30.54\n\n- Share of unpaid employment/other 6.13 4.96 7.88\n\nSource: _ENVCOVI_ 2000\n\n\n\n34\n\nMention: \"_ENVCOVI_ 2000\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"analyze\", \"summary\": \"Supplies the employment status and wage, self-employment and unpaid work shares reported by education level.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:003263:30:0", "occurrence_id": "faf8b611fe23190a4fc0b2d1", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: Table 4: Estimation of Net Migration using UN sources – Example of Morocco, 1950-2000\n\n\n____________________________________________________________________\n\n\nYear t Total Birth Death Natural Expected Net\n\n\nPopulation Rate Rate Increase Population Migration\n\n\n[t,t+5] [t,t+5] [t,t+5] [t,t+5]\n\n\n(1) (2) (3) (4) (5) (6)\n\n\n____________________________________________________________________\n\n\n1950 8953 0,0504 0,0257 0,0247 8953 2\n\n\n1955 10132 0,0504 0,0227 0,0277 10130 -11\n\n\n1960 11626 0,0501 0,0196 0,0305 11637 -218\n\n\n1965 13323 0,0482 0,0174 0,0308 13541 -231\n\n\n1970 15310 0,0456 0,0157 0,0299 15541 -474\n\n\n1975 17305 0,0394 0,013 0,0264 17779 -365\n\n\n1980 19382 0,0371 0,0114 0,0257 19747 -45\n\n\n1985 21995 0,0323 0,0089 0,0234 22040 -161\n\n\n1990 24564 0,0267 0,0074 0,0193 24725 -214\n\n\n1995\n\nMention: \"UN sources\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"analyze\", \"summary\": \"Supplies population, birth and death rates from which expected population and the net migration residual are computed.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:003865:18:0", "occurrence_id": "2fc7e650896b255c8af39c10", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: Government of Moldova, 2004. Policy and Poverty Impact Report. Ministry of Economy and Trade.\n\n\n_Mimeo_ .\n\n\nGovernment of Moldova, 2005. Medium Term Expenditure Framework 2006-2008. Ministry of\n\n\nFinance. _Mimeo_ .\n\n\nImai, Kosuke, King, Gary, Stuart, Elizabeth, 2006. The Balance Test Fallacy in Matching Methods\n\n\nfor Causal Inference. _Wired at: polmeth.wustl.edu/_\n\n\nLokshin, Michael, and Ravallion, Martin, 2000. Welfare impacts of the 1998 financial crisis in\n\n\nRussia and the response of the public safety net. _The Economics of Transition 8, 2, 269-295_ .\n\n\nLeuven, Edwin and Sianesi, Barbara, 2003. PSMATCH2: Stata module to perform full Mahalanobis\n\n\nand propensity score matching, common support graphing, and covariate imbalance testing. _Wired_\n\n\n_[at: http://ideas.repec.org/c/boc/bocode/s432001.html](http://ideas.repec.org/c/boc/bocode/s432001.html)_ .\n\n\nLokshin, Michael, and Yemtsov, Ruslan, 2003. Evaluating the impact of infrastructure rehabilitation\n\n\nprojects on household welfare in rural Georgia. _World Bank Policy Research_ _Working Paper 3155_ .\n\n\nMilanovic, Branko, 2000. Social transfers and social assistance: An empirical analysis using\n\n\nLatvian household survey data. _World Bank Policy Research Working Paper 2328_ .\n\n\nOkrasa,Wlodzimierz, 1999a. The dynamics of poverty and the effectiveness of Poland’s safety net\n\n\n(1993-1996). _World Bank Policy Research Working Paper 2221_ .\n\n\nOkrasa, Wlodzimierz, 1999b. Who avoids and who escapes from poverty during the transition?\n\n\nEvidence\n\nMention: \"Latvian household survey data\""}, {"role": "assistant", "content": "{\"role\": \"background\", \"usage_action\": \"inform\", \"summary\": \"Household survey behind a cited study on social transfers and assistance, listed only in the references.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:004054:6:0", "occurrence_id": "fe57ef998ece4014d3b63c11", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: rural customers all over Bangladesh (REB 2007). Since the inception of REB, rural\n\n\nelectrification has grown significantly – starting from less than 10 percent connectivity in\n\n1977, about 61 percent villages have received electricity by 2007. 2 [^2: Our data, which were collected in 2005, show a 58 percent connectivity at village level in Bangladesh.] Under REB’s program,\n\n\nabout 800,000 new rural customers get electricity every year, which is phenomenal for a poor\n\ncountry like Bangladesh. The REB consumers are mostly domestic users of electricity (85\n\n\npercent), although industrial and commercial customers are also served, including those\n\nneeding connection for irrigation pumps. REB plans to cover 75,000 villages of Bangladesh\n\nby the year 2020. 3 [^3: According 1991 census, total number of villages in Bangladesh is about 86,000. The 11,000 villages that are\nnot included in REB’s plan are covered by PDB, DESA and other distributors.] A detailed breakdown of rural electrification rates by region is given later\n\nwhen we discuss the sample data.\n\n\nThe rural electrification program of REB is often viewed as one of the most\n\nsuccessful government programs in Bangladesh. A 2004 study of electricity distribution and\n\n\ntransmission in Bangladesh found that system loss in 2000 for REB was much lower (16\n\npercent) than that for other major electricity distribution bodies – PDB (28 percent), DESA\n\n(30 percent) and DESCO (33 percent) (Alam and others 2004). 4 [^4: System loss is the difference between the quantity produced (generated) and the actual quantity sold, and is\nexpressed as a percentage of the quantity produced. It is a widely accepted measure of the efficiency of the\ndistribution system.] This is because the usual\n\ndistributional problems that plague other Bangladeshi distributors (theft, non-payment of bill\n\n\nby influential subscribers, illegal connection, over-billing, etc.\n\nMention: \"1991 census\""}, {"role": "assistant", "content": "{\"role\": \"supporting\", \"usage_action\": \"inform\", \"summary\": \"Supplies the total number of villages, used to show how many remain outside the electrification plan.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:004289:2:1", "occurrence_id": "449681c6b648ad94f5e83384", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: Barro, Eli Berman, Edward Glaeser, Timothy Guinnane,\nMonica Das Gupta, Partha Dasgupta, Larry Iannaccone, Siddiq Osmani, Abusaleh Shariff, Chander Velu,\nDavid Voas, and to participants at the American Economic Association 2007 meetings in Chicago, the\n‘Religion, Economics and Culture’ 2004 Annual Meetings in Kansas City, Missouri, and the 2005 ESRC\nseminar on ‘Demography and Religion’ in Lancaster, UK. We are also grateful to Sarina Siddhanti for\nexcellent research assistance, We are especially grateful to the Editor and two anonymous referees for their\ninvaluable comments.\n\n_†_ Faculty of Economics and Politics, University of Ulster, Northern Ireland. vk.borooah@ulst.ac.uk\n\n_‡_ Development Economics Research Group, The World Bank. qdo@worldbank.org\n_§_ Corresponding author: Faculty of Economics and St. Catharine’s College, University of Cambridge,\nSidgwick Avenue, Cambridge CB3 9DD, United Kingdom. Tel: 44 1223 335257; Fax: 44 1223 335475;\nEmail: Sriya.Iyer@econ.cam.ac.uk\n\n_¶_ The School of Foreign Service, Georgetown University. shareen.joshi@gmail.com\n\n1The estimate of the number of missing women is based on comparisons with Europe and North America\nwhich have 1050 females per 1000 males.\n\n2An often-cited figure from the National Family Health Survey conducted in 1998-99, shows that the\nTotal Fertility Rate (TFR) for Hindus and Muslims was 2.8 and 3.6 respectively.\n\n\n1\n\nMention: \"the National Family Health Survey\""}, {"role": "assistant", "content": "{\"role\": \"background\", \"usage_action\": \"inform\", \"summary\": \"Footnote cites its total fertility rates for Hindus and Muslims as a commonly quoted reference point.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:004322:5:0", "occurrence_id": "e07b27056351f4f791217d9f", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: - 4 \n\n200 banks from 37 countries analyzed in DDT). This is not just a simple increase in sample size:\n\n\nthe sample of rated banks was not a representative sample, since rated banks tend to be larger,\n\n\nmore internationally active, and more likely to adhere to international accounting standards.\n\n\nFrom a policy point of view, we would like to investigate the effect on all types of banks\n\n\noperating in different country circumstances, rather than a select subgroup. In this study, the\n\n\nricher sample allows us to explore whether the relationship between BCPs and bank soundness\n\n\nvaries across different types of banks.\n\n\nAll in all, we do not find support for the hypothesis that better compliance with BCPs\n\n\nresults in sounder banks as measured by Z-scores. This result holds after controlling for the\n\n\nmacroeconomic environment, institutional quality, and bank characteristics. We also fail to find\n\n\na significant relationship when we consider different samples, such a sample of rated banks only,\n\n\na sample including only commercial banks, and samples including only the largest financial\n\n\ninstitutions. In an additional test, we calculate aggregate Z-scores at the country level to try to\n\n\ncapture the stability of the system as a while rather than that of individual banks, but also this\n\n\nmeasure of soundness is not significantly related to overall BCP compliance.\n\n\nWhen we explore the relationship between soundness and compliance with specific\n\n\ngroups of principles, which refer to separate areas of prudential supervision and regulation, we\n\n\ncontinue to find no evidence that good compliance is related to improved soundness. If anything,\n\n\nwe find that stronger compliance with principles related to the power of supervisors to license\n\n\nbanks and regulate market structure are associated with riskier banks.\n\n\nWhile these results cast doubts on whether international efforts to improve financial\n\n\nregulation and supervision should continue to place a strong emphasis on BCPs, a number of\n\n\n_caveats_ are in order. First, insignificant results may simply indicate that accounting-based\n\n\nmeasures, such as Z-scores, do not adequately capture bank soundness, especially for\n\nMention: \"DDT\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"analyze\", \"summary\": \"Bank-level database providing the 200 banks from 37 countries that widen the sample beyond rated banks.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:004372:14:0", "occurrence_id": "371f7675c1b0201bd61c5539", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: 30\n\n\n25\n\n\n20\n\n\n15\n\n\n10\n\n\n5\n\n\n0\n\n\n-5\n\n\n-10\n\n\n\n120\n\n\n110\n\n\n100\n\n\n90\n\n\n80\n\n\n70\n\n\n60\n\n\n50\n\n\n40\n\n\n\n**Figure 4:** Exchange rate and price developments, 2001-2008\n\n\n\n\n\n\n\n_Source_ : Authors’ calculation based on IMF data.\n\nIn addition, goods exports, dominated by coffee and tea, do not seem to have suffered, likely due\nto their dependence on non-price factors (such as infrastructure and supply constraints) rather\nthan prices and exchange rates. 11 [^11: See also Foster and Killick (2006).] In fact, Burundi’s export performance improved from an\naverage of 6.1 percent of GDP during 2000-2004 to 6.4 percent of GDP during 2005-2008,\nindicating that the appreciation of the real effective exchange rate has not been detrimental to\nexports. 12 [^12: The share of other, non-traditional exports remained fairly constant.] Dutch disease does not seem to be a significant problem in Burundi so far. This is\nconfirmed by the IMF’s assessment of Burundi’s exchange rate, which concluded that the real\nexchange rate has been broadly in line with economic fundamentals (IMF, 2008).\n\n\n**4.** **Allocation of increased aid and impact on growth**\n\n\nBurundi has not experienced the expected post-conflict growth spike seen in other post-conflict\ncountries. This is despite the high levels of aid Burundi has been receiving, most of which has\nbeen spent, as established in the previous section. Real GDP growth averaged only 3.0 percent\nbetween 2001 and 2008 and real GDP per capita declined on average by 0.3 percent. This section\nanalyses the allocation of spending and tries to determine the linkages between aid, spending in\ndifferent sectors, and economic growth. Of course, aid is only one of many factors affecting\ngrowth as shown by an extensive literature on determinants and factors of growth. We also\nexamine how the composition of the domestically financed budget has contributed to Burundi\n\nMention: \"IMF data\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"analyze\", \"summary\": \"Supplies the exchange rate and price series plotted for 2001-2008 and used in the IMF exchange-rate assessment.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:004407:7:1", "occurrence_id": "c3dacf88454909b4fcd48ce2", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: ations
R-squared|
267.6***
(22.72)
409.0***
(4.75)
No
742
0.419|
330.0***
(13.96)
201.2***
(2.48)
Yes
742
0.407|\n\n\n\nt-statistics in parentheses\n\n*** p<0.01, ** p<0.05, * p<0.1\n\n\n**2.2 Estimating Undernourishment**\n\n\nAfter estimating the calorie-income relationship, we require caloric requirements that\n\n\ndefine the threshold for undernourishment by region. These numbers derived from FAO\n\nMention: \"FAO\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"inform\", \"summary\": \"Supplies the regional caloric requirements that define the undernourishment threshold in the estimates.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:004621:7:0", "occurrence_id": "ec7e709b045b4efb82e87a36", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: 6\n\n\nremittances, and consistent definitions of remittance variables could not be developed for all four\n\n\nwaves of the IFLS survey, the focus here is on the last two waves of the survey, IFLS 3 (2000)\n\n\nand IFLS 4 (2007). These two waves include a total of 5,301 urban and rural households. While\n\n\nthe IFLS Survey was never designed to be nationally representative, the last two waves of the\n\n\nsurvey do include households from 19 of Indonesia’s 33 provinces. In terms of data collected,\n\n\nthe IFLS Survey was comprehensive, collecting detailed information on a wide range of topics,\n\n\nincluding expenditure, education, health, nutrition, financial assets, household enterprises and\n\n\nremittances.\n\n\nIt should, however, be emphasized that the IFLS Survey was not designed as a migration\n\n\nor remittances survey. In fact, it collected very limited information on these topics. With respect\n\n\nto international migration, the survey collected only limited information on migrants who have\n\n\nbeen gone from the household for more than one year: their age, education or income earned\n\n\naway from home. 2 This means that limited data are available on the characteristics of most\n\n\ninternational migrants who are currently living outside of the household. With respect to\n\n\ninternational remittances, the IFLS Survey only contains information from three types of\n\n\nquestions: (1) Does your household receive remittances from spouse, parents or children? (2)\n\n\nWhere do these people sending remittances live? and (3) How much (remittance) money did\n\n\nyour household receive in the past 12 months? The lack of data on individual migrant\n\n\ncharacteristics in the IFLS survey is unfortunate, but the presence of detailed information on\n\n\nremittances and household expenditures makes it possible to use responses in the survey to\n\n\nexamine the impact of remittances on poverty, inequality and household expenditure behavior.\n\n\nSince the focus here is on remittances, it is important to clarify how these income\n\n\ntransfers are measured and defined. Each household that\n\nMention: \"the IFLS survey\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"analyze\", \"summary\": \"Waves 3 and 4 supply household expenditure, asset and remittance information for 5,301 urban and rural households.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:005013:8:0", "occurrence_id": "81c66dbf56f8333336e1745a", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: portfolio decelerated in 2004, on the basis of macroeconomic variables, the model would have\njustified a decline in proportion to GDP. This deviation from the equilibrium path, however, can\nbe still explained by convergence. In turn, it is hard to explain a decline in the equilibrium path\ndriven by high nominal interest rates in the case of a transition economy. Consequently, in the\nreview period there was no credit boom in the case of households; however, the risk of its\nemergence was greater in this sector than in the corporate sector.\n\n\n**Chart 4. Net change of loans outstanding to households by currency breakdown**\n\n\n\n\n\n\n\n\n\nSource: MNB. Note: ―Banks‖ includes banks, branches, and cooperative credit institutions.\n\n\n**Chart 5. Estimation of equilibrium credit/GDP of households**\n\n\n\n\n\n\n\n\n\nSource: Kiss et al. (2006); authors‘ calculations.\n\n\n**_II. 2. Period of excessive credit expansion (2004–2008)_**\n\n\n**_Corporate segment_**\n\n\nThe year 2004 marked the end of the era of state-subsidized, forint-based housing loans\npreviously dominant in household lending, and banks started to offer new, foreign-currency\n\n7\n\nMention: \"MNB\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"Central bank statistics behind the chart of net changes in household loans by currency.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:005141:10:1", "occurrence_id": "54564c1d4e8b6db1c262b0d9", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: variables of interest by gender. The “pooled sample”\nincludes Lesotho and Swaziland only because in the empirical analysis we will first show results for\nLesotho and Swaziland and subsequently compare them with Zimbabwe. In addition to HIV\ninfection, we use behaviors and attitudes related to HIV prevention as dependent variables, such as\nabstinence, extra-marital sexual relationships and condom use. These sexual behaviors are at the\nheart of most prevention efforts, including the so-called \"ABC\" strategy (\"Abstain, Be Faithful and\nuse a Condom\"), the most widespread information campaign on HIV prevention in many African\ncountries. Abstinence, defined as not having any sexual intercourse in the last year, is generally\nhigher for men than for women and is much lower in Lesotho than in the other countries. More\nprecisely, the survey reports that about 34 percent of men and about 30 percent of women had no\nsexual relationships in the last year. This may be driven by the fact that men tend to marry later.\nIndeed, while the survey does not include age at first marriage, we observe that the average age for\ncurrently married men in the sample is 37 years, compared to 31 years for women.\n\nExtra-marital intercourses, measured with an indicator equal to one if currently married\nrespondents have at least one sexual relationship outside the marriage in the last 12 months, are\nfrequently reported in all three countries and are more than 10 percentage points greater for men\nthan for women. The highest percentage of extra-marital relationships is reported in Lesotho:\nfigures from the DHS suggest that 29.8 percent of currently married men and 12.7 percent of\ncurrently married women had non-marital sexual relationships in the last year.\n\n\n9\n\nMention: \"the DHS\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"analyze\", \"summary\": \"Supplies the reported rates of extra-marital sexual relationships used as HIV-prevention outcome variables.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:005166:7:0", "occurrence_id": "0363266ebf6f11db914c2405", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: 14 workers also face high severance pay costs if they lay workers off. Finally, firms with revenues\n\n\nexceeding 500,000 LKR per quarter or 1.8 million LKR per year must also register for VAT. The VAT\n\n\ntax rate is 20% of value-added for most goods, with producers of some goods paying a lower 10% rate\n\n\nand others exempt entirely.\n\n\n**2.1 Formality Levels in Practice**\n\n\nFigure 1 summarizes the percentage of firms which reported being registered with each of the\n\n\nfour government entities according to the number of paid employees in the firm. The data come from the\n\n\nbaseline of the Sri Lanka Longitudinal Survey of Enterprises (SLLSE), collected by the authors between\n\n\nJanuary and May 2008. The survey contains 2,865 enterprises, and is representative of enterprises in the\n\n\n31 largest cities and towns (outside the Northern province which was inaccessible due to civil conflict). A\n\n\ndoor-to-door listing exercise of households was carried out, to ensure the survey was able to detect both\n\n\nformal and informal firms. The vast majority of enterprises have zero paid workers, and we see that only\n\n\n23 percent of these non-employers are registered at the local (P.S. / UCMC) level and only 20 percent are\n\n\nregistered at the DS Division level. Less than 1 percent of the non-employers report being registered for\n\n\nVAT. Registration at all four levels rises quickly with firm size, so that 75 percent of those with 5 paid\n\n\nemployees are registered with the P.S. or UCMC and 68 percent with the DS. However, the percent\n\n\nregistered then appears to plateau, with approximately 70 to 80 percent registered with the DS for firms\n\n\nwith 6 to 20 employees. There are fewer firms in the SLLSE sample as the number of paid workers\n\n\ngrows, making the point estimates more variable at larger firm sizes. Registration of at least some of the\n\n\nworkers of the firm with EPF/ETF is less common\n\nMention: \"Sri Lanka Longitudinal Survey of Enterprises\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"analyze\", \"summary\": \"Baseline of 2,865 enterprises supplying registration status with four government entities by firm size.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:005178:15:0", "occurrence_id": "35b978f544c037ad759af3f6", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: been recently upheld by the Supreme Court. 20 [^20: The Supreme Court has refused to stay a recent Karnataka High Court verdict that affirms that the Central\nGovernment is liable to pay wages in tandem with the state minimum wage rate.] On the other hand, concerns have been raised that\n\n\nthe wage rate on MGNREGS is being set too high, relative to actual casual labor market wages.\n\n\nThe concern here is that the scheme will attract workers from market work and so bid up the\n\nmarket wage rate. 21 [^21: Evidence for this effect is reported by Imbert and Papp (2011) who compare districts that started early on the\nscheme with those that started later. However, they do not examine the extent of rationing.] (Though to many supporters of the scheme this is counted as a benefit.)\n\n\nWhat does the evidence suggest? Table 6 gives the average wage rates from the\n\n\nadministrative data. These are calculated as total MGNREGS spending on unskilled labor\n\ndivided by total person days of employment provided. 22 [^22: Note that the scheme stipulates both piece rates and daily rates. Under the piece rate, whether a given worker can\nearn the mandated wage rate depends on her work effort. If the scheme attracts workers with lower than average\nphysical ability then the realized average wage rate by our calculations can fall short of the mandated wage.] The table also reports estimates for\n\naverage wages in (private) casual labor from the NSS for the same year. 23 [^23: Note that the reference periods for MGNREGS and casual market wages reported in the table are slightly different\n(see notes to Table 6).]\n\n\nWe see that it is not the case that the MGNREGS wage rate is everywhere well above the\n\n\nmarket wage rate. Indeed, for India as a whole the two wages are quite close. If rural India\n\nMention: \"NSS\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"analyze\", \"summary\": \"Supplies private casual labour wage estimates compared with the MGNREGS administrative wage rate.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:005183:7:0", "occurrence_id": "d0948695c6a22ef31e90edb3", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: Between 2008 and 2009, activity rates for women increased by 16.9% and for men by 12.3%. The\nincrease in activity rates was due to the job loss associated with the global economic crisis. Worsening\neconomic hardships made women who did not work before the crisis join the labor force to supplement\nfamily incomes – a trend observed in some other countries of the region (e.g. Turkey, Lithuania) 2 [^2: Koettl, Johannes Isil Oral and Indhira Santos. 2011. “Employment recovery in Europe and Central Asia”. ECA\nKnowledge brief. Special Issue1, World Bank, Washington DC] . As\ncould be seen from Figure 1 above, the global economic crisis has increased unemployment among men\nmore than among women. This is because male-dominated sectors (e.g. construction, mining and\nquarrying, and manufacturing) have been affected more than female-dominated sectors like health or\neducation (See Annex 2 for more information on the sectoral employment changes of men and women\nafter the crisis).\n\n\nWomen of all age groups have higher inactivity and unemployment rates than men. The highest\nunemployment rate for both genders – 39.8% for men and 45.9% for women – is observed in the 15-24\nage group (Serbia LFS 2009). Scarce job opportunities for young people have high social costs as they\nprevent new entrants in the labor market from obtaining relevant skills.\n\n\nActivity and employment rates are much higher among people with upper secondary and university\neducation (Figure 2). For instance, activity rates for women vary from 9.1% for those with no education\nto 83.8% for those with a master’s degree. The respective rates for men are 18.7% and 70.5%.\nEmployment rates follow a similar pattern. Women with low educational attainment are almost twice less\nlikely to be employed than men with similar education levels. However, university-educated women have\nhigher employment rates than men. This difference\n\nMention: \"Serbia LFS 2009\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"analyze\", \"summary\": \"Labour force survey supplying the gendered and age-specific unemployment and activity rates reported.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:005281:14:1", "occurrence_id": "6bb8da1f28559e157a8d768b", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: we include the total export value of product k from country\n\nc to all countries in the initial year of the trade relationship (total_exportckt0),\nin log terms. This variable captures the experience the exporting country has in\n\nsupplying the world market with product k. We also control for the degree of\n\ncompetition for a given product on the US market, incorporating the number of\n\ncountries exporting product k to the USA in the initial year of the trade rela\ntionship (NSupplierskt0). Finally we account for trade relationships with multiple\nspells, including a multiple spell dummy that takes value one if the spell is a higher\n\norder spell (multiple_spellck). This last regressor does not vary according to the\n\n\n9BACI is the French acronym for “Base pour l’Analyse du Commerce International”: Database for International Trade Analysis. See http://www.cepii.fr/anglaisgraph/bdd/baci.htm.\n\n10We are using BACI in HS from 1992 that covers the period 1994-2005. As the survival\nanalysis relies on the length of export spells, we cannot use the data from the initial year. This\nleaves us with the data for 1995-2005 available for survival analysis.\n\n\n13\n\nMention: \"BACI\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"analyze\", \"summary\": \"Bilateral trade file in HS classification supplying export values and supplier counts for the survival analysis of trade spells.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:005284:14:1", "occurrence_id": "b58e7e31b1a9f1782233184e", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: a day, which is the median poverty line amongst developing countries as a whole (RCS). 25\n\n\nOver the 28 year period, we find that the percentage of the population of the developing\n\n\nworld living below $1.25 per day was halved, falling from 52% to 22%. The number of poor fell\n\n\nby 600 million, from 1.9 billion to 1.3 billion over 1981-2005 (Table 2). The trend rate of decline\n\n\nin the $1.25 a day poverty line over 1981-2008 was 1% point per year. (Regressing the poverty\n\n\nrate on time the estimated trend is -1.03% per year with a standard error of 0.06%, with\n\n\n24 Note that there is a ―hole‖ in coverage for South Asia in 1999. This reflects the well-known comparability\nproblem due to India’s National Sample Survey (NSS) for 1999/2000. (Further discussion and references can be\nfound in Datt and Ravallion, 2002). We decided to drop that NSS survey round given that we now have a new\nsurvey for 2004/05 that we consider to be reasonably comparable to the previous survey round of 1993/94. We also\ndecided to only use the 5-yearly rounds of the NSS, which have larger samples and more detailed and more\ncomparable consumption modules (aside from the 1999/00 round). Unfortunately, this leaves a 10-year gap in our\nsurvey coverage for India; the estimates for India over the intervening period use our interpolation method.\nIncluding all available survey rounds for India adds to the variability in the series but does not change the trend.\n25 Further details on these estimates and results for other poverty lines and for the poverty gap index can be\nfound in Chen and Ravallion (2012).\n\n\n13\n\nMention: \"National Sample Survey\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"validate\", \"summary\": \"Its five-yearly household consumption rounds feed the poverty series, with the 1999/2000 round dropped for comparability.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:005322:9:0", "occurrence_id": "5d43ab449ca452a3f4497ab1", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: needs. Indeed, there is evidence that such inertia in the labor market reduces the responsiveness of\nemployment to growth. Plotting the estimated OLC against hiring and firing scores from the Doing\nBusiness Report reveals an interesting relationship: more rigid labor market regulations result in a lower\nOLC. This holds for the short-run, yielding a considerable R-squared of 0.6 (Figure 3). Considering the\nPhilippines an outlier (since its OLC is statistically insignificant), the effect is similarly pronounced in the\nmedium run (Figure 4).\n\n\nEast Asia generally has comparatively flexible labor market regulations. Singapore and Hong Kong SAR,\nChina have the most flexible hiring and firing rules in the world. In the medium run, employment has\nresponded most sensitively to economic growth in these countries, while the effect was weaker in more\nstrongly regulated countries like China and Taiwan, China.\n\n#### **Results 2: Okun’s Law and economic crises**\n\n\nHaving established that the strength of Okun’s Law varies across countries, it is interesting to explore if\nit varies across time. This is important especially to establish of the effect only works in one direction; in\nother words, does an economic expansion create jobs in the same way that an economic contraction\ndestroys jobs? Just looking at the association captured by the OLC does not answer this question. Thus,\nthe sample was split to isolate times of crisis – the Great Recession of 2008-2011 – from a period of calm\nbetween 2001 and 2007. Table 4 presents the short-run results. 5 [^5: Estimating the medium-run OLC in times of turbulence with considerable variation in the variables makes the\ncoefficients more difficult to interpret.]\n\n\n**Table 4:** Total employment, 2001-2007, 2008-2011, Short Run\n\n|Col1|2001-2007|Col3|Col4|Col5|2008-2011\n\nMention: \"the Doing\nBusiness Report\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"analyze\", \"summary\": \"Supplies the hiring and firing regulation scores plotted against estimated Okun employment responsiveness.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:005429:1:0", "occurrence_id": "27f77a525f8aaebe3cd349a9", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: Policy Research Working Paper 6268\n\n### **Abstract**\n\nRecent research shows that employment in Mexico’s\noffshoring _maquiladora_ industries is twice as volatile as\nemployment in their U.S. industry counterparts. The\nanalyses in this paper use data from Mexico’s social\nsecurity records and U.S. customs between the first\nquarter of 2007 and the last quarter of 2009 to identify\nfour channels through which economic shocks emanating\nfrom the United States were amplified when transmitted\ninto Mexico’s offshoring labor market of Northern\nMexico. First, employment and imports within industries\nare complements, which is consistent with imports being\nused as inputs for the assembly of exportable goods\nwithin industries. That is, when imports fell during\nthe crisis, employment in Mexico was reduced rather\nthan protected by the fall of imports. Second, contrary\nto other studies, employment is more responsive than\n\n\n\nwages to trade shocks. Third, fluctuations in Mexico-U.S.\ntrade were associated with changes in the composition of\nemployment, with the skill level of workers rising during\ndownturns and falling during upswings. This implies that\nthe correlation between average wages and trade shocks is\npartly driven by labor-force compositional effects, which\nmay obscure individual-worker wage flexibility. Fourth,\ntrade shocks affecting related industries (industries\nlinked by employment flows affect employment at least\nas much as own-industry trade shocks, thus amplifying\nemployment volatility through the propagation of shocks\nacross industries within Northern Mexico. Furthermore,\nthe data suggest that the observed fluctuations in U.S.Mexico trade at the onset of the Great Recession in the\nU.S. were not associated with pre-existing employment\ntrends in Northern Mexico.\n\n\n\nThis paper is a product of the International Trade Department, Poverty Reduction and Economic Management Network.\nIt is part of a larger effort by the World Bank to provide open access to its research and make a contribution to development\npolicy discussions around the world. Policy Research Working Papers are also posted on the Web\n\nMention: \"Mexico’s social\nsecurity records\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"analyze\", \"summary\": \"Administrative social security records supply the establishment employment and wage series for the offshoring analysis.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:005800:26:0", "occurrence_id": "5c02a6d8ad87f0b1af3ba573", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: **Figure 1: Delays in BREGS wage payments**\n\n\n_Note_ : Sample restricted to participants who have not been fully paid BREGS wages\nowed to them. _Source:_ Authors’ estimates based on BREGS Survey.\n\n\n25\n\nMention: \"BREGS Survey\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"analyze\", \"summary\": \"Survey of programme participants underlying the estimates of delays in paying owed wages.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:005818:16:2", "occurrence_id": "6cea2b828f1ddb8604eaf7c1", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: |2.80|3.26|\n|Processed food|13.17|12.83|16.18|0.0|0.08|0.08|\n|
Petroleum|3.05|4.45|3.65|0.0|0.00|0.00|\n|Other manufacturing|12.53|12.57|12.76|0.0|22.54|34.37|\n|
Construction|0.61|0.52|0.30|0.0|30.47|47.47|\n|Utilities|2.74|2.48|4.78|0.0|4.98|0.00|\n|Services|16.90|29.18|21.22|0.0|3.75|4.07|\n|Public services|0.00|0.00|0.00|53.1|0.00|0.00|\n|
Education/Health|0.19|0.85|2.21|46.9|28.33|1.87|\n|Total|100.00|100.00|100.00|100.00|100.00|100.00|\n\n\n\n_Source:_ Authors’ calculations using the microeconomic SAM for Niger, 2009.\n\n\n\n15\n\nMention: \"microeconomic SAM\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"analyze\", \"summary\": \"Social accounting matrix supplying the sectoral shares used in the household income decomposition.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:005884:11:0", "occurrence_id": "4c56516aa0faea90fb368801", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: **Employment Elasticity and Structural Reform**\n\n\nStructural factors are likely to influence the relationship between employment and output change.\nFor example, firms might be more readily responding to economic expansions in case workers can\nbe hired and layed off at low cost. More broadly, labor market institutions, product market\nreforms, economic policy, governance and economic diversification could all affect the\nemployment elasticity of growth. There are a large number of structural variables that could be\nincluded in the regressions, and parameter estimates could turn out to be sensitive to the selection\nof variables. In the following, we use a simple approach. We include variables separately as righthand side regressors, along with growth and fixed year and country effects. Even with this\nsimplified approach, structural variables are often not significant. However, we find a number of\nstatistically significant relationships where structural reforms boost employment growth:\n\n\n- On labor markets, employment growth increases with less hiring regulations in ECA and the\nEU10, and a smaller shadow economy in the EU10 and the Balkan and Turkey (Table 3).\n\n- On product markets, employment growth increases with a greater ease of doing business in\nECA and the CIS and less credit regulations in ECA (Table 4). With regard to EBRD transition\nindicators, we find that employment growth increases with more firm restructuring in ECA and\nthe EU10, better competition policy in the CIS, more banking reform in the EU10, and more\ninfrastructure reform in the CIS (Table 5).\n\n- On economic policy, employment growth increases with smaller size of government in ECA,\nsound money in ECA, and greater economic flows across borders in ECA, the EU10 and the CIS\n(Table 6).\n\n- On governance, employment growth increases with more corruption control in ECA and the\nCIS, more political stability in the CIS, better quality of regulation in ECA (but not in the EU10),\nmore government effectiveness in ECA and the CIS, and more voice\n\nMention: \"EBRD transition\nindicators\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"analyze\", \"summary\": \"Transition progress ratings used as right-hand side regressors explaining employment growth by region.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:005963:11:1", "occurrence_id": "75f32e0a903a463d5a7a18df", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: idea that a fall in the interest rate lowers the volatility of prices (smoothing transitory\n\n\nshocks through lower inventory costs) and increases the correlations of price returns if covariant\n\n\nshocks are more persistent than idiosyncratic shocks. Byrne, Fazio and Fiess (2013) argue that the\n\n\nstandard deviation of stock market prices can be used as a proxy of market uncertainty, in line\n\n\nwith Beck (1993) and Dixit and Pindyck (1994)’s suggestion that market risk and uncertainty might\n\n\nbe associated with movements in commodity prices. According to Beck (1993), uncertainty may\n\n\nhave a positive effect on commodity prices because volatile commodity prices are likely to reduce\n\n\ninventories and, consequently, their price. Dixit and Pindyck (1994) predict a negative effect\n\n\nof uncertainty on commodity prices as uncertainty increases the option value of waiting (since\n\n\ninvestment in the production of primary commodities may be irreversible). Gilbert (2010) also\n\n\nsuggests that co-movements across commodity prices can be better explained by macroeconomic\n\n\nand financial conditions than by market-specific factors.\n\n\nIn this study we consider two possible determinants of the co-movement of commodity price\n\n\nreturns: (i) a real interest rate series computed as the difference between an annualized 3-month\n\n\nTreasury bill interest rate series obtained from the Board of Governors of the Federal Reserve\n\n\nSystem and a series of annual inflation rates calculated from a monthly non-seasonally adjusted\n\n\nconsumer price index series taken from the Federal Reserve Bank of St Louis Economic Dataset\n\n\n(FRED); and (ii) the standard deviation of Standard & Poor’s 500 (S&P500) stock price returns\n\n\n13The technical details are presented in Section A.4.\n\n\n9\n\nMention: \"Federal Reserve Bank of St Louis Economic Dataset\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"analyze\", \"summary\": \"Supplies the monthly consumer price index used to deflate the Treasury bill rate into a real interest rate.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:006106:16:1", "occurrence_id": "87890c8c0bf045b2e2c35dea", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: much bigger role in Eastern and Central Africa. The effect of distance is also\nslightly higher than in Versailles (2012), who finds a distance coefficient of around 0.015 for\nstaple foods (i.e. for rice, maize potatoes and sweet potatoes). Computing a distance-equivalent\nas suggested by Engel and Rogers (1996), we find that crossing a border in the region impedes\nmarket integration by the same amplitude as increasing the distance between cities by 8km\n(computed as exp(0.0742/0.0352)) while Versailles finds a distance equivalent of 220km and\nBroda and Weinstein of around 328km. The low distance equivalent reveals the predominance\nof the effect of distance on market integration in the region. Araujo and Brunelin (2013) found\nsimilarly a small border effect in West Africa between Benin, Burkina Faso, Mali and Niger for\nmil, sorghum and maize, between 2km and 35km. 16 [^16: As these authors argue, the distance equivalent proposed by Engel and Rogers (1996) is unitless, i.e. it does not\nvary according to the measurement unit for distance. However, it is usual to express it in terms of the unit of\nmeasurement of distance in the sample, which is in kilometers in this paper.]\n\nMany factors could explain that the border effects between African countries are\nrelatively low. First, the high number of weighbridges and policy controls along intra-national\nroads increase transport delays and, therefore, constitute substantial barriers to trade within\nAfrican countries. Second, within-country differences of ethnicity and language could explain\nthe low domestic market integration. Third, the lack of control at the border and the corruption of\ncustoms may facilitate trade of primary commodities between countries; which is reflected in the\nlarge amount of informal trade estimated by Stryker (2012) based on FEWSNET data. For\nexample, according to Stryker (2012), 15’815 MT of Maize have been informally traded between\nTanzania and Kenya in 2011. In this\n\nMention: \"FEWSNET data\""}, {"role": "assistant", "content": "{\"role\": \"supporting\", \"usage_action\": \"inform\", \"summary\": \"Underlying data for the cited estimates of informal cross-border maize trade between Tanzania and Kenya.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:006125:7:0", "occurrence_id": "35b08525bbde3822299b31e5", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: |National
14
12
10
8
6
4
-2 0 2 4
Asset index|Rural
14
12
10
8
6
4
-2 0 2 4
Asset index|\n|---|---|\n|4
6
8
10 12 14
-2
0
2
4
Asset index
Monrovia|4
6
8
10 12 14
-2
0
2
4
Asset index
Other urban|\n\n\n\n\n\nThe asset index used in the DHS generally does not assign a strict ranking nor designate a poverty\nline as is commonly done with consumption aggregates. Instead, quintiles are constructed. Tables\n2a through 2c in the appendix show the frequency of observations for population quintiles\nconstructed using the asset index and the consumption aggregate. The findings corresponded to the\nresults of the scatterplots above. The Pearson chi-square relationship between the rows\n(consumption quintile) and columns (asset quintiles) is positive and significant. The Cramér's V\nstatistics however are low, indicating the explanatory powers are low. The Cramér's V statistic was\nsimilarly higher also for urban areas than rural areas.\n\n\nIn addition, the findings from the asset indices contradict some standard findings in the literature\nregarding correlates of poverty. One finding that is fairly common across poverty analyses is that\npoor households have larger household sizes than rich households. The consumption quintiles show\nan average household size of 4.2 members for the richest quintile, which increased to 5.4, 5.7,\n\nMention: \"DHS\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"validate\", \"summary\": \"Its asset index is compared against consumption quintiles to test whether it ranks households consistently.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:006199:29:1", "occurrence_id": "c684991d4b62afb6c03ca6d3", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: primary channel through\n\n\nwhich the poor net-consumers of rice will be compensated for the higher cost of living, may\n\n\n15 As a percentage of farm households it is estimated that 71% sold some rice produce in 2010/11, up from\n35% in 1998/99, which suggests that we are seeing a shift toward market-oriented agriculture (Lao Census,\n2012).\n\n28\n\nMention: \"Lao Census\""}, {"role": "assistant", "content": "{\"role\": \"supporting\", \"usage_action\": \"inform\", \"summary\": \"Cited in a footnote for the rising share of farm households selling rice, indicating market-oriented agriculture.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:006213:11:1", "occurrence_id": "55e5839a8901e6f0ae150118", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: are assumed to grow at the same rate as the working age\npopulation, and the populations by age tranche grow following the medium fertility scenario of the\nUnited Nations (2013). This assumption preserves the skill share of the number of employed in a given\neconomy over time and is useful for the purposes of decomposing the effects of demographic change on\naggregate labor supply by controlling for the effect of improvements in the skill-share of labor. Data\nfrom the _Global Economics Prospects 2013_ (GEP) (World Bank, 2013d) are used to determine investment\nas a share of GDP from 2007 to 2011, after which investment is endogenously determined as the model\nsolves for different equilibria over time. GEP data are also used to track the current account balances as\nshares of nominal GDP of the various countries from 2007 to 2015, after which they descend to\nsustainable long run levels by 2030. Finally, GEP data are used to track the real GDP growth from 2007\nto 2015. 10\n\n\n\nWith the baselines thus defined, 11 three alternative simulations are designed to isolate the\nimpact of demographics on the results in the two baselines. The alternative scenarios generally hold all\nthe exogenous shocks the same as in the baseline, except that the GDP growth is endogenized, and the\nproductivity growth that allowed for that GDP growth in the baseline is now applied as an exogenous\nshock. The three alternative scenarios are used to determine the sensitivity of growth in Africa to\ndemographic change by isolating individually and together the direct demographic impact on savings\nand on labor supply.\n\n\n10 The simulations do not account for Nigeria’s 2014 re-basing of the national accounts data.\n11 The growth rates by country can be found in Table A3.\n10\n\nMention: \"GEP data\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"analyze\", \"summary\": \"Supplies investment shares, current account balances and real GDP growth used to calibrate the model baseline.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:006239:56:1", "occurrence_id": "d495507d752392c4a15faedb", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: >**2010**
**2011**
**2012**
− Lines serving the port (units)
• Cargo
5
5
5
5
5
• Passenger
6
6
6
6
6
− Calls (units)
• Cargo
403
464
437
344
295
• Passenger
27
19
25
34
31
|**OECS (2012)**
5
16
591
183
|\n|
**II. Traffic**
**2008**
**2009**
**2010**
**2011**
**2012**
− Composition
• Container (TEU/year)
2,453
3,002
2,852
3,046
2,665
• General cargo (tonnes/year)
2,947
8,064
\n\nMention: \"OECS\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"Regional organisation statistics cited as the source for the port lines, calls and traffic figures in the table.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:006277:12:0", "occurrence_id": "234601c54d8739ecb14befb2", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: Mobile Na 0.7%\nSMS Na 0.008%\nVote turnout (%) 15.1% 14.0%\n\n- Notes: There were 7,348,996 registered voters in 2012 (data from PROCERGS). Turnout in 2011 is calculated\nusing the 2012 data on the number of voters.\n\n\nConcerns about the integrity of the voting process are rarely expressed. However, nothing\n\n\nprevents a participant from voting both online and offline, since the online and offline voter\n\nlists are not compared at any point in the process, nor is there any protection against voter\n\ncoercion in the remote voting. 19 [^19: Some of the more sophisticated e-voting systems try to minimize the risk of so-called ‘over the shoulder attacks’\nby enabling users to change their vote after they have been cast (e.g. Estonia’s electoral i-voting). Identifying solutions for mitigating the risk of multiple-voting and other factors that may distort outcomes is currently one of the\nactivities supported by the World Bank’s Digital Engagement Unit.] It is important to note, however, that among online engage\nment processes around the world, only a few adopt a more advanced security system that\n\nallows the voter to change the vote to discourage improper influence and use stronger au\n\nthentication procedures (e.g. Estonia, Switzerland). Notably, stronger security e-voting\n\nmeasures are limited in their overwhelming majority to electoral processes. Furthermore, as\n\nthe literature on election fraud has shown, electoral integrity continues to be a problem even\n\nin offline systems (Hyde 2011; Sjoberg 2012).\n\n##### 4. Methodology & Data\n\n\nOne approach to investigate the issue of turnout and the effect of digital divide on inclusive\nness is to observe changes in aggregate-level turnout when i-voting is introduced. However,\n\nsince electoral dynamics can change significantly from one election (at time t1) to another\n\n(\n\nMention: \"data from PROCERGS\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"analyze\", \"summary\": \"Voter registration records supplying the registered-voter counts used to compute turnout.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:006317:6:1", "occurrence_id": "5b3c4aa53cfaf0eb742f7615", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: the WDI database was the\npreferred choice. That said, comparisons between these two databases give us very useful insights on how\nsurveys are planned and carried out in the field. We will come back to this point in section 6, where we\ndiscuss practical concerns in addressing the “Data Deprivation”.\n\n\n**3.** **Key Findings**\n\n\nThe availability of poverty data has increased sharply since the early 1990s (Figure 1). A first rapid increase\noccurred between 1990 and 1996 when data points for those particular years increased from 13 to 36, driven\nlargely by the Europe and Central Asia (ECA), Latin America and Caribbean (LAC), and Sub-Saharan\nAfrica (SSA) regions. At the beginning of the 1990s, poverty data from the ECA region were not available\nin the WDI database, mainly due to the fact that many post-Soviet states did not yet exist or data were not\naccessible to the World Bank. The number of poverty estimates in the ECA region increased significantly\nsince 1992 and rose to an average of eight data points per year between 1992 and 1999. During this time,\nthe number of poverty estimates also increased significantly in both the LAC and SSA regions.\n\n\nThe years 2000 to 2005 brought about another spike in the availability of poverty data; the number of\ncountries with available poverty data almost doubled from 37 countries in 2000 to 60 countries in 2010 and\nremained fairly constant since then with 62 countries producing poverty estimates in 2011. The ECA region\nwas again a key driver of this second wave of improvements in data availability. The number of poverty\nestimates in the ECA region increased from 9 in 2000 to 26 in 2004 while the number of poverty estimates\nin other regions fluctuated, but overall showed improvements. The average of all data points in a given 10\nyear period illustrates significant improvements in Sub-Saharan Africa with increases in the availability of\ndata points by almost 50 percent from 5.1 in the 1990s to 7\n\nMention: \"WDI database\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"analyze\", \"summary\": \"Chosen as the source for tracking the availability of national poverty estimates over time.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:006549:28:0", "occurrence_id": "9cf97c5c94bb537ed5dcd74a", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: police), but this threat is significantly more frequent for crossovers. In addition, crossovers experience\n\n\nmore frequent vandalism of their premises. Both of these could be because crossovers stand out within\n\n\ntheir sectors. However, these could also be features of the sectors within which crossovers operate. For\n\n\nexample, compare a metal fabricator and a caterer. A caterer can pack up most of her capital and move\n\n\nher business quite easily, while a metal fabricator is more likely to have larger machinery that makes her\n\n\nbusiness less mobile. 25 [^25: The KASSIDA data set (table 4) provides some support for this fact as there are no significant differences between\nmen and women in the crossover sectors across the forms of harassment. However, this is not a primary focus in\nthe KASSIDA data collection and some numbers appear less reliable (e.g. much lower rates of sexual harassment).]\n\n\n**Table 10: Harassment in the past 12 months (%)**\n**Crossover** **Non‐crossover** **Difference**\nThreats to shut down business 33.9 20.0 13.9**\nShouting, scolding, making a nuisance in or\n21.0 15.0 6.0\nnear enterprise premises\n\nVandalism of premises or merchandise 8.1 2.5 5.5*\nConfiscation of property or merchandise 8.1 6.7 1.3\nPushing or shoving 14.5 11.8 2.8\nSexual proposals 29.0 16.8 12.2*\nFondling or inappropriate touching 3.2 2.5 0.7\nBeating 6.5 2.5 3.9\nArson 3.2 0.8 2.4\nWitchcraft 19.4 14.\n\nMention: \"KASSIDA data set\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"validate\", \"summary\": \"Enterprise survey whose table 4 is used to test whether harassment differences are driven by sector rather than gender.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:006549:28:0", "occurrence_id": "31d3ea50bf0d6c300402977a", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: police), but this threat is significantly more frequent for crossovers. In addition, crossovers experience\n\n\nmore frequent vandalism of their premises. Both of these could be because crossovers stand out within\n\n\ntheir sectors. However, these could also be features of the sectors within which crossovers operate. For\n\n\nexample, compare a metal fabricator and a caterer. A caterer can pack up most of her capital and move\n\n\nher business quite easily, while a metal fabricator is more likely to have larger machinery that makes her\n\n\nbusiness less mobile. 25 [^25: The KASSIDA data set (table 4) provides some support for this fact as there are no significant differences between\nmen and women in the crossover sectors across the forms of harassment. However, this is not a primary focus in\nthe KASSIDA data collection and some numbers appear less reliable (e.g. much lower rates of sexual harassment).]\n\n\n**Table 10: Harassment in the past 12 months (%)**\n**Crossover** **Non‐crossover** **Difference**\nThreats to shut down business 33.9 20.0 13.9**\nShouting, scolding, making a nuisance in or\n21.0 15.0 6.0\nnear enterprise premises\n\nVandalism of premises or merchandise 8.1 2.5 5.5*\nConfiscation of property or merchandise 8.1 6.7 1.3\nPushing or shoving 14.5 11.8 2.8\nSexual proposals 29.0 16.8 12.2*\nFondling or inappropriate touching 3.2 2.5 0.7\nBeating 6.5 2.5 3.9\nArson 3.2 0.8 2.4\nWitchcraft 19.4 14.\n\nMention: \"KASSIDA data collection\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"validate\", \"summary\": \"Collection whose reliability for certain harassment items is qualified since they were not a primary focus.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:006757:4:0", "occurrence_id": "e9932410b3d69ed93e5ee852", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: across sectors is neither a necessary nor a sufficient condition of inefficiency. When production\n\n\nfollows a Cobb-Douglas technology in presence of perfect competition, marginal productivity\n\n\nis simply the product of average productivity and the labor share of income. The deviation in\n\n\nlabor income shares across sectors drives a wedge between marginal and average productivity\n\n\ngaps. If the sector with higher average productivity also has a higher relative labor share of\n\n\nincome, then marginal gaps are larger than observed average gaps. To estimate labor shares at\n\n\nthe sectoral level, I use the data from Global Trade Analysis Project (GTAP). I find significant\n\n\ndeviation between marginal and average gaps and as such considering the gaps at margin is not\n\n\nonly a theoretical concern. On average, distortions estimated using average gaps in productivity\n\n\nare around 35% and 22% lower than when estimated using marginal gaps for Industry and Services\n\n\nrespectively. Vollrath (2009) also considers differences in marginal productivity to measure impact\n\n\nof misallocation. Though, in his calculations he assumes the labor shares to be invariant across\n\n\ncountries and hence uses the US labor shares to estimate marginal productivity in each country.\n\n\nHowever, labor shares obtained from GTAP show that there is a considerable variation in sector\n\n\nlabor shares across countries. Thus, using a common set of labor shares may not be an appropriate\n\n\nstrategy.\n\n\nIn order to quantify the productivity impact of the sectoral gaps, I develop a simple model of\n\n\nresource allocation in which the gaps arise due to distortions in the form of asymmetrical taxes\n\n\non labor inputs across three broad sectors: Agriculture, Industry and Services. These taxes are\n\n\na stylized way of capturing the net effect of a menu of factors that create barriers to movement\n\n\nof resources across sectors. A model of resource allocation is essential in contrast to a shift\n\nshare analysis of aggregate productivity because productivity in both sectors change as a result of\n\n\nresources flowing from the low productivity sector to the high productivity sector. An important\n\n\npoint is that the growth impact of changes in distortions depends crucially on the amount of resources\n\nMention: \"data from Global Trade Analysis Project\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"analyze\", \"summary\": \"Supplies sectoral labor income shares used to convert average into marginal productivity gaps.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:006757:4:0", "occurrence_id": "ab606ef298f993903402ae84", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: across sectors is neither a necessary nor a sufficient condition of inefficiency. When production\n\n\nfollows a Cobb-Douglas technology in presence of perfect competition, marginal productivity\n\n\nis simply the product of average productivity and the labor share of income. The deviation in\n\n\nlabor income shares across sectors drives a wedge between marginal and average productivity\n\n\ngaps. If the sector with higher average productivity also has a higher relative labor share of\n\n\nincome, then marginal gaps are larger than observed average gaps. To estimate labor shares at\n\n\nthe sectoral level, I use the data from Global Trade Analysis Project (GTAP). I find significant\n\n\ndeviation between marginal and average gaps and as such considering the gaps at margin is not\n\n\nonly a theoretical concern. On average, distortions estimated using average gaps in productivity\n\n\nare around 35% and 22% lower than when estimated using marginal gaps for Industry and Services\n\n\nrespectively. Vollrath (2009) also considers differences in marginal productivity to measure impact\n\n\nof misallocation. Though, in his calculations he assumes the labor shares to be invariant across\n\n\ncountries and hence uses the US labor shares to estimate marginal productivity in each country.\n\n\nHowever, labor shares obtained from GTAP show that there is a considerable variation in sector\n\n\nlabor shares across countries. Thus, using a common set of labor shares may not be an appropriate\n\n\nstrategy.\n\n\nIn order to quantify the productivity impact of the sectoral gaps, I develop a simple model of\n\n\nresource allocation in which the gaps arise due to distortions in the form of asymmetrical taxes\n\n\non labor inputs across three broad sectors: Agriculture, Industry and Services. These taxes are\n\n\na stylized way of capturing the net effect of a menu of factors that create barriers to movement\n\n\nof resources across sectors. A model of resource allocation is essential in contrast to a shift\n\nshare analysis of aggregate productivity because productivity in both sectors change as a result of\n\n\nresources flowing from the low productivity sector to the high productivity sector. An important\n\n\npoint is that the growth impact of changes in distortions depends crucially on the amount of resources\n\nMention: \"GTAP\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"validate\", \"summary\": \"Its labor shares show considerable cross-country variation, undermining the use of a common set of shares.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:006789:40:0", "occurrence_id": "06d80b03fb85312f64632242", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: Table A1: List of Countries\n\n\nCountry Region Income\nCongo,Dem.Rep. Africa Low Income\nGhana Africa Low Income\nKenya Africa Low Income\nNamibia Africa Higher Middle Income\nNigeria Africa Low Income\nSouthSudan Africa Low Income\nSudan Africa Low Income\nTanzania Africa Low Income\nUganda Africa Low Income\nZambia Africa Low Income\nMalawi Africa Low Income\nBangladesh South Asia Low Income\nIndia South Asia Lower Middle Income\nNepal South Asia Low Income\nPakistan South Asia Low Income\nAlbania Eastern Europe Lower Middle Income\nArmenia Eastern Europe Lower Middle Income\nAzerbaijan Eastern Europe Lower Middle Income\nBelarus Eastern Europe Higher Middle Income\nBosnia and Herzegovina Eastern Europe Lower Middle Income\nBulgaria Eastern Europe Higher Middle Income\nCroatia Eastern Europe Higher Middle Income\nCzech Republic Eastern Europe High Income\nEstonia Eastern Europe Higher Middle Income\nGeorgia Eastern Europe Lower Middle Income\nHungary Eastern Europe Higher Middle Income\nKazakhstan Eastern Europe Higher Middle Income\nKosovo Eastern Europe Lower Middle Income\nKyrgyzstan Eastern Europe Low Income\nLatvia Eastern Europe Higher Middle Income\nLithuania Eastern Europe Higher Middle Income\nMacedonia Eastern Europe Lower Middle Income\nMoldova Eastern Europe Low Income\nMongolia Eastern Europe Lower Middle Income\nMontenegro Eastern Europe Higher Middle Income\nPoland Eastern Europe Higher Middle Income\nRomania Eastern Europe Higher Middle Income\nRussia Eastern Europe Higher Middle Income\nSerbia Eastern Europe Higher Middle Income\nSlovakia Eastern Europe High Income\nSlovenia Eastern Europe High Income\nTajikistan Eastern Europe Low Income\nTurkey Eastern Europe Higher Middle Income\nUkraine Eastern Europe Lower Middle Income\nUzbekistan Eastern Europe Low Income\nEgypt MENA Lower Middle Income\nIsrael MENA High Income\nJordan MENA Lower Middle Income\nLebanon MENA Higher Middle Income\nMorocco MENA Lower Middle Income\nTunisia MENA Lower Middle Income\nWest Bank MENA Lower Middle Income\nYemen MENA Low Income\n\n\nSource: World Bank Enterprise Surveys, 2013.\n\n\n39\n\nMention: \"World Bank Enterprise Surveys, 2013\""}, {"role": "assistant", "content": "{\"role\": \"supporting\", \"usage_action\": \"inform\", \"summary\": \"Survey round whose coverage defines the list of countries, regions and income groups tabulated in the appendix.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:006820:4:1", "occurrence_id": "2076cb93646cf8f127c1834a", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: section 2, we provide some summary statistics from our\n\n\nmain source of data, the UNHCR Population Statistics Database. Section 3 describes the method\n\n\nfollowed to construct duration statistics and presents a few stylized facts. The results of our anal\n\nysis are presented in section 4. Section 5 concludes.\n\n##### **1 Background: Definitions and Data**\n\n\nUnder the terms of the 1951 Convention Relating to the Status of Refugees –henceforth the Convention–\n\n\nlater amended by the 1967 Protocol, a refugee is a person, who “owing to a well-founded fear of\n\n\nbeing persecuted for reasons of race, religion, nationality, membership of a particular social group\n\n\nor political opinion, is outside the country of his nationality, and is unable to, or owing to such\n\n\nfear, is unwilling to avail himself of the protection of that country.”\n\n\nData on refugees and asylum seekers are collected by individual countries, international orga\n\n3\n\nMention: \"UNHCR Population Statistics Database\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"analyze\", \"summary\": \"Main data source, supplying refugee and asylum-seeker population statistics used to construct duration measures.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:006842:20:0", "occurrence_id": "2c89ff99e04e8d8a0539443a", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: significantly higher in language and math tests in the early years of primary school compared to\n\n\ntheir peers who enrolled only in playgroup or kindergarten. In addition to the sequence of early\n\n\neducation service participation, we found that the timing of entry into playgroups and\n\n\nkindergartens was an important predictor of children’s subsequent learning outcomes. Children\n\n\nwho enrolled in playgroup at age 3-4 followed by kindergarten at age 5-6 performed significantly\n\n\nhigher in language and math tests in primary school than their peers who enrolled in other early\n\n\neducation pathways. Finally, over and above the sequence and timing, we found that duration of\n\n\nearly education was a significant predictor of children’s math test scores in primary school, as\n\n\nthose who enrolled in at least two years of playgroup and kindergarten scored significantly better\n\nthan their peers who enrolled for shorter periods of time. 5\n\n\n**8. Costs of various early education pathways**\n\n\nThe Indonesian government is currently weighing alternatives for investing smartly in\n\n\nearly childhood education to ensure that all young children enter primary school ready to learn.\n\n\nIn this section, we estimate the cost of various early education pathways to inform public\n\n\nresource allocation decisions for early childhood education in Indonesia. We do not have causal\n\n\nestimates of ECED pathways on primary school test scores. Thus we cannot calculate actual\n\n\nestimates of the different pathways. Despite this, we feel that our controls and robustness checks\n\nvalidate the presentation of these estimates as cost-effectiveness estimates. 6 We do so by\n\n\ncalculating the marginal effect at representative values (MER) of the ECED timing variable at\n\n\ndiscrete values of ECED duration (shown in Tables 5c). We used the average of the language and\n\n\nmath assessments for our effectiveness measure as these two tests were aligned with what children\n\n\nwere expected to know in the early years of primary school.\n\n\nThe cost of each early education pathway was drawn from the Indonesia ECED Project\n\n\nevaluation data (\n\nMention: \"Indonesia ECED Project\n\n\nevaluation data\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"analyze\", \"summary\": \"Project evaluation data supplying the costs of each early childhood education pathway used in the cost-effectiveness estimates.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:006869:4:0", "occurrence_id": "88d2f04b91740b5ca02cefc2", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: household level, the PSF data provide us with information at each survey date on the\nstock of savings of each household member, which allows us to focus on wives’\nsavings and resource allocation decisions.\n\n\nWe implement a two-step analysis, detailed in the Empirical Approach and\nIdentification Strategy section. In the first step, we obtain for each union the predicted\nrisk of polygamy with a duration model. Identification in the second step relies on the\ndifferent time patterns of transitions of unions to polygamy depending on the\npolygamy of the husband’s father. We thus make the assumption that the polygamy of\nthe husband’s father does not affect the variation of saving behaviors over time other\nthan through the risk of polygamy. Potential violations of this assumption caused by\ndifferential inheritance rules across groups or polygamy of the husband’s father partly\ncapturing household wealth are investigated and ruled out in the Empirical Approach\nand Identification Strategy section.\n\n\nOur main results show that the risk of polygamy has a positive impact on wife\nsavings, but only on savings entrusted to formal or informal institutions, as opposed to\nsavings kept at home, especially for women living in the poorest households.\nHousehold food expenditures are found to decrease with the risk of polygamy,\nsuggesting a possible reallocation of women’s resources from food consumption to\nsavings. In addition, women facing a larger increase in their risk of polygamy spend\nmore on the education of their children, but this increase in education expenditures is\nexclusively funded by a higher contribution of their husband, while their own\ncontribution decreases. They are also found to transfer more to their social networks.\nThese results suggest that the risk of polygamy leads monogamous wives to engage in\nself-protective strategies by investing in assets that are out of the reach of their\nhusbands and in their social networks. On the other hand, the risk of polygamy is not\nfound to affect women’s labor market participation. By contrast, the risk of polygamy\nis positively correlated with monogamous husbands’ labor market participation and\nincome, consistent with\n\nMention: \"PSF data\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"analyze\", \"summary\": \"Panel providing each members savings stock at every survey date, used to study wives savings and household allocation.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:006964:6:0", "occurrence_id": "a83363c1d8adf37342024f28", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: PovcalNet continues to rely on such data. 10 To obtain a consistent number of observations per\ncountry-year, we fit a parametric Lorenz curve to the quantile groups and build a data set of\npercentile groups throughout. 11 The Appendix includes a robustness check which uses the raw\nquantile data without fitting a parametric Lorenz curve.\n\nEach percentile group is population-weighted in the analysis, so every person is assigned the\naverage consumption expenditure of her percentile in the country-year distribution. Welfare is\nmeasured using per capita consumption expenditure (or income), expressed in 2011 PPPadjusted USD (see methodological details in the Appendix). Because we compare consumption\nlevels across countries it is important to account for differences in purchasing power across\ncountries using purchasing power parity (PPP) exchange rates. For the same reason, welfare\naggregates could also be adjusted for spatial price differences within countries, as recently\ndiscussed by Ferreira et al. (2016) in the context of estimating global poverty. In the baseline\nresults, we follow the approach adopted in PovcalNet (Chen and Ravallion, 2010) and adjust\nfor spatial price differences within China and Indonesia (see Appendix), but not in other\ncountries in the region. 12 In the Appendix, we present robustness checks with further withincountry spatial price adjustments between 2002 and 2012, as well as using the older set of 2005\nPPP exchange rates.\n\n\n10 The number of quantiles per country-year ranges from 9 to 200, with an average of 71 across all years (and 36\non average in 1988).\n11 We fit a log-normal Lorenz curve to the quantiles and use it to generate a distribution of 10,000 points. We use\nthe ‘ungroup’ Stata routine (Abdelkrim and Duclos, 2007) which implements the Shorrocks\n\nMention: \"2005\nPPP exchange rates\""}, {"role": "assistant", "content": "{\"role\": \"supporting\", \"usage_action\": \"validate\", \"summary\": \"Older conversion factors used in a robustness check alongside the 2011 PPP baseline welfare measures.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:007239:18:2", "occurrence_id": "0d1dd035faf0694c4b8b18bd", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: s include: (log) age, (log) size, (log) total assets, assets per employee; and financial leverage. The F‐test and P‐value in the thre last line_\n_referest to the test of joint significance of SBD and SBD X lagging coefficients._\n\n###### 7. Conclusions and further research\n\n\nThis paper aims to provide an exploratory assessment of the relationship between the business\nenvironment and firm performance in European regions, with an emphasis on understanding if and\nhow business environment constraints may be a factor holding back investment, employment, and\ngrowth in lagging regions. The analysis, exploiting unique firm‐level data from the _Orbis_ data set along\nwith regional business environment data from the World Bank’s _Subnational Doing Business_ reports,\nprovides strong support for the relationship between the business environment and several aspects of\nfirm performance. The paper also shows that this relationship matters somewhat more for lagging\nregions, not only because the business environment is rather worse in these regions, but also because\nthe impact of the business environment on firm performance is stronger.\n\n\n17\n\nMention: \"_Orbis_ data set\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"analyze\", \"summary\": \"Commercial firm-level panel providing the performance variables regressed on regional business environment measures.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:007360:32:0", "occurrence_id": "101ef2da51a147adf3963e12", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: 6. Trade Linkages between China and other B&R Economies\n\n\n**6. Trade Linkages between China and other B&R Economies**\n\n\n**_6.1. Gross Trade between China and other B&R Economies_**\n\n\nB&R Economies are already important trading partners of China. In terms of the destination of total gross\nexports, B&R economies were the destination of 22 % of China’s gross exports, while non-B&R accounted\nfor 66 % (Figure 36). Repeating the exercise in Figure 44 from the point of view of China’s gross imports,\nB&R economies are much more important to China as sources of imports, accounting for 30% of its total\nimports in 2010 (\n\nFigure 37).\n\nFIGURE 36: EXPORTS OF CHINA BY DESTINATION, 1995-2010\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\nGraphs by year\n\n|Col1|non-B&R B&R
ROW|\n|---|---|\n|||\n\n\n\n**Source:** Author’s calculations using the Tiva database.\n\n\nFIGURE 37: IMPORTS OF CHINA BY ORIGIN, 1995-2010\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n31\n\nMention: \"Tiva database\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"analyze\", \"summary\": \"Source underlying the authors calculations of Chinas gross exports and imports by destination and origin.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:007485:50:7", "occurrence_id": "ab7b7817950372538e79bbf6", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: using the poverty line of $5.50 per day in
2011 PPP.
|Source: own estimates based on Romanian HBS (2016).
Notes:
1. Original income is considered as Market Income in the Sensitivity Analysis and as Market Income plus Pensions in the Benchmark
Analysis
2. Redistributive effect equals the difference between market income Gini and the relevant ending income concept Gini. The shown change
is measured in Gini points.
3. Size equals the ratio of the amount collected or spent divided by total market income.
4. Marginal contribution equals the difference between the Gini coefficient of the relevant ending income concept without the intervention in
question and the Gini coefficient of the relevant ending income concept (which, of course, includes that intervention). By definition, the sum
of the marginal contributions does not fulfill the adding-up principle so it will not be equal to the redistributive effect unless by coincidence.
The marginal contribution shown above is measured in Gini points.
5. Poverty Reduction effect based on poverty headcount index using the poverty line of $5.50 per day in
2011 PPP.
|Source: own estimates based on Romanian HBS (2016).
Notes:
1. Original income is considered as Market Income in the Sensitivity Analysis and as Market Income plus Pensions in the Benchmark
Analysis
\n\nMention: \"Romanian HBS (2016)\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"analyze\", \"summary\": \"Household budget survey underlying the estimates of redistributive effects, Gini changes and poverty reduction.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:007629:13:0", "occurrence_id": "78060deb3022a36faf8d93b5", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: 11\n\n\n\nFigure 4: Food-related government policies\n\n\n\n(A) Interventions in agricultural markets\n\n\n\nPercent Reference price Percent\n\n1.05 Nominal rate of protection (RHS) 20\n\n\n\n(B) Policy interventions during the 2007-08\nfood price spike\n\n\nPercent of respondents\n\n60\n\n\n40\n\n\n20\n\n\n0\n\n\n(D) Increase in world prices, 2010-11\n\n\nPercent With active policy\n\n50 Without active policy\n\n\n40\n\n\n30\n\n\n20\n\n\n10\n\n\n0\n\nRice Wheat Maize\n\n\n\n1.05\n\n\n1.00\n\n\n0.95\n\n\n0.90\n\n\n0.85\n\n\n0.80\n\n\n0.75\n\n\n\n20\n\n\n\n16\n\n\n12\n\n\n8\n\n\n4\n\n\n0\n\n\n\n(C) Insulation and correction coefficients\n\n\nCoefficient Insulation Correction\n\n0.0\n\n\n-0.2\n\n\n-0.4\n\n\n-0.6\n\n\n-0.8\n\n\n-1.0\n\n\n\nSources: Ag-Incentives Database, Ivanic and Martin (2014b), World Bank.\nA. Nominal Rate of Protection (NRP) is computed as the price difference between the farm gate price\nreceived by producers and an undistorted reference price at the farm gate level. The reference price at the\nfarm gate level is defined as the net price of the product when it leaves the farm, after marketing costs have\nbeen subtracted. The undistorted farm gate price is defined as the price prevailing in competitive world\nmarkets.\n\nB. Percent of respondents based on a survey of 80 EMDEs.\nC. Estimates based on the Error Correction Model described in Annex 6.1. The coefficient of price\ninsulation ranges from 0 for countries that do not insulate against the rise in world prices, to -1 for\ncountries that adopt policies that fully insulate domestic markets. The error correction term represents the\ncost of being out of equilibrium or the speed with which polices achieve the target level of protection or at\nwhich policy makers move back toward this equilibrium after being forced away from it by a shock to\nworld prices. Based on data for 82 countries, of which 26 advanced economies, 44 EMDEs, and 12 LICs for\nthe\n\nMention: \"Ag-Incentives Database\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"analyze\", \"summary\": \"Source of the nominal rate of protection and policy intervention measures shown for agricultural markets.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:007629:13:0", "occurrence_id": "fb4ef7cd7b1056c47a28ba4e", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: 11\n\n\n\nFigure 4: Food-related government policies\n\n\n\n(A) Interventions in agricultural markets\n\n\n\nPercent Reference price Percent\n\n1.05 Nominal rate of protection (RHS) 20\n\n\n\n(B) Policy interventions during the 2007-08\nfood price spike\n\n\nPercent of respondents\n\n60\n\n\n40\n\n\n20\n\n\n0\n\n\n(D) Increase in world prices, 2010-11\n\n\nPercent With active policy\n\n50 Without active policy\n\n\n40\n\n\n30\n\n\n20\n\n\n10\n\n\n0\n\nRice Wheat Maize\n\n\n\n1.05\n\n\n1.00\n\n\n0.95\n\n\n0.90\n\n\n0.85\n\n\n0.80\n\n\n0.75\n\n\n\n20\n\n\n\n16\n\n\n12\n\n\n8\n\n\n4\n\n\n0\n\n\n\n(C) Insulation and correction coefficients\n\n\nCoefficient Insulation Correction\n\n0.0\n\n\n-0.2\n\n\n-0.4\n\n\n-0.6\n\n\n-0.8\n\n\n-1.0\n\n\n\nSources: Ag-Incentives Database, Ivanic and Martin (2014b), World Bank.\nA. Nominal Rate of Protection (NRP) is computed as the price difference between the farm gate price\nreceived by producers and an undistorted reference price at the farm gate level. The reference price at the\nfarm gate level is defined as the net price of the product when it leaves the farm, after marketing costs have\nbeen subtracted. The undistorted farm gate price is defined as the price prevailing in competitive world\nmarkets.\n\nB. Percent of respondents based on a survey of 80 EMDEs.\nC. Estimates based on the Error Correction Model described in Annex 6.1. The coefficient of price\ninsulation ranges from 0 for countries that do not insulate against the rise in world prices, to -1 for\ncountries that adopt policies that fully insulate domestic markets. The error correction term represents the\ncost of being out of equilibrium or the speed with which polices achieve the target level of protection or at\nwhich policy makers move back toward this equilibrium after being forced away from it by a shock to\nworld prices. Based on data for 82 countries, of which 26 advanced economies, 44 EMDEs, and 12 LICs for\nthe\n\nMention: \"survey of 80 EMDEs\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"analyze\", \"summary\": \"Respondent survey of emerging economies reporting the share with active policies during the price spike.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:007642:36:0", "occurrence_id": "ef73fbdbf4ddf4ad00d8e476", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: The changes in population and per capita GDP will also have an impact on water demand for domestic\nand industrial uses. Projections from the Water Futures and Solutions fast‐track modeling effort which\nwere used to model water demand from domestic and industrial/energy users for SSPs 1‐3 (Wada et\nal. 2016). In our modeling approach, agriculture is the residual user of water, meaning demand for\nwater for domestic and industry/energy takes priority over agriculture (Figure 25).\n\n\nFigure 25. Water demand by domestic and industrial users by region from 2010‐2050 from PCR‐GLOBWB (Wada et al 2016)\n(km 3 ).\n\n\nBy 2050, global population is expected to increase about 9 billion in SSP2, 8.4 billion in SSP1 and 9.9\nbillion in SSP3. By 2100, the differences are more far greater: 6.8 billion in SSP1, 8.9 billion in SSP2,\nand 12.4 billion in SSP3. Global average per capita GDP triples in SSP1, doubles in SSP2, but increases\nonly 50% in SSP3 by 2050. The differences between SSPs are more dramatic on the regional level,\nespecially in AFR and SAR. Both population and per capita GDP impact the demand for crop and\nlivestock products.\n\n\nCompared the differences between the total production under _MaxInvest_ and _ZeroInvest_ investment\nstrategies, total production for SSP1 is the highest of all SSPs with most of the increase in production\ncoming from EAP. With higher incomes in SSP1, calorie availability increases in nearly all the regions,\nespecially in SAR and LCR compared to SSP2 and SSP3, though AFR and MNA see the largest increase\n\n\n35\n\nMention: \"PCR‐GLOBWB\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"analyze\", \"summary\": \"Water futures model providing projected domestic and industrial water demand by region under the scenarios.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "prwp", "source_key": "prwp:007664:19:0", "occurrence_id": "47352d0536bb6fb1647d4408", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: _Labor market distortions_\n\n\nDistortions in the labor market and rigid regulations have also combined to constrain\njob creation (especially for women and youth) and generate high and persistent\nunemployment. High hiring and firing costs are an important impediment in that regard,\nwhereas inadequate access to information hampers the efficient functioning and adjustment\nof the job market, most notably by constraining job search and making it costlier. Compared\nto neighboring countries, or countries at the same level of income, Morocco has one of the\nhighest ratios of minimum to average wages, which has an adverse impact on formal sector\nemployment and competitiveness in labor‐intensive industries. Other sources of distortions\nin the labor market in Morocco include the quality (or lack thereof) of cooperation between\nemployers and unions (which play a significant role in wage formation and labor practices),\nfrictions in the functioning of the legal framework for resolving labor disputes; and low impact\nof government programs, such as the National Agency for the Promotion of Employment and\nSkills (ANAPEC), to help young people find work. Another distortion is skill mismatches, as\ndiscussed next. According to the World Economic Forum's 2018 Global Competitiveness\nIndex, Morocco was ranked only 119, out of 140 countries, for labor market efficiency, as well\nas 91 for redundancy costs, 102 for the taxation of labor, and 103 for hiring and firing\npractices.\n\n_Education System and the Quality of Human Capital_\n\n\nWeaknesses in Morocco’s education system have also contributed to low job creation,\nlow quality of the workforce, and high unemployment. According to the World Economic\nForum (2018), Morocco is ranked 95 out of 140 countries in terms of its pupil‐to‐teacher ratio\nin primary education – a common indicator of the quality of basic education. At about 70\npercent, the gross enrollment rate in secondary education in Morocco is one of the lowest in\nMENA. Dropout rates are also among the highest; 72 percent of students leave the education\nsystem without qualification. Among\n\nMention: \"2018 Global Competitiveness\nIndex\""}, {"role": "assistant", "content": "{\"role\": \"supporting\", \"usage_action\": \"analyze\", \"summary\": \"Comparative rankings on labour market efficiency, redundancy costs, labour taxation and hiring practices cited as evidence.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "reliefweb", "source_key": "reliefweb:000199:9:0", "occurrence_id": "ac4390b97b83daffbe3843cb", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: Situation Overview\n\n\nIn 2024, some 3.8 million people are recognized as refugees or persons in refugee-like situation in Iran,\nmaking Iran the largest refugee-hosting country in the world, according to UNHCR Global Trend Report\npublished in June 2024. The country continues to face innumerable challenges to meet the protection and\nhumanitarian needs of this displaced population. The RRP is funded only at 18% of the required budget\n(USD 46 million against overall needs of 252 million), resulting in reduced access to protection and essential\nservices, in particular for the most vulnerable.\n\n\nAccess to protection and essential services has been largely governed by their documentation status\nthrough several new government-led schemes. In May 2023, the Government of the Islamic Republic of Iran\nannounced plans to issue a new unified smart ID card to consolidate the various forms of documentation\nheld by foreign nationals in Iran, aiming to replace Amayesh cards for long-stay Afghans, _Hoviat_ cards for\nIraqi refugees, 2022 headcount slips, special residence permits and family passports, with gradual access to\nbanking, judicial, and administrative services and SIM cards. The smart cards started to be issued early 2024.\nBy the end of June, a number of those who had been registered for Smart Governance Scheme has yet to\nreceive the card. Access to services has been limited for undocumented Afghans, In addition, Government has\ntaken more restrictive policies on undocumented Afghans.\n\n\nIn January 2024, another newly-established scheme called the Management of Immigrants and Foreign\nNational’s Micro and Macro Financial Resources in the Supply Chain (hereinafter the Financial Scheme) was\nintroduced. According to the National Organization for Migration (NOM), the scheme aims to create a safe\nenvironment for investment for foreign nationals, calling for voluntary financial deposit from foreigners to\nenable access to various governmental and infrastructural services. The rights associated with the “foreign\ninvestor” status remains the most complex, with clarification sought on the voluntary nature of the scheme,\nand effective access to services.\n\nMention: \"UNHCR Global Trend Report\""}, {"role": "assistant", "content": "{\"role\": \"supporting\", \"usage_action\": \"inform\", \"summary\": \"Report cited for the 3.8 million refugees and refugee-like population making Iran the largest hosting country.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "reliefweb", "source_key": "reliefweb:000608:1:1", "occurrence_id": "47e8f89da94d424ead2f9409", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: after several days of intense fighting, Goma fell under AFC/M23\ncontrol, including the airport and the provincial government headquarters. For\nnearly a week, Goma was plunged into a total blackout, with no access to running\nwater, electricity, or the internet, further exacerbating the humanitarian crisis.\n\nAs of 7 th of February 5, 2025, reports indicate that the fighting killed over 2900\npeople, 2 injured more than 3000 3 people and displaced 500,000 people, while\nroad closures and insecurity further restrict humanitarian access. 4 A relative calm\nis now reportedly observed, with shops and businesses starting to reopen, though\nit remains fragile and volatile.\n\n\n_1_ _[Interactive map on mines in RDC (IPIS)](https://ipisresearch.be/mapping/webmapping/drcongo/v6/)_\n\n_[2 https://youtu.be/R-aD8mOCbI0https://youtu.be/R-aD8mOCbI0?si=iMoFFf93fBY02Y6t?si=iMoFFf93fBY02Y6t](https://youtu.be/R-aD8mOCbI0?si=iMoFFf93fBY02Y6t)_\n\n_3 SRSG allocution at the 37th special session of the Human Rights Council_\n\n\n_4_ _[https://news.un.org/en/story/2025/02/1159756](https://news.un.org/en/story/2025/02/1159756)_\n\n\nUNHCR 2\n\nMention: \"Interactive map on mines in RDC\""}, {"role": "assistant", "content": "{\"role\": \"supporting\", \"usage_action\": \"inform\", \"summary\": \"Interactive mapping product referenced for mined areas underlying the conflict and displacement context.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "reliefweb", "source_key": "reliefweb:000670:15:1", "occurrence_id": "bc58332810ab9ba3a9dd39e9", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: . No common factor has been shown to entirely explain variance in integration\nlevels in all three cases. However, some patterns are evident.\n\n\nFirst, temporal considerations contribute to refugee integration in all three countries.\nNepal, Pakistan, and Kenya all demonstrate a strong trend: refugees integrated with\nmore ease in past decades than they do today. As all three cases illustrate, profound\ngeopolitical shifts generate different perceptions, and therefore treatment, of refugees.\nOne UNHCR official has suggested that countries that previously embraced socialism\nand believed in sharing land have rejected such notions since the end of the Cold War,\nmaking local settlement and integration a less viable option for refugees. 21 Another\npossibility is that the advent of the international refugee regime has encouraged host\ncountries to utilize NGOs and UNHCR with greater frequency, and, in so doing,\ncontrol their refugee populations more directly and allow less integration. 22\n\n\nTime plays a critical role not only concerning when the conflict and refugee influx\noccurred in history, but also for what duration refugees remain as such. Particularly\n\n\n19 Internal statistical UNHCR documentation.\n20 While there is an SPLA presence in the camps, no one this author spoke to mentioned this as a reason\nwhy the Sudanese were in camps in such high numbers.\n21 Interview with Yassin Hamid, Senior Desk Officer, UNHCR. August 7, 2003.\n22 To the author's knowledge, this controversial notion, repeatedly present in the research for this paper,\nhas not been specifically studied with any methodological rigor. The relationship between\nUNHCR/NGO presence and refugee integration is suggested for further research.\n\n\n14\n\nMention: \"Internal statistical UNHCR documentation\""}, {"role": "assistant", "content": "{\"role\": \"supporting\", \"usage_action\": \"source\", \"summary\": \"Unpublished agency statistics cited in an endnote behind the refugee population figures used in the comparison.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "reliefweb", "source_key": "reliefweb:000702:13:0", "occurrence_id": "212ebbf043140cb14104a225", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: related complementary protection. 71 [^71: Earlier instances of complementary protection can be found in relation to League of Nations\ninstruments on refugee protection.] The refugees did not strictly fall within the\ntemporal requirements of the Convention definition, however the High Commissioner\ndetermined that since the flight of Hungarian refugees was related to recent events and\npolitical changes resulting from the end of the Second World War, they should be\nconsidered as falling within the Convention’s scope. 72 [^72: UNHCR ‘The Problem of Hungarian Refugees in Austria’ UN Doc A/AC.79/49 (17 January 1957)\nAnnex IV [4].] Austria followed this\ninterpretation when it granted asylum to 180,000 Hungarian refugees. 73 [^73: ibid.] It issued them\nwith normal refugee eligibility certificates as soon as technically possible, unless\nindividual status determination showed that a person was not entitled to the\nConvention’s benefits.\n\n\nMost other States granted protection on a prima facie basis, at least initially. 74 [^74: ibid [5].] Norway\ngranted all Hungarian citizens a residence permit for one year that included\npermission to work, renewed automatically on request. After two years, they could\nrequest a permanent residence permit, which was mostly granted. It was only at this\npoint that individual status determination took place. 75 [^75: Letter from A Fjellbu (Norwegian Refugee Council) to P Weis (1 July 1959), in UNHCR Archives\nFonds 11 Sub-fonds 1, 6/1/HUN.] The distinction between\nHungarian refugees and Convention refugees in Norway lay in the grant of travel\ndocuments. If an individual had not left Hungary for an article 1A(2) reason, then he\nor she was not entitled to a Convention travel document but to an alien’s passport. In\n\nMention: \"UNHCR Archives\nFonds\""}, {"role": "assistant", "content": "{\"role\": \"supporting\", \"usage_action\": \"source\", \"summary\": \"Archival holdings cited for the correspondence documenting Norwegian treatment of Hungarian refugees.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "reliefweb", "source_key": "reliefweb:000759:12:0", "occurrence_id": "3d1288aefa9d4ff344b10215", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: 2023 Post-Earthquake Population Movement Dynamics Analysis - Türkiye\n\n\n**Syrian and others moving westwards** : In 2023, 56,954 individuals were intercepted\n\n\nor rescued by the Turkish Coast Guard along the western sea borders 4 . Within this\n\n\ngroup, **Syrians** made up **only 18 per cent (9,984)** of the entire intercepted population.\n\n\nThe most intercepted groups remain Afghans and Palestinians. However, 2023 figures\n\n\nindicate a 97 per cent increase in the number of Syrians intercepted compared to the\n\n\nprevious year. The Turkish Coast Guard reported a 15 per cent 5 increase in the\n\n\ninterception of irregular migrants in 2023 when compared to 2022. **Afghans**, likely due\n\n\nto their protection situation in the broader region, constituted the most prevalent\n\n\nnationality among all intercepted individuals, accounting for 36 per cent of the total\n\n\ngroup (20,345 people). The number of Afghans intercepted in 2023 shows a 45 per\n\n\ncent increase when compared to 2022. Other nationalities in 2023 include Palestinians\n\n\n(10,736), Yemenis (6,186), people of the Democratic Republic of the Congo (2,131),\n\n\nLiberian (1,525), Sudanese (1026), Egyptians (957), Iraqi (737), Eritrean (593), Malian\n\n\n(485), and Somali (432). 6\n\n##### **Profile Observations**\n\n\nAccording to interview findings, **most refugees who opted to move within Türkiye**\n\n\n**post-earthquake** were families. In contrast, return movements to Syria were\n\n\nundertaken mainly by people travelling alone. A similar trend was indicated by the\n\n\nIAPNA Round 7, for which 52 per cent of all refugees leaving the earthquake area\n\n\nwere children displaced with their families or other caregivers.\n\nMention: \"IAPNA Round 7\""}, {"role": "assistant", "content": "{\"role\": \"supporting\", \"usage_action\": \"validate\", \"summary\": \"Survey round corroborating interview findings that most refugees leaving the earthquake area moved with families.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "reliefweb", "source_key": "reliefweb:000910:3:0", "occurrence_id": "aa53bf0a83659bf509932a21", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: **Current situation of Colombian refugees in Ecuador**\n\nIn 2008 UNHCR estimated in their Global Needs Assessment in Ecuador that there\nwere between 130,000 to 140,000 Colombians in need of international protection in\nEcuador. As of December 2010 the government of Ecuador had recognized 53,342\nrefugees, a long way from the 390 recognized at the end of 2000.\n\n**Table 1: UNHCR’s population of concern in Ecuador, end 2009**\n\n\n\n\n\n\n\n\n\n\n\n\n\n|Refugees|People in
refugee-like
situations|Total refugees
and people in
refugee-like
situations|Assisted by
UNHCR|Asylum
seekers
(pending)|Total
population of
concern|\n|---|---|---|---|---|---|\n|
45,192|
71,365|
116,557|
45,192|
50,632|
167,189|\n\n\n**Table 2: Breakdown of UNHCR’s population of concern in Ecuador, end 2009** **1** [^1: _UNHCR_ _2009 Global Trends,_ UNHCR, June 2010.]\n\n\n\n\n\n\n\n\n\n\n\n\n\n|Type of population|Origin|Total|Assisted by UNHCR|Per cent
females|Per cent
under 18|\n|---|---|---|---|---|---|\n|Refugees
|Colombia|44,400|33,400|48|28|\n|Refugees
|Various|800|800|34|9|\n|People in a
refugee-like situation|Colombia|71,400|10,900|||\n|As\n\nMention: \"Global Needs Assessment in Ecuador\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"analyze\", \"summary\": \"Assessment supplying the estimate of 130,000-140,000 Colombians needing international protection in Ecuador.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "reliefweb", "source_key": "reliefweb:000926:2:1", "occurrence_id": "124fe949c5d4dc4c5966351d", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: for Victims (UARIV). The coordinated\nwork between UNHCR and the Sub-Directorate General notices a change in terms of the\nnumber of cases in which the entry register is based on displacement situations, in urban\nviolence situations and in the degree of inclusion of data in the register.\n\n\nThis is where it becomes necessary to think about how to respond to the challenges of\nprotection – in humanitarian language – and how to promote and strengthen the compliance\nof State responsibilities under international human rights standards. Doing so requires a\nmultidimensional perspective of human mobility taking into consideration the actors who\noperate in the context of expulsion, transit and reception, and additional causes of generalized\nviolence.\n\n\nIn line with its protection strategy 9 [^9: The protection strategy prioritizes four objectives: a) to promote mitigation to specific risks of boys, girls and\nwomen, and action against mines; b) to respond to the humanitarian needs of displaced populations and\ncommunities affected by the conflict by strengthening the protection response; c) to influence the agendas of\ngovernment at the national, departmental and municipal level as well as the donors, making visible the impact of\nthe conflict and the humanitarian needs; d) protection is central to the humanitarian action of all actors and\ncoordination mechanisms in the humanitarian coordination architecture.] and its mandate to promote respect, protection and\nguarantee of human rights in humanitarian action, the Protection Cluster gives priority to\nidentify protection risks and gaps in the State’s response to violence in urban areas, to clarify\nthe applicability of the protection legal frameworks and obligations of duty bearers, to\npromote comprehensive responses based on the international human rights law and\ninternational humanitarian law, and to propose coordinated action between the Humanitarian\nCountry Team and the United Nations System. In this regard, it is essentialventura\n\nMention: \"entry register\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"analyze\", \"summary\": \"Administrative register whose case entries on displacement and urban violence show changing coverage under joint work.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "reliefweb", "source_key": "reliefweb:000960:20:0", "occurrence_id": "9de6f59b9a0787b8acb587ed", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: In Guatemala and Nicaragua, the distribution modalities were amended after\nmounting evidence that cash grants were not being used for the purposes for which\nthey were designed, so that a portion of the grant (including that allocated in respect\nof any children) was paid directly to women. In Burundi women have been\nencouraged to assume the role of “administrator” of the bank account. The decision\nwhether to take on this role, however, is left to both spouses. However, in cases were\ngrants have been paid directly to women, there has been little or no monitoring of\nany potentially negative protection implications.\n\n\n_Security Issues_\n\n\nThe review found little evidence of security risks posed by the use of cash grants.\n\nIn some cases “security plans for cash distribution” existed (Afghanistan 1990-93) In\nGuatemala concerns about the risk of transporting large amounts of cash were raised.\n\n\n_Verification and the avoidance of ‘recycling’_\n\n\nThe biggest challenge encountered in nearly every operation was “recycling” (i.e.\nwhen returnees attempt to receive the cash grant more than once.\n\nRecycling can be countered by making entitlement to assistance contingent on\nverification against a registration database (Afghan refugees in Iran 2000, Burundian\nrefugees in Tanzania). Cross-checking of VRFs, pre-registration or use of family\nphotos, inspections of vehicles and truckloads, have all been used as techniques to\nreduce recycling. The use of biometric verification mechanisms (such as iris scanning\nof Afghans or fingerprinting of Guatemalans) is believed to have significantly\nreduced recycling and to be a effective means of discouraging it. However, in the\nabsence of baseline data, the impact of such mechanisms is difficult to assess. In\ngeneral, without a comprehensive data protection policy framework, heavy reliance\non electronic records and use of biometrics raises certain dilemmas.\n\n**5. Lessons learned and effective/ineffective practices**\n\n_General_\n\n\n - Cash grants can be a useful tool for UNHCR to ease the delivery of\n\nMention: \"registration database\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"validate\", \"summary\": \"Registration records used to verify entitlement and prevent returnees collecting a cash grant more than once.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "reliefweb", "source_key": "reliefweb:001052:52:1", "occurrence_id": "d5ee63a6c8d52926e3f503ed", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: UNHCR survey on birth\n\nregistration revealing that 77 per cent of 781\n\nrefugee newborns did not have an official birth\n\ncertificate. This problem was particularly prevalent\n\nin the Bekaa Valley and the north of Lebanon.\n\n\nUNHCR staff in Jordan also confirmed that access\n\nto birth registration is a serious concern. In\n\nZa’atari camp, over 1,400 children born between\n\nthe end of November 2012 and the end of July\n\n2013 have not received birth certificates.\n\n\nBirth certificates are now issued on a weekly\n\nbasis by the Civil Registry in Mafraq, Jordan. From\n\n1 August to 12 October 2013, 66 birth certificates\n\nwere issued to babies born in Za’atari camp, a\n\ndramatic increase from the two birth certificates\n\nissued between January and July 2013.\n\n\nThe classification of Syrian personal identity\n\ndocuments by UNHCR staff in a new Jordanian\n\nreception centre, Rabaa Al-Sarhan, has made\n\nit possible to find and copy Syrian identity\n\ndocuments for families. This helps those seeking\n\nto register their newborns in Za’atari camp.\n\n\n55\n\nMention: \"UNHCR survey on birth\n\nregistration\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"analyze\", \"summary\": \"Survey of 781 refugee newborns documenting that 77 per cent lacked an official birth certificate.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "reliefweb", "source_key": "reliefweb:001203:18:0", "occurrence_id": "9b282b1c4761301ecd380775", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: METHODS\n\n\n**Country Contexts: Jordan, KRI, Lebanon**\n\n\nAs of December 2016, almost 230,000 registered Syrian refugees reside in KRI, approximately 655,000 in\nJordan, and around one million in Lebanon. They continue to face grinding challenges, including limited\nlivelihood and education opportunities as well as racism and public harassment. Refugees throughout the\nregion are being pushed deeper into poverty as their savings become depleted: 93 per cent of registered\nSyrian refugees residing outside of camps in Jordan and more than 70 per cent of refugee households in\nLebanon live below the national poverty line; in Iraq, 37 per cent live below the poverty line. In addition,\nmore than 110,000 Palestine refugees from Syria (PRS) have fled the conflict, and are confronted with a\nvariety of protection risks such as refoulement, in part due to their irregular status as “double refugees.”\n\n\nThe Regional Refugee and Resilience Plan (3RP) has made important gains in coordinating a coherent\nregional response to the Syria crisis. However, needs have outstripped funding with only 56 per cent of the\ntotal $4.54 billion appeal by the 3RP funded as of September 2016. The protection sector is underfunded by\n52 per cent, compromising the delivery of key services including SGBV programmes. In addition to being\nunable to sufficiently meet refugees’ basic needs, the lack of funding has long-ranging consequences as\nwell: a UNDP assessment of violence in Iraq found that underserved communities were eight times more\nlikely to engage in violence or violent behavior than those who were economically resilient.\n\n\nUnited Nations High Commissioner for Refugees, 3RP Regional Refugee and Resilience Plan 2017-2018 in Response\nto the Syria Crisis: Regional Strategic Overview (December 2016).\n\n\n**• Document review**\nA literature review on SVM in conflict settings was undertaken, with a particular focus on the MENA region.\nDocuments included published research, grey literature including external and internal UN and NGO documents,\nand GBV IMS\n\nMention: \"UNDP assessment of violence in Iraq\""}, {"role": "assistant", "content": "{\"role\": \"supporting\", \"usage_action\": \"inform\", \"summary\": \"Assessment finding underserved communities far more likely to engage in violence, used to argue funding consequences.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "reliefweb", "source_key": "reliefweb:001203:18:0", "occurrence_id": "034355a6869bed9d81180aab", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: METHODS\n\n\n**Country Contexts: Jordan, KRI, Lebanon**\n\n\nAs of December 2016, almost 230,000 registered Syrian refugees reside in KRI, approximately 655,000 in\nJordan, and around one million in Lebanon. They continue to face grinding challenges, including limited\nlivelihood and education opportunities as well as racism and public harassment. Refugees throughout the\nregion are being pushed deeper into poverty as their savings become depleted: 93 per cent of registered\nSyrian refugees residing outside of camps in Jordan and more than 70 per cent of refugee households in\nLebanon live below the national poverty line; in Iraq, 37 per cent live below the poverty line. In addition,\nmore than 110,000 Palestine refugees from Syria (PRS) have fled the conflict, and are confronted with a\nvariety of protection risks such as refoulement, in part due to their irregular status as “double refugees.”\n\n\nThe Regional Refugee and Resilience Plan (3RP) has made important gains in coordinating a coherent\nregional response to the Syria crisis. However, needs have outstripped funding with only 56 per cent of the\ntotal $4.54 billion appeal by the 3RP funded as of September 2016. The protection sector is underfunded by\n52 per cent, compromising the delivery of key services including SGBV programmes. In addition to being\nunable to sufficiently meet refugees’ basic needs, the lack of funding has long-ranging consequences as\nwell: a UNDP assessment of violence in Iraq found that underserved communities were eight times more\nlikely to engage in violence or violent behavior than those who were economically resilient.\n\n\nUnited Nations High Commissioner for Refugees, 3RP Regional Refugee and Resilience Plan 2017-2018 in Response\nto the Syria Crisis: Regional Strategic Overview (December 2016).\n\n\n**• Document review**\nA literature review on SVM in conflict settings was undertaken, with a particular focus on the MENA region.\nDocuments included published research, grey literature including external and internal UN and NGO documents,\nand GBV IMS\n\nMention: \"GBV IMS\""}, {"role": "assistant", "content": "{\"role\": \"supporting\", \"usage_action\": \"curate\", \"summary\": \"Case management information system data included among the grey literature reviewed for the study.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "reliefweb", "source_key": "reliefweb:001645:18:1", "occurrence_id": "31c84e0f1c5c2e1cbd45d4b2", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: Mexican Act on Refugees and Complementary Protection ( _Ley sobre Refugiados y_\n_Protección Complementaria)_, which entered into force on 28 January 2011, incorporates the\nrefugee definition as provided in the 1951 Refugee Convention. 133 Additionally, it recognizes\n‘gender’ to be a separate ground of persecution 134 and it includes the refugee definition of the\nCartagena Declaration. 135 [^135: Americas - Miscellaneous, _Cartagena Declaration on Refugees, Colloquium on the International Protection_\n_of Refugees in Central America, Mexico and Panama_, 22 November 1984, available at:\nhttp://www.unhcr.org/refworld/docid/3ae6b36ec.html [last accessed: 22 April 2012].] That means that also persons who fled their country “whose life,\nsecurity or liberty were threatened due to generalized violence, foreign aggression, internal\n\n\n132 IOM Diagnóstico 2011, _supra_ note 12, p. 56.\n133 Ley sobre Refugiados y Protección Complementaria, Diario Oficial de la Federación 27 de enero de 2011\n(Act on Refugees and Complementary Protection, official publication 27 January 2011), available at:\nhttp://www.diputados.gob.mx/LeyesBiblio/pdf/LRPC.pdf [last accessed: 22 April 2012] (hereinafter: _Act on_\n_Refugees and Complementary Protection_ ), Article 13(I); 1951 Convention Relating to the Status of Refugees,\navailable at: http://www.unhcr.org/3b66c2aa10.html [last accessed: 22 April 2012].\n134 Article 1A (2) of the 1951 Refugee Convention gives the following persecution grounds: race, religion,\nnationality, membership of a particular social group, and political opinion.\n135 Americas - Miscellaneous, _Cartagena Declaration on Refugees, Colloquium on the International Protection_\n_of Refugees in Central America, Mexico and Panama_, 22 November 1984, available at:\nhttp://www.unhcr.org/refworld/docid/3ae6b\n\nMention: \"IOM Diagnóstico 2011\""}, {"role": "assistant", "content": "{\"role\": \"supporting\", \"usage_action\": \"source\", \"summary\": \"Migration diagnostic cited by page number as background evidence earlier in the discussion of Mexican asylum law.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "umar_pads", "source_key": "umar_pads:000034:3:0", "occurrence_id": "bd9df6c28f15fcc6b8aada3f", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: **The World Bank**\nWomen's Voices in the Monitoring and Improvement of Indonesia's Universal Health Care Insurance Services\n\n\n[2] The World Bank in Indonesia, April 2020, https://www.worldbank.org/en/country/indonesia/overview\n\n\nSectoral and Institutional Context\n**Health outcomes and outputs in Indonesia have improved in recent years.** Life expectancy is 71, which has\nnot increased from 2013 to 2018. Under-five mortality has declined from 29/1,000 live births in 2013 to\n25/1,000 live births in 2018 and Indonesia is projected to meet the child-health related to Sustainable\nDevelopment Goals (SDGs). According to the Susenas-SSGBI 2019, 27.7 percent of Indonesian children under\n5 years of age were stunted (almost 8 million children), 16.3 percent of children under five were underweight\nand 7.4 percent were wasted (low weight-for-height). Although the prevalence of stunting declined\nsignificantly from the 2013 (37.2%), the stunting rates remain unacceptably high. However, key challenges\nremain, including slow progress on maternal mortality and chronic malnutrition, as well as inequalities in\nhealth outcomes.\n\n\n**Indonesians have become healthier over the past several decades but are now faced with an unfinished**\n**Millennium Development Goal agenda and a growing non-communicable disease (NCD) burden.** Between\n1960 and 2018, life expectancy increased from 45 to 71.5 years, under-five mortality declined from 222 to 25\nper 1,000 live births, and infant mortality declined six-fold to 21 per 1,000 live births. However, a maternal\nmortality ratio (MMR) of 305 per 100,000 live births (or 1.4 maternal deaths every 1.4 hours) remains high\nrelative to its income level and regional peers. One-third of children\n\nMention: \"Susenas-SSGBI 2019\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"analyze\", \"summary\": \"Household survey reporting stunting, underweight and wasting among children under five.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "umar_pads", "source_key": "umar_pads:000394:4:1", "occurrence_id": "f22265f126b7ed7cc65297d3", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: the adoption of a high-level strategy to ensure universal access to civil registration,\nand the creation of an ID management database which will feed into the digital governance strategy. The\nreforms will build on the 2017 National Strategy for Civil Registration reform, and the adoption of new\nlegislation in 20194, which calls for the creation of a National Civil Registration and Identification Center\n(NCRIC) to manage the central civil registry and national identification databases, which will be the\nfoundation for the issuance of identity credentials. Following the onset of the COVID crisis, the President\nof the Republic announced the creation of a population registry for all areas affected by the lockdown, to\nfacilitate the implementation of cash transfers.\n\n\n**8.** **The Presidency has created a digital governance unit to develop and coordinate the**\n**implementation of the national digital governance strategy** **5**, which is fully aligned with the PRODIGY\nproject. The strategy is based on international best practice, including an agile and user-centric design\napproach. A Chief Digital Officer (CDO), with longstanding private sector expertise, was recruited in\nDecember 2019 to lead the digital governance unit. The government is currently setting up the remaining\nteam within the DGU, and the CDO has begun reviewing and supporting the development of various digital\nservices 6 .\n\n\n4 Law #2018-027 on civil registry\n\n\n5 The digital governance strategy was presented by the Secretary General of the Presidency in October 2019.\n6 These digital services are aligned with the PDO of the PAPSP. Additional services that are not related to this\nproject will supported once the PRODIGY funds are available.\n\n\nMar 11, 2020 Page 5 of 14\n\nMention: \"population registry\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"inform\", \"summary\": \"Registry announced for lockdown areas to identify recipients and deliver cash transfers.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "umar_pads", "source_key": "umar_pads:000454:4:2", "occurrence_id": "e2d28987af5893bc01a47d9b", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: with no formal education which stands at 73 percent. When the distribution of the working age\npopulation is disaggregated by gender and geographic location, the following are observed: (i) there are\nrelatively more women (58 percent) than men (48 percent) who have not received a formal education; and (ii)\nrural areas, and especially regions of Kaffrine, Mattam and Djourbel, have the highest proportion of the working\nage population with no formal education. For example, 82 and 81 percent of the population in Kaffrine and\nMattam regions, respectively, have not received any formal education, and on average, rural areas have higher\npercentages of working age people (73 percent) with no education compared to urban areas (36 percent).\n\n\n2 “World Bank. 2019. Ending Learning Poverty : What Will It Take?. World Bank, Washington, DC. © World Bank.\nhttps://openknowledge.worldbank.org/handle/10986/32553 License: CC BY 3.0 IGO\n3 This calculation is proxied by data from grade 6 in 2014 from the PASEC. Better performance in the 2019 PASEC may result in a\nlower learning poverty rate, although out of school rates remain high.\n\n\nNov 03, 2021 Page 5 of 11\n\nMention: \"data from grade 6 in 2014\""}, {"role": "assistant", "content": "{\"role\": \"supporting\", \"usage_action\": \"analyze\", \"summary\": \"Grade 6 results used as a proxy to compute the learning poverty rate cited in the analysis.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "umar_pads", "source_key": "umar_pads:000454:4:2", "occurrence_id": "d8665ed8d1b76c4093f51536", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: with no formal education which stands at 73 percent. When the distribution of the working age\npopulation is disaggregated by gender and geographic location, the following are observed: (i) there are\nrelatively more women (58 percent) than men (48 percent) who have not received a formal education; and (ii)\nrural areas, and especially regions of Kaffrine, Mattam and Djourbel, have the highest proportion of the working\nage population with no formal education. For example, 82 and 81 percent of the population in Kaffrine and\nMattam regions, respectively, have not received any formal education, and on average, rural areas have higher\npercentages of working age people (73 percent) with no education compared to urban areas (36 percent).\n\n\n2 “World Bank. 2019. Ending Learning Poverty : What Will It Take?. World Bank, Washington, DC. © World Bank.\nhttps://openknowledge.worldbank.org/handle/10986/32553 License: CC BY 3.0 IGO\n3 This calculation is proxied by data from grade 6 in 2014 from the PASEC. Better performance in the 2019 PASEC may result in a\nlower learning poverty rate, although out of school rates remain high.\n\n\nNov 03, 2021 Page 5 of 11\n\nMention: \"PASEC\""}, {"role": "assistant", "content": "{\"role\": \"supporting\", \"usage_action\": \"validate\", \"summary\": \"Later assessment round noted as potentially lowering the learning poverty estimate.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "umar_pads", "source_key": "umar_pads:000486:2:1", "occurrence_id": "90226011197597a2703c945c", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: of the population. There is a clear recognition among high-level authorities\nthat tackling the problem of air pollution is crucial for enhancing the quality of life, strengthening competitiveness\nand reinforcing the achievement of objectives of Poland’s global climate related commitments.\n\nPoland has come under considerable national and international scrutiny because of air pollution. Although Poland\nhas made considerable progress in reducing air quality pollutants such as SO2 and NOX, it has made more limited\nprogress in reducing particulate pollution from coarse and fine particulates (PM10 and PM2.5 respectively), leading to\nnon-compliance with EU standards. In early 2018, the European Court of Justice found Poland guilty of failing to\nmeet air quality norms, and in particular for repeatedly failing to meet the EU’s daily and annual limits for course\nparticulates. Failing remedial actions, the EC could impose financial penalties on Poland.\n\nThe current government made the fight against air pollution its top priority. The 2017 Governmental Clean Air\nProgram (CAP) put forward 15 measures structured around three pillars: (i) improving boiler standards;\n(ii) improving solid fuel standards; (iii) education and awareness; and (iv) supporting and tackling energy poverty.\n\nSectoral (or multi-sectoral) and Institutional Context of the Program\n\nPoland has made impressive achievement in decoupling energy growth from economic growth but must now deal\nwith serious local and global environmental problems due to its reliance on coal. Between 1987 and 2016, Poland\nreduced its energy intensity by 30 percent – more than any other country reviewed in IEA’s Energy Efficiency Report\n2017. Between 2000 and 2016, the shares of renewable energy (RE), mainly biomass and wind, and natural gas in\nthe electricity generation mix more than quintupled, reducing the coal share by 12 percentage points. However,\nPoland’s energy sector faces serious environmental problems, that if not addressed, could jeopardize the country’s\nprogress toward sustainability.\n\n\nMar 18, 2019 Page 3 of 9\n\nMention: \"Energy Efficiency Report\n2017\""}, {"role": "assistant", "content": "{\"role\": \"supporting\", \"usage_action\": \"analyze\", \"summary\": \"Cross-country review used to benchmark Polands 30 percent fall in energy intensity since 1987.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "umar_pads", "source_key": "umar_pads:000504:5:0", "occurrence_id": "4b3871b89a7fc90c781a84e0", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: **The World Bank**\nRenewable Energy Development Project (P170236)\n\n\nfor the period from 2019 – 2020.\n\nAs part of the preparation of the Master Plan, the GoCV developed a RE Atlas in 2010 which identified the sites for potential\nsolar and wind projects and designated them as Renewable Energy Development Zones (Zonas de Desenvolimento de\nEnergia Renovável, or ZDERs) under the Decree Law no. 1/2011. The ZDERs are reserved for VRE projects. A dynamic\nstability study identified associated infrastructure investments required to facilitate increased RE penetration, mainly\nstorage and grid extension and reinforcement.\n\nThe GoCV plans to attract private sector investment to larger VRE projects (5 MW and above) through tenders for\nIndependent Power Producers (IPPs). Public funds are planned be used to finance small-scale RE generation that cannot\nattract private developers.\n\nThe GoCV also seeks to capitalize on its potential for distributed energy generation; Cabo Verde is estimated to have 250\nMW of rooftop solar PV potential, of which only 4 MW has been installed so far. Studies under the Distributed Solar Energy\nSystems Project (P151979) identified challenges for scaling up distributed generation, including lack of adequate financing\nfor residential and small and medium enterprises (SMEs), insufficient local technical capacity and import duties. In 2019,\nthe GoCV approved regulation for net billing, which allows solar PV system owners to export any surplus production to\nthe grid at a pre-defined tariff (approximately USD 0.08/kWh). Additionally, the GoCV budgeted USD 5 million in 2019 to\nprovide subsidies to commercial banks to reduce lending rates on distributed PV generation systems, which is expected\nto support approximately 3 MW of additional distributed solar generation.\n\n\nRelationship to CPF\n\nThe Project aligns with the draft CPF under preparation for FY20-25 and seeks to address key challenges identified in the\nStrategic Country Diagnostic published in March 2019.\n\nIt is directly aligned with the draft\n\nMention: \"RE Atlas\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"analyze\", \"summary\": \"Spatial atlas identifying solar and wind sites that were designated as reserved renewable energy development zones.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "umar_pads", "source_key": "umar_pads:000569:2:1", "occurrence_id": "15a9b78d6602293ffa6bec60", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: spatially unbalanced outcomes for the population. The\npopulation in Metropolitan Lima and Callao reached 10,479,899 in 2017, accounting for one third of the total population\nof the country. The cost of service delivery and connectivity in the vast Sierra and Selva regions is high, which has\nconcentrated economic activity in the Costa region, especially in the area of Lima, the country’s capital.\n\n\n3. **According to the figures of the Ministry of Interior, between 2011 and 2017 crimes increased by 8.91% at the**\n**national level.** In the case of the districts of Metropolitan Lima and Callao, the number of crimes increased by 6.07% and\n3.58% annually respectively during the same period. Likewise, the cases of emergencies registered by the Firefighter\ndepartment of Peru have increased by 2.68%, between 2012 and 2018. In 2018, the main emergencies attended where\nthe following: medical emergencies (52.68%), traffic accidents (13.39%) and fires (11.25%). According to national surveys\nthat correspond to the January-June 2018 semester, 85.3% of the population of the urban area perceive that in the next\ntwelve months they may be victims of criminal offenses that may threaten their safety.\n\n\n4. **Gender based violence (GBV) in Peru is one of the highest in Latin America and is present in all regions and**\n**across all socioeconomic strata.** Two out of three women in Peru experience intimate partner violence (IPV), however\n\n\nMay 06, 2019 Page 3 of 10\n\nMention: \"figures of the Ministry of Interior\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"analyze\", \"summary\": \"Ministry records reporting an 8.91 percent national rise in crime over the period, with district-level detail.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "umar_pads", "source_key": "umar_pads:000585:3:1", "occurrence_id": "7e3197148d2a37841ee98406", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: insufficient infrastructure, elevate the exposure and vulnerability, thus generating significant and frequent human\nand economic impacts.\n\n\n7. **Impacts due to disasters and climate change are expected to grow.** Through its lasting Technical Assistance sustained\nby the Global Facility for Disaster Risk Reduction (GFDRR), the World Bank has been able to develop cutting edge\nknowledge on Brazil’s exposure to disaster risks. For instance, between 1995 and 2014, Brazil has reported losses on\nthe average of BRL 800 million monthly according to an assessment of over 23 thousand reports from National, State\nand Municipal Civil Defense. In addition, a novel study in Santa Catarina led to the understanding that disaster events\ncan lead to annual average losses of BRL 645 million while a 20-year return period event can incur losses up to BRL 2.3\nbillion to the State. The report gave the WB Team the ability to project future losses and therefore be better prepared\nto justify investments to mitigate risks through urban resilience lenses 2 .\n\n\n8. **The** **Southern Region is no exception to the increasing urban and disaster issues in Brazil.** With an extension of\n563,802 km 2 and a population of 29.6 million inhabitants (85% in urban areas), the region encompasses the states of\nParaná, Santa Catarina, and Rio Grande do Sul. It is recurrently affected by floods, flash-floods, droughts, landslides,\nwindfalls, among others. According to Federal Data (S2ID System 3 [^3: S2ID: Sistema Integrado de Informações de Desastres [https://s2id.mi.gov.br/]] ), 8,428 events were classified and reported by the\nCivil Defense as disasters in the three Southern States between 1991 and 2017, which resulted in 459 deaths, 1.87\nmillion people displaced or made homeless, and a total of 36.87 million people affected.\n\nMention: \"Federal Data\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"analyze\", \"summary\": \"Federal disaster records quantifying events, deaths, displacement and affected people in the southern states.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "umar_pads", "source_key": "umar_pads:000585:3:1", "occurrence_id": "eb94d01bf7fdf43da0b35592", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: insufficient infrastructure, elevate the exposure and vulnerability, thus generating significant and frequent human\nand economic impacts.\n\n\n7. **Impacts due to disasters and climate change are expected to grow.** Through its lasting Technical Assistance sustained\nby the Global Facility for Disaster Risk Reduction (GFDRR), the World Bank has been able to develop cutting edge\nknowledge on Brazil’s exposure to disaster risks. For instance, between 1995 and 2014, Brazil has reported losses on\nthe average of BRL 800 million monthly according to an assessment of over 23 thousand reports from National, State\nand Municipal Civil Defense. In addition, a novel study in Santa Catarina led to the understanding that disaster events\ncan lead to annual average losses of BRL 645 million while a 20-year return period event can incur losses up to BRL 2.3\nbillion to the State. The report gave the WB Team the ability to project future losses and therefore be better prepared\nto justify investments to mitigate risks through urban resilience lenses 2 .\n\n\n8. **The** **Southern Region is no exception to the increasing urban and disaster issues in Brazil.** With an extension of\n563,802 km 2 and a population of 29.6 million inhabitants (85% in urban areas), the region encompasses the states of\nParaná, Santa Catarina, and Rio Grande do Sul. It is recurrently affected by floods, flash-floods, droughts, landslides,\nwindfalls, among others. According to Federal Data (S2ID System 3 [^3: S2ID: Sistema Integrado de Informações de Desastres [https://s2id.mi.gov.br/]] ), 8,428 events were classified and reported by the\nCivil Defense as disasters in the three Southern States between 1991 and 2017, which resulted in 459 deaths, 1.87\nmillion people displaced or made homeless, and a total of 36.87 million people affected.\n\nMention: \"S2ID System\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"analyze\", \"summary\": \"Integrated disaster information system into which civil defense bodies classify and report events.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "umar_pads", "source_key": "umar_pads:000654:2:1", "occurrence_id": "b20bc71e34abae4c0b6cb370", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: next couple of\nyears is regularly featured in the media and has since sparked an excitement for renewable energy amongst\nHaitians.\n\n\n[1] The World Bank Group’s (WBG) Fragile, Conflict and Violence Group (formally the Center on Conflict,\nSecurity and Development CCSD) annually releases the Harmonized List of Fragile Situations. ‘Fragile\nSituations’ include countries or territories with (i) a harmonized CPIA country rating of 3.2 or less, and/or (ii)\nthe presence of a UN and/or regional peace-keeping or political/peace-building mission during the last three\nyears. Haiti meets both criteria – with a WBG CPIA of 2.875 in FY18.\n\n\n[2] Verner, Dorte; Heinemann, Alessandra. 2006. Social Resilience and State Fragility in Haiti: Breaking the\nConflict-Poverty Trap. en breve; No. 94. World Bank, Washington, DC. © World Bank:\nhttps://openknowledge.worldbank.org/handle/10986/10311\n\n\n**Kenya**\n\n\nKenya is the global leader in the adoption of off-grid solar technology, with approximately nearly 10 million\npeople now meeting their basic electricity needs (Tier 1) with quality-verified off-grid solar products. The\nKenyan government has now included off-grid access into its 2018 Kenya National Electrification Strategy\n(KNES). Kenya has also adopted national standards for off-grid solar products that are harmonized with\nLighting Global Quality Standards.\n\n\n**Nigeria**\n\n\nMillions of Nigerians do not have access to grid electricity, relying instead on polluting lighting sources such\nas kerosene lanterns, candles, and torches. The situation in rural areas is particularly acute with only 41.1%\n\n\nSep 11, 2019 Page 3 of 18\n\nMention: \"Harmonized List of Fragile Situations\""}, {"role": "assistant", "content": "{\"role\": \"supporting\", \"usage_action\": \"analyze\", \"summary\": \"Annual harmonized listing classifying countries as fragile using policy ratings and peacekeeping presence.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "umar_pads", "source_key": "umar_pads:000846:4:0", "occurrence_id": "88b69ee2d1e2721c6a3e7fc4", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: **The World Bank**\nUnleashing the Blue Economy of the Eastern Caribbean (UBEEC) (P171833)\n\n\n7. **The fisheries sector remains an important source of jobs and food security in the OECS region.** Whereas the marine\ncapture fisheries and aquaculture sector represent less than 1% of GDP of OECS countries, it employs between twenty\npercent (Dominica) and seven percent (SVG) of the total labor force 9 [^9: FAO Fishery and Aquaculture Country Profiles http://www.fao.org/fishery/countryprofiles/search/en] and is a key supplier to the hotel sector. Women\nconduct the majority of supportive roles and processing and marketing work in the fisheries sector, but their roles\nmay not be adequately measured, valued, and/or compensated. 10 [^10: Nembhard, Nadine. “Caribbean Fisheries: Perspectives on Gender.” Gender in Fisheries Team, University of the West Indies - Centre for Resource Management and\nEnvironmental Studies.] The sector faces ongoing decline in overall landings\ndue to overfishing, poor governance, changing environmental conditions, and the falling domestic and international\ndemand caused by the COVID-19 crisis. Opportunities for sustainable blue growth in the fisheries sector rest on valueaddition, rebuilding depleted and overfished stocks, improving management through greater investment in data\ncollection and human resources, fostering fishers’ stewardship through co-management schemes, and combating\nIllegal, unreported and unregulated (IUU) fisheries.\n\n8. **Aquaculture, the world’s fastest growing food production system, has considerable potential to grow and generate**\n**jobs in the OECS, while diversifying island economies beyond tourism.** The commercial aquaculture sector in OECS\ncountries has traditionally been very small-scale with a focus on seamoss mariculture and on-shore farming of tilapia\nand shrimp. The lack of scale in off-shore aquaculture has been due to challenging environmental conditions, whereas\nthe factors limiting on-shore farming include competition for scarce flat land,\n\nMention: \"FAO Fishery and Aquaculture Country Profiles\""}, {"role": "assistant", "content": "{\"role\": \"supporting\", \"usage_action\": \"analyze\", \"summary\": \"Country fishery profiles supplying the shares of the labour force employed in capture fisheries and aquaculture.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "umar_pads", "source_key": "umar_pads:000846:4:1", "occurrence_id": "27dc439120c5a0b718001db9", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: to challenging environmental conditions, whereas\nthe factors limiting on-shore farming include competition for scarce flat land, and sometimes freshwater shortages.\nBut three important realities have paved way for increased aquaculture in the OECS: (i) new technological options for\ngrowing a wider range of species are being designed and piloted in and for small islands; (ii) export markets for seafood\nkeep growing; and (iii) local markets are likely to become an important source of demand for farmed seafood.\n\n9. **Ocean pollution is a significant issue for the OECS, damaging valuable natural capital, affecting the quality of life of**\n**local inhabitants and visitors, and impacting the economies of the entire region.** About eighty percent comes from\nland-based sources (mostly untreated wastewater, litter, and ag ricultural run-off) 11 [^11: Diez et al (2019). Marine Pollution in the Caribbean: Not a Minute To Waste. World Bank Group.], but industrial pollutants, heavy\nmetals and discharges from shipping and cruise ship also contribute to the problem. Analysis of the available marine\nlitter and plastics data collected in the Caribbean region indicates that much of the debris reaches the ocean from\nlandfills due to storms and coastal flooding, or after being dumped along roadsides or into creeks, rivers, storm drains\nand sewers. The lack of proper solid waste management, especially waste disposal systems and services, is extremely\nalarming. There is an apparent lack of overall and integral planning for the sector. This prevents efficient waste\ncollection operations where the recycling market is also relatively nascent. Tackling waste management will become\neven more important to the tourism competitiveness and socioeconomic sustainability as the OECS endeavors to\nattract back a shrinking number of international tourists.\n\n10. **At the regional level, the OECS took a first important step to promote a common approach to ocean governance by**\n**adopting the Eastern Caribbean Regional\n\nMention: \"marine\nlitter and plastics data\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"analyze\", \"summary\": \"Regional observations analysed to show that debris mostly reaches the ocean from landfills and roadside dumping.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "umar_pads", "source_key": "umar_pads:001030:48:0", "occurrence_id": "316d4855cd88b4299133a2d8", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: **The World Bank**\nSecond District Heating Efficiency Improvement Project (P172668)\n\n\nreporting and Operating Costs, including provision of consulting services;\n(ii) carrying out of TE’s and Project`s audits.\n\n\n9. **Heat and power generation in Chisinau** is expected grow after the investment under the project. The graph below\nshows heat and power generation forecast until 2035 from different sources.\n\n\n**10.** **Expected Results of the Investments:**\n\n`o` The heat generation capacity of the new cogeneration units covers the needed summer load and generates heat\n\nand power all the year round with high efficiency;\n\n`o` Reconstruction of Unit 2 at CHP Source-1 will extend the lifetime of the Unit by 50 000 hours (about 8\n\nOperational years), ensuring heat and electricity production at CHP Source-1. In addition, the investment will\nincrease gross electricity production capacity from 80 MWe up to 98 MWe and it will improve the total efficiency\nof the Unit by 1%;\n\n\nPage 40 of 60\n\nMention: \"heat and power generation forecast until 2035\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"analyze\", \"summary\": \"Projected output by source to 2035, shown to justify the planned generation investments.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "umar_pads", "source_key": "umar_pads:001376:14:1", "occurrence_id": "21b3c9ce29b67f4beae4da49", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: -2018, may suggest that welfare indicators may have deteriorated since. 6 [^6: Source: IHSI (Haitian Institute of Statistics - Institut Haïtien de Statistique et d'Informatique). Population data are projections based on\nthe 2003 census; poverty data on a 2012 household survey (ECVMAS – _Enquête sur les conditions de vie des ménages après le séisme_ ).]\n\n9. **While macroeconomic stability was broadly preserved in the years immediately after the 2010**\n**earthquake, a combination of domestic and external factors – including steadily falling levels of international**\n**aid – have weakened the macroeconomic framework.** Just after the earthquake, the authorities reduced the\nfiscal deficit supported by substantial donor assistance and inflation was kept in check. But the return of\ninternational aid to pre-earthquake level intensified fiscal pressure. Donor assistance fell from 15.8 percent of\nGDP in 2010 to 3.6 percent in 2019. Reduced donor support and the suspension of oil shipments from Venezuela\nunder the Petrocaribe arrangement 7 [^7: The PetroCaribe arrangement, created in 2005, provided preferentially financed Venezuelan oil to Central America and Caribbean\nmembers.] are compounding Haiti’s underlying fiscal vulnerabilities.\n\n\n10. **Haiti continues to be vulnerable to recurrent natural disasters and climate change exacerbates these**\n**risks.** The projected impacts of climate change for Haiti include an increase in average temperatures of 0.5°C to\n2.3°C by 2060, with the warming expected to be most marked for the period covering December to February\nevery year. These higher temperatures, coupled with predicted changes in precipitation patterns and likely\nrainfall decreases from June to August, are expected to increase the frequency, intensity and impacts of extreme\nweather events in the country, including hurricanes, storm surges, and flooding. The latest major disaster\nhappened in October 2016\n\nMention: \"2003 census\""}, {"role": "assistant", "content": "{\"role\": \"supporting\", \"usage_action\": \"analyze\", \"summary\": \"Population census serving as the base for the demographic projections used in the analysis.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "umar_pads", "source_key": "umar_pads:001376:14:1", "occurrence_id": "61746420b4026c34ea0a9005", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: -2018, may suggest that welfare indicators may have deteriorated since. 6 [^6: Source: IHSI (Haitian Institute of Statistics - Institut Haïtien de Statistique et d'Informatique). Population data are projections based on\nthe 2003 census; poverty data on a 2012 household survey (ECVMAS – _Enquête sur les conditions de vie des ménages après le séisme_ ).]\n\n9. **While macroeconomic stability was broadly preserved in the years immediately after the 2010**\n**earthquake, a combination of domestic and external factors – including steadily falling levels of international**\n**aid – have weakened the macroeconomic framework.** Just after the earthquake, the authorities reduced the\nfiscal deficit supported by substantial donor assistance and inflation was kept in check. But the return of\ninternational aid to pre-earthquake level intensified fiscal pressure. Donor assistance fell from 15.8 percent of\nGDP in 2010 to 3.6 percent in 2019. Reduced donor support and the suspension of oil shipments from Venezuela\nunder the Petrocaribe arrangement 7 [^7: The PetroCaribe arrangement, created in 2005, provided preferentially financed Venezuelan oil to Central America and Caribbean\nmembers.] are compounding Haiti’s underlying fiscal vulnerabilities.\n\n\n10. **Haiti continues to be vulnerable to recurrent natural disasters and climate change exacerbates these**\n**risks.** The projected impacts of climate change for Haiti include an increase in average temperatures of 0.5°C to\n2.3°C by 2060, with the warming expected to be most marked for the period covering December to February\nevery year. These higher temperatures, coupled with predicted changes in precipitation patterns and likely\nrainfall decreases from June to August, are expected to increase the frequency, intensity and impacts of extreme\nweather events in the country, including hurricanes, storm surges, and flooding. The latest major disaster\nhappened in October 2016\n\nMention: \"ECVMAS\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"analyze\", \"summary\": \"Post-earthquake household survey providing the welfare data underlying the poverty estimates.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "umar_pads", "source_key": "umar_pads:001424:3:2", "occurrence_id": "a6b813ad2141afa4183eefb1", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: more\nthan 80 percent since 2013.\n\n6. **A minority of Haitians have access to a primary health care facility of good quality.** Only 23 percent of\nHaitians live within 5 km of a dispensary or health center that meets adequate service readiness standards. 3 [^3: Service readiness refers to the availability of basic amenities (water, sanitation, power, phone etc.) basic equipment and the\nadherence to standard precautions for infection prevention. See Anna D Gage et al.: “Assessing the Quality of Primary Care in\nHaiti.” Bulletin of the WHO (2017) 95:182–190.]\nGender disparities are also evident, with women experiencing significant difficulties in accessing care. with\nabout 78% of women reporting challenges in accessing care. 4 [^4: See Demographic Health Survey Haiti 2016-2017.] Weaknesses in supply chains and a lack of\nplanning and management are also constraints to access and utilization of HF services. 5 [^5: See “Lessons Learned and Findings from Diagnostic Work: Background Paper for Project Appraisal Document for\nStrengthening Primary Health Care and Surveillance in Haiti Project”.] Low accountability of\nhealth workers and poor incentives for them to perform well lead to their low productivity; outpatient visits\nper health worker per day are less than four in three-quarters of Haiti’s health centers and dispensaries.\n\n\n1 See “Lessons Learned and Findings from Diagnostic Work: Background Paper for Project Appraisal Document\n\nMention: \"Demographic Health Survey Haiti\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"analyze\", \"summary\": \"Household survey supporting the finding that about 78 percent of women report difficulties accessing care.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "umar_pads", "source_key": "umar_pads:001424:3:3", "occurrence_id": "f96db346c33c413ab0590565", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: the availability of basic amenities (water, sanitation, power, phone etc.) basic equipment and the\nadherence to standard precautions for infection prevention. See Anna D Gage et al.: “Assessing the Quality of Primary Care in\nHaiti.” Bulletin of the WHO (2017) 95:182–190.\n4 See Demographic Health Survey Haiti 2016-2017.\n5 See “Lessons Learned and Findings from Diagnostic Work: Background Paper for Project Appraisal Document for\nStrengthening Primary Health Care and Surveillance in Haiti Project”.\n\n\nMar 24, 2020 Page 4 of 9\n\nMention: \"Demographic Health Survey Haiti 2016-2017\""}, {"role": "assistant", "content": "{\"role\": \"supporting\", \"usage_action\": \"source\", \"summary\": \"Household survey listed in the endnotes as the referenced source for health access evidence.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "umar_pads", "source_key": "umar_pads:001461:3:2", "occurrence_id": "e87b38350ba24464b8133034", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: 2011, Mauritania MICS 2011 and 2015). Other countries have made better progress. The\ndemographic transition has not yet started in Mauritania, with a total fertility rate of 5.1 (6.1 in rural, MICS 2015).\nRegarding HIV-AIDS, the prevalence is still low but nevertheless doubled between 1990 and 2015. The country’s\nepidemiological profile is still marked by the predominance of infectious and parasitic disease, although\nnoncommunicable disease, particularly cardiovascular disease and diabetes have grown to the point of becoming\na worrisome public health problem.\n\n\nMar 20, 2020 Page 4 of 11\n\nMention: \"MICS\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"analyze\", \"summary\": \"Household survey rounds providing the fertility and demographic indicators used to describe the transition.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "umar_pads", "source_key": "umar_pads:001461:8:1", "occurrence_id": "14757c3e84a34027b6f99a45", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: to\ndate market/price data. No Bank prior review, and later post review on a sample basis. The Directorate General\nof Resources will report directly to the Minister, and it will share the project’s technical and financial updates\nwith the Directorate General of Resources. If necessary, the Directorate General of Resources will also be\nreinforced with additional staff, including accountants and procurement officers, to manage project activities.\nMauritania MOH will also deploy the staff needed for proper implementation of the environmental and social\nframework elements of the project.\n\n\n.\n\n\n\n\n\nMar 20, 2020 Page 9 of 11\n\nMention: \"market/price data\""}, {"role": "assistant", "content": "{\"role\": \"supporting\", \"usage_action\": \"validate\", \"summary\": \"Price references used to update procurement costs, subject to ex-post review on a sample basis.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "umar_pads", "source_key": "umar_pads:001465:14:2", "occurrence_id": "ff2ea3dcd9601924542cbed4", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: case” and its transmission as “Imported cases only” 7 . To\nmanage the COVID-19 outbreak, the Government adopted an integrated plan in early March 2020, that is costed\nat almost US$311 million with an announced state budget of only six (06) billion XOF (more than US$10 million)\nfor the first emergency response 8 . The integrated plan is structured around five pillars:\n\n - **Country-level coordination, planning, and monitoring:** The country has at an early stage activated national\n\n\n4 Demographic Health Survey 2018.\n5 World Development Indicators 2018.\n6 WHO, COVID-19 Strategic preparedness and response plan. Country Preparedness and Response Status for COVID-19 as of March 16,\n2020.\n7 WHO, 2020 https://www.who.int/docs/default-source/coronaviruse/situation-reports/20200404-sitrep-75-covid19.pdf?sfvrsn=99251b2b_2\n8 This plan goes beyond the COVID-19 emergency response, it includes the Health System Strengthening that account for almost\n80percentage of the plan.\n\n\nPage 10 of 39\n\nMention: \"Demographic Health Survey 2018\""}, {"role": "assistant", "content": "{\"role\": \"supporting\", \"usage_action\": \"source\", \"summary\": \"Household survey cited in the endnotes for the demographic and health context.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "umar_pads", "source_key": "umar_pads:001465:14:2", "occurrence_id": "5610e2de434df583b34a3cf9", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: case” and its transmission as “Imported cases only” 7 . To\nmanage the COVID-19 outbreak, the Government adopted an integrated plan in early March 2020, that is costed\nat almost US$311 million with an announced state budget of only six (06) billion XOF (more than US$10 million)\nfor the first emergency response 8 . The integrated plan is structured around five pillars:\n\n - **Country-level coordination, planning, and monitoring:** The country has at an early stage activated national\n\n\n4 Demographic Health Survey 2018.\n5 World Development Indicators 2018.\n6 WHO, COVID-19 Strategic preparedness and response plan. Country Preparedness and Response Status for COVID-19 as of March 16,\n2020.\n7 WHO, 2020 https://www.who.int/docs/default-source/coronaviruse/situation-reports/20200404-sitrep-75-covid19.pdf?sfvrsn=99251b2b_2\n8 This plan goes beyond the COVID-19 emergency response, it includes the Health System Strengthening that account for almost\n80percentage of the plan.\n\n\nPage 10 of 39\n\nMention: \"World Development Indicators 2018\""}, {"role": "assistant", "content": "{\"role\": \"supporting\", \"usage_action\": \"source\", \"summary\": \"Indicator compilation referenced alongside the survey for the sector statistics.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "umar_pads", "source_key": "umar_pads:001492:4:1", "occurrence_id": "4f435ef96a8b2252bd98ba81", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: org/site/seao/Philippines.pdf)\nMindanao leads in terms of the value of agricultural production and has also seen an increase in corporate farms,\nparticularly for pineapple and banana production. In recent years, Mindanao has produced some 88 percent of the\ncountry’s pineapples, 81 percent of bananas, 76 percent of cassava, 59 percent of coconuts, 50 percent of corn, and 100\npercent of the rubber production. But despite this substantial contribution and growth potential for the country’s\nagricultural output, there remain vast areas under subsistence farming and shifting cultivation, primarily on lands\ndesignated as ADs occupied by various Indigenous Cultural Communities (ICCs).\n\n\n**Agricultural production in Mindanao -and hence rural livelihoods- is highly impacted by unpredictable weather patterns**\n**and extreme climate events.** Over the last few decades annual total rainfall over central and western Mindanao have\ndeclined and a significant drying trend is observed. However, in the northeastern and southwestern sections of Mindanao,\nrainfall has increased over that period. Extreme rainfall events increased in the latter part of the 20th century. Analysis of\nextreme precipitation indicators show tendencies toward a drier dry season (January-March) and wetter rainy seasons\n(July-September). This is further impacted by ENSO events, causing 30 to 40 percent reduction in yield for farmers. This\nhas been particularly relevant because of the widespread lack of irrigation systems in Mindanao, which has the lowest\nlevel of development in terms of water infrastructure within the Philippines and is even less common in ADs. The current\nrampant deforestation in Mindanao is an additional driver for lower soil quality and lower yields. Drought conditions\nworsen as a result of the soil's decreased water holding capacity, which has been significantly reduced by surface runoff\nand flash floods following heavy rainfall in deforested areas. ADs in Mindanao have mostly a rugged access by roads, as\nthey are mostly unpaved and show very poor quality because of wear and\n\nMention: \"extreme precipitation indicators\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"analyze\", \"summary\": \"Rainfall measures analysed to show a drier dry season and wetter rainy season, with consequences for yields.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "umar_pads", "source_key": "umar_pads:001494:31:0", "occurrence_id": "4f50a98cd01dd884cba6dee3", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: **The World Bank**\nSri Lanka COVID-19 Emergency Response and Health Systems Preparedness Project (P173867)\n\n\nworkers beyond personal protective equipment (e.g., menstrual hygiene, transport when changing shifts and returning\nhome), are issues that will require close attention while managing the social risks associated with the project. Further,\nprevention of social tensions, especially in the vicinity of isolation units over the spread of disease and waste\nmanagement; conflicts resulting from false rumors; and risks and impacts from the use of security personnel for labor\nservices during the setting up of isolation wards, will be important considerations under the project.\n\n66. **To mitigate these risks, adequate measures will be taken to ensure access of services to vulnerable groups.** The\nprovision of services and supplies will be based on the urgency of the need, in line with the latest data related to the\nprevalence of the cases. In addition, Government will put in place adequate measures, as outlined in the ESMP, to\nensure that the medical isolation of individuals does not increase their vulnerability, especially to gender based\nviolence and sexual exploitation and abuse. The COVID-19 Outbreak and Gender: Key Advocacy Points from Asia and\nthe Pacific, UN Women, 2020 and the COVID-19 resources to address gender-based violence risks, will be used as a\nguide towards the design and implementation of such measures. Additionally, provisions will also be put in place for\nproper safety systems, with a focus on isolation units/wards, screening posts, and laboratories to be funded by the\nproject; encompassing above all occupational health safety and waste management procedures. WBG EHS Guidelines,\nsuch as those related to Community Health and Safety will apply to the extent relevant.\n\n67. **The MoH will use the Stakeholder Engagement Plan (SEP) which outlines a structured approach to engagement**\n**with stakeholders that is based upon meaningful consultation and disclosure of appropriate information,**\n*\n\nMention: \"latest data related to the\nprevalence of the cases\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"inform\", \"summary\": \"Current case prevalence information determining the urgency-based allocation of services and supplies.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "umar_pads", "source_key": "umar_pads:001522:4:1", "occurrence_id": "1d42fcf5de275725d7ebd51a", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: (c) implement effective risk communication campaigns\nfor mass awareness and education of the population to tackle the COVID-19 emergency, and enhance internet\nconnectivity across health facilities.\n\n**Sub-Component 1.1: Enhance case detection, confirmation, and contact tracing (US$1.05 million equivalent)**\n\n11. This sub-component will focus on strengthening Fiji’s capacity for early detection, case confirmation, and contact\ntracing for COVID-19 by equipping laboratories with relevant supplies and consumables. Equipment to be procured\nunder this component for laboratories include biosafety cabinets, GeneXpert cartridges, analyzers, and swabs.\n\n**Sub-Component 1.2: Enhance health service delivery (US$2.50 million equivalent)**\n\n\n12. This sub-component will support enhancing clinical care capacity to manage COVID-19 cases and infection\nprevention and control capacity, including: (a) providing personal protective equipment and essential medical\n\n\n[1 UNICEF (2020). Available: https://data.unicef.org/country/fji/ [Accessed: 30 March 2020]](https://data.unicef.org/country/fji/)\n2 Institute for Health Metrics and Evaluation, “GBD Compare,” 2017. [Online]. Available: http://www.healthdata.org/datavisualization/ gbd-compare. [Accessed: 26 March 2020].\n\n\nApr 23, 2020 Page 5 of 10\n\nMention: \"GBD Compare\""}, {"role": "assistant", "content": "{\"role\": \"supporting\", \"usage_action\": \"analyze\", \"summary\": \"Disease burden visualization tool cited for the health profile information behind the needs analysis.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "umar_pads", "source_key": "umar_pads:001653:44:2", "occurrence_id": "0ad53323ed0276292a8f0980", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: >discharges to the Vinh
River) will also be
collected an external
comparison.
PMU/Consultant
|Level of water pollution discharged to the
Vinh river (biochemical oxygen demand
(milligrams/liter)
Level of water pollution
discharged to the Vinh river,
as measured by biochemical
oxygen demand (BOD)
(milligrams/liter), due to the
construction of interceptor
sewers as part of new river
embankment installed
under the project.
Annually
PMU/Consult
ant reports
This indicator will be
measured using data on
Vinh River water quality
at two points that are
currently polluted :
At the outlet of
Cua Nam lake;
and
At the outlet of
Vinh market.
Baseline data will be
collected before the
start of construction
and data will be
collected annually after
the embankments
enter service. Data on
the water quality of the
start of Vinh River
(where the Ke Gai River
discharges to the Vinh
River) will also be
collected an external
comparison.
PMU/Consultant
|Level of water pollution discharged to the
Vinh river (biochemical oxygen demand
(milligrams/liter\n\nMention: \"Vinh River water quality\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"validate\", \"summary\": \"Monitoring measurements at two polluted outlets used to measure the pollution reduction indicator against a baseline.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "umar_pads", "source_key": "umar_pads:001698:2:0", "occurrence_id": "556b59f276b30072220aee2a", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: **The World Bank**\nSouth Africa COVID-19 Emergency Response Project (P174259)\n\n\n**Introduction and Context**\n\nCountry Context\n\n\n1. **South Africa is an upper-middle income country that is still emerging from massive economic and racial**\n**inequality.** With a population of approximately 60 million people, the country’s gross domestic product per capita\n(current US$) in 2020 is US$5,091. After the apartheid government ended in 1994, it was replaced by a constitutional\ndemocracy and had 15 years of significant development progress. However, the country still suffers from its legacy of\napartheid with inequality. With a Gini coefficient of 63, South Africa is ranked by the World Bank as the most unequal\ncountry in the world.\n\n2. **Coronavirus disease (COVID)-19 hit the South African economy at a time when the economy was already in**\n**recession.** The recent International Monetary Fund (IMF) World Economic Outlook estimates economic growth had\nfallen to 1.5 percent in 2019 compared with 3.0 percent in 2010 and the economy contracted by 6.4 percent in 2020\ncompared with the regional average of 1.7 percent. The unemployment had soared to 29.1 percent in the third quarter\nof 2019 reached a record of 34.9 percent, with 7.6 million jobless people by the third quarter in 2021 (Department of\nStatistics South Africa, 2021). While poverty had registered some improvement since 2015, it remained high at 49.2\npercent in 2019, compared with 55.5 percent in 2015 (World Bank 2020). The severe contraction in 2020 is estimated\nto have put additional 2 million people into poverty. The COVID-19 pandemic is expected to reverse some progress in\nhuman capital formation which may have long-lasting consequences for human capital accumulation and productivity\ngrowth.\n\n3. **South Africa is hit hard by the CO\n\nMention: \"World Economic Outlook\""}, {"role": "assistant", "content": "{\"role\": \"supporting\", \"usage_action\": \"analyze\", \"summary\": \"Fund outlook supplying the growth estimates showing the pre-pandemic slowdown and 2020 contraction.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "umar_pads", "source_key": "umar_pads:001926:2:1", "occurrence_id": "4284e199ef4ae133f45b4593", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: **\n**Sahel.** At the immediate north of the target subregion, Sahel is one of the world’s most fragile and risk\n\n1 The Gulf of Guinea region is located within the West and Central African coastlines and the surrounding territorial waters of the\nAtlantic Ocean. In the context of this project, it refers to Benin, Côte d’Ivoire, Ghana, and Togo.\n2IMF (International Monetary Fund). 2021. _Regional Economic Outlook: Sub-Saharan Africa._ Real GDP (annual percentage change)\nin 2018 for Benin is 6.7 percent, Côte d’Ivoire is 6.9 percent, Ghana is 6.9 percent, and Togo is 5.0 percent. Real GDP in 2020 for\nBenin is 3.8 percent, Côte d’Ivoire is 2.0 percent, Ghana is 0.4 percent, and Togo is 1.8 percent.\n3 Per World Development Indicators (WDI), population (in million) in 2019 for Benin is 11.8, Côte d’Ivoire is 25.72, Ghana is 30.42,\nand Togo is 8.8.\n\n\nNov 17, 2021 Page 3 of 27\n\nMention: \"World Development Indicators\""}, {"role": "assistant", "content": "{\"role\": \"supporting\", \"usage_action\": \"source\", \"summary\": \"Indicator compilation supplying the population figures for the four coastal countries.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "umar_pads", "source_key": "umar_pads:001928:4:1", "occurrence_id": "f1beebc771ee6e4e734f6828", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: (i) adjust the Results Framework including the addition of\nCorporate Scorecard Indicators; (ii) extend the closing date of the project from December 31, 2027 to December\n31, 2028; and (iii) change the implementing agency in Togo from the National Agency for Support to Rural\nDevelopment ( _Agence Nationale d’Appui au Developpement a la Base, ANADEB)_ to the Ministry of Finance and\nBudget.\n\n\nSectoral and Institutional Context\n\n**2.** **The northern border regions of Benin, Côte d'Ivoire, and Togo face longstanding development deficits, where poverty**\n**rates significantly exceed national averages, state presence is weakest, and access to basic services remains deeply**\n**uneven.** Infrastructure gaps are pronounced, with large shares of rural populations lacking access to improved water\nand sanitation, electricity, all-season roads, and adequate health and education facilities. These structural shortfalls\nhave fueled grievances and eroded trust between communities and public institutions, creating fertile ground for social\ntensions at a moment when FCV and climate risks are intensifying and the demands placed on local service systems are\ngrowing.\n\n**3.** **The spillover of insecurity from the Sahel continues to pose an immediate fragility risk to all three countries, and the**\n**three countries continue to absorb refugees fleeing violence in the Sahel, largely hosted in communities already**\n**characterized by high levels of poverty.** Data from the Armed Conflict Location & Event Data Project (ACLED) indicate\nthat violent incidents linked to extremist groups have expanded southward toward coastal countries, with activity\nintensifying across border areas of Burkina Faso and the northern Gulf of Guinea. As of January to March 2026, Togo\n\n\nPage 4\n\n\nOfficial Use Only\n\nMention: \"Armed Conflict Location & Event Data Project\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"analyze\", \"summary\": \"Event dataset documenting the southward expansion of extremist-linked violent incidents toward coastal border areas.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "umar_pads", "source_key": "umar_pads:001953:4:1", "occurrence_id": "2579109d6966800ea1411d9b", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: further from already low\nlevels – 14 percent in 2020 to 12 percent in 2021. Credit to the private sector is extremely limited – very\nlow not only in comparison to middle income peers, but also Latin America and the Caribbean average\n(60 percent average in 2020). At the same time lending interest rates have been historically high, rising\nto 67 percent in 2019 and falling to 29 percent in 2021. Consequently, financing for innovation and\nentrepreneurship is especially hard to get, as it faces higher thresholds than accessing other types of\nfinancing, due to the inherent information asymmetries and relatively higher transaction costs. These\ncapital markets limitations affect the allocation of capital across firms, generating allocative inefficiencies\nat large.\n\n\n8. **Argentina has a small, growing, yet an underdeveloped venture capital (VC) and private equity (PE)**\n**financing ecosystem.** Venture capital and seed capital investments – key for innovation and early-stage\nfinancing, have been limited but steadily growing, albeit from a very low base, with annual investments\nbelow US$200 million prior to 2019. For the size of the economy and the income level, VC/PE landscape\nremains small; investments only amount to 0.001 percent of GDP; by contrast, the average OECD country\ninvested 0.08 percent of GDP on VC in 2019, while large investors such as the US invested as much as 0.6\npercent through VCs. 2 [^2: OECD Data.] Still, in recent years, VC funding portrayed a significant increase, as 2019 had the\nhighest historical investment amount in US$ 403 million, while investments fell to 347 US$ million in\n2020. Moreover, VC/PE in Argentina have weathered the recent economic contraction relatively well,\nand increased in terms of both deals and volume of investment notwithstanding Argentina’s shrinking\nGDP in 2019-20. In 2019, there were 92 private investment transactions in the country, summing up to\nUS$ 1.1\n\nMention: \"OECD Data\""}, {"role": "assistant", "content": "{\"role\": \"supporting\", \"usage_action\": \"analyze\", \"summary\": \"Statistics source supplying the venture capital intensity averages used to benchmark the countrys small ecosystem.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "umar_pads", "source_key": "umar_pads:001966:3:2", "occurrence_id": "058ba8e9b984a9db69252627", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: greater utilization of population data creating more incentives for\nlocal governments to make registration easier and more accessible for people, and significant efforts and reforms by\nnational Dukcapil to increase service levels, including to integrate civil and population registration and issue NIKs at the\ntime of birth registration. In terms of utilization, national Dukcapil has signed cooperation agreements with 3,880\ninstitutional users as of March 2022, who have carried out over 7 billion verification requests.\n\n7. **But key challenges remain in terms of coverage gaps, under-utilization, the absence of a digital identification**\n**system, and data protection and cybersecurity – and these undermine Indonesia’s aspirations for inclusion and digital**\n**transformation.** For example, NIK, birth certificate, and e-KTP coverage is lower in Eastern provinces and among\nvulnerable subgroups, which also stand the most to gain from increased access to proof of their legal identity and a digital\nidentity for online transactions, as well as being included in vital and demographic statistics produced based on SIAK.\nReliable and up to date marriage and death registration coverage estimates are not available – but available evidence\n\n\n1 Foundational identification systems are those primarily created to manage identity information for the general population and provide credentials\nthat serve as proof of identity for a wide variety of public and private sector transactions and services. Common types of foundational ID systems\ninclude civil registries, national ID systems, and population registers.\n\n\nMar 28, 2022 Page 4 of 12\n\nMention: \"population data\""}, {"role": "assistant", "content": "{\"role\": \"supporting\", \"usage_action\": \"inform\", \"summary\": \"Registration records whose greater use gives local governments incentives to make registration more accessible.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "umar_pads", "source_key": "umar_pads:001966:3:2", "occurrence_id": "0adbb90c4b240cf6a0ce5d2e", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: greater utilization of population data creating more incentives for\nlocal governments to make registration easier and more accessible for people, and significant efforts and reforms by\nnational Dukcapil to increase service levels, including to integrate civil and population registration and issue NIKs at the\ntime of birth registration. In terms of utilization, national Dukcapil has signed cooperation agreements with 3,880\ninstitutional users as of March 2022, who have carried out over 7 billion verification requests.\n\n7. **But key challenges remain in terms of coverage gaps, under-utilization, the absence of a digital identification**\n**system, and data protection and cybersecurity – and these undermine Indonesia’s aspirations for inclusion and digital**\n**transformation.** For example, NIK, birth certificate, and e-KTP coverage is lower in Eastern provinces and among\nvulnerable subgroups, which also stand the most to gain from increased access to proof of their legal identity and a digital\nidentity for online transactions, as well as being included in vital and demographic statistics produced based on SIAK.\nReliable and up to date marriage and death registration coverage estimates are not available – but available evidence\n\n\n1 Foundational identification systems are those primarily created to manage identity information for the general population and provide credentials\nthat serve as proof of identity for a wide variety of public and private sector transactions and services. Common types of foundational ID systems\ninclude civil registries, national ID systems, and population registers.\n\n\nMar 28, 2022 Page 4 of 12\n\nMention: \"vital and demographic statistics\""}, {"role": "assistant", "content": "{\"role\": \"supporting\", \"usage_action\": \"curate\", \"summary\": \"Civil registration statistics generated from the population information system, from which excluded groups would benefit.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "umar_pads", "source_key": "umar_pads:002035:2:0", "occurrence_id": "adce8473ee4d66a69a15bfbc", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: **The World Bank**\nAdditional Financing to Rural Electrification Project (P175456)\n\n\n|World Bank Group Financing|Col2|\n|---|---|\n|International Development Association (IDA)|10.00|\n|IDA Grant|10.00
|\n\n\n\n\n\n\n\nOther Decision (as needed)\n\n\n**B. Introduction and Context**\n\n\nCountry Context\n\n\n1. **Tajikistan is a landlocked country located in southeast Central Asia. It has a population of 8.5 million**\n**and a Gross National Income per capita of US$1,010 (2018)** . 1 [^1: In current US$, Atlas Method, World Development Indicators, The World Bank. Source:\n[https://data.worldbank.org/indicator/NY.GNP.PCAP.CD?locations=TJ](https://data.worldbank.org/indicator/NY.GNP.PCAP.CD?locations=TJ)] In 2016-2019, Tajikistan’s real Gross Domestic\nProduct (GDP) exhibited healthy growth rates. According to official statistics, GDP growth was 6.9 percent in\n2016 and accelerated to 7.5 percent in 2019, supported by robust year-on-year growth in industry, agriculture,\nand retail trade. On the demand side, consumption and net exports drove growth. Growth was largely\nsupported by heightened public investment in infrastructure projects.\n\n\n2. **The current account deficit narrowed in 2019 due to larger growth in exports and slow increase of**\n**imports** . A jump in exports and a recovery in remittances helped narrow the current account deficit to an\nestimated 4.3 percent of GDP in 2019. Merchandise imports increased by 6.3 percent in U.S. dollar terms.\nExport earnings rose by 9.4 percent in 2019, supported by higher shipments abroad of precious metals and\nelectricity.\n\n\n3.\n\nMention: \"World Development Indicators\""}, {"role": "assistant", "content": "{\"role\": \"supporting\", \"usage_action\": \"source\", \"summary\": \"Indicator compilation cited for the per-capita income figure, with the method and indicator link specified.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "umar_pads", "source_key": "umar_pads:002048:3:1", "occurrence_id": "cdd1227d4e6ad294048c3310", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: with flood-prone lowlands.\n\n\n4. **Guinea-Bissau is a natural resource-rich country with a population of just 1.9 million in 2019, two thirds of**\n**whom live below the national poverty line of US$1.9 per day** . The country has a GDP of US$697 per capita, and the\nhighest proportion of natural capital wealth per capita (47 %) in West Africa. A 2014 wealth accounting exercise\nestimates Guinea-Bissau’s natural wealth at US$3,874 per capita, over 90% derived from renewable natural resources,\nincluding an extensive system of protected areas (26% of national territory) which hosts ecosystems and biodiversity of\nlocal, regional and global significance. This rich and relatively undamaged natural resource base, if well managed under\nthe governance of stable and accountable institutions, could transform the economy, reduce poverty, and improve the\nlives of its citizens.\n\n\nSectoral and Institutional Context\n\n\n5. **The West African coastline, spanning from Mauritania to Gabon, includes 17 countries1 that are at**\n**varying stages of economic development.** Eight of the countries2 have a per capita gross domestic product (GDP)\nbelow US$1,000, ranking among the lowest in the world. Many of these countries have gone through conflict or\npolitical and social unrest over the last 10 years. Although the West African economies have been growing\nsteadily,1 the countries continue to be heavily dependent on natural resources such as fisheries, fossil fuel,\nminerals, and timber. A very large proportion, about 42 percent, of West Africa’s GDP is generated from its coastal\nareas (e.g. fisheries, ports, tourism). The West African coastal areas are home to almost one-third of the countries’\npopulation.2 Across Sub-Saharan Africa, the urban population, largely located in the coastal areas, is growing at\nan annual rate of 4 percent,\n\nMention: \"2014 wealth accounting exercise\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"analyze\", \"summary\": \"Accounting exercise estimating national natural wealth per capita and the share from renewable resources.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "umar_pads", "source_key": "umar_pads:002227:2:1", "occurrence_id": "31373cdc8010616bf2da7515", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: however, will be difficult to maintain over the medium term in the absence of a resolution to political\nbottlenecks. Meanwhile, a slump in tax revenues and higher spending led to an estimated fiscal deficit of 1.8 percent of\nGDP in 2020, with a further widening expected in 2022. The latter comes against the background of some rebuilt fiscal\nbuffers. Fiscal surpluses ranged between 2 and 3 percent of GDP over the past six years prior to the pandemic, which in\nturn helped rein in the current account deficits averaging below 4 percent since 2015. The external shortfall was largely\nfinanced by net FDI inflows, mainly into the foreign-owned banking sector, which remained stable during the pandemic.\nSteady, albeit low, economic growth has not translated into more and better jobs, with a large share of the workforce\nactive in the informal sector. Hence, poverty rates do not seem to have improved, according to the latest official data\nfrom 2015. Implementation of much needed structural reforms is sluggish due to political deadlock, pressures from\nfrequent elections, corruption that pervades all levels of society, and a complex governing structure characterized by\nfragmentation of responsibilities between the two entities and Cantons. The pandemic has further highlighted these\nshortages in institutional effectiveness resulting in the slow release of fiscal support to households and businesses,\nwhich has weighed on economic activity.\n\n\nSectoral and Institutional Context\n\n**Air pollution is a key development challenge for BiH with its negative impact on human health, welfare of citizens,**\n**and the economy.** A 2019 World Bank report on air quality management in BiH estimated that poor air quality costs lives\n(more than 3,300 people die prematurely every year in BIH due to it), negatively impacts the economy (more than 8.2\npercent of GDP is lost every year) and contributes to loss of human capital as it influences the decisions of many families\nto emigrate. The report estimates that almost three-fifths of PM2.5 air pollutant emissions\n\nMention: \"latest official data\nfrom 2015\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"analyze\", \"summary\": \"Most recent official household figures indicating that growth has not reduced poverty.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "umar_pads", "source_key": "umar_pads:002227:5:1", "occurrence_id": "813c528e163f7b3b2f5cb4ac", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: is among the top sources contributing\nto local air pollution-and growing-, and with the understanding that, despite moderate levels of motorization,\ncongestion and high polluting vehicles are impacting Sarajevo canton’s livability, in 2020, the Canton Sarajevo approved\na Sustainable Urban Mobility Plan (SUMP). The SUMP was followed up with the EBRD- funded Green Cantonal Action\nPlan (GCAP, 2020). The proposed Bank-financed activities would address priority green urban mobility programs\nreflected in the SUMP and GCAP that support air quality improvement beyond those public transport and intelligent\ntransport systems already financed by EBRD/EIB, including: i) the expansion of the Sarajevo bikeway system in prioritized\nareas, including upgrades to existing bikeways and new bikeways and, potentially, support to bike sharing facilities\n(including e-bikes); ii) the development and implementation of a low emission zone 5 [^5: The Swedish Environmental Research Institute, with SIDA funding, is currently advancing a study to scope a proposed low emission zone for\nSarajevo] in the city center, with investments\nand policies associated with possible improvements to public space, smart mobility management and parking regulation\nand residential heating.\n\n\n**Component 3 – Project implementation support**\n\n\n**This component will support activities related to the implementation of the proposed project, i.e** ., supporting the\nproject with equipment, logistics, M&E and key project consultant salaries (e.g., head of PMU(s), technical experts\nacross relevant sectors, financial experts, procurement specialists, environmental and social experts). 6 [^6: The estimated cost of this component will be reviewed based on findings of the Project Procurement Strategy Document (PPSD).]\n\n\n3 According to the 2013 Population Census, there were about 51,000 single homes and 95,000 apartments in Sarajevo Canton.\n\n\n4 Strategy for Limited Use of Coal and Other Solid Fuels entails, among other things, an analysis of the\n\nMention: \"2013 Population Census\""}, {"role": "assistant", "content": "{\"role\": \"supporting\", \"usage_action\": \"analyze\", \"summary\": \"Census housing counts giving the number of single homes and apartments relevant to heating interventions.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "umar_pads", "source_key": "umar_pads:002239:3:0", "occurrence_id": "263eafd4dd52a7a5ab453004", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: **The World Bank**\nNE_ INVESTMENT CLIMATE, COMPETITIVENESS SUPPORT AND COVID-19 RESPONSE\n\n\n90 percent of recently surveyed firms have been affected by COVID; 20 percent have temporarily closed; 27\npercent of enterprises are unable to survive more than 1 month without support; 38 percent between 30 and\n60 days and 16 percent between 60 and 90 days (T-Ventures Survey).\n\n\nSectoral and Institutional Context\nAmong Niger’s most important economic and industrial sectors are:\n\n\n\n\n- **Agriculture** which accounts for over 40 percent of the national GDP and is the main source of\n\nlivelihood for the population, despite its precariousness and vulnerability as a result of being\nparticularly drought-prone, and given desertification and increasing climate change volatility.\n\n- **Uranium mining** which provides about 5% of world mining output from Africa's highest-grade\n\n\n\nuranium ores.\n\n- **Oil** ; the Republic of Niger is a new oil-producing nation and as such is attracting more and more\n\n\n\nattention.\n\n- **Livestock,** with strong cross-border trade being conducted between Niger and Nigeria.\n\n\n\nNiger’s economy is primarily comprised of informal micro and small enterprises, with particular\nemphasis on the agricultural sector. The country’s formal private sector base is one of the smallest in\nthe region. According to the National Statistical Institute (INS), there are less than 6,000 formal\nbusinesses in the country, 77 percent of which have less than 10 employees. The INS estimates that\n70 percent of Niger’s production takes place in the informal sector.\n\n\nThe Covid pandemic has impacted small and medium firms disproportionally. In the June 2020 survey\nof the Covid-19 impact assessment on the private sector, 99% of SMEs reported a reduction in sales\nagainst 81% of large enterprises. The following sectors have been the hardest hit by the Covid\npandemic : i) hospitality (80 percent\n\nMention: \"T-Ventures Survey\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"analyze\", \"summary\": \"Business survey reporting infection impact, temporary closures and how long firms can survive without support.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "umar_pads", "source_key": "umar_pads:002239:3:0", "occurrence_id": "e287773e6daed851711c50f6", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: **The World Bank**\nNE_ INVESTMENT CLIMATE, COMPETITIVENESS SUPPORT AND COVID-19 RESPONSE\n\n\n90 percent of recently surveyed firms have been affected by COVID; 20 percent have temporarily closed; 27\npercent of enterprises are unable to survive more than 1 month without support; 38 percent between 30 and\n60 days and 16 percent between 60 and 90 days (T-Ventures Survey).\n\n\nSectoral and Institutional Context\nAmong Niger’s most important economic and industrial sectors are:\n\n\n\n\n- **Agriculture** which accounts for over 40 percent of the national GDP and is the main source of\n\nlivelihood for the population, despite its precariousness and vulnerability as a result of being\nparticularly drought-prone, and given desertification and increasing climate change volatility.\n\n- **Uranium mining** which provides about 5% of world mining output from Africa's highest-grade\n\n\n\nuranium ores.\n\n- **Oil** ; the Republic of Niger is a new oil-producing nation and as such is attracting more and more\n\n\n\nattention.\n\n- **Livestock,** with strong cross-border trade being conducted between Niger and Nigeria.\n\n\n\nNiger’s economy is primarily comprised of informal micro and small enterprises, with particular\nemphasis on the agricultural sector. The country’s formal private sector base is one of the smallest in\nthe region. According to the National Statistical Institute (INS), there are less than 6,000 formal\nbusinesses in the country, 77 percent of which have less than 10 employees. The INS estimates that\n70 percent of Niger’s production takes place in the informal sector.\n\n\nThe Covid pandemic has impacted small and medium firms disproportionally. In the June 2020 survey\nof the Covid-19 impact assessment on the private sector, 99% of SMEs reported a reduction in sales\nagainst 81% of large enterprises. The following sectors have been the hardest hit by the Covid\npandemic : i) hospitality (80 percent\n\nMention: \"June 2020 survey\nof the Covid-19 impact assessment\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"analyze\", \"summary\": \"Rapid assessment comparing sales reductions between small and large enterprises during the pandemic.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "umar_pads", "source_key": "umar_pads:002336:5:1", "occurrence_id": "516ee322ae38573a2ddb933e", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: There is\nevidence of misalignment between the amount of resources allocated to sectors such as education and health\nand the expenditure needs associated with their service delivery responsibilities. 12 [^12: World Bank, Public Finance Review (March 2019).]\n\n\n12. **While not new, the urgency of addressing these issues has been underlined by the need to consolidate**\n**the country’s fiscal position while responding to the impacts of the pandemic and supporting the economic**\n**recovery.** The Government’s strategy for the medium-term fiscal policy is focused on consolidating public\nexpenditure while boosting economic activity through capital expenditure and infrastructure investment, 13 [^13: Republic of North Macedonia. Government of the Republic of North Macedonia. 2022-2024 Fiscal Strategy of the Republic of North\nMacedonia (with prospects until 2026). May 2021. https://finance.gov.mk/wp-content/uploads/2021/10/2022-2024-FISCAL-STRATEGYOF-THE-REPUBLIC-OF-NORTH-MACEDONIA-with-prospects-until-2026.pdf] with\nplans to scale up on-budget public investments from 2.6 percent of GDP in 2019 to 4 percent by 2022. However,\nthere is evidence that in the past, resources allocated to public investment have not been fully (and, at times, not\neffectively) utilized. Capital expenditures were under-executed by approximately 21 percent on average during\nthe period between 2015 and 2020, 14 [^14: Draft - Form 3: Narrative part of the PFM program 2022 – 2025. Mimeo.] and those that are utilized do not seem to be optimally used; according to\nthe 2018 Public Finance Review, both the quality and efficiency of investment appeared to have had declined in\nrecent years. 15 [^15: World Bank, Public Finance Review (March 2019).]\n\n13. **To fully realize the benefits of the planned scale-up, the Government will need to address underlying**\n*\n\nMention: \"2018 Public Finance Review\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"analyze\", \"summary\": \"Review finding that the quality and efficiency of public investment had declined, alongside misaligned sector allocations.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "umar_pads", "source_key": "umar_pads:002336:8:2", "occurrence_id": "ff7930f4c9ce81a1c6b978dc", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: Public Revenue Office IT System Design (P175799). June 2021.\n31 In 2021, only 36 percent of citizens responded affirmatively to a question on their confidence in the national government. (Gallup\n[Analytics. < https://analyticscampus-gallup-com.libproxy-wb.imf.org/Profiles/>. Accessed on January 26, 2022.)](https://analyticscampus-gallup-com.libproxy-wb.imf.org/Profiles/)\n32 Supported by the World Bank DPO P171851.\n33 The existing Treasury system was established in 2007. In order to enhance the monitoring of arrears, the Budget Department established\na separate application where all budget users (including municipalities) and State-owned enterprises report their arrears periodically since\n2017.\n\n34Other advances include the incorporation of municipal transactions into the Open Finance portal dataset since June 2020; the publication\nof enterprise-level data on public and state-owned companies’ revenues and expenditures as well as the execution of local governments’\nbudgets since October 2020; and increased coverage of the financial operations on public enterprises and trade companies included in the\nGovernment’s recent Fiscal Strategies.\n35 The PEFA carried out in North Macedonia in 2021 found public access to fiscal information to meet all of the criteria set forward to\nmeasure public access to fiscal information (scoring an “A” in indicator PI-9). (PEFA 2021 North Macedonia Assessment Report: Draft Post\nPeer Review. February 2022.)\n\n\nMar 21, 2022 Page 9 of 17\n\nMention: \"enterprise-level data\""}, {"role": "assistant", "content": "{\"role\": \"supporting\", \"usage_action\": \"curate\", \"summary\": \"Published firm-level records of public and state-owned company revenues and spending, listed as a transparency advance.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "umar_pads", "source_key": "umar_pads:002409:13:1", "occurrence_id": "c760e601e0335fcdcb15c65d", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: US$3 billion in 2005 to over US$18 billion\nin 2019, opportunities for growth through regional trade remain largely untapped. In South Asia, regional trade\nis around 5 percent of total trade, which compares poorly with East Asia and Sub-Saharan Africa, where regional\ntrade accounts for 50 percent and 22 percent of total trade, respectively. 2 The unexploited potential for regional\ntrade is estimated at 93 percent for Bangladesh, 9 percent for Bhutan, 50 percent for India, and 76 percent for\nNepal. 3\n\n\n3. **Low regional trade reflects the high cost of connectivity** . Several countries in the region trade on better\nterms with distant economies than with their neighbors. The World Bank’s 2021 Connecting to Thrive-report\nestimates that it is about 15–20 percent less expensive for a company in India to trade with a company in Brazil\nor Germany than with a company in Bangladesh. 4 Several factors account for the high cost, including inadequate\ntransport and trade infrastructure, cumbersome regulations, manual processes, and protective tariffs and nontariff barriers. The Trade Restrictiveness Index, which captures the trade policy distortions that each country\nimposes on its import bundle, shows South Asia with the greatest protection compared to any other region.\n\n\n4. **The impact of poor connectivity manifests itself the most in landlocked countries and regions.** Goods\nfrom Bhutan, Nepal, and the Northeast Region (NER) of India suffer delays when passing through to seaports in\nneighboring Bangladesh and India. Transit restrictions lead to long diversionary routes, increasing the costs of\ntransport and trade and pushing up the prices of imported, essential and non-essential consumer goods, as well\nas the prices of inputs. For example, goods from Agartala (NER) travel 1,600 kilometers (km) through the Siliguri\ncorridor to reach Kolkata Port\n\nMention: \"2021 Connecting to Thrive-report\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"analyze\", \"summary\": \"Trade facilitation report quantifying how much cheaper trade with distant partners is than with neighbours.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "umar_pads", "source_key": "umar_pads:002541:7:1", "occurrence_id": "7f0a823b7936d01b0f0e6179", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: market recovery.** The lack of workers with the right skills is a\nchallenge facing the private sector in Argentina. Approximately 40 percent of firms surveyed in the World Bank’s 2017\nEnterprise Survey reported an inadequately educated workforce as a major constraint compared to an average in the\nLatin America and the Caribbean region of 29 percent. Indeed, firms seem unable to find workers with the skills they need.\nA 2016 survey found that 59 percent had difficulty finding workers with the right skills. 19 [^19: OECD (Organisation for Economic Co-operation and Development). 2017. _Argentina: Multi-dimensional Economic Survey_ .\nParis: OECD.] The unmet labor demand survey,\n_Encuesta de Demanda Laboral Insatisfecha,_ shows persistent skills gaps, especially for operational and professional\nworkers. 20 [^20: World Bank. 2018. _Argentina: Escaping Crises, Sustaining Growth, Sharing Prosperity_ . Washington, DC: World Bank.] Problems arise as much because of under- as because of over-qualified workers. Argentina has the third-highest\nrate of ‘qualification mismatch’ among G-20 countries. 21 [^21: OECD and ILO. 2018 _. Global Skills Trends, Training Needs and Lifelong Learning Strategies for the Future of Work_ . G-20\nEmployment Working Group, Geneva.] While skills shortages are modest compared to other G-20\nmembers, Argentina is still experiencing these shortages in many high-level cognitive and social skills, such as reasoning\nabilities and complex problem solving, and digital economy skills such as computer and electronics skills. 22 [^22: OECD and ILO. 2018. _Global Skills Trends, Training Needs and Lifelong Learning Strategies for the Future of Work_ . G-20\nEmployment Working Group, Geneva.]\n\n19. **Ensuring that workers have the rights skills will be essential for a strong jobs recovery from the COVID-19**\n**outbreak.** Ensuring that workers displaced by the COVID-19\n\nMention: \"2017\nEnterprise Survey\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"analyze\", \"summary\": \"Staff use the World Bank Enterprise Survey to quantify how many Argentine firms cite an inadequately educated workforce.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "umar_pads", "source_key": "umar_pads:002541:7:1", "occurrence_id": "65fbd0f6cc39f052392a323d", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: market recovery.** The lack of workers with the right skills is a\nchallenge facing the private sector in Argentina. Approximately 40 percent of firms surveyed in the World Bank’s 2017\nEnterprise Survey reported an inadequately educated workforce as a major constraint compared to an average in the\nLatin America and the Caribbean region of 29 percent. Indeed, firms seem unable to find workers with the skills they need.\nA 2016 survey found that 59 percent had difficulty finding workers with the right skills. 19 [^19: OECD (Organisation for Economic Co-operation and Development). 2017. _Argentina: Multi-dimensional Economic Survey_ .\nParis: OECD.] The unmet labor demand survey,\n_Encuesta de Demanda Laboral Insatisfecha,_ shows persistent skills gaps, especially for operational and professional\nworkers. 20 [^20: World Bank. 2018. _Argentina: Escaping Crises, Sustaining Growth, Sharing Prosperity_ . Washington, DC: World Bank.] Problems arise as much because of under- as because of over-qualified workers. Argentina has the third-highest\nrate of ‘qualification mismatch’ among G-20 countries. 21 [^21: OECD and ILO. 2018 _. Global Skills Trends, Training Needs and Lifelong Learning Strategies for the Future of Work_ . G-20\nEmployment Working Group, Geneva.] While skills shortages are modest compared to other G-20\nmembers, Argentina is still experiencing these shortages in many high-level cognitive and social skills, such as reasoning\nabilities and complex problem solving, and digital economy skills such as computer and electronics skills. 22 [^22: OECD and ILO. 2018. _Global Skills Trends, Training Needs and Lifelong Learning Strategies for the Future of Work_ . G-20\nEmployment Working Group, Geneva.]\n\n19. **Ensuring that workers have the rights skills will be essential for a strong jobs recovery from the COVID-19**\n**outbreak.** Ensuring that workers displaced by the COVID-19\n\nMention: \"unmet labor demand survey\""}, {"role": "assistant", "content": "{\"role\": \"supporting\", \"usage_action\": \"analyze\", \"summary\": \"Encuesta de Demanda Laboral Insatisfecha results are read as evidence of unmet demand for operational and professional workers.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "umar_pads", "source_key": "umar_pads:002642:3:1", "occurrence_id": "1b17b6e7b4df352f687a7dcf", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: where the UHC\neffective coverage index stands at only 57.7. Iraq’s Human Capital Index is one of the lowest in the MENA region at\n0.41 in 2020.\n\n5. Non-communicable diseases (NCDs) have become the most significant cause of mortality and morbidity, representing\n77.1 percent of deaths and 65.8 percent of disability-adjusted life years (DALYs) in 2019. In 2019, ischemic heart\ndisease, stroke, diabetes, and chronic kidney disease were the top four causes of mortality in the country. The\nprevalence of the main NCD risk remains high: 21 percent of the population uses tobacco, 14 percent of the\npopulation has diabetes, 35.6 percent of the population has high blood pressure, 65 percent are overweight or obese,\nand 39.6 percent have elevated cholesterol.\n\n\n6. Health infrastructure was severely damaged by conflicts. With the exception of Tal Afar, Al-Muqdadya (Ibid) and AlRamadi, all cities for which data were available have at least half of their facilities either partially or fully damaged.\nService delivery is also affected by the functionality of facilities. Data show high rates of nonfunctional health facilities\nin cities with high levels of damages. According to the Damage and Needs Assessment conducted by the World Bank\nin 2018, the estimated damages to Iraq’s health system in the seven governorates affected by the prolonged conflict\ntotal US$2.3 billion. Out of this amount, damages to hospitals in the 16 assessed cities are approximately US$1 billion,\nwhile damage to health centers and health offices are around US$12.6 million.\n\n\n7. The Iraqi health system is primarily financed by general government revenues and direct payments by households,\nand fiscal space has remained constrained. Over the past decade, per capita health spending in Iraq has fluctuated\nfrom a low of US$150.5 in 2010 to a high of US$239.4 in\n\nMention: \"Damage and Needs Assessment\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"The US$2.3 billion health-system damage estimate and city-level facility damage figures come from this assessment.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "umar_pads", "source_key": "umar_pads:002722:2:1", "occurrence_id": "4f1d3c728f43bb8fb5f3736a", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: /sup> but while urbanization is usually paired with economic\ngrowth, increased productivity, and higher living standards, Haiti has taken a different course due to lack of basic services,\ncongestion, pollution, and spatial fragmentation, all of which hold back urban sustainable development.\n\n\nSectoral and Institutional Context\n\n\nUrban transport in Haiti is also a limiting factor for access to economic activities and economic growth. Congestion levels\nare severe in several main cities (Port-au-Prince, Cap-Haitien, les Cayes) due to a combination of the poor condition of\nthe road infrastructure the lack of maintenance, and the suboptimal use of public street space. In addition, the\naffordability of the urban public transport is low, due to high operation costs. As a result of the low-quality, expensive\nand inefficient public transport, walking remains the primary mode of transportation. However, the urban infrastructure\nposes significant challenges for pedestrians.\n\nAdditionally, road connectivity remains limited since secondary and tertiary road networks have benefitted from few\ninvestments, leaving 50 percent of the national territory poorly connected, while entire regions remain isolated for several\ndays at a time during the rainy season. Haiti’s rural access index (RAI, 2015) is about 39 percent, and much of the tertiary\nand rural networks are in very poor condition. Two-thirds of rural Haitians, an estimated 3.2 million people, live rural areas\nthat are difficult-to-access and where poverty rates are significantly higher than other parts of the country. The recent\nearthquake in August 2021 demonstrated once more that natural hazards continue to challenge and disrupt connectivity\nand accessibility.\n\n\n1 Global Rapid Damage Estimation (GRADE) Report, August 27, 2021, World Bank Group.\n2 GFDRR, 2018, https://www.gfdrr.org/en/feature-story/five-reasons-why-haiti-should-invest-resilient-cities.\n\n\nOct 18, 2021 Page\n\nMention: \"Global Rapid Damage Estimation (GRADE) Report\""}, {"role": "assistant", "content": "{\"role\": \"supporting\", \"usage_action\": \"source\", \"summary\": \"Footnote cites the August 2021 damage estimation report behind the hazard-and-transport context.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "umar_pads", "source_key": "umar_pads:002929:3:0", "occurrence_id": "fe11ed2da36bcd1220a51806", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: **The World Bank**\nSecondary Cities Urban Mobility and Development Project (P177918)\n\n\n**B. Introduction and Context**\n\n\nCountry Context\n\n\n1. **Burkina Faso is one of the world’s poorest countries, with an extreme poverty headcount of 32.7**\n**percent** **1** [^1: The World Bank in Burkina Faso. [BURKINA FASO MPO (worldbank.org).](https://thedocs.worldbank.org/en/doc/bae48ff2fefc5a869546775b3f010735-0500062021/related/mpo-bfa.pdf)] **in 2022 (7.5 million people), a gross domestic product (GDP) of US$21.3 billion, and a GDP per capita**\n**of US$941 in 20221** . **2** [^2: World Development Indicators (WDI) in Burkina Faso: World Bank. https://data.worldbank.org/country/burkina-faso] According to the World Development Indicators, its population growth was 2.7 percent in\n2021, one of the highest in the world. Its turbulent political history, difficult biophysical environment, and\nisolation from major trade corridors generate daunting development challenges. 19 percent of the population\nhad access to electricity in 2020, and less than one-third of adults are literate. **3** [^3: World Development Indicators (WDI) in Burkina Faso: World Bank. https://data.worldbank.org/country/burkina-faso] The country ranks 144th out of\n157 countries in the 2020 World Bank’s Human Capital Index and 184th out of 191 countries in the 2021-22\nHuman Development Index report of the United Nations Development Program.\n\n\n2. **Burkina Faso is confronted with acute insecurity threats that compound its considerable development**\n**challenges*\n\nMention: \"World Development Indicators\""}, {"role": "assistant", "content": "{\"role\": \"supporting\", \"usage_action\": \"source\", \"summary\": \"Country context quotes WDI for population growth, GDP and electricity access.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "umar_pads", "source_key": "umar_pads:002929:3:2", "occurrence_id": "c1722cb766c66713748998b3", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: in resilient basic infrastructure and services, connectivity,\ncapacity for resilient urban planning and management, and investments that will foster job creation and social\ninclusion, Burkina Faso can harness their potential for creating opportunities and contributing to the region’s\nfuture growth, stability and social inclusion. Needed investments differ – depending on local city/town\ncircumstances – but will include interventions that would improve living conditions, foster job creation and\n\n\n1 The World Bank in Burkina Faso. [BURKINA FASO MPO (worldbank.org).](https://thedocs.worldbank.org/en/doc/bae48ff2fefc5a869546775b3f010735-0500062021/related/mpo-bfa.pdf)\n2 World Development Indicators (WDI) in Burkina Faso: World Bank. https://data.worldbank.org/country/burkina-faso\n3 World Development Indicators (WDI) in Burkina Faso: World Bank. https://data.worldbank.org/country/burkina-faso\n4 Burkina Faso: Internally displaced population Overview (January 31, 2023), UN Office for the Coordination of Humanitarian Affairs.\n\n\nJul 10, 2023 Page 4 of 11\n\nMention: \"World Development Indicators\""}, {"role": "assistant", "content": "{\"role\": \"supporting\", \"usage_action\": \"source\", \"summary\": \"Footnote cites WDI for the urban context figures behind the project's intervention areas.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "umar_pads", "source_key": "umar_pads:002957:60:0", "occurrence_id": "5789ef08aadc5e4c9e992420", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: **The World Bank**\nIndonesia Mangroves for Coastal Resilience Project (P178009)\n\n\ncentral government, the private sector), and it needs to be updated regularly. This subcomponent will support\nthe following activities:\n\n**i.** **Identification and inventory of mangrove data, specifically biophysical and socioeconomic parameters**\n\nthat can be mapped and are important for the management of Indonesia’s mangrove ecosystem. These\nparameters include identifying and inventorying parameters, the methods used to map parameters, data\nsources, training data requirements, computational considerations, update frequency, and derived\nmanagement information.\nii. **Design and implementation of a web-based spatial data portal** **to improve the quality of mangrove data.**\n\nThis portal will include information on biophysical (including carbon) and socioeconomic variables. This\nactivity will finance (i) storage of data, (ii) enterprise security, (iii) capture and management of training\ndata used to validate models, (iv) data capture and mapping capabilities, (v) workflow engine for system\norchestration and automation, (vi) capacity building required to manage the system, and (vii) metadata\nand ancillary information for products that include validation results.\n**iii.** **Institutional capacity building and infrastructure for mapping mangroves.** This activity will include (i)\n\nassessment of different mapping paradigms including local processing, containerized processing, cloud\nprocessing, and service-based processing; (ii) provision of the software, hardware and equipment\nrequired to support the development and operationalization of mapping products; and (iii) capacity\nbuilding to support mapping operations.\niv. **Generation and dissemination of data and mapping products.** Mangrove data and the National\n\nMangrove Map will be updated building on the activities above and disseminated. The map will also be\nupdated based on additional data from stakeholders, training, and satellite images.\n\n\nSubcomponent 1.3.\n\nMention: \"mangrove data\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"curate\", \"summary\": \"Sub-component funds identifying parameters, mapping methods, sources and training-data needs.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "umar_pads", "source_key": "umar_pads:002957:64:0", "occurrence_id": "4310d21154a112d78da7505e", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: **The World Bank**\nIndonesia Mangroves for Coastal Resilience Project (P178009)\n\n\nmangroves (for villages where rehabilitation will not take place). 49 [^49: Selection will consider the Ministry of Villages’ Self-Reliant Village Index ( _Indeks Desa Mandiri_ ), which village\nleadership monitors annually.]\nii. **Village-based mangrove management planning and integration into village sustainable**\n\n**development and spatial planning:** The subcomponent will finance facilitators to support village-level\nplanning, as well as the development of mangrove management plans. Initial village mapping will be\nconducted to develop village profiles (social, economic, ecological and resilience assessment).\nParticipatory land-use planning will be facilitated to inform village spatial planning. Mangrove\nmanagement plans will outline longer term measures for sustainable mangrove management, which\ncould include the development of village mangrove protection areas and regulations, how mangrove\nresource access and use rights can be legalized and highlight how activities contribute to climate\nresilience and mitigation; they will also identify additional financial support from government budgets\nand programs to ensure the sustainability of these efforts. Villages will be assisted in integrating\nprotection and management activities from these plans into village sustainable development planning\nand budgeting processes. 50 [^50: The village-level planning processes include sustainable development planning (MUSRENBANGdes, RPJMDes),\nvillage budgeting (APBDes), and the development of regulation (SK Desa),]\niii. **Implementation of mangrove management activities:\n\nMention: \"Self-Reliant Village Index\""}, {"role": "assistant", "content": "{\"role\": \"supporting\", \"usage_action\": \"inform\", \"summary\": \"Index guides village selection for mangrove rehabilitation and planning support.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "umar_pads", "source_key": "umar_pads:003064:4:0", "occurrence_id": "b0c7cf7a8b52693fef4556bf", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: **The World Bank**\nCameroon COVID19 Additional Financing for Vaccines (P178255)\n\n\n7. **Cameroon’s health indicators and its epidemiological profile remain comparable to those of low-income**\n**countries, with deep regional and rural-urban disparities** . Cameroon reports the 14th lowest life expectancy\nrate in the world, the burden of disease remains high and maternal deaths have increased over the last two\ndecades. The epidemiological profile remains dominated by communicable diseases. HIV/AIDS, malaria and\ntuberculosis represent about 23.7 percent of total morbidity and 25 percent of deaths. Non-communicable\ndiseases are emerging strongly because of changes in people’s lifestyle and eating habits, especially those of\npeople in urban areas. Potentially epidemic diseases (cholera, meningococcal cerebrospinal meningitis, yellow\nfever, measles), worsen the morbidity and mortality of the population from time to time. The upsurge of health\nemergencies is generally related to epidemics, traumas, movements of populations, and floods. Cameroon is at\nvery high risk of infectious disease outbreaks, particularly those of animal origin (zoonotic diseases). In recent\nyears, Cameroon has had numerous disease outbreaks. These include leishmaniosis (2017), polio (2014, 2019),\nyellow fever (2013), measles (2015, 2019), and cholera (2011, 2014, 2020). Despite Cameroon’s vulnerability to\noutbreaks, particularly in the Far North, there has been minimal investment in strengthening communicable\ndisease surveillance and response systems.\n\n8. **The COVID-19 pandemic has strained primary healthcare services and reduced utilization rates of**\n**primary healthcare services.** According to a World Bank and GFF assessment carried out in July 2021, health\ncare services were moderately affected particularly during the first and second waves of the pandemic.\nUtilization of services were decreased in comparison to the previous year, including outpatient consultations (7 percent), Antenatal\n\nMention: \"World Bank and GFF assessment\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"Quoted for percentage declines in outpatient consultations and other services.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "umar_pads", "source_key": "umar_pads:003106:2:1", "occurrence_id": "2e55dbc408f4a0729b71f1a0", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: traditional growth drivers, namely the agriculture,\ntourism, and manufacturing sectors, while embracing key structural reforms to diversify the economy for sustaining\ngrowth momentum and enhancing socio-economic resilience.\n\n\n3. **Urbanization has also led to increased stress on basic urban services in secondary cities and in emerging small**\n**and medium size towns.** **1** Recent urbanization growth has largely been driven by the capital city of Phnom Penh followed\nby a few secondary cities and small and medium towns. Infrastructure services, including water and sanitation, in these\ncities and towns, and cities at proximity to Phnom Penh Capital are barely able to meet the growing demand stemming\nfrom population growth, let alone the rapid urbanization and expansion of the capital city that is expected to occur in\nthe coming years.\n\n\nSectoral and Institutional Context\n\n\n4. **Cambodia has made good progress on increasing access to basic water supply and sanitation, although**\n**achieving Sustainable Development Goal 6 (SDG 6) remains a challenge.** Access to improved water supply and improved\nsanitation both reached around 70 percent in 2020 from 50 percent and 10 percent respectively in 2000. 2 Remarkable\n\n\n1 World Bank. 2018. _Cambodia Achieving the Potential of Urbanization._\n2 Joint Monitoring Programme 2020 (Updated July 2021). For ease of reference, improved water refers to improved source within 30\nminutes. Improved sanitation refers to improved service which is not shared.\n\n\nJun 13, 2022 Page 3 of 11\n\nMention: \"Joint Monitoring Programme 2020\""}, {"role": "assistant", "content": "{\"role\": \"supporting\", \"usage_action\": \"source\", \"summary\": \"Footnote sources 2000-2020 access rates and defines the improved-service thresholds.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "umar_pads", "source_key": "umar_pads:003293:2:1", "occurrence_id": "4cb047cfffb8a231e3b11143", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: , leading to vulnerability to market\nfluctuations and expensive access to international credit 3 .\n\n\n3. **Kenya’s natural resources underpin the employment, food security, and energy use of its 54 million people.** It is\nthe primary source of livelihood for over 80 percent of the population. It accounts for 35 percent 4 of the total wealth in\nKenya, 42 percent of the GDP, and nearly 70 percent of total employment. The latest estimates in the Kenya Continuous\nHousehold Survey (KCHS, 2021) indicate that 48 percent of workers are employed in agriculture, which is highly climate\n\n\n1 The World Bank Group, 2023. Kenya Country Climate and Development Report.\n2 World Bank (2023). _Kenya Country Economic Memorandum: Seizing Kenya’s Services Momentum_ .\n3 First Fiscal Sustainability and Resilient Growth Development Policy Financing (P500912)\n4 Ministry of Environment and Natural Resources (2016). Land Degradation Assessment in Kenya, Ministry of Environment and\nNatural Resources (MENR), Nairobi.\n\n\nPage 2\n\nMention: \"Kenya Continuous\nHousehold Survey\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"Cited for the worker share in agriculture behind the natural-capital argument.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "umar_pads", "source_key": "umar_pads:003321:3:0", "occurrence_id": "f060e73e0fab9a11b692ce35", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: **The World Bank**\nRoad Sector Sustainability Project AF (P178924)\n\n\n4. **Although it is the typhoon season for Indian Ocean, it is rare for four storms (Ana, Batsirai,**\n**Dumako and Emnati) to hit Madagascar in span of four weeks during Jan 22 – Feb 23, 2022.** Local\npopulations, business, infrastructure, and public services are severely impacted across the country. The\nWorld Bank conducted a Global Rapid Damage Estimation (GRADE) which estimated that the cyclones\nhave displaced around 455,000 people, partially or fully destroyed 56,000 houses, destroyed 10,800\nclassrooms affecting 349,000 students, damaged more than hundred health facilities, and flooded\n212,000 ha of agricultural land. The GRADE analysis estimates the direct damages and losses amount to\naround US$658 million, distributed across residential buildings (20%), non-residential buildings (12%),\ninfrastructure (26%) and agriculture (42%). The total losses are equivalent to 4.8% of Madagascar’s\nnational GDP (2020). While the World Bank’s assessment is based on most urgent needs, the\ngovernment’s assessment reflecting both short term and medium-term needs, is slightly larger at about\nUS$878 million, of which the needs from infrastructure sector are among the largest.\n\n\n5. **Before cyclones the country already suffered from a lack infrastructure and connectivity, and**\n**the extreme weather has worsened the situations.** Despite being the backbone of Madagascar transport\nsector, Madagascar roads remain largely undeveloped with a road density of 5.4 km per 100 km 2 [^2: https://data.worldbank.org/indicator/EG.ELC.ACCS.ZS?end=2020&most_recent_value_desc=false&start=1996&view=chart] of land,\namong the lowest in Sub-Saharan Africa (and the world). Of the 32\n\nMention: \"Global Rapid Damage Estimation\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"Cited for displacement, housing, classroom, health-facility and flood damage totals.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "umar_pads", "source_key": "umar_pads:003341:2:1", "occurrence_id": "b327d7bf2343e7f0e0cfbf03", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: consumption. The Gambia’s Human Capital Index (HCI) is\nlow at 42 percent which is slightly higher than the average for Sub-Saharan Africa (40 percent) and lower than the global\naverage (56 percent) 1 . The country was ranked 174 out of 189 countries on the Human Development Index 2 with a gross\nnational income (GNI) per capita of US$710 in 2018. Overall, 48.6 percent of the population live below the poverty line\n(Integrated Household Survey [his] 2015/16) with a large difference between urban (31.6 percent) and rural areas (69.5\npercent). The Gender Inequality Index rank of the country decreased from 128 in 2012 to 148 in 2015 3 . Women,\nespecially those in rural areas, are faced with disparities in literacy, access to education, health care, and salaried\nemployment, among others. In addition, women have limited access to resources such as land and financing and their\nrate of participation in the labor force is only 37.8 percent as compared to 53.2 for men. 4 [^4: African Development Bank - AfDB: http://comstat.comesa.int/wiqcbkg/afdb-socio-economic-database-19602019?tsId=1443440.]\n\n\n1 The Human Capital Index 2020 Update: Human Capital in the Time of COVID-19; Human Capital Project (HCP) https://databank.worldbank.org/data/download/hci/HCI_2pager_GMB.pdf?cid=GGH_e_hcpexternal_en_ext\n2 UNDP’s 2017 Global Human Development Report 2017.\n3 African Development Bank - AfDB: http://comstat.comesa.int/wiqcbkg/afdb-socio-economic-database-19602019?tsId=1443440.\n4 African Development Bank - AfDB: http:/\n\nMention: \"Integrated Household Survey\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"Cited for the poverty headcount and the urban-rural disparity.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "umar_pads", "source_key": "umar_pads:003480:3:2", "occurrence_id": "b75dd03d1acd5c3973be2008", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: response. The SSNP has so far benefited 4,217 families in sixty-nine\nvillages, including 2,507 women recipients, through its cash-for-work component. It has also enabled access to\nsafety net and nutrition services to 187 poor communities, with over 30,000 pregnant or lactating women,\nadolescent girls and/or children under age five benefiting from basic nutrition services. Following the outbreak\nof the COVID-19 pandemic, the project allocated US$6.5 million to support the Government of Comoros (GoC)\nto address the socioeconomic effects of the pandemic through Unconditional Cash Transfers (UCTs) that\nbenefited 21,556 vulnerable households in urban and peri-urban areas. Similarly, in response to cyclone Kenneth\nin 2019, 10,290 vulnerable households in 118 villages in the three islands were supported through socio\n\n4 Comoros Poverty Assessment Report, World Bank, 2021.\n5 Comoros Poverty Assessment Report, World Bank, 2021.\n\n\nNov 18, 2022 Page 4 of 12\n\nMention: \"Comoros Poverty Assessment Report\""}, {"role": "assistant", "content": "{\"role\": \"supporting\", \"usage_action\": \"source\", \"summary\": \"Footnotes attribute the programme reach and poverty statistics in this section.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "umar_pads", "source_key": "umar_pads:003484:47:1", "occurrence_id": "1cde0bf400b2182a13e74ec6", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: benefit
from the program's capacity development activities to improve the quality and reach of support offered to women at the
country level.|\n|Frequency|Annual.|\n|Data source|Procurement Report.|\n|Methodology for Data
Collection|Administrative Data.|\n|Responsibility for Data
Collection|PIU.|\n|**Regional market ecosystem enablers supported (Number) **|**Regional market ecosystem enablers supported (Number) **|\n|Description|Regional organizations (social enterprises, associations, incubators, NGOs, cooperatives, BDS providers, etc.) that
benefitted from the program's capacity development activities to improve the quality and reach of support offered to
women.|\n|Frequency|Annual.|\n|Data source|Procurement Report.|\n|Methodology for Data
Collection|Administrative Data.|\n|Responsibility for Data
Collection|PIU.|\n|**GBV survivors who sought help to stop the violence (Percentage) **|**GBV survivors who sought help to stop the violence (Percentage) **|\n|Description|Percentage of ever-married women who have ever experienced any physical or sexual violence who sought help to stop
violence.|\n|Frequency|Once at program completion.|\n|Data source|DHS.|\n|Methodology for Data
Collection|Most recent DHS.|\n|Responsibility for Data
Collection|PIU.|\n|**4. Project Implementation Support**|**4. Project Implementation Support**|\n|**Registered grievances satisfactorily resolved in line with the Grievance Redress System (Percentage) **|**Registered grievances satisfactorily resolved in line with the Grievance Redress System (Percentage\n\nMention: \"DHS\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"Indicator on violence survivors seeking help is measured from the most recent survey.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "umar_pads", "source_key": "umar_pads:003490:12:0", "occurrence_id": "7003d40fe4381bb7fbe31934", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: **The World Bank**\nTürkiye Flood and Drought Management Project (P179313)\n\n\n**Note to Task Teams:** This summary section is downloaded from the PCN data sheet and is editable. It should match\nthe text provided by E&S specialist. If it is revised after the initial download the task team must manually update the\nsummary in this section. **_Please delete this note when finalizing the document._**\n\n\nEnvironmental and social risk rating is considered as Substantial at the concept stage. Component 1 includes no regret flood\nrisk measures, and other investments reducing and improving flood risk management in the selected basins and enhancing\nwell-being of population living in risk prone areas. The scale of the proposed flood management structures under\nComponent 1 (e.g. small dams, check dams, levees, retaining walls, embankments, reservoirs, dry and wet polders, etc.) is\nexpected to be medium to large scale. Activities planned under Component 2 are composed of reviewing of existing early\nwarning systems for gap identification, improvement of the systems and relevant capacity building activities, establishment\nof a flood management center and feasibility study for expansion of the early warning system in the country. Those are soft\ncomponents that do no include civil works and thus, do not pose any adverse environmental and social impacts. Thus, the\npotential environmental and social risks and impacts will be mostly relevant to Component 1 and be comprised of impacts\non aquatic and terrestrial habitats due to construction of flood management structures, river bed alteration, water\npollution, land clearance and impacts on floodplain habitats and vegetation\n\nMention: \"PCN data sheet\""}, {"role": "assistant", "content": "{\"role\": \"background\", \"usage_action\": \"curate\", \"summary\": \"Section text is synced from the data sheet and must be updated manually after edits.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "umar_pads", "source_key": "umar_pads:003490:6:0", "occurrence_id": "df4f1a10acacd0d85142654a", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: **The World Bank**\nTürkiye Flood and Drought Management Project (P179313)\n\n\nand flood risk management plans. Accordingly, Regulation on Preparation, Implementation and Monitoring of\nManagement Plans has been put into effect in 2016. Since then, flood management plans Plans are completed for\n23 river basins: Yeşilırmak, Antalya, Sakarya, Susurluk, Ceyhan, Kuzey Ege, Gediz, Küçük Menderes, Batı Karadeniz,\nBurdur, Batı Akdeniz, Büyük Menderes, Akarçay, Kızılırmak, Aras, Doğu Akdeniz, Van Lake, Konya Closed, Asi,\nSeyhan Fırat-Dicle, Doğu Karadeniz and Çoruh, The preparation of Marmara FMP and Meriç-Ergene FMP are\nongoing. The FMPs, for all river basins, are planned to be completed by the end of 2023. Additionally, as stated in\nthe EU Flood Directive, studies have been started for reviewing and updating in Yeşilırmak, Antalya, Sakarya,\nSusurluk, and Ceyhan Basins Flood Management Plans which were completed in 2016. DSI, in consultation with\nother stakeholders, is preparing a new Regulation for Flood Management which is expected to be enacted in 2023.\n\n15. **Drought Management Plans (DMPs) aim to reduce the negative effects of drought risks.** DG Water Management\nprepares these plans based on drought analysis and drought maps, hydrological studies, sectoral vulnerability\nanalysis. These are used to determine critical intervention measures that will be taken before, during and after\nthe drought event. Drought Management Plans have been completed in 15 basins (Kuzey Ege, K. Menderes, Batı\nAkdeniz, Burdur, Akarçay, Antalya, Konya,\n\nMention: \"drought analysis and drought maps\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"inform\", \"summary\": \"Used with hydrological and vulnerability studies to set pre-, during- and post-drought measures.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "umar_pads", "source_key": "umar_pads:003603:2:1", "occurrence_id": "5681c3f730cc9f6b84f3b9c1", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: which is the main emitter, and the forest sector, the only sector with removal capacity. Studies\nconducted under the PMR informed a national decision-making process which resulted in the GoP’s\ncommitment to move forward with the design and piloting of the National Carbon Market of Panama\n(MNCP), as established by Executive Decree 142 of 2021. Moreover, the World Bank (WB) supported the\ndevelopment of the National Strategy for the Rational and Efficient Use of Energy, which was enacted by the\nNational Energy Secretariat’s (SNE) Resolution 13286 of April 8th, 2022, and Cabinet Resolution 66 of June\n1st, 2022. Action line 37 of this strategy includes the design and implementation of a National EE Certificates\nProgram. Thus, the GoP is committed to moving forward with the piloting of this program, as well as the\ndesign of instrument options for the participation of the transport sector in national and international\nmarket-based mechanisms.\n\n\nSectoral and Institutional Context\nThe energy sector is the main GHG emitter with 62.9% (17,780.9 kt CO2 eq) of emissions in 2017. In Panama,\n74.4% of energy is supplied by imported fossil fuels (oil products, carbon, and natural gas) and 25.6% from\nrenewable sources. According to the SNE’s energy balance, 46% of energy is consumed by the transport\nsector, 22.9% by the industry, 14.9% by commercial and public services, and 14.7% by the residential sector.\nTransport is responsible for 60% of all fossil fuels consumed in Panama. The country’s high dependence on\nfossil fuels makes its economy vulnerable to changing world prices for crude oil and hence, a transition to\nclean energy is crucial for Panama’s long-term energy security and economic stability.\n\n\nPanama is working on diversifying its power generation matrix and reducing its fossil fuels dependence\nthrough the introduction of non-conventional renewable\n\nMention: \"SNE’s energy balance\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"analyze\", \"summary\": \"Used to show transport dominance in fossil fuel use for the carbon market design.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "umar_pads", "source_key": "umar_pads:003643:8:1", "occurrence_id": "268d2d6e2e95bc94487ec7ee", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: of reaching agreement with potential project sponsors on the legal and financing arrangements of the Project.\n\n\n_C_ omponent 1 of MPA Phase 1: Geophysical and geotechnical surveys of the Black Sea seabed (US$20 million)\n\n\n35. **As part of the feasibility study process, and prior to the bidding on the construction contract of the Black Sea**\n**Submarine Cable Project, three studies of the seabed will need to be carried out:**\n\n - **Geological investigation.** The geological investigation is part of the scope of the ongoing feasibility study\n(under Task 2, Technical Definition of the Project). Based on a desktop study, the consultant will recommend\na wide corridor for the interconnection routing based on all applicable guidelines and laws, as well as existing\nknowledge of the geological and geotechnical aspects of the Black Sea.\n\n - **Geophysical investigation.** The geophysical investigation involves scanning the seabed to further detail the\nidentified corridor. The survey can be conducted from vessel-mounted equipment for water depths under 50100 meters, but it requires remotely operated vehicles or other systems that can operate close to the seabed\nfor higher depths. The survey equipment for this investigation may include: (i) a multi-beam echo sounder\nand a side scan sonar to acquire bathymetry and seabed data, (ii) a sub-bottom profiler to remotely sense\nlayers of sediment and rock beneath the seabed, and (iii) magnetometers (gradiometer) to detect the\npresence of ferrous material such as shipwrecks, cables/pipelines and unexploded ordnance on the seabed.\n\n - **Geotechnical investigation.** The geotechnical investigation is performed within the identified narrow corridor\nbuilding on the data from the geophysical investigation. It is carried out by specialized vessels that can perform\n\n\nMar 18, 2023 Page 9 of 13\n\nMention: \"data from the geophysical investigation\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"analyze\", \"summary\": \"Multibeam, sub-bottom profiler and magnetometer results define the corridor for drilling.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "umar_pads", "source_key": "umar_pads:003671:5:2", "occurrence_id": "5f1b70ede9e2e0a25e384463", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: labor. Customary\nlaws drive access and ownership of land and often dictate that on-farm resources belong to men, a situation which\nleaves women at a disadvantage. Child labor is widespread in all subsectors of agriculture, and hazardous child\nlabor is very common. According to the Ghana Living Standards Survey (GLSS) 2016/17, the agricultural sector\naccounts for 79.1% of all cases of hazardous child labor. Reports indicate that reliance on child labor is high in\ncocoa production, especially its harvest. The practice reflects factors like labor shortages, limited access to finance\nand low household incomes, lack of access to quality education, and a host of traditions.\n\n\n9 The parastatal supports production and processing including on-farm productivity through research and extension, fertilizer subsidies and provision\nof rehabilitation services like cutting and pruning.\n10 Almost 25% of cocoa trees are now around 30 years old and their productivity is declining (COCOBOD, 2015).\n\n\nNov 01, 2022 Page 6 of 14\n\nMention: \"Ghana Living Standards Survey\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"Cited for agriculture's share of hazardous child labour cases.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "umar_pads", "source_key": "umar_pads:003738:3:0", "occurrence_id": "f5236bd2c8a8be5a78e6e337", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: **The World Bank**\nGovernment Efficiency, Accountability, and Results Upscaling Program for Kenya(P180287)\n\n\nfundamental reform challenge. Kenya was ranked 123rd out of 180 countries in 2022 in Transparency International’s\nCorruption Perception Index. The Ethics and Anti-Corruption Commission found in a 2018 survey that 42% of respondents\nwho sought government services in 2018 experienced some form of corruption, up from 39% the previous year. These\nchallenges can impact citizen trust in government: in the Afrobarometer Survey for 2016-18, 2 [^2: See: https://afrobarometer.org/online-data-analysis/analyse-online] 71% of Kenyans surveyed\nconsidered that the Government was handling the issue of fighting corruption badly and almost two-thirds considered\nthat the Government was handling the improvement of living standards for the poor badly.\n\n**Higher revenue mobilization and efficiency in spending is needed to operationalize the Government’s development**\n**agenda.** Kenya’s revenue effort approximates the Sub-Saharan Africa average despite the country being an LMIC. Kenya’s\ntax-to-GDP ratio is lower than the average of 30 African countries and much lower than some aspirational peers. Despite\nthe progress achieved in public financial management (PFM) reform, several systemic issues continue to plague the public\nexpenditure management landscape. These include: (i) continuing inefficiencies and fragmentation in budget and treasury\nmanagement limiting the credibility of the budget, funds flow, and accountability for expenditures; (ii) weaknesses in\npublic investment management (PIM) leading to non-performing projects which limit the fiscal space available in the\ndevelopment budget; and (iii) incomplete rollout of the public procurement legal and regulatory framework impacting the\nefficiency and transparency with which procurement spending is undertaken. The limitations in fiscal space, partly driven\nby a rising wage bill, impact the timeliness of allocations and transfers to development programs. Gaps in the clarification\nand assignment of the functional responsibilities of MDAs lead to duplication in service delivery functions\n\nMention: \"Afrobarometer Survey\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"Cited for the shares of citizens rating anti-corruption efforts badly.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "umar_pads", "source_key": "umar_pads:004082:3:1", "occurrence_id": "fffa9981f95d7cb6600536d6", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: \nCambodia 2019–2024 (CPF Objectives 8 ‘Expand and Improve Sustainable Infrastructure Services’). The project\ncontributes to the World Bank’s mission to end extreme poverty and boost shared prosperity on a livable planet by\nextending the benefits of climate-resilient road accessibility and lower transportation costs to a broader segment of the\npopulation in rural areas, where most of the poor and near-poor are concentrated. The project also contributes to RGC’s\ndevelopment strategy which prioritizes the enhancement of transport connectivity and efficiency to support economic\ndiversification and competitiveness under the Pentagonal Strategy Phase 1 (2023).\n\n\n**C. Proposed Development Objective(s)**\n\nOriginal PDO\n\n\n6. The project development objective is to improve climate resilient road access to economic and human\ndevelopment facilities in targeted provinces.\n\n\nCurrent PDO\n\n\n7. There is no change from the original PDO. The PDO remains as to improve climate resilient road access to\neconomic and human development facilities in targeted provinces and, in case of an Eligible Crisis or Emergency, repond\npromptly and effectively to it.\n\n\nKey Results\n\n\n8. The achievement of the PDO is measured by the following key result indicators. The Result Framework (RF) and\nresult indicators of the original project remain effective and relevant. The proposed Additional Financing (AF) will update\nthe target values and measurement methodology for several result indicators to align with recently completed baseline\nsocio-economic surveys, and to better monitoring and measuring progress and impact.\n\n\n(a) Facilities with improved climate resilient road access (number, disaggregated by facility):\n\n\nNov 13, 2023 Page 4 of 9\n\nMention: \"baseline\nsocio-economic surveys\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"Additional financing updates targets and measurement based on these surveys.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "umar_pads", "source_key": "umar_pads:004502:2:1", "occurrence_id": "494ab3c2607b6385f5c72f83", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: is further exacerbated by\nthe recent conflict that initially started in October 2023 but faced significant escalation between September and\nNovember 2024, sparking a wave of internal displacement and emigration.\n\n**Although the multiple crises have had a major impact on employment and jobs, some high-growth potential sectors**\n**are doing relatively better, including in technology and digital sectors.** Prior to the 2019 crisis, Lebanon had already\ngrappled with labor market issues, including stagnant job creation, inability to produce high-quality jobs, low\nworkforce engagement—particularly among women—youth unemployment, skill gaps, and a prevalence of informal,\nlow-yield employment. With the onset of the crises, the labor situation worsened, marked by rising joblessness due to\nfirings, voluntary job exits, and widespread business shutdowns, which in turn fueled the informal sector. This\nelevated inactivity among the Lebanese workforce saps both the economy and human capital. Nevertheless, certain\nindustries like agriculture and agro-food are experiencing growth, potentially replacing costly imports with local goods\namid currency devaluation. Moreover, the drop in average wages has rendered Lebanese labor more globally\ncompetitive, notably in sectors such as ICT, where outsourcing opportunities lie in customer relationship management\n(CRM) services, software/applications development and integration, engineering design and consulting, marketing\n[services, business consulting and market research, and telemedicine/remote education (BCG MENA Talent Map,](https://www.bcg.com/publications/2023/future-of-outsourcing-mena-talent-map)\n2023). With a skilled talent pool, Lebanon can provide services ranging from managing customer relationships and\ndeveloping software solutions to offering engineering design and marketing expertise.\n\n**Technology and digital sectors are expanding globally, and remote work trends, such as gig work, are impacting job**\n**dynamics, providing much needed work opportunities for workers in Lebanon.** The necessity for all populations to\nhave\n\nMention: \"BCG MENA Talent Map\""}, {"role": "assistant", "content": "{\"role\": \"supporting\", \"usage_action\": \"inform\", \"summary\": \"Used to select high-potential digital service sectors in the jobs analysis.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "umar_pads", "source_key": "umar_pads:004502:2:2", "occurrence_id": "445f7f2afa4c64c8910e23a0", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: expertise.\n\n**Technology and digital sectors are expanding globally, and remote work trends, such as gig work, are impacting job**\n**dynamics, providing much needed work opportunities for workers in Lebanon.** The necessity for all populations to\nhave access to internet and be digitally literate and skilled has never been more important. Globally, it is estimated\nthat 44 percent of workers’ skills will be disrupted in the next five years, 83 million jobs will be displaced by 2025 while\n[69 million jobs will be created (World Economic Forum, 2023). Six in ten workers will require training before 2027, but](https://www3.weforum.org/docs/WEF_Future_of_Jobs_2023.pdf)\n[only half of workers are seen to have access to adequate training opportunities today (World Economic Forum, 2023).](https://www3.weforum.org/docs/WEF_Future_of_Jobs_2023.pdf)\nIn addition, globally, almost one quarter million youth are engaged in online gig work (out of the 435 million gig\nworkers of all ages) **.** In Lebanon for instance, the share of youth engaged in gig work stands at 52 percent, one of the\nhighest alongside Egypt, Morocco and Tunisia ( [S4YE, 2023). The Online Labour Index (OLI) indicates a 41 percent](https://openknowledge.worldbank.org/entities/publication/ebc4a7e2-85c6-467b-8713-e2d77e954c6c)\n[increase in demand for gig work between 2016 and Q1 2023, accelerated by the COVID-19 pandemic (S4YE, 2023).](https://openknowledge.worldbank.org/entities/publication/\n\nMention: \"Online Labour Index\""}, {"role": "assistant", "content": "{\"role\": \"supporting\", \"usage_action\": \"source\", \"summary\": \"Cited for the rise in gig work demand since 2016.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "umar_pads", "source_key": "umar_pads:004548:3:1", "occurrence_id": "43e28bd0f22fc82750bf3ce3", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: *reforms to accelerate recovery, enable leapfrogging in public service delivery through digital transformation, and**\n**strengthen climate resilience, consistent with the World Bank Group’s Climate Change Action Plan (CCAP).** **5** It will\nfinance essential digital foundations and enablers to scale service delivery, improve system resilience and adaptability,\nand build capacity to manage shocks and disruptions. To address climate vulnerabilities, the project will implement\nadaptation measures to protect data hosting infrastructure and will strengthen Lebanon’s adaptive capacity by improving\npublic service reliability, continuity, and inclusivity; expanding remote employment—particularly for women and\nvulnerable groups—and enhancing redundancy and disaster recovery capabilities for public sector data. The project aligns\nwith the CCAP’s Green, Resilient, and Inclusive Development (GRID) approach and Lebanon’s strategic and political\ncommitments—including its endorsement of the Green Digital Declaration at COP29. 6\n\n\nSectoral and Institutional Context\n\n\n5. **Despite recent progress in the digitalization of public services, institutional gaps and insufficient**\n**implementation capacity have constrained the digital transformation of Lebanon’s Government.** The COVID-19\npandemic and economic crisis catalyzed the development of platforms such as the vaccination system and DAEM social\nregistry for social assistance. Other notable digital initiatives include the IMPACT open data information system, 7 the\ndigitalization of civil status extracts and consumer protection services, and various digital health platforms. Despite these\nefforts, Lebanon still lags its peers in digital government transformation. 8 Access to online government services is notably\nlow, and a recent survey found that women’s access to online government services in Lebanon was nearly nonexistent,\ncompared to 25 percent in Jordan. 9 Key challenges include outdated legal and regulatory frameworks\n\nMention: \"IMPACT open data information system\""}, {"role": "assistant", "content": "{\"role\": \"background\", \"usage_action\": \"source\", \"summary\": \"Named among initiatives that have not yet closed the gap with peer countries.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "umar_pads", "source_key": "umar_pads:004548:3:3", "occurrence_id": "8aeae94299e7c60466172d08", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: .lb/.\n8 Lebanon ranks 126th globally in the United Nations’ 2024 E-Government Development Index (EGDI), placing it ahead of only Iraq, Syria, Yemen,\n[and Djibouti within the Middle East and North Africa region (link).](https://publicadministration.un.org/egovkb/en-us/Data-Center)\n9 World Bank. Forthcoming. “State of the Mashreq Women Flagship: Digital Transformation and Its Role in Expanding Women’s Economic\nOpportunities in Iraq, Jordan, and Lebanon.”\n\n\nPage 3\n\nMention: \"2024 E-Government Development Index\""}, {"role": "assistant", "content": "{\"role\": \"supporting\", \"usage_action\": \"source\", \"summary\": \"Cited for the country's low global and regional ranking.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "umar_pads", "source_key": "umar_pads:004553:3:0", "occurrence_id": "767d243727ad3736fed886cd", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: **The World Bank**\nGeospatial Infrastructure for Sustainable Territorial Development(P506803)\n\n\nand promote sustainable territorial and urban development, However, there is still much work to be done to enhance\nresilience in Uzbekistan, particularly in terms of land management, territorial planning and ensuring the effective\nimplementation and enforcement of policies and strategies along with strengthening institutional capacity and\ncoordination.\n\n\nSectoral and Institutional Context\n\n5. **While Uzbekistan has experienced remarkable economic growth, spatial inequalities persist with a significant gap in**\n**income and the provision of services and infrastructure between regions.** This disparity is further exacerbated by an\nurban-rural divide, with employment opportunities concentrated in big urban centers.\n\n\n6. **Uneven territorial development is further exacerbated by rapid urban growth in Uzbekistan which generates a new**\n**set of challenges resulting in significant pressure on land.** In the past 30 years, the country has experienced a significant\ndemographic shift from predominantly rural to increasingly urban living, with over 50 percent of the population now\nresiding in urban areas. As migration restrictions ease, rural-to-urban migration is expected to rise further, intensifying\nthe demand for housing and land 5 [^5: Sivaev, D., Kamilov I., Rossitti G., Orlova, N., Vaggione 2022, P. The Time is Now: How Can Uzbekistan Leverage Urbanization as a Driver of Sustainable\nDevelopment? Washington, DC: World Bank.] . This growth has been and continues to be largely spontaneous and unmanaged, leading\nto increased vulnerability to climate change and disasters, and unmet needs for infrastructure and services, which\nhampers residents’ quality of life, diminishes cities' attractiveness to investors, and limits job creation.\n\n\n7. **For the Uzbekistan 2030 Strategy to achieve its goals, leveraging spatial data for evidence-based reforms is crucial.**\nWithout accurate cadastral and geospatial data, initiatives risk resulting in uncoordinated urban expansion, informal\nsprawl, and agricultural land encroachment. Inefficient planning may result in\n\nMention: \"spatial data\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"inform\", \"summary\": \"Absence of accurate cadastral and spatial data is cited as a driver of uncoordinated expansion.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "umar_pads", "source_key": "umar_pads:004658:5:1", "occurrence_id": "7444a1a2c064976ab9a77930", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: carbonize their domestic energy and industrial value chain, creating the need for concessional financing. At the\nsame time, Brazil’s heavy industries need to respond to the market signals from the EU’s Carbon Border Adjustment\nMechanism (CBAM), which will come into full effect in 2026 10 [^10: CBAM entails taxes on goods imported to the EU according to the carbon emitted during their production. The list of sectors\ncovered in the first phase (2023-2025) include cement, iron and steel, aluminum, fertilizers, electricity, and hydrogen (this list could\nbe adjusted when the definitive regime begins in 2026).] ; based on 2022 export figures, USD 3 billion of Brazilian\nexports would be affected by the mechanism, with iron, steel, and aluminum sectors accounting for the largest\nshare 11 [^11: [https://www.iisd.org/system/files/2024-07/border-carbon-adjustments-brazil.pdf](https://www.iisd.org/system/files/2024-07/border-carbon-adjustments-brazil.pdf)] . Brazil is also preparing legislation for a carbon market, but the impact on the industrial sector is not yet clear.\n\n\n9. **Large amounts of funding must be leveraged to finance the energy transition and industrial decarbonization in**\n**Brazil, including from the private sector, yet challenges remain to attracting commercial financing for these**\n**investments.** The Brazilian National Confederation of Industries (CNI) estimates that R$40 billion will need to be\ninvested by Brazilian industries by 2050, excluding investments in other sectors that will be key to enable such\ndecarbonization, such as renewable energy generation to support electrification of industries and green hydrogen\nproduction. In the World Bank’s Brazil Country Climate and Development Report (CCDR), additional clean energy\ninvestment needs to support industry and transport decarbonization were estimated to total approximately R$300\n\nMention: \"2022 export figures\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"analyze\", \"summary\": \"Used to identify the most affected heavy industry sectors.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "umar_pads", "source_key": "umar_pads:005095:40:0", "occurrence_id": "6977fd95174d9fcdaa9a0c62", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: **The World Bank**\n\nParaiba Water Security Project (Northeast MPA Phase I) (P511557)\n\n\n**Monitoring & Evaluation Plan: PDO Indicators by PDO Outcomes**\n\n\n\n\n\n\n\n|Phase 1 – PDO Outcome 1. Strengthen the foundations to water security in the State|Col2|\n|---|---|\n|**PDO Indicator 1. People benefitting from climate resilient planning, preparation, surveillance, and/or response -scorecard**
**indicator- (Number of people)**|**PDO Indicator 1. People benefitting from climate resilient planning, preparation, surveillance, and/or response -scorecard**
**indicator- (Number of people)**|\n|Description|Refers to individuals who benefit from interventions in Component 1, more specifically, those
within the Paraíba and Piancó-Piranhas basins linked to the PISF (São Francisco River
Integration Project) beneffited from SEIRA and monitoring actions. The baseline is set at zero,
and the target will be established using the current population of these basins as reported by
IBGE|\n|Frequency|Annual|\n|Data source|AESA|\n|Methodology for Data Collection|Cumulative number of beneficiaries in activities of Component 1 that contribute to an
enhanced resilience, avoiding double counting in case of multiple interventiones in the
same area.|\n|Responsibility for Data Collection|AESA|\n|**PDO Indicator 2. Water resources management instruments strengthened (Number)**|**PDO Indicator 2. Water resources management instruments strengthened (Number)**|\n|Description|Reflects progress in improvements of water resources instruments based on performance
levels (detailed informations will be\n\nMention: \"AESA\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"Also sets the basin population baseline for the resilience indicator.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "umar_pads", "source_key": "umar_pads:005128:11:1", "occurrence_id": "f00e00062c9a537617a126d0", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: ) region. 2 [^2: World Bank 2014: _Natural Disasters in the Middle East and North Africa: A Regional Overview_ . Washington D.C.: World Bank.] The September 2023 Al Haouz earthquake highlighted vulnerabilities, especially in some\nrural regions, in infrastructure, livelihoods, and rainfed agriculture, which employs around a third of the workforce.\nClimate change is set to intensify these risks further. Projections point to continued warming, reduced rainfall, and more\nfrequent extreme precipitation events, which are projected to reduce GDP by up to 6.5 percent in coming decades. The\neconomic toll is already visible: climate shocks already account for nearly 37 percent of GDP volatility up to 2022. 3 [^3: World Bank 2022, _Morocco CCDR_ .]\n\n**3.** **Ensuring that households and firms have access to appropriate financial services is critical for supporting their**\n**resilience against shocks** . Despite progress, significant gaps in financial inclusion remain. According to 2024 Findex data,\nonly 44 percent of adults had an account (55 percent of men vs. 35 percent of women), and only 32 percent had made or\nreceived a digital payment (43 percent of men vs. 23 percent of women). 4 [^4: World Bank 2025: _The Global Findex Database 2025._ Washington D.C.: World Bank.] Insurance coverage is characterized by similar\ngaps: according to a nationally representative study, 56 percent of men held at least one insurance policy, compared with\n39 percent of women. 5 [^5: ACAPS, Inclusive Insurance Barometer, 2022] The first phase of the National Financial Inclusion Strategy (SNIF), launched in 2019, began to\naddress this challenge by improving the enabling environment for microfinance, inclusive insurance and digital payments.\nThe second phase of the SNIF\n\nMention: \"2024 Findex data\""}, {"role": "assistant", "content": "{\"role\": \"primary\", \"usage_action\": \"source\", \"summary\": \"Establishes the inclusion baseline the project targets.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}
{"origin": "umar_pads", "source_key": "umar_pads:005128:11:1", "occurrence_id": "5582e6c48bf5601aa1aa5237", "messages": [{"role": "system", "content": "Describe how the author uses the cited data mention, using only the passage. Output ONLY JSON with keys role, usage_action, summary. Pick usage_action from these boundaries: source = the mention is where the quoted figures come from; analyze = the author computes, estimates, regresses or aggregates values from it; validate = it is used to cross-check or corroborate another estimate; curate = the author describes collecting, compiling, archiving or maintaining it; inform = cited for context or trend without its values being used. role is primary, supporting, or background. summary is one concise sentence in English, whatever language the passage is in; do not invent details."}, {"role": "user", "content": "Text: ) region. 2 [^2: World Bank 2014: _Natural Disasters in the Middle East and North Africa: A Regional Overview_ . Washington D.C.: World Bank.] The September 2023 Al Haouz earthquake highlighted vulnerabilities, especially in some\nrural regions, in infrastructure, livelihoods, and rainfed agriculture, which employs around a third of the workforce.\nClimate change is set to intensify these risks further. Projections point to continued warming, reduced rainfall, and more\nfrequent extreme precipitation events, which are projected to reduce GDP by up to 6.5 percent in coming decades. The\neconomic toll is already visible: climate shocks already account for nearly 37 percent of GDP volatility up to 2022. 3 [^3: World Bank 2022, _Morocco CCDR_ .]\n\n**3.** **Ensuring that households and firms have access to appropriate financial services is critical for supporting their**\n**resilience against shocks** . Despite progress, significant gaps in financial inclusion remain. According to 2024 Findex data,\nonly 44 percent of adults had an account (55 percent of men vs. 35 percent of women), and only 32 percent had made or\nreceived a digital payment (43 percent of men vs. 23 percent of women). 4 [^4: World Bank 2025: _The Global Findex Database 2025._ Washington D.C.: World Bank.] Insurance coverage is characterized by similar\ngaps: according to a nationally representative study, 56 percent of men held at least one insurance policy, compared with\n39 percent of women. 5 [^5: ACAPS, Inclusive Insurance Barometer, 2022] The first phase of the National Financial Inclusion Strategy (SNIF), launched in 2019, began to\naddress this challenge by improving the enabling environment for microfinance, inclusive insurance and digital payments.\nThe second phase of the SNIF\n\nMention: \"nationally representative study\""}, {"role": "assistant", "content": "{\"role\": \"supporting\", \"usage_action\": \"source\", \"summary\": \"Cited for insurance penetration gaps in the resilience discussion.\"}"}], "task": "usage", "is_synthetic": false, "origin_model": ""}