Buckets:

Pranav2748's picture
download
raw
85.1 kB
{"id": "ts:clutrr-effc7ced7a:train:10954:choice-criteria-permutation", "kind": "hard", "fresh": true, "reasoning_source": true, "source": "clutrr", "v2_readout_p_gold": 0.17862898362339782}
{"id": "ts:reclor-3f0b326481:train:617", "kind": "hard", "fresh": true, "reasoning_source": true, "source": "reclor", "v2_readout_p_gold": 0.7985963585918657}
{"id": "ts:strategy-qa-44f34e040f:train:1078", "kind": "hard", "fresh": true, "reasoning_source": true, "source": "strategy-qa", "v2_readout_p_gold": 0.3629691917376782}
{"id": "ts:logiqa-2-0-nli-cf23683f05:train:3965", "kind": "hard", "fresh": true, "reasoning_source": true, "source": "logiqa-2.0-nli", "v2_readout_p_gold": 0.7879311856832191}
{"id": "ts:utilitarianism-44bbb16ec2:train:10410:noul-label-verification", "kind": "hard", "fresh": false, "base_correct_of_4": 2, "v2_readout_p_gold": 0.743167997235783}
{"id": "ts:lsat-qa-all-05417eda9d:train:118", "kind": "hard", "fresh": true, "reasoning_source": true, "source": "lsat_qa/all", "v2_readout_p_gold": 0.3395600079802427}
{"id": "ts:dynabench-dynasent-8074025339:train:79974e6a74956f92:dynasent-r1_votes", "kind": "soft", "fresh": false, "base_correct_of_4": 3, "v2_readout_p_gold": 0.6909702329737304}
{"id": "ts:babi-nli-positional-reasoning-aa912c540b:train:41:choice-criteria-permutation", "kind": "hard", "fresh": true, "reasoning_source": true, "source": "babi_nli/positional-reasoning", "v2_readout_p_gold": 0.20181322466072713}
{"id": "ts:FOL-nli-3deb6ff51f:train:27927", "kind": "hard", "fresh": true, "reasoning_source": true, "source": "FOL-nli", "v2_readout_p_gold": 0.5075366673181967}
{"id": "ts:english-grading-vocabulary-6df5aad673:train:3153", "kind": "hard", "fresh": true, "reasoning_source": false, "source": "english-grading/vocabulary", "v2_readout_p_gold": 0.7035623287388924}
{"id": "ts:logical-fallacy-49ee8e577f:train:707", "kind": "hard", "fresh": true, "reasoning_source": true, "source": "logical-fallacy", "v2_readout_p_gold": 0.5820700343560884}
{"id": "ts:multilingual-indic-glue-inltkh-828bd89f7c:train:136", "kind": "hard", "fresh": true, "reasoning_source": false, "source": "multilingual/indic_glue/inltkh", "v2_readout_p_gold": 0.7337104631004124}
{"id": "ts:anli-a1-bca8387399:train:pack-7d58583b5f09:label-B", "kind": "hard", "fresh": false, "base_correct_of_4": 3, "v2_readout_p_gold": 0.7426333732896225}
{"id": "ts:auditor-review-d22853943d:train:2541:choice-criteria-permutation", "kind": "hard", "fresh": true, "reasoning_source": false, "source": "auditor_review", "v2_readout_p_gold": 0.7920973728576206}
{"id": "ts:help-nli-63b76526b1:train:3905", "kind": "hard", "fresh": true, "reasoning_source": false, "source": "help-nli", "v2_readout_p_gold": 0.5621765008857981}
{"id": "ts:pragmeval-pdtb-0d313c7bbc:train:12063", "kind": "hard", "fresh": false, "base_correct_of_4": 2, "v2_readout_p_gold": 0.1767580843608806}
{"id": "proc:graph_navigation:train:8139:first_hop", "kind": "exact", "fresh": false, "base_correct_of_4": 2, "v2_readout_p_gold": 0.7983645635410379}
{"id": "ts:prompt-injections-68fc037019:train:28", "kind": "hard", "fresh": true, "reasoning_source": false, "source": "prompt-injections", "v2_readout_p_gold": 0.7310585727705126}
{"id": "ts:multilingual-xstory-cloze-eu-523ea8855a:train:189", "kind": "hard", "fresh": true, "reasoning_source": false, "source": "multilingual/xstory_cloze/eu", "v2_readout_p_gold": 0.5}
{"id": "proc:instruction_execution:train:19363:target_count", "kind": "exact", "fresh": false, "base_correct_of_4": 2, "v2_readout_p_gold": 0.6102238479322659}
{"id": "ts:naturallogic-ba86bebf3b:train:pack-4dda7bff702e:count-0", "kind": "hard", "fresh": true, "reasoning_source": true, "source": "naturallogic", "v2_readout_p_gold": 0.2950656422103946}
{"id": "ts:folio-6c5df13928:train:617", "kind": "hard", "fresh": true, "reasoning_source": true, "source": "folio", "v2_readout_p_gold": 0.7397253968563157}
{"id": "ts:SpaRTUN-ae090fe669:train:25110", "kind": "hard", "fresh": true, "reasoning_source": true, "source": "SpaRTUN", "v2_readout_p_gold": 0.29421497216298875}
{"id": "ts:community-datasets-proto-qa-proto-qa-1bbafc24d1:train:71cf433005ea139b:proto_qa-proto_qa", "kind": "soft", "fresh": false, "base_correct_of_4": 3, "v2_readout_p_gold": 0.3518197080019154}
{"id": "ts:FOL-nli-3deb6ff51f:train:pack-4e90ec62ea6a:label-B", "kind": "hard", "fresh": true, "reasoning_source": true, "source": "FOL-nli", "v2_readout_p_gold": 0.6709786305357284}
{"id": "ts:code-x-glue-cc-defect-detection-1c76c57e72:train:7396", "kind": "hard", "fresh": false, "base_correct_of_4": 3, "v2_readout_p_gold": 0.37754066879814546}
{"id": "ts:ruletaker-511880334b:train:11940", "kind": "hard", "fresh": true, "reasoning_source": true, "source": "ruletaker", "v2_readout_p_gold": 0.7549149868676283}
{"id": "ts:webgpt-comparisons-30f5b33bbc:train:8579:choice-criteria-permutation", "kind": "hard", "fresh": false, "base_correct_of_4": 3, "v2_readout_p_gold": 0.7549149868676283}
{"id": "ts:lsat-ar-eb3f507971:train:1451", "kind": "hard", "fresh": true, "reasoning_source": true, "source": "lsat-ar", "v2_readout_p_gold": 0.835121234534678}
{"id": "ts:sbic-offensiveness-fa09cf4572:train:2295", "kind": "hard", "fresh": true, "reasoning_source": false, "source": "sbic/offensiveness", "v2_readout_p_gold": 0.6762432858929482}
{"id": "ts:PromptShield-316f4c62ab:train:15300:choice-criteria-permutation", "kind": "hard", "fresh": true, "reasoning_source": false, "source": "PromptShield", "v2_readout_p_gold": 0.21206881431678096}
{"id": "ts:lsat-rc-094f659543:train:1684", "kind": "hard", "fresh": true, "reasoning_source": true, "source": "lsat-rc", "v2_readout_p_gold": 0.5226563652334311}
{"id": "ts:magpie-idiomatic-9964397cb2:train:4915", "kind": "hard", "fresh": false, "base_correct_of_4": 3, "v2_readout_p_gold": 0.9149009526726544}
{"id": "ts:hans-8800578b51:train:29039", "kind": "hard", "fresh": true, "reasoning_source": false, "source": "hans", "v2_readout_p_gold": 0.8354835309589073}
{"id": "ts:logical-entailment-5fde239036:train:19270", "kind": "hard", "fresh": true, "reasoning_source": true, "source": "logical-entailment", "v2_readout_p_gold": 0.48438008427698437}
{"id": "ts:tasksource-lewidi-hs-brexit-320212f38d:train:06f20613a30fadb7:lewidi-hs_brexit", "kind": "hard", "fresh": false, "base_correct_of_4": 3, "v2_readout_p_gold": 0.7662936377487304}
{"id": "ts:hh-rlhf-helpful-rejection-sampled-f5856bd383:train:21499", "kind": "hard", "fresh": false, "base_correct_of_4": 3, "v2_readout_p_gold": 0.32082130731838393}
{"id": "ts:strategy-qa-44f34e040f:train:460", "kind": "hard", "fresh": false, "base_correct_of_4": 2, "v2_readout_p_gold": 0.6791786926816161}
{"id": "ts:winogrande-winogrande-xl-eb5b02a7c5:train:4956", "kind": "hard", "fresh": true, "reasoning_source": true, "source": "winogrande/winogrande_xl", "v2_readout_p_gold": 0.5774953651858118}
{"id": "ts:anli-a3-9d2e281b32:train:28602", "kind": "hard", "fresh": true, "reasoning_source": false, "source": "anli/a3", "v2_readout_p_gold": 0.7892246211087375}
{"id": "ts:argument-feedback-e0d74b9ca8:train:21744", "kind": "hard", "fresh": true, "reasoning_source": false, "source": "argument-feedback", "v2_readout_p_gold": 0.4040930206242937}
{"id": "ts:HelpSteer-helpfulness-6699944564:train:20937", "kind": "hard", "fresh": true, "reasoning_source": false, "source": "HelpSteer/helpfulness", "v2_readout_p_gold": 0.2116338974740821}
{"id": "ts:spartqa-yn-a9b30ae554:train:16051", "kind": "hard", "fresh": true, "reasoning_source": true, "source": "spartqa-yn", "v2_readout_p_gold": 0.5959083418910411}
{"id": "ts:yahoo-answers-topics-8fd5d7e862:train:10337", "kind": "hard", "fresh": false, "base_correct_of_4": 3, "v2_readout_p_gold": 0.9199502241971553}
{"id": "ts:matres-temporal-203312ab87:train:5560", "kind": "hard", "fresh": true, "reasoning_source": true, "source": "matres/temporal", "v2_readout_p_gold": 0.272426449930179}
{"id": "ts:multilingual-offenseval-dravidian-malayalam-1179fc9fff:train:260", "kind": "hard", "fresh": false, "base_correct_of_4": 2, "v2_readout_p_gold": 0.4137384189024802}
{"id": "ts:amazon-counterfactual-en-16c5c659fd:train:2337:noul-label-verification", "kind": "hard", "fresh": true, "reasoning_source": false, "source": "amazon_counterfactual/en", "v2_readout_p_gold": 0.743167997235783}
{"id": "ts:lsat-ar-eb3f507971:train:318", "kind": "hard", "fresh": true, "reasoning_source": true, "source": "lsat-ar", "v2_readout_p_gold": 0.30105766736362327}
{"id": "ts:clutrr-effc7ced7a:train:11614", "kind": "hard", "fresh": true, "reasoning_source": true, "source": "clutrr", "v2_readout_p_gold": 0.195252294945384}
{"id": "ts:LogicNLI-321618d609:train:4054", "kind": "hard", "fresh": true, "reasoning_source": true, "source": "LogicNLI", "v2_readout_p_gold": 0.35658152023113504}
{"id": "ts:strategy-qa-44f34e040f:train:1460", "kind": "hard", "fresh": true, "reasoning_source": true, "source": "strategy-qa", "v2_readout_p_gold": 0.8175744850834649}
{"id": "ts:logical-fallacy-49ee8e577f:train:662", "kind": "hard", "fresh": true, "reasoning_source": true, "source": "logical-fallacy", "v2_readout_p_gold": 0.27296187962126256}
{"id": "ts:lex-glue-unfair-tos-e0fa400828:train:3120", "kind": "hard", "fresh": false, "base_correct_of_4": 3, "v2_readout_p_gold": 0.8767859798440304}
{"id": "proc:evidence_sufficiency:train:12022:strongest_support_origin", "kind": "exact", "fresh": false, "base_correct_of_4": 3, "v2_readout_p_gold": 0.9476270726126923}
{"id": "ts:pragmeval-gum-4abdfde4d7:train:525", "kind": "hard", "fresh": true, "reasoning_source": false, "source": "pragmeval/gum", "v2_readout_p_gold": 0.7673785913720405}
{"id": "proc:goal_directed_planning:train:11472:minimal_actions", "kind": "exact", "fresh": false, "base_correct_of_4": 3, "v2_readout_p_gold": 0.16907276767782162}
{"id": "ts:crowdflower-tweet-global-warming-6cc81c33a4:train:1317", "kind": "hard", "fresh": false, "base_correct_of_4": 2, "v2_readout_p_gold": 0.9496693706075925}
{"id": "ts:google-civil-comments-22ba067369:train:2af4e6e8a33dae21:civil_comments-insult_share", "kind": "soft", "fresh": true, "reasoning_source": false, "source": "civil_comments/insult_share", "v2_readout_p_gold": 0.798186775339273}
{"id": "ts:HelpSteer3-preference-strength-41624ca038:train:27801", "kind": "hard", "fresh": false, "base_correct_of_4": 2, "v2_readout_p_gold": 0.10482070892192563}
{"id": "ts:AES2-essay-scoring-c558122bd2:train:10383", "kind": "hard", "fresh": false, "base_correct_of_4": 3, "v2_readout_p_gold": 0.3752426535257681}
{"id": "ts:stepgame-1cc74264d9:train:20141", "kind": "hard", "fresh": true, "reasoning_source": true, "source": "stepgame", "v2_readout_p_gold": 0.20277176117788415}
{"id": "ts:proofwriter-b45cbfe5f7:train:14595", "kind": "hard", "fresh": true, "reasoning_source": true, "source": "proofwriter", "v2_readout_p_gold": 0.43734875007059465}
{"id": "ts:Zhengping-UNLI-d536174804:train:031ac258293d488e:UNLI", "kind": "soft", "fresh": false, "base_correct_of_4": 3, "v2_readout_p_gold": 0.6513548714339145}
{"id": "ts:weblinx-dom-element-815194ebdc:train:6764", "kind": "hard", "fresh": true, "reasoning_source": false, "source": "weblinx/dom-element", "v2_readout_p_gold": 0.2257921480211193}
{"id": "proc:evidence_sufficiency:train:109:strongest_support_origin", "kind": "exact", "fresh": false, "base_correct_of_4": 2, "v2_readout_p_gold": 0.3410145579196658}
{"id": "ts:probability-words-nli-reasoning-2hop-e10bbfbc39:train:3841", "kind": "hard", "fresh": true, "reasoning_source": true, "source": "probability_words_nli/reasoning_2hop", "v2_readout_p_gold": 0.7772998611746911}
{"id": "ts:multilingual-paws-x-en-91b0851f4a:train:2183", "kind": "hard", "fresh": false, "base_correct_of_4": 3, "v2_readout_p_gold": 0.9196425372343816}
{"id": "ts:spartqa-mchoice-d5acb91813:train:4528", "kind": "hard", "fresh": true, "reasoning_source": true, "source": "spartqa-mchoice", "v2_readout_p_gold": 0.6887579919421805}
{"id": "ts:tasksource-sick-9e0850a4d0:train:25873151e94feefd:sick-relatedness", "kind": "soft", "fresh": true, "reasoning_source": false, "source": "sick/relatedness", "v2_readout_p_gold": 0.4365414835665004}
{"id": "ts:logical-entailment-5fde239036:train:14712", "kind": "hard", "fresh": true, "reasoning_source": true, "source": "logical-entailment", "v2_readout_p_gold": 0.5926665999540697}
{"id": "ts:multilingual-NusaX-senti-ind-99da6b456a:train:228", "kind": "hard", "fresh": true, "reasoning_source": false, "source": "multilingual/NusaX-senti/ind", "v2_readout_p_gold": 0.5858964729772559}
{"id": "ts:contract-nli-contractnli-b-full-1b955ccb0f:train:3216", "kind": "hard", "fresh": true, "reasoning_source": true, "source": "contract-nli/contractnli_b/full", "v2_readout_p_gold": 0.7435238990317323}
{"id": "ts:humicroedit-subtask-1-5903f8a67b:train:6590", "kind": "hard", "fresh": false, "base_correct_of_4": 3, "v2_readout_p_gold": 0.308402992425778}
{"id": "proc:event_state_reconstruction:train:7543:is_open", "kind": "exact", "fresh": false, "base_correct_of_4": 3, "v2_readout_p_gold": 0.48438008427698437}
{"id": "ts:LogicNLI-321618d609:train:1215", "kind": "hard", "fresh": true, "reasoning_source": true, "source": "LogicNLI", "v2_readout_p_gold": 0.38576863705134323}
{"id": "ts:babi-nli-conjunction-d20ab32beb:train:pack-9835125fd6c4:count-0", "kind": "hard", "fresh": true, "reasoning_source": true, "source": "babi_nli/conjunction", "v2_readout_p_gold": 0.156517014724123}
{"id": "ts:probability-words-nli-reasoning-2hop-e10bbfbc39:train:3815", "kind": "hard", "fresh": true, "reasoning_source": true, "source": "probability_words_nli/reasoning_2hop", "v2_readout_p_gold": 0.8354835309589073}
{"id": "ts:ekar-english-c64b9556eb:train:566", "kind": "hard", "fresh": true, "reasoning_source": false, "source": "ekar_english", "v2_readout_p_gold": 0.6489537961445406}
{"id": "ts:robust-nli-ST-SE-0253f03cd4:train:364", "kind": "hard", "fresh": true, "reasoning_source": false, "source": "robust_nli/ST_SE", "v2_readout_p_gold": 0.3405274470124452}
{"id": "ts:math-qa-1c90874154:train:10350", "kind": "hard", "fresh": true, "reasoning_source": true, "source": "math_qa", "v2_readout_p_gold": 0.2378926779756189}
{"id": "proc:state_perturbation:train:18650:risk_direction", "kind": "exact", "fresh": false, "base_correct_of_4": 2, "v2_readout_p_gold": 0.142602915443119}
{"id": "ts:tasksource-wikipedia-detox-votes-attack-2338f0e747:train:797f93898ed02a85:wikipedia-detox-attack", "kind": "soft", "fresh": true, "reasoning_source": false, "source": "wikipedia-detox/attack", "v2_readout_p_gold": 0.4073334000459302}
{"id": "ts:maud-antitrust-efforts-83bc92e868:train:2", "kind": "hard", "fresh": true, "reasoning_source": false, "source": "maud/antitrust-efforts", "v2_readout_p_gold": 0.7369447724110998}
{"id": "ts:logiqa-519764b05f:train:1536", "kind": "hard", "fresh": true, "reasoning_source": true, "source": "logiqa", "v2_readout_p_gold": 0.7172865354497124}
{"id": "proc:event_state_reconstruction:train:1643:current_owner", "kind": "exact", "fresh": false, "base_correct_of_4": 3, "v2_readout_p_gold": 0.9212223064804405}
{"id": "ts:probability-words-nli-reasoning-1hop-4241424585:train:306", "kind": "hard", "fresh": true, "reasoning_source": true, "source": "probability_words_nli/reasoning_1hop", "v2_readout_p_gold": 0.7772998611746911}
{"id": "ts:ruletaker-511880334b:train:2275", "kind": "hard", "fresh": true, "reasoning_source": true, "source": "ruletaker", "v2_readout_p_gold": 0.20181322466072713}
{"id": "ts:auditor-review-d22853943d:train:517", "kind": "hard", "fresh": false, "base_correct_of_4": 2, "v2_readout_p_gold": 0.6466755797828196}
{"id": "ts:ruletaker-511880334b:train:14131", "kind": "hard", "fresh": true, "reasoning_source": true, "source": "ruletaker", "v2_readout_p_gold": 0.7772998611746911}
{"id": "ts:privacy-200k-Mistral-Large-3-9105a98f2f:train:4891", "kind": "hard", "fresh": false, "base_correct_of_4": 3, "v2_readout_p_gold": 0.4937542108292944}
{"id": "ts:hover-fbc5881426:train:182", "kind": "hard", "fresh": true, "reasoning_source": false, "source": "hover", "v2_readout_p_gold": 0.7879311856832191}
{"id": "ts:faithdial-grounding-cd051b9afb:train:pack-3dfbe5e9ff8d:same-A-B", "kind": "hard", "fresh": false, "base_correct_of_4": 2, "v2_readout_p_gold": 0.5926665999540697}
{"id": "ts:logical-entailment-5fde239036:train:27374", "kind": "hard", "fresh": true, "reasoning_source": true, "source": "logical-entailment", "v2_readout_p_gold": 0.8267117919359419}
{"id": "ts:humicroedit-subtask-2-96687c1ca0:train:2074", "kind": "hard", "fresh": false, "base_correct_of_4": 3, "v2_readout_p_gold": 0.42864408890925626}
{"id": "proc:record_eligibility:train:6083:first_eligible", "kind": "exact", "fresh": false, "base_correct_of_4": 3, "v2_readout_p_gold": 0.8545259762705727}
{"id": "ts:stepgame-1cc74264d9:train:20429:noul-label-verification", "kind": "hard", "fresh": true, "reasoning_source": true, "source": "stepgame", "v2_readout_p_gold": 0.15610488959337065}
{"id": "ts:natural-language-satisfiability-c9f8dbdaf5:train:325", "kind": "hard", "fresh": false, "base_correct_of_4": 2, "v2_readout_p_gold": 0.8175744850834649}
{"id": "ts:lsat-ar-eb3f507971:train:570", "kind": "hard", "fresh": true, "reasoning_source": true, "source": "lsat-ar", "v2_readout_p_gold": 0.1996080671145586}
{"id": "ts:temporal-nli-0d8184c0f1:train:11381", "kind": "hard", "fresh": true, "reasoning_source": true, "source": "temporal-nli", "v2_readout_p_gold": 0.35469962006655403}
{"id": "ts:SChem-Disagreement-a96c850955:train:4272", "kind": "hard", "fresh": true, "reasoning_source": false, "source": "SChem_Disagreement", "v2_readout_p_gold": 0.7057850278370112}
{"id": "proc:entity_belief_tracking:train:2846:nested_belief_location", "kind": "exact", "fresh": false, "base_correct_of_4": 3, "v2_readout_p_gold": 0.8587231630315283}
{"id": "ts:multidogo-software-intent-7b749275b2:train:1902", "kind": "hard", "fresh": true, "reasoning_source": false, "source": "multidogo/software/intent", "v2_readout_p_gold": 0.5770657527758299}
{"id": "ts:sharc-b8153674dd:train:pack-3e4e6683aa9e:count-2", "kind": "hard", "fresh": false, "base_correct_of_4": 3, "v2_readout_p_gold": 0.32270087429387073}
{"id": "ts:glue-mrpc-c0f4e7338d:train:525", "kind": "hard", "fresh": true, "reasoning_source": false, "source": "glue/mrpc", "v2_readout_p_gold": 0.7879311856832191}
{"id": "ts:tweet-eval-stance-hillary-a916bac70a:train:533", "kind": "hard", "fresh": false, "base_correct_of_4": 3, "v2_readout_p_gold": 0.3768830886796765}
{"id": "ts:naturallogic-ba86bebf3b:train:5403", "kind": "hard", "fresh": true, "reasoning_source": true, "source": "naturallogic", "v2_readout_p_gold": 0.8284494362263617}
{"id": "ts:temporal-nli-0d8184c0f1:train:10420", "kind": "hard", "fresh": true, "reasoning_source": true, "source": "temporal-nli", "v2_readout_p_gold": 0.28754220061259067}
{"id": "ts:logiqa-519764b05f:train:1900", "kind": "hard", "fresh": true, "reasoning_source": true, "source": "logiqa", "v2_readout_p_gold": 0.8162357095047694}
{"id": "proc:record_eligibility:train:7035:decisive_constraint", "kind": "exact", "fresh": false, "base_correct_of_4": 3, "v2_readout_p_gold": 0.4282824598778262}
{"id": "ts:spartqa-mchoice-d5acb91813:train:4214", "kind": "hard", "fresh": true, "reasoning_source": true, "source": "spartqa-mchoice", "v2_readout_p_gold": 0.7024093778544122}
{"id": "ts:logical-entailment-5fde239036:train:17745", "kind": "hard", "fresh": true, "reasoning_source": true, "source": "logical-entailment", "v2_readout_p_gold": 0.3486451285660856}
{"id": "ts:spartqa-yn-a9b30ae554:train:22976", "kind": "hard", "fresh": true, "reasoning_source": true, "source": "spartqa-yn", "v2_readout_p_gold": 0.17000055935991437}
{"id": "ts:folio-6c5df13928:train:176", "kind": "hard", "fresh": true, "reasoning_source": true, "source": "folio", "v2_readout_p_gold": 0.34133492174907704}
{"id": "ts:HelpSteer2-complexity-2a4ce850bc:train:6571", "kind": "hard", "fresh": false, "base_correct_of_4": 2, "v2_readout_p_gold": 0.06846571538228091}
{"id": "ts:spartqa-mchoice-d5acb91813:train:8114", "kind": "hard", "fresh": true, "reasoning_source": true, "source": "spartqa-mchoice", "v2_readout_p_gold": 0.616824406385224}
{"id": "ts:hh-rlhf-helpful-rejection-sampled-f5856bd383:train:19920", "kind": "hard", "fresh": false, "base_correct_of_4": 3, "v2_readout_p_gold": 0.9196425372343816}
{"id": "ts:recast-white-dpr-428ec197ab:train:pack-ee46a7b5dbb3:same-A-C", "kind": "hard", "fresh": true, "reasoning_source": false, "source": "recast_white/dpr", "v2_readout_p_gold": 0.6513548714339145}
{"id": "proc:evidence_sufficiency:train:2401:strongest_support_origin", "kind": "exact", "fresh": false, "base_correct_of_4": 2, "v2_readout_p_gold": 0.9119564310641405}
{"id": "ts:babi-nli-positional-reasoning-aa912c540b:train:66", "kind": "hard", "fresh": true, "reasoning_source": true, "source": "babi_nli/positional-reasoning", "v2_readout_p_gold": 0.743167997235783}
{"id": "proc:policy_under_uncertainty:train:15134:access_allowed", "kind": "exact", "fresh": false, "base_correct_of_4": 3, "v2_readout_p_gold": 0.798186775339273}
{"id": "proc:graph_navigation:train:7305:first_hop", "kind": "exact", "fresh": false, "base_correct_of_4": 3, "v2_readout_p_gold": 0.9287301144405453}
{"id": "ts:Dilemmas-Disagreement-1815b940b0:train:1742", "kind": "hard", "fresh": false, "base_correct_of_4": 2, "v2_readout_p_gold": 0.3345894478883556}
{"id": "ts:multilingual-x-stance-7ba675de62:train:pack-0fe90962630e:count-1", "kind": "hard", "fresh": true, "reasoning_source": false, "source": "multilingual/x-stance", "v2_readout_p_gold": 0.2644781789986624}
{"id": "ts:multilingual-masakhanews-orm-c0523c2270:train:1015", "kind": "hard", "fresh": false, "base_correct_of_4": 3, "v2_readout_p_gold": 0.643175458706634}
{"id": "ts:dataset-train-nli-91e59a492d:train:8309", "kind": "hard", "fresh": false, "base_correct_of_4": 2, "v2_readout_p_gold": 0.8596637523076225}
{"id": "ts:winogrande-winogrande-xl-eb5b02a7c5:train:11777", "kind": "hard", "fresh": true, "reasoning_source": true, "source": "winogrande/winogrande_xl", "v2_readout_p_gold": 0.7549149868676283}
{"id": "ts:multilingual-xcsr-X-CODAH-ru-68e3252cf7:train:61:noul-label-verification", "kind": "hard", "fresh": false, "base_correct_of_4": 3, "v2_readout_p_gold": 0.7057850278370112}
{"id": "ts:tweet-eval-emoji-43b60cc2f5:train:26290", "kind": "hard", "fresh": false, "base_correct_of_4": 3, "v2_readout_p_gold": 0.05349095406668743}
{"id": "ts:lsat-rc-094f659543:train:513", "kind": "hard", "fresh": true, "reasoning_source": true, "source": "lsat-rc", "v2_readout_p_gold": 0.8144390435180047}
{"id": "ts:contract-nli-contractnli-a-seg-c5d5a7346a:train:4522", "kind": "hard", "fresh": true, "reasoning_source": true, "source": "contract-nli/contractnli_a/seg", "v2_readout_p_gold": 0.5288213784864879}
{"id": "ts:contract-nli-contractnli-a-seg-c5d5a7346a:train:6401", "kind": "hard", "fresh": true, "reasoning_source": true, "source": "contract-nli/contractnli_a/seg", "v2_readout_p_gold": 0.8099488208384867}
{"id": "ts:SDOH-NLI-f61a63216f:train:pack-69b39efeb00e:same-B-C", "kind": "hard", "fresh": false, "base_correct_of_4": 3, "v2_readout_p_gold": 0.7310585727705126}
{"id": "ts:mpe-864f124608:train:7236:choice-criteria-permutation", "kind": "hard", "fresh": true, "reasoning_source": false, "source": "mpe", "v2_readout_p_gold": 0.39001339539093316}
{"id": "ts:contract-nli-contractnli-b-full-1b955ccb0f:train:3269", "kind": "hard", "fresh": true, "reasoning_source": true, "source": "contract-nli/contractnli_b/full", "v2_readout_p_gold": 0.5534885031433194}
{"id": "ts:strategy-qa-44f34e040f:train:pack-d9d97c32cb1c:label-C", "kind": "hard", "fresh": true, "reasoning_source": true, "source": "strategy-qa", "v2_readout_p_gold": 0.32082130731838393}
{"id": "ts:lsat-ar-eb3f507971:train:868", "kind": "hard", "fresh": false, "base_correct_of_4": 3, "v2_readout_p_gold": 0.5586878246055423}
{"id": "ts:AdjectiveScaleProbe-nli-c125da07dd:train:pack-a46c11961321:same-A-B", "kind": "hard", "fresh": true, "reasoning_source": false, "source": "AdjectiveScaleProbe-nli", "v2_readout_p_gold": 0.32082130731838393}
{"id": "ts:multilingual-xcsr-X-CSQA-pl-1dd9705065:train:278", "kind": "hard", "fresh": true, "reasoning_source": false, "source": "multilingual/xcsr/X-CSQA-pl", "v2_readout_p_gold": 0.18664532083386576}
{"id": "ts:PARARULE-Plus-f91c7ae0ff:train:28223", "kind": "hard", "fresh": true, "reasoning_source": true, "source": "PARARULE-Plus", "v2_readout_p_gold": 0.8354835309589073}
{"id": "ts:Politeness-Disagreement-8e63cd8514:train:1235", "kind": "hard", "fresh": true, "reasoning_source": false, "source": "Politeness_Disagreement", "v2_readout_p_gold": 0.3345894478883556}
{"id": "ts:mindgames-dfe4fff9e3:train:8506", "kind": "hard", "fresh": true, "reasoning_source": false, "source": "mindgames", "v2_readout_p_gold": 0.8267117919359419}
{"id": "ts:FOL-nli-3deb6ff51f:train:12261", "kind": "hard", "fresh": true, "reasoning_source": true, "source": "FOL-nli", "v2_readout_p_gold": 0.7709040544869944}
{"id": "ts:temporal-nli-0d8184c0f1:train:pack-cfe16dc0c6c9:all-same", "kind": "hard", "fresh": true, "reasoning_source": true, "source": "temporal-nli", "v2_readout_p_gold": 0.718594386544335}
{"id": "proc:record_eligibility:train:2291:eligible_count", "kind": "exact", "fresh": false, "base_correct_of_4": 2, "v2_readout_p_gold": 0.25242077630449117}
{"id": "ts:clutrr-effc7ced7a:train:172", "kind": "hard", "fresh": true, "reasoning_source": true, "source": "clutrr", "v2_readout_p_gold": 0.4039886559088455}
{"id": "ts:lsat-qa-all-05417eda9d:train:201", "kind": "hard", "fresh": true, "reasoning_source": true, "source": "lsat_qa/all", "v2_readout_p_gold": 0.47776521648761916}
{"id": "ts:implicit-hate-stg1-b5fb457f0b:train:581", "kind": "hard", "fresh": true, "reasoning_source": false, "source": "implicit-hate-stg1", "v2_readout_p_gold": 0.35129664841676034}
{"id": "ts:conceptrules-v2-83f331d8b8:train:pack-5ec17cbeacbf:exists-0", "kind": "hard", "fresh": true, "reasoning_source": true, "source": "conceptrules_v2", "v2_readout_p_gold": 0.3629691917376782}
{"id": "ts:SDOH-NLI-f61a63216f:train:10521", "kind": "hard", "fresh": true, "reasoning_source": false, "source": "SDOH-NLI", "v2_readout_p_gold": 0.5774953651858118}
{"id": "ts:PKU-SafeRLHF-helpfulness-e84d80e18c:train:18801", "kind": "hard", "fresh": true, "reasoning_source": false, "source": "PKU-SafeRLHF/helpfulness", "v2_readout_p_gold": 0.8354835309589073}
{"id": "ts:SpaRTUN-ae090fe669:train:19459", "kind": "hard", "fresh": true, "reasoning_source": true, "source": "SpaRTUN", "v2_readout_p_gold": 0.8175744850834649}
{"id": "ts:glue-mnli-2e2e2f18a7:train:16171", "kind": "hard", "fresh": false, "base_correct_of_4": 2, "v2_readout_p_gold": 0.39056540132743}
{"id": "ts:blog-authorship-corpus-gender-5fe8900d6d:train:5132", "kind": "hard", "fresh": false, "base_correct_of_4": 3, "v2_readout_p_gold": 0.7310585727705126}
{"id": "ts:logical-entailment-5fde239036:train:17703", "kind": "hard", "fresh": true, "reasoning_source": true, "source": "logical-entailment", "v2_readout_p_gold": 0.21206881431678096}
{"id": "ts:lexical-relation-classification-K-H-N-7adfb9ec3a:train:17938", "kind": "hard", "fresh": false, "base_correct_of_4": 3, "v2_readout_p_gold": 0.8551567858160758}
{"id": "ts:logical-entailment-5fde239036:train:12763", "kind": "hard", "fresh": true, "reasoning_source": true, "source": "logical-entailment", "v2_readout_p_gold": 0.37754066879814546}
{"id": "ts:babi-nli-three-supporting-facts-f6540ced19:train:pack-c7b8d98a1327:most-common", "kind": "hard", "fresh": true, "reasoning_source": true, "source": "babi_nli/three-supporting-facts", "v2_readout_p_gold": 0.5156199157230156}
{"id": "ts:english-grading-cohesion-97c0e3c3ab:train:2656:choice-criteria-permutation", "kind": "hard", "fresh": true, "reasoning_source": false, "source": "english-grading/cohesion", "v2_readout_p_gold": 0.6243293017193051}
{"id": "ts:nli4ct-semeval2024-4a16101db5:train:pack-4984bd60b9b7:count-0", "kind": "hard", "fresh": false, "base_correct_of_4": 3, "v2_readout_p_gold": 0.19078211895202615}
{"id": "ts:Zhengping-UNLI-d536174804:train:08a77999ad3d4a57:UNLI", "kind": "soft", "fresh": false, "base_correct_of_4": 3, "v2_readout_p_gold": 0.5312093733737563}
{"id": "proc:goal_directed_planning:train:2453:minimal_actions", "kind": "exact", "fresh": false, "base_correct_of_4": 2, "v2_readout_p_gold": 0.841196879047083}
{"id": "ts:wildguardmix-cleaned-response-harm-cb15efae1c:train:3808:noul-label-verification", "kind": "hard", "fresh": false, "base_correct_of_4": 3, "v2_readout_p_gold": 0.9149009526726544}
{"id": "ts:multilingual-disrpt-tha-pdtb-tdtb-rels-2e20a61c83:train:4147", "kind": "hard", "fresh": false, "base_correct_of_4": 3, "v2_readout_p_gold": 0.9112551878203983}
{"id": "ts:tasksource-lewidi-mp-ce0ace9aaf:train:f6780c3d6b7a34a6:lewidi-mp", "kind": "soft", "fresh": false, "base_correct_of_4": 3, "v2_readout_p_gold": 0.808067204308405}
{"id": "ts:logiqa-519764b05f:train:4473", "kind": "hard", "fresh": true, "reasoning_source": true, "source": "logiqa", "v2_readout_p_gold": 0.47868600017899393}
{"id": "ts:multilingual-xcsr-X-CODAH-sw-ce3ba20f62:train:49:noul-label-verification", "kind": "hard", "fresh": false, "base_correct_of_4": 2, "v2_readout_p_gold": 0.7310585727705126}
{"id": "ts:robustLR-408a7e4eae:train:pack-594d7ba685a3:exists-0", "kind": "hard", "fresh": false, "base_correct_of_4": 2, "v2_readout_p_gold": 0.4378234991142019}
{"id": "proc:policy_under_uncertainty:train:18730:requester_role", "kind": "exact", "fresh": false, "base_correct_of_4": 2, "v2_readout_p_gold": 0.2868065856533617}
{"id": "ts:spartqa-mchoice-d5acb91813:train:21196", "kind": "hard", "fresh": true, "reasoning_source": true, "source": "spartqa-mchoice", "v2_readout_p_gold": 0.7185572883281179}
{"id": "ts:tasksource-wikipedia-detox-votes-aggression-dd9465a42d:train:src-train-67790:wikipedia-detox-aggression", "kind": "soft", "fresh": false, "base_correct_of_4": 1, "v2_readout_p_gold": 0.8354835309589073}
{"id": "ts:PARARULE-Plus-f91c7ae0ff:train:1056", "kind": "hard", "fresh": true, "reasoning_source": true, "source": "PARARULE-Plus", "v2_readout_p_gold": 0.6654105521116443}
{"id": "ts:lsat-qa-all-05417eda9d:train:107", "kind": "hard", "fresh": true, "reasoning_source": true, "source": "lsat_qa/all", "v2_readout_p_gold": 0.7481821590886284}
{"id": "ts:sen-making-2-62b7d5fc4a:train:278", "kind": "hard", "fresh": false, "base_correct_of_4": 2, "v2_readout_p_gold": 0.7369447724110998}
{"id": "ts:SpaRTUN-ae090fe669:train:21811", "kind": "hard", "fresh": true, "reasoning_source": true, "source": "SpaRTUN", "v2_readout_p_gold": 0.3345894478883556}
{"id": "ts:tasksource-wikipedia-detox-votes-toxicity-609e6d28e8:train:e69e297767ceb57e:wikipedia-detox-toxicity_score", "kind": "soft", "fresh": false, "base_correct_of_4": 2, "v2_readout_p_gold": 0.48274530236884794}
{"id": "ts:folio-6c5df13928:train:pack-9114dc15a5e5:in-A-1", "kind": "hard", "fresh": true, "reasoning_source": true, "source": "folio", "v2_readout_p_gold": 0.3629691917376782}
{"id": "ts:multilingual-amazon-reviews-multi-all-languages-2dc9b25f8d:train:14558", "kind": "hard", "fresh": false, "base_correct_of_4": 2, "v2_readout_p_gold": 0.4402766019862475}
{"id": "ts:SpaRTUN-ae090fe669:train:22364:noul-label-verification", "kind": "hard", "fresh": true, "reasoning_source": true, "source": "SpaRTUN", "v2_readout_p_gold": 0.6224593312018546}
{"id": "ts:Zhengping-UNLI-d536174804:train:f7c1dcf4d467f82b:UNLI", "kind": "soft", "fresh": false, "base_correct_of_4": 2, "v2_readout_p_gold": 0.7057850278370112}
{"id": "proc:graph_navigation:train:2890:shortest_cost", "kind": "exact", "fresh": false, "base_correct_of_4": 3, "v2_readout_p_gold": 0.3743704539730488}
{"id": "ts:winogrande-winogrande-xl-eb5b02a7c5:train:11225", "kind": "hard", "fresh": true, "reasoning_source": true, "source": "winogrande/winogrande_xl", "v2_readout_p_gold": 0.7662936377487304}
{"id": "ts:casey-martin-CommonLit-Ease-of-Readability-dd18b7d832:train:18ba69666ba8e2d4:clear-readability", "kind": "soft", "fresh": true, "reasoning_source": false, "source": "clear/readability", "v2_readout_p_gold": 0.28905343454564736}
{"id": "ts:arct-8cfb6b7d9e:train:597", "kind": "hard", "fresh": false, "base_correct_of_4": 2, "v2_readout_p_gold": 0.8267117919359419}
{"id": "ts:PARARULE-Plus-f91c7ae0ff:train:2838", "kind": "hard", "fresh": false, "base_correct_of_4": 3, "v2_readout_p_gold": 0.6926419767901475}
{"id": "ts:logiqa-2-0-nli-cf23683f05:train:5969", "kind": "hard", "fresh": true, "reasoning_source": true, "source": "logiqa-2.0-nli", "v2_readout_p_gold": 0.8354835309589073}
{"id": "ts:glue-rte-2dc856f29b:train:180", "kind": "hard", "fresh": true, "reasoning_source": false, "source": "glue/rte", "v2_readout_p_gold": 0.8438951104066295}
{"id": "ts:tasksource-scruples-0505561118:train:6e9a07e41cf7ee98:scruples-verdict_votes", "kind": "soft", "fresh": false, "base_correct_of_4": 3, "v2_readout_p_gold": 0.4286891196206228}
{"id": "ts:strategy-qa-44f34e040f:train:690", "kind": "hard", "fresh": true, "reasoning_source": true, "source": "strategy-qa", "v2_readout_p_gold": 0.48438008427698437}
{"id": "ts:clutrr-effc7ced7a:train:9659", "kind": "hard", "fresh": true, "reasoning_source": true, "source": "clutrr", "v2_readout_p_gold": 0.24705188999397396}
{"id": "ts:cosmos-qa-81b1d873b1:train:22604", "kind": "hard", "fresh": false, "base_correct_of_4": 3, "v2_readout_p_gold": 0.5223422779148963}
{"id": "ts:strategy-qa-44f34e040f:train:701", "kind": "hard", "fresh": true, "reasoning_source": true, "source": "strategy-qa", "v2_readout_p_gold": 0.5312093733737563}
{"id": "ts:multilingual-clue-ocnli-970cc11880:train:3713", "kind": "hard", "fresh": true, "reasoning_source": false, "source": "multilingual/clue/ocnli", "v2_readout_p_gold": 0.7988591877876652}
{"id": "ts:clutrr-effc7ced7a:train:748", "kind": "hard", "fresh": true, "reasoning_source": true, "source": "clutrr", "v2_readout_p_gold": 0.3224071671974978}
{"id": "proc:event_triggered_execution:train:11320:object_final_state", "kind": "exact", "fresh": false, "base_correct_of_4": 3, "v2_readout_p_gold": 0.6370308082623217}
{"id": "ts:HelpSteer3-feedback-f2a9ed8734:train:20850", "kind": "hard", "fresh": false, "base_correct_of_4": 3, "v2_readout_p_gold": 0.5952923036717009}
{"id": "ts:tasksource-google-wellformed-query-9308d390df:train:e761aeaa98392d73:google_wellformed_query", "kind": "soft", "fresh": false, "base_correct_of_4": 3, "v2_readout_p_gold": 0.7057850278370112}
{"id": "ts:medmcqa-d10217a116:train:3333", "kind": "hard", "fresh": true, "reasoning_source": false, "source": "medmcqa", "v2_readout_p_gold": 0.6487907525895379}
{"id": "proc:instruction_execution:train:840:target_count", "kind": "exact", "fresh": false, "base_correct_of_4": 3, "v2_readout_p_gold": 0.7641399223448953}
{"id": "proc:table_lookup:train:6287:find_person", "kind": "exact", "fresh": false, "base_correct_of_4": 3, "v2_readout_p_gold": 0.8923993066304516}
{"id": "ts:HelpSteer2-coherence-06fbf6346d:train:pack-48a7cfd7514c:label-B", "kind": "hard", "fresh": true, "reasoning_source": false, "source": "HelpSteer2/coherence", "v2_readout_p_gold": 0.25905187970418786}
{"id": "ts:wands-a340aa1a78:train:22881", "kind": "hard", "fresh": true, "reasoning_source": false, "source": "wands", "v2_readout_p_gold": 0.7817549894812875}
{"id": "ts:chatbot-arena-conversations-93d787d507:train:15255:noul-label-verification", "kind": "hard", "fresh": true, "reasoning_source": false, "source": "chatbot_arena_conversations", "v2_readout_p_gold": 0.23370636225126956}
{"id": "ts:multilingual-AfriSenti-twitter-sentiment-amh-d94b71d898:train:5858", "kind": "hard", "fresh": true, "reasoning_source": false, "source": "multilingual/AfriSenti-twitter-sentiment/amh", "v2_readout_p_gold": 0.2807316427142596}
{"id": "ts:tasksource-acceptability-prediction-a432edde29:train:7fb4baf070032af3:acceptability-prediction-rating_votes", "kind": "soft", "fresh": false, "base_correct_of_4": 1, "v2_readout_p_gold": 0.13845166041425117}
{"id": "proc:graph_navigation:train:11484:first_hop", "kind": "exact", "fresh": false, "base_correct_of_4": 3, "v2_readout_p_gold": 0.7974836555489919}
{"id": "ts:multilingual-xlwic-xlwic-it-it-9281cfdec4:train:1063", "kind": "hard", "fresh": false, "base_correct_of_4": 2, "v2_readout_p_gold": 0.5156199157230156}
{"id": "ts:twitter-financial-news-sentiment-51254a6cfb:train:1166", "kind": "hard", "fresh": false, "base_correct_of_4": 3, "v2_readout_p_gold": 0.8690713792533277}
{"id": "ts:contract-nli-contractnli-a-seg-c5d5a7346a:train:pack-fabb8d90554f:in-B-0.1", "kind": "hard", "fresh": true, "reasoning_source": true, "source": "contract-nli/contractnli_a/seg", "v2_readout_p_gold": 0.5621765008857981}
{"id": "ts:multilingual-AfriSenti-twitter-sentiment-ibo-641afcdf5a:train:3031", "kind": "hard", "fresh": false, "base_correct_of_4": 2, "v2_readout_p_gold": 0.3316039792696333}
{"id": "ts:toxigen-data-annotated-f5da96eb45:train:2753", "kind": "hard", "fresh": true, "reasoning_source": false, "source": "toxigen-data/annotated", "v2_readout_p_gold": 0.42250463481418826}
{"id": "ts:math-qa-1c90874154:train:28300", "kind": "hard", "fresh": true, "reasoning_source": true, "source": "math_qa", "v2_readout_p_gold": 0.4053970338372855}
{"id": "ts:probability-words-nli-reasoning-2hop-e10bbfbc39:train:1776", "kind": "hard", "fresh": true, "reasoning_source": true, "source": "probability_words_nli/reasoning_2hop", "v2_readout_p_gold": 0.8267117919359419}
{"id": "ts:logiqa-2-0-nli-cf23683f05:train:5146:choice-criteria-permutation", "kind": "hard", "fresh": true, "reasoning_source": true, "source": "logiqa-2.0-nli", "v2_readout_p_gold": 0.808067204308405}
{"id": "proc:graph_navigation:train:9753:first_hop", "kind": "exact", "fresh": false, "base_correct_of_4": 2, "v2_readout_p_gold": 0.6135239482806051}
{"id": "ts:esconv-strategy-ac8bf45fd2:train:8835:noul-label-verification", "kind": "hard", "fresh": true, "reasoning_source": false, "source": "esconv/strategy", "v2_readout_p_gold": 0.8175744850834649}
{"id": "ts:add-one-rte-945197ac40:train:2314", "kind": "hard", "fresh": true, "reasoning_source": false, "source": "add_one_rte", "v2_readout_p_gold": 0.5926665999540697}
{"id": "ts:health-fact-2b57c3f8f9:train:21446", "kind": "hard", "fresh": false, "base_correct_of_4": 2, "v2_readout_p_gold": 0.4510184905191574}
{"id": "proc:table_lookup:train:4618:count_matching", "kind": "exact", "fresh": false, "base_correct_of_4": 3, "v2_readout_p_gold": 0.20762417599950175}
{"id": "ts:winogrande-winogrande-xl-eb5b02a7c5:train:24119", "kind": "hard", "fresh": false, "base_correct_of_4": 3, "v2_readout_p_gold": 0.798186775339273}
{"id": "ts:spartqa-mchoice-d5acb91813:train:10821", "kind": "hard", "fresh": true, "reasoning_source": true, "source": "spartqa-mchoice", "v2_readout_p_gold": 0.624838153463601}
{"id": "ts:multilingual-AfriSenti-twitter-sentiment-tso-99f751c444:train:228", "kind": "hard", "fresh": true, "reasoning_source": false, "source": "multilingual/AfriSenti-twitter-sentiment/tso", "v2_readout_p_gold": 0.5640850800020962}
{"id": "ts:humicroedit-subtask-1-5903f8a67b:train:1251", "kind": "hard", "fresh": false, "base_correct_of_4": 2, "v2_readout_p_gold": 0.2854746029909557}
{"id": "ts:tasksource-sick-9e0850a4d0:train:93e70d71067de339:sick-relatedness", "kind": "hard", "fresh": false, "base_correct_of_4": 3, "v2_readout_p_gold": 0.43263808913730845}
{"id": "ts:headline-cause-en-simple-1a168961c0:train:1391", "kind": "hard", "fresh": false, "base_correct_of_4": 3, "v2_readout_p_gold": 0.6818263500892471}
{"id": "ts:tasksource-sick-9e0850a4d0:train:e5446ad9c7d238f2:sick-relatedness", "kind": "soft", "fresh": false, "base_correct_of_4": 2, "v2_readout_p_gold": 0.3018060531784673}
{"id": "ts:monotonicity-entailment-5b266929a5:train:1016", "kind": "hard", "fresh": true, "reasoning_source": true, "source": "monotonicity-entailment", "v2_readout_p_gold": 0.3345894478883556}
{"id": "ts:spartqa-mchoice-d5acb91813:train:19414", "kind": "hard", "fresh": true, "reasoning_source": true, "source": "spartqa-mchoice", "v2_readout_p_gold": 0.7081710142271858}
{"id": "ts:args-me-e12a7a349e:train:6084", "kind": "hard", "fresh": false, "base_correct_of_4": 2, "v2_readout_p_gold": 0.8438951104066295}
{"id": "ts:babi-nli-lists-sets-ca872109f7:train:170", "kind": "hard", "fresh": true, "reasoning_source": true, "source": "babi_nli/lists-sets", "v2_readout_p_gold": 0.3486451285660856}
{"id": "ts:avicenna-a169739455:train:1617", "kind": "hard", "fresh": true, "reasoning_source": false, "source": "avicenna", "v2_readout_p_gold": 0.32082130731838393}
{"id": "ts:anli-a3-9d2e281b32:train:20781", "kind": "hard", "fresh": false, "base_correct_of_4": 3, "v2_readout_p_gold": 0.5331408315500603}
{"id": "ts:reclor-3f0b326481:train:3380", "kind": "hard", "fresh": true, "reasoning_source": true, "source": "reclor", "v2_readout_p_gold": 0.6515121586015689}
{"id": "proc:record_eligibility:train:14578:eligible_count", "kind": "exact", "fresh": false, "base_correct_of_4": 2, "v2_readout_p_gold": 0.13121649171847066}
{"id": "ts:multilingual-paws-x-zh-5dbdd2fe01:train:5223", "kind": "hard", "fresh": true, "reasoning_source": false, "source": "multilingual/paws-x/zh", "v2_readout_p_gold": 0.5467381519846138}
{"id": "proc:evidence_sufficiency:train:7195:strongest_support_origin", "kind": "exact", "fresh": false, "base_correct_of_4": 3, "v2_readout_p_gold": 0.9369757153847166}
{"id": "ts:tasksource-oasst2-dense-flat-90075f7000:train:dbf591b4cc19fb6d:oasst2-helpfulness", "kind": "soft", "fresh": false, "base_correct_of_4": 1, "v2_readout_p_gold": 0.34902937190925903}
{"id": "ts:SpaRTUN-ae090fe669:train:7642", "kind": "hard", "fresh": true, "reasoning_source": true, "source": "SpaRTUN", "v2_readout_p_gold": 0.6076631627277604}
{"id": "ts:tweets-hate-speech-detection-8cd975265a:train:pack-e67520cd97a8:all-same", "kind": "hard", "fresh": true, "reasoning_source": false, "source": "tweets_hate_speech_detection", "v2_readout_p_gold": 0.3345894478883556}
{"id": "ts:social-i-qa-d41f9445c6:train:20586", "kind": "hard", "fresh": true, "reasoning_source": false, "source": "social_i_qa", "v2_readout_p_gold": 0.620670212955561}
{"id": "ts:spartqa-mchoice-d5acb91813:train:1397", "kind": "hard", "fresh": true, "reasoning_source": true, "source": "spartqa-mchoice", "v2_readout_p_gold": 0.6702599499650276}
{"id": "ts:tasksource-wikipedia-detox-votes-aggression-dd9465a42d:train:257a5800afe8c679:wikipedia-detox-aggression_score", "kind": "soft", "fresh": false, "base_correct_of_4": 1, "v2_readout_p_gold": 0.68555494079575}
{"id": "ts:agent-action-safety-d817396454:train:12478", "kind": "hard", "fresh": true, "reasoning_source": true, "source": "agent_action_safety", "v2_readout_p_gold": 0.7549149868676283}
{"id": "ts:temporal-nli-0d8184c0f1:train:19369", "kind": "hard", "fresh": true, "reasoning_source": true, "source": "temporal-nli", "v2_readout_p_gold": 0.45372417631537726}
{"id": "ts:multilingual-disrpt-por-rst-cstn-rels-825ffa218f:train:pack-03780bf38875:all-same", "kind": "hard", "fresh": true, "reasoning_source": false, "source": "multilingual/disrpt/por.rst.cstn.rels", "v2_readout_p_gold": 0.743167997235783}
{"id": "ts:contract-nli-contractnli-a-seg-c5d5a7346a:train:5047", "kind": "hard", "fresh": true, "reasoning_source": true, "source": "contract-nli/contractnli_a/seg", "v2_readout_p_gold": 0.23849569987584016}
{"id": "ts:proofwriter-b45cbfe5f7:train:3888", "kind": "hard", "fresh": true, "reasoning_source": true, "source": "proofwriter", "v2_readout_p_gold": 0.22404597588820654}
{"id": "ts:disrpt-eng-dep-scidtb-rels-615591f14c:train:1905", "kind": "hard", "fresh": true, "reasoning_source": false, "source": "disrpt/eng.dep.scidtb.rels", "v2_readout_p_gold": 0.6489294699361652}
{"id": "ts:spartqa-yn-a9b30ae554:train:23913", "kind": "hard", "fresh": true, "reasoning_source": true, "source": "spartqa-yn", "v2_readout_p_gold": 0.46104159358472474}
{"id": "ts:probability-words-nli-reasoning-2hop-e10bbfbc39:train:1211", "kind": "hard", "fresh": true, "reasoning_source": true, "source": "probability_words_nli/reasoning_2hop", "v2_readout_p_gold": 0.3073580232098525}
{"id": "ts:conceptrules-v2-83f331d8b8:train:pack-ffdfa1da56da:label-A", "kind": "hard", "fresh": true, "reasoning_source": true, "source": "conceptrules_v2", "v2_readout_p_gold": 0.6791786926816161}
{"id": "ts:logical-entailment-5fde239036:train:pack-e92040ced64f:same-B-D", "kind": "hard", "fresh": true, "reasoning_source": true, "source": "logical-entailment", "v2_readout_p_gold": 0.3486451285660856}
{"id": "ts:lsat-ar-eb3f507971:train:1212", "kind": "hard", "fresh": true, "reasoning_source": true, "source": "lsat-ar", "v2_readout_p_gold": 0.20967407391214823}
{"id": "ts:multilingual-NusaX-senti-nij-4190e2353c:train:186", "kind": "hard", "fresh": false, "base_correct_of_4": 3, "v2_readout_p_gold": 0.6981329747138266}
{"id": "ts:boolq-natural-perturbations-508f5ac0f9:train:4691", "kind": "hard", "fresh": true, "reasoning_source": false, "source": "boolq-natural-perturbations", "v2_readout_p_gold": 0.45326184801538616}
{"id": "ts:google-civil-comments-22ba067369:train:2a651da306b21396:civil_comments-identity_attack_share", "kind": "hard", "fresh": false, "base_correct_of_4": 2, "v2_readout_p_gold": 0.8267117919359419}
{"id": "proc:event_triggered_execution:train:4237:total_firings", "kind": "exact", "fresh": false, "base_correct_of_4": 2, "v2_readout_p_gold": 0.22903618768247036}
{"id": "ts:glue-wnli-02fce42ea4:train:89:choice-criteria-permutation", "kind": "hard", "fresh": true, "reasoning_source": false, "source": "glue/wnli", "v2_readout_p_gold": 0.7310585727705126}
{"id": "ts:babi-nli-lists-sets-ca872109f7:train:pack-c22d85b84db9:count-0", "kind": "hard", "fresh": true, "reasoning_source": true, "source": "babi_nli/lists-sets", "v2_readout_p_gold": 0.7486346973327631}
{"id": "ts:FOL-nli-3deb6ff51f:train:10631:noul-label-verification", "kind": "hard", "fresh": true, "reasoning_source": true, "source": "FOL-nli", "v2_readout_p_gold": 0.718594386544335}
{"id": "ts:SHP-456c0ad125:train:6611", "kind": "hard", "fresh": false, "base_correct_of_4": 2, "v2_readout_p_gold": 0.6654105521116443}
{"id": "ts:LogicNLI-321618d609:train:12809", "kind": "hard", "fresh": true, "reasoning_source": true, "source": "LogicNLI", "v2_readout_p_gold": 0.3422266540886587}
{"id": "ts:glue-mrpc-c0f4e7338d:train:pack-122946fff2a5:count-1", "kind": "hard", "fresh": false, "base_correct_of_4": 3, "v2_readout_p_gold": 0.6431647820784939}
{"id": "ts:tasksource-wikipedia-detox-votes-aggression-dd9465a42d:train:d6c942010333815f:wikipedia-detox-aggression_score", "kind": "soft", "fresh": false, "base_correct_of_4": 3, "v2_readout_p_gold": 0.8432386592786987}
{"id": "ts:HelpSteer2-complexity-2a4ce850bc:train:16526", "kind": "hard", "fresh": false, "base_correct_of_4": 3, "v2_readout_p_gold": 0.5229582588625755}
{"id": "ts:conceptrules-v2-83f331d8b8:train:20076", "kind": "hard", "fresh": false, "base_correct_of_4": 2, "v2_readout_p_gold": 0.8354835309589073}
{"id": "ts:nyu-mll-glue-stsb-ad720c97de:train:5830c839a66ee363:glue-stsb", "kind": "soft", "fresh": false, "base_correct_of_4": 1, "v2_readout_p_gold": 0.33471014893526774}
{"id": "ts:babi-nli-single-supporting-fact-64e2c2137a:train:pack-9dbcf5f1ae1e:count-1", "kind": "hard", "fresh": true, "reasoning_source": true, "source": "babi_nli/single-supporting-fact", "v2_readout_p_gold": 0.5538785716133734}
{"id": "ts:monotonicity-entailment-5b266929a5:train:3902", "kind": "hard", "fresh": true, "reasoning_source": true, "source": "monotonicity-entailment", "v2_readout_p_gold": 0.7662936377487304}
{"id": "ts:casey-martin-CommonLit-Ease-of-Readability-dd18b7d832:train:05763573ed1ff172:clear-readability", "kind": "soft", "fresh": false, "base_correct_of_4": 2, "v2_readout_p_gold": 0.2445184676526543}
{"id": "ts:logical-fallacy-49ee8e577f:train:492", "kind": "hard", "fresh": true, "reasoning_source": true, "source": "logical-fallacy", "v2_readout_p_gold": 0.2293582234061942}
{"id": "ts:FOL-nli-3deb6ff51f:train:27064", "kind": "hard", "fresh": true, "reasoning_source": true, "source": "FOL-nli", "v2_readout_p_gold": 0.43595402447853865}
{"id": "ts:babi-nli-basic-induction-fc99234f83:train:827", "kind": "hard", "fresh": true, "reasoning_source": true, "source": "babi_nli/basic-induction", "v2_readout_p_gold": 0.8267117919359419}
{"id": "proc:state_perturbation:train:16668:risk_direction", "kind": "exact", "fresh": false, "base_correct_of_4": 2, "v2_readout_p_gold": 0.825901297693935}
{"id": "ts:lsat-rc-094f659543:train:1212", "kind": "hard", "fresh": true, "reasoning_source": true, "source": "lsat-rc", "v2_readout_p_gold": 0.737854860905993}
{"id": "ts:winogrande-winogrande-xl-eb5b02a7c5:train:25300", "kind": "hard", "fresh": true, "reasoning_source": true, "source": "winogrande/winogrande_xl", "v2_readout_p_gold": 0.6076631627277604}
{"id": "ts:multilingual-americas-nli-all-languages-dd166da2c2:train:887", "kind": "hard", "fresh": true, "reasoning_source": false, "source": "multilingual/americas_nli/all_languages", "v2_readout_p_gold": 0.28571540304349313}
{"id": "ts:babi-nli-positional-reasoning-aa912c540b:train:618", "kind": "hard", "fresh": true, "reasoning_source": true, "source": "babi_nli/positional-reasoning", "v2_readout_p_gold": 0.7772998611746911}
{"id": "ts:multilingual-multilingual-NLI-26lang-2mil7-93be83beda:train:1246:choice-criteria-permutation", "kind": "hard", "fresh": false, "base_correct_of_4": 2, "v2_readout_p_gold": 0.1993965754838934}
{"id": "ts:stepgame-1cc74264d9:train:20654", "kind": "hard", "fresh": true, "reasoning_source": true, "source": "stepgame", "v2_readout_p_gold": 0.23294702339461257}
{"id": "ts:FOL-nli-3deb6ff51f:train:22148", "kind": "hard", "fresh": true, "reasoning_source": true, "source": "FOL-nli", "v2_readout_p_gold": 0.7295618917545736}
{"id": "proc:evidence_sufficiency:train:9880:strongest_support_origin", "kind": "exact", "fresh": false, "base_correct_of_4": 3, "v2_readout_p_gold": 0.9181736051055975}
{"id": "ts:fracas-5f7968191b:train:143", "kind": "hard", "fresh": false, "base_correct_of_4": 2, "v2_readout_p_gold": 0.8114644666853313}
{"id": "ts:ShellRisk-Bench-e3f9ab32c4:train:14493", "kind": "hard", "fresh": false, "base_correct_of_4": 3, "v2_readout_p_gold": 0.7662936377487304}
{"id": "ts:github-issue-similarity-9758040744:train:pack-a25dbb5092bf:label-B", "kind": "hard", "fresh": false, "base_correct_of_4": 3, "v2_readout_p_gold": 0.7310585727705126}
{"id": "ts:tasksource-wikipedia-detox-votes-toxicity-609e6d28e8:train:c38b876c5bac7328:wikipedia-detox-toxicity_score", "kind": "soft", "fresh": true, "reasoning_source": false, "source": "wikipedia-detox/toxicity_score", "v2_readout_p_gold": 0.31101650441491835}
{"id": "proc:taxonomy_routing:train:3003:conditions_met", "kind": "exact", "fresh": false, "base_correct_of_4": 3, "v2_readout_p_gold": 0.42298483150869526}
{"id": "ts:ruletaker-511880334b:train:18385", "kind": "hard", "fresh": true, "reasoning_source": true, "source": "ruletaker", "v2_readout_p_gold": 0.21206881431678096}
{"id": "proc:evidence_sufficiency:train:12640:strongest_support_origin", "kind": "exact", "fresh": false, "base_correct_of_4": 3, "v2_readout_p_gold": 0.9140578511317402}
{"id": "ts:spartqa-yn-a9b30ae554:train:2549", "kind": "hard", "fresh": true, "reasoning_source": true, "source": "spartqa-yn", "v2_readout_p_gold": 0.7309087836976426}
{"id": "ts:tasksource-sick-9e0850a4d0:train:3924cf511930e1a3:sick-relatedness", "kind": "soft", "fresh": false, "base_correct_of_4": 3, "v2_readout_p_gold": 0.5884622446674419}
{"id": "proc:graph_navigation:train:7366:edge_essential", "kind": "exact", "fresh": false, "base_correct_of_4": 3, "v2_readout_p_gold": 0.8354835309589073}
{"id": "ts:HelpSteer2-verbosity-bbb1bd07fa:train:17879", "kind": "hard", "fresh": false, "base_correct_of_4": 3, "v2_readout_p_gold": 0.5263643877487824}
{"id": "ts:babi-nli-counting-e9dfb27722:train:43:noul-label-verification", "kind": "hard", "fresh": true, "reasoning_source": true, "source": "babi_nli/counting", "v2_readout_p_gold": 0.718594386544335}
{"id": "ts:LogicNLI-321618d609:train:pack-7692b0662699:exists-3", "kind": "hard", "fresh": true, "reasoning_source": true, "source": "LogicNLI", "v2_readout_p_gold": 0.5621765008857981}
{"id": "ts:wice-a788fdf753:train:1483", "kind": "hard", "fresh": false, "base_correct_of_4": 2, "v2_readout_p_gold": 0.15935414689266372}
{"id": "ts:probability-words-nli-reasoning-1hop-4241424585:train:861:choice-criteria-permutation", "kind": "hard", "fresh": true, "reasoning_source": true, "source": "probability_words_nli/reasoning_1hop", "v2_readout_p_gold": 0.8175744850834649}
{"id": "ts:lsat-ar-eb3f507971:train:534", "kind": "hard", "fresh": true, "reasoning_source": true, "source": "lsat-ar", "v2_readout_p_gold": 0.17907237135958246}
{"id": "ts:pragmeval-squinky-implicature-27cac01586:train:pack-a67d1c5f0f52:same-A-C", "kind": "hard", "fresh": false, "base_correct_of_4": 3, "v2_readout_p_gold": 0.5312093733737563}
{"id": "ts:nli-veridicality-transitivity-aedb9369e8:train:6865", "kind": "hard", "fresh": true, "reasoning_source": false, "source": "nli-veridicality-transitivity", "v2_readout_p_gold": 0.8267117919359419}
{"id": "ts:github-issue-similarity-9758040744:train:10565", "kind": "hard", "fresh": true, "reasoning_source": false, "source": "github-issue-similarity", "v2_readout_p_gold": 0.6926419767901475}
{"id": "ts:FOL-nli-3deb6ff51f:train:27002", "kind": "hard", "fresh": true, "reasoning_source": true, "source": "FOL-nli", "v2_readout_p_gold": 0.4654458623303941}
{"id": "ts:babi-nli-path-finding-c5b9204899:train:42:choice-criteria-permutation", "kind": "hard", "fresh": true, "reasoning_source": true, "source": "babi_nli/path-finding", "v2_readout_p_gold": 0.6791786926816161}
{"id": "ts:tweet-eval-emotion-2266170a95:train:pack-56072503fa9b:all-same", "kind": "hard", "fresh": false, "base_correct_of_4": 2, "v2_readout_p_gold": 0.2689414272294874}
{"id": "proc:policy_under_uncertainty:train:16567:requester_role", "kind": "exact", "fresh": false, "base_correct_of_4": 3, "v2_readout_p_gold": 0.4378234991142019}
{"id": "ts:FLD-v2-star-3d102ff4cd:train:13287", "kind": "hard", "fresh": true, "reasoning_source": false, "source": "FLD.v2/star", "v2_readout_p_gold": 0.6285317261699966}
{"id": "ts:english-grading-conventions-c7df10dc80:train:1557", "kind": "hard", "fresh": false, "base_correct_of_4": 2, "v2_readout_p_gold": 0.6051746925636403}
{"id": "ts:super-glue-copa-d05b628098:train:58:noul-label-verification", "kind": "hard", "fresh": true, "reasoning_source": false, "source": "super_glue/copa", "v2_readout_p_gold": 0.5467381519846138}
{"id": "ts:babi-nli-basic-deduction-2f54b7a691:train:pack-fae8200bd116:label-C", "kind": "hard", "fresh": true, "reasoning_source": true, "source": "babi_nli/basic-deduction", "v2_readout_p_gold": 0.5312093733737563}
{"id": "proc:state_perturbation:train:17480:risk_direction", "kind": "exact", "fresh": false, "base_correct_of_4": 2, "v2_readout_p_gold": 0.6544019108231774}
{"id": "ts:pragmeval-persuasiveness-eloquence-0288d6be99:train:17", "kind": "hard", "fresh": true, "reasoning_source": false, "source": "pragmeval/persuasiveness-eloquence", "v2_readout_p_gold": 0.32082130731838393}
{"id": "proc:graph_navigation:train:2949:shortest_cost", "kind": "exact", "fresh": false, "base_correct_of_4": 3, "v2_readout_p_gold": 0.07038627587292416}
{"id": "ts:blog-authorship-corpus-age-8880d04019:train:2288", "kind": "hard", "fresh": false, "base_correct_of_4": 3, "v2_readout_p_gold": 0.8454926312680604}
{"id": "ts:logical-entailment-5fde239036:train:19052", "kind": "hard", "fresh": true, "reasoning_source": true, "source": "logical-entailment", "v2_readout_p_gold": 0.7772998611746911}
{"id": "ts:dynabench-dynasent-8074025339:train:4d6561ddc69b1d06:dynasent-r1_votes", "kind": "soft", "fresh": false, "base_correct_of_4": 2, "v2_readout_p_gold": 0.24232972977500503}
{"id": "ts:spartqa-yn-a9b30ae554:train:21796", "kind": "hard", "fresh": true, "reasoning_source": true, "source": "spartqa-yn", "v2_readout_p_gold": 0.7056268429052577}
{"id": "ts:stepgame-1cc74264d9:train:8165", "kind": "hard", "fresh": true, "reasoning_source": true, "source": "stepgame", "v2_readout_p_gold": 0.3088426875533124}
{"id": "proc:graph_navigation:train:4822:shortest_cost", "kind": "exact", "fresh": false, "base_correct_of_4": 2, "v2_readout_p_gold": 0.031482505670255505}
{"id": "ts:mutual-410e5f4f25:train:4307", "kind": "hard", "fresh": true, "reasoning_source": false, "source": "mutual", "v2_readout_p_gold": 0.18059951030204072}
{"id": "ts:stepgame-1cc74264d9:train:14826", "kind": "hard", "fresh": false, "base_correct_of_4": 3, "v2_readout_p_gold": 0.37076401071014436}
{"id": "ts:spartqa-yn-a9b30ae554:train:9597", "kind": "hard", "fresh": true, "reasoning_source": true, "source": "spartqa-yn", "v2_readout_p_gold": 0.28101567991563114}
{"id": "ts:multilingual-AfriSenti-twitter-sentiment-hau-f8463d38f0:train:pack-170a4cc553d0:count-2", "kind": "hard", "fresh": true, "reasoning_source": false, "source": "multilingual/AfriSenti-twitter-sentiment/hau", "v2_readout_p_gold": 0.18125900674210246}
{"id": "ts:contract-nli-contractnli-b-full-1b955ccb0f:train:1722", "kind": "hard", "fresh": true, "reasoning_source": true, "source": "contract-nli/contractnli_b/full", "v2_readout_p_gold": 0.1713716318071269}
{"id": "ts:spartqa-yn-a9b30ae554:train:22920", "kind": "hard", "fresh": true, "reasoning_source": true, "source": "spartqa-yn", "v2_readout_p_gold": 0.631667432572621}
{"id": "ts:logiqa-2-0-nli-cf23683f05:train:5875", "kind": "hard", "fresh": true, "reasoning_source": true, "source": "logiqa-2.0-nli", "v2_readout_p_gold": 0.7549149868676283}
{"id": "ts:SpaRTUN-ae090fe669:train:11619", "kind": "hard", "fresh": true, "reasoning_source": true, "source": "SpaRTUN", "v2_readout_p_gold": 0.8175744850834649}
{"id": "ts:arct-8cfb6b7d9e:train:398", "kind": "hard", "fresh": false, "base_correct_of_4": 3, "v2_readout_p_gold": 0.9496693706075925}
{"id": "ts:patent-classification-abstract-14b128d7be:train:pack-47b447e0fe51:exists-1", "kind": "hard", "fresh": true, "reasoning_source": false, "source": "patent-classification/abstract", "v2_readout_p_gold": 0.6791786926816161}
{"id": "ts:lsat-ar-eb3f507971:train:468", "kind": "hard", "fresh": true, "reasoning_source": true, "source": "lsat-ar", "v2_readout_p_gold": 0.3958703752159664}
{"id": "ts:probability-words-nli-reasoning-2hop-e10bbfbc39:train:107", "kind": "hard", "fresh": true, "reasoning_source": true, "source": "probability_words_nli/reasoning_2hop", "v2_readout_p_gold": 0.37754066879814546}
{"id": "ts:clutrr-effc7ced7a:train:4953", "kind": "hard", "fresh": true, "reasoning_source": true, "source": "clutrr", "v2_readout_p_gold": 0.19730238152262408}
{"id": "proc:state_perturbation:train:15517:risk_direction", "kind": "exact", "fresh": false, "base_correct_of_4": 3, "v2_readout_p_gold": 0.6352719168079618}
{"id": "ts:multilingual-paws-x-fr-fe0a6825d0:train:22672", "kind": "hard", "fresh": true, "reasoning_source": false, "source": "multilingual/paws-x/fr", "v2_readout_p_gold": 0.46879062662624377}
{"id": "proc:graph_navigation:train:16773:first_hop", "kind": "exact", "fresh": false, "base_correct_of_4": 2, "v2_readout_p_gold": 0.08200657858596462}
{"id": "ts:babi-nli-basic-deduction-2f54b7a691:train:930", "kind": "hard", "fresh": true, "reasoning_source": true, "source": "babi_nli/basic-deduction", "v2_readout_p_gold": 0.5926665999540697}
{"id": "ts:logical-entailment-5fde239036:train:7484", "kind": "hard", "fresh": true, "reasoning_source": true, "source": "logical-entailment", "v2_readout_p_gold": 0.8267117919359419}
{"id": "ts:spartqa-yn-a9b30ae554:train:14570", "kind": "hard", "fresh": true, "reasoning_source": true, "source": "spartqa-yn", "v2_readout_p_gold": 0.6148271584146803}
{"id": "ts:dynahate-224d6896b5:train:10937", "kind": "hard", "fresh": true, "reasoning_source": false, "source": "dynahate", "v2_readout_p_gold": 0.5156199157230156}
{"id": "ts:ethos-multilabel-da83722077:train:1447", "kind": "hard", "fresh": false, "base_correct_of_4": 3, "v2_readout_p_gold": 0.8933094110250331}
{"id": "ts:stepgame-1cc74264d9:train:4262", "kind": "hard", "fresh": false, "base_correct_of_4": 2, "v2_readout_p_gold": 0.05875067778912972}
{"id": "ts:logiqa-519764b05f:train:3519", "kind": "hard", "fresh": true, "reasoning_source": true, "source": "logiqa", "v2_readout_p_gold": 0.5518870772859371}
{"id": "ts:tweet-eval-hate-68050029a1:train:7373", "kind": "hard", "fresh": true, "reasoning_source": false, "source": "tweet_eval/hate", "v2_readout_p_gold": 0.5312093733737563}
{"id": "ts:multilingual-tweet-sentiment-multilingual-31edbb5b11:train:9377", "kind": "hard", "fresh": false, "base_correct_of_4": 2, "v2_readout_p_gold": 0.7578020437134426}
{"id": "ts:FOL-nli-3deb6ff51f:train:12857", "kind": "hard", "fresh": true, "reasoning_source": true, "source": "FOL-nli", "v2_readout_p_gold": 0.4585242182998923}
{"id": "ts:MSciNLI-ae9f75f228:train:2050", "kind": "hard", "fresh": false, "base_correct_of_4": 3, "v2_readout_p_gold": 0.4808134391300779}
{"id": "ts:tasksource-sts-companion-fbb4266f83:train:f1bf11b537a92a65:sts-companion", "kind": "hard", "fresh": false, "base_correct_of_4": 2, "v2_readout_p_gold": 0.3906131397954893}
{"id": "ts:logical-entailment-5fde239036:train:7219", "kind": "hard", "fresh": true, "reasoning_source": true, "source": "logical-entailment", "v2_readout_p_gold": 0.3629691917376782}
{"id": "ts:tasksource-lewidi-mp-ce0ace9aaf:train:f4d11d548eaf2e13:lewidi-mp", "kind": "hard", "fresh": false, "base_correct_of_4": 2, "v2_readout_p_gold": 0.5}
{"id": "proc:policy_under_uncertainty:train:18416:access_allowed", "kind": "exact", "fresh": false, "base_correct_of_4": 3, "v2_readout_p_gold": 0.9196425372343816}
{"id": "ts:multilingual-xcsr-X-CSQA-ru-1dcb55f7d3:train:72", "kind": "hard", "fresh": false, "base_correct_of_4": 3, "v2_readout_p_gold": 0.6675460840562745}
{"id": "ts:lsat-rc-094f659543:train:1806:noul-label-verification", "kind": "hard", "fresh": true, "reasoning_source": true, "source": "lsat-rc", "v2_readout_p_gold": 0.23370636225126956}
{"id": "ts:glue-cola-48f8044491:train:pack-3da1c1c8841b:label-B", "kind": "hard", "fresh": false, "base_correct_of_4": 3, "v2_readout_p_gold": 0.8267117919359419}
{"id": "ts:HelpSteer3-edit-quality-998a96cfe4:train:2368:choice-criteria-permutation", "kind": "hard", "fresh": false, "base_correct_of_4": 3, "v2_readout_p_gold": 0.5}
{"id": "ts:code-x-glue-cc-defect-detection-1c76c57e72:train:16392", "kind": "hard", "fresh": false, "base_correct_of_4": 2, "v2_readout_p_gold": 0.5774953651858118}
{"id": "ts:spartqa-yn-a9b30ae554:train:14147", "kind": "hard", "fresh": true, "reasoning_source": true, "source": "spartqa-yn", "v2_readout_p_gold": 0.8174608590630307}
{"id": "ts:syntactic-augmentation-nli-1c82215119:train:478", "kind": "hard", "fresh": true, "reasoning_source": false, "source": "syntactic-augmentation-nli", "v2_readout_p_gold": 0.5577515603207195}
{"id": "ts:ethos-multilabel-da83722077:train:1895:choice-criteria-permutation", "kind": "hard", "fresh": false, "base_correct_of_4": 2, "v2_readout_p_gold": 0.6654105521116443}
{"id": "ts:poem-sentiment-b148f25f95:train:3", "kind": "hard", "fresh": false, "base_correct_of_4": 2, "v2_readout_p_gold": 0.06597057670019364}
{"id": "ts:multilingual-disrpt-por-rst-cstn-rels-825ffa218f:train:pack-af165dee4b7a:same-B-C", "kind": "hard", "fresh": false, "base_correct_of_4": 3, "v2_readout_p_gold": 0.45326184801538616}
{"id": "ts:tasksource-sick-9e0850a4d0:train:1adcbec6f6238a0a:sick-relatedness", "kind": "soft", "fresh": false, "base_correct_of_4": 1, "v2_readout_p_gold": 0.06110978963543959}
{"id": "ts:multilingual-AfriSenti-twitter-sentiment-twi-32a4496e5c:train:6", "kind": "hard", "fresh": true, "reasoning_source": false, "source": "multilingual/AfriSenti-twitter-sentiment/twi", "v2_readout_p_gold": 0.3375894847448154}
{"id": "ts:idioms-nli-a923f4bb2a:train:pack-4629ebdb8e31:exists-0", "kind": "hard", "fresh": false, "base_correct_of_4": 3, "v2_readout_p_gold": 0.25683200276421697}
{"id": "ts:tasksource-scirepeval-search-3cb476d0a1:train:c12d32d99957ed32:scirepeval-search", "kind": "hard", "fresh": true, "reasoning_source": false, "source": "scirepeval/search", "v2_readout_p_gold": 0.6936687774778225}
{"id": "ts:lex-glue-case-hold-c8db5a9011:train:6888", "kind": "hard", "fresh": false, "base_correct_of_4": 3, "v2_readout_p_gold": 0.9212377911670192}
{"id": "ts:stepgame-1cc74264d9:train:15667", "kind": "hard", "fresh": true, "reasoning_source": true, "source": "stepgame", "v2_readout_p_gold": 0.2142593525517135}
{"id": "ts:edos-750a60f1e3:train:7890:choice-criteria-permutation", "kind": "hard", "fresh": true, "reasoning_source": false, "source": "edos", "v2_readout_p_gold": 0.7879311856832191}
{"id": "ts:cloth-a8d3866ed4:train:25734", "kind": "hard", "fresh": true, "reasoning_source": false, "source": "cloth", "v2_readout_p_gold": 0.17931199340907722}
{"id": "ts:regset-68fd053640:train:2796", "kind": "hard", "fresh": false, "base_correct_of_4": 3, "v2_readout_p_gold": 0.5312093733737563}
{"id": "ts:nope-76272dc4fa:train:pack-3a2b6c13c4ef:same-A-C", "kind": "hard", "fresh": true, "reasoning_source": false, "source": "nope", "v2_readout_p_gold": 0.48438008427698437}
{"id": "ts:reclor-3f0b326481:train:2985", "kind": "hard", "fresh": true, "reasoning_source": true, "source": "reclor", "v2_readout_p_gold": 0.7631147159650704}
{"id": "ts:strategy-qa-44f34e040f:train:1517", "kind": "hard", "fresh": true, "reasoning_source": true, "source": "strategy-qa", "v2_readout_p_gold": 0.3345894478883556}
{"id": "ts:clutrr-effc7ced7a:train:3188", "kind": "hard", "fresh": true, "reasoning_source": true, "source": "clutrr", "v2_readout_p_gold": 0.2542116259455749}
{"id": "proc:instruction_execution:train:12328:resolution", "kind": "exact", "fresh": false, "base_correct_of_4": 1, "v2_readout_p_gold": 0.944358827289062}
{"id": "ts:babi-nli-three-supporting-facts-f6540ced19:train:652", "kind": "hard", "fresh": true, "reasoning_source": true, "source": "babi_nli/three-supporting-facts", "v2_readout_p_gold": 0.743167997235783}
{"id": "ts:ruletaker-511880334b:train:13000:noul-label-verification", "kind": "hard", "fresh": true, "reasoning_source": true, "source": "ruletaker", "v2_readout_p_gold": 0.5}
{"id": "ts:contract-nli-contractnli-b-full-1b955ccb0f:train:4224", "kind": "hard", "fresh": true, "reasoning_source": true, "source": "contract-nli/contractnli_b/full", "v2_readout_p_gold": 0.7527119867569269}
{"id": "ts:argument-feedback-e0d74b9ca8:train:13386", "kind": "hard", "fresh": false, "base_correct_of_4": 3, "v2_readout_p_gold": 0.3178999971518278}
{"id": "proc:instruction_execution:train:7835:resolution", "kind": "exact", "fresh": false, "base_correct_of_4": 1, "v2_readout_p_gold": 0.9347289736769931}
{"id": "proc:graph_navigation:train:18180:first_hop", "kind": "exact", "fresh": false, "base_correct_of_4": 2, "v2_readout_p_gold": 0.531315297794545}
{"id": "ts:folio-6c5df13928:train:pack-36d625730de8:all-same", "kind": "hard", "fresh": true, "reasoning_source": true, "source": "folio", "v2_readout_p_gold": 0.718594386544335}
{"id": "ts:tasksource-lewidi-mp-ce0ace9aaf:train:ec48b860231fb8b2:lewidi-mp", "kind": "soft", "fresh": false, "base_correct_of_4": 1, "v2_readout_p_gold": 0.5312093733737563}
{"id": "ts:prm800k-dpo-step-70a14c2146:train:21", "kind": "hard", "fresh": false, "base_correct_of_4": 2, "v2_readout_p_gold": 0.7772998611746911}
{"id": "ts:multilingual-xcsr-X-CSQA-pt-11340cf0c7:train:166", "kind": "hard", "fresh": false, "base_correct_of_4": 3, "v2_readout_p_gold": 0.8843284664492163}
{"id": "ts:naturallogic-ba86bebf3b:train:5366", "kind": "hard", "fresh": true, "reasoning_source": true, "source": "naturallogic", "v2_readout_p_gold": 0.21276803009692236}
{"id": "ts:tasksource-dpo-pairs-4e48c7452b:train:9713:noul-label-verification", "kind": "hard", "fresh": false, "base_correct_of_4": 2, "v2_readout_p_gold": 0.45326184801538616}
{"id": "ts:FLD-v2-default-80e9c588e7:train:10297", "kind": "hard", "fresh": false, "base_correct_of_4": 2, "v2_readout_p_gold": 0.48389830258296207}
{"id": "ts:conceptrules-v2-83f331d8b8:train:1269", "kind": "hard", "fresh": true, "reasoning_source": true, "source": "conceptrules_v2", "v2_readout_p_gold": 0.6513548714339145}
{"id": "ts:nli4ct-semeval2024-4a16101db5:train:138:choice-paired-text-format", "kind": "hard", "fresh": false, "base_correct_of_4": 2, "v2_readout_p_gold": 0.45326184801538616}
{"id": "ts:webgpt-comparisons-30f5b33bbc:train:11389", "kind": "hard", "fresh": false, "base_correct_of_4": 2, "v2_readout_p_gold": 0.5}
{"id": "ts:HelpSteer-correctness-b6bde711ef:train:11436", "kind": "hard", "fresh": false, "base_correct_of_4": 2, "v2_readout_p_gold": 0.10985322854604386}
{"id": "ts:monotonicity-entailment-5b266929a5:train:pack-e3c1601a7d8d:exists-0", "kind": "hard", "fresh": true, "reasoning_source": true, "source": "monotonicity-entailment", "v2_readout_p_gold": 0.7057850278370112}
{"id": "ts:yahoo-answers-topics-8fd5d7e862:train:5321:choice-instruction-paraphrase", "kind": "hard", "fresh": true, "reasoning_source": false, "source": "yahoo_answers_topics", "v2_readout_p_gold": 0.5299073569351606}
{"id": "proc:instruction_execution:train:15300:resolution", "kind": "exact", "fresh": false, "base_correct_of_4": 1, "v2_readout_p_gold": 0.8344463968596897}
{"id": "ts:AmbigNQ-clarifying-question-7df26f7ebb:train:pack-538be003841b:most-common", "kind": "hard", "fresh": false, "base_correct_of_4": 3, "v2_readout_p_gold": 0.8354835309589073}
{"id": "ts:folio-6c5df13928:train:pack-886e587b17a4:count-0", "kind": "hard", "fresh": false, "base_correct_of_4": 2, "v2_readout_p_gold": 0.36687595418446023}
{"id": "ts:lsat-rc-094f659543:train:1065", "kind": "hard", "fresh": true, "reasoning_source": true, "source": "lsat-rc", "v2_readout_p_gold": 0.6881158618177772}
{"id": "ts:logiqa-2-0-nli-cf23683f05:train:pack-fd72c35937ad:count-1", "kind": "hard", "fresh": true, "reasoning_source": true, "source": "logiqa-2.0-nli", "v2_readout_p_gold": 0.4045257140067991}
{"id": "ts:code-x-glue-cc-defect-detection-1c76c57e72:train:14769", "kind": "hard", "fresh": false, "base_correct_of_4": 2, "v2_readout_p_gold": 0.46879062662624377}
{"id": "ts:multilingual-masakhanews-xho-6c770d1103:train:387", "kind": "hard", "fresh": true, "reasoning_source": false, "source": "multilingual/masakhanews/xho", "v2_readout_p_gold": 0.5452603756318019}
{"id": "ts:multilingual-masakhanews-orm-c0523c2270:train:pack-ee029edfc9b6:label-C", "kind": "hard", "fresh": false, "base_correct_of_4": 3, "v2_readout_p_gold": 0.9434701295386129}
{"id": "ts:causal-reasoning-transitivity-09db96cbf3:train:22365", "kind": "hard", "fresh": true, "reasoning_source": true, "source": "causal-reasoning/transitivity", "v2_readout_p_gold": 0.8175744850834649}
{"id": "ts:logiqa-2-0-nli-cf23683f05:train:508", "kind": "hard", "fresh": true, "reasoning_source": true, "source": "logiqa-2.0-nli", "v2_readout_p_gold": 0.8175744850834649}
{"id": "ts:ruletaker-511880334b:train:29011", "kind": "hard", "fresh": true, "reasoning_source": true, "source": "ruletaker", "v2_readout_p_gold": 0.42250463481418826}
{"id": "ts:conceptrules-v2-83f331d8b8:train:15002", "kind": "hard", "fresh": true, "reasoning_source": true, "source": "conceptrules_v2", "v2_readout_p_gold": 0.6513548714339145}
{"id": "ts:logical-entailment-5fde239036:train:13659", "kind": "hard", "fresh": true, "reasoning_source": true, "source": "logical-entailment", "v2_readout_p_gold": 0.29421497216298875}
{"id": "ts:proofwriter-b45cbfe5f7:train:28895", "kind": "hard", "fresh": true, "reasoning_source": true, "source": "proofwriter", "v2_readout_p_gold": 0.7201605118413871}
{"id": "ts:scitail-snli-format-ced6916b77:train:pack-a9902a7bd8cc:label-C", "kind": "hard", "fresh": false, "base_correct_of_4": 3, "v2_readout_p_gold": 0.7662936377487304}
{"id": "ts:path-naturalness-prediction-aaaf32f666:train:29222", "kind": "hard", "fresh": false, "base_correct_of_4": 3, "v2_readout_p_gold": 0.4073334000459302}
{"id": "ts:winogrande-winogrande-xl-eb5b02a7c5:train:5362", "kind": "hard", "fresh": true, "reasoning_source": true, "source": "winogrande/winogrande_xl", "v2_readout_p_gold": 0.6926419767901475}
{"id": "ts:faithdial-grounding-cd051b9afb:train:8980", "kind": "hard", "fresh": false, "base_correct_of_4": 3, "v2_readout_p_gold": 0.8991213806488609}
{"id": "ts:proofwriter-b45cbfe5f7:train:29829", "kind": "hard", "fresh": true, "reasoning_source": true, "source": "proofwriter", "v2_readout_p_gold": 0.49421942662856677}
{"id": "ts:babi-nli-lists-sets-ca872109f7:train:641", "kind": "hard", "fresh": true, "reasoning_source": true, "source": "babi_nli/lists-sets", "v2_readout_p_gold": 0.7879311856832191}
{"id": "ts:temporal-nli-0d8184c0f1:train:2123", "kind": "hard", "fresh": true, "reasoning_source": true, "source": "temporal-nli", "v2_readout_p_gold": 0.6274317484110121}
{"id": "ts:conj-nli-0f0ab95726:train:pack-37cdc37f177b:same-A-B", "kind": "hard", "fresh": true, "reasoning_source": false, "source": "conj_nli", "v2_readout_p_gold": 0.4073334000459302}
{"id": "proc:graph_navigation:train:6471:shortest_cost", "kind": "exact", "fresh": false, "base_correct_of_4": 3, "v2_readout_p_gold": 0.21668515219106518}
{"id": "ts:ruletaker-511880334b:train:25707", "kind": "hard", "fresh": true, "reasoning_source": true, "source": "ruletaker", "v2_readout_p_gold": 0.7549149868676283}
{"id": "ts:headline-cause-en-simple-1a168961c0:train:759", "kind": "hard", "fresh": false, "base_correct_of_4": 3, "v2_readout_p_gold": 0.8087146033083988}
{"id": "ts:logical-entailment-5fde239036:train:19845", "kind": "hard", "fresh": true, "reasoning_source": true, "source": "logical-entailment", "v2_readout_p_gold": 0.6791786926816161}
{"id": "ts:multilingual-offenseval-dravidian-tamil-d1ddb06256:train:23313", "kind": "hard", "fresh": false, "base_correct_of_4": 3, "v2_readout_p_gold": 0.9218266711285436}
{"id": "ts:tasksource-sts-companion-fbb4266f83:train:a1d06c3b68d269ba:sts-companion", "kind": "hard", "fresh": true, "reasoning_source": false, "source": "sts-companion", "v2_readout_p_gold": 0.7188465644715568}
{"id": "ts:parade-28e532d56b:train:2337", "kind": "hard", "fresh": true, "reasoning_source": false, "source": "parade", "v2_readout_p_gold": 0.808067204308405}
{"id": "ts:winogrande-winogrande-xl-eb5b02a7c5:train:20852", "kind": "hard", "fresh": true, "reasoning_source": true, "source": "winogrande/winogrande_xl", "v2_readout_p_gold": 0.7310585727705126}
{"id": "ts:commonsense-qa-2-0-fe3c76eb16:train:pack-589bc658d041:count-1", "kind": "hard", "fresh": true, "reasoning_source": false, "source": "commonsense_qa_2.0", "v2_readout_p_gold": 0.3290997976723628}
{"id": "ts:spartqa-yn-a9b30ae554:train:13157", "kind": "hard", "fresh": true, "reasoning_source": true, "source": "spartqa-yn", "v2_readout_p_gold": 0.6297978911903089}
{"id": "ts:FOL-nli-3deb6ff51f:train:12238", "kind": "hard", "fresh": true, "reasoning_source": true, "source": "FOL-nli", "v2_readout_p_gold": 0.15455892345678662}
{"id": "ts:dataset-train-nli-91e59a492d:train:5468:noul-label-verification", "kind": "hard", "fresh": true, "reasoning_source": false, "source": "dataset_train_nli", "v2_readout_p_gold": 0.7549149868676283}
{"id": "ts:lsat-rc-094f659543:train:1101", "kind": "hard", "fresh": true, "reasoning_source": true, "source": "lsat-rc", "v2_readout_p_gold": 0.4328904704113716}
{"id": "ts:tasksource-acceptability-prediction-a432edde29:train:72cf2491241dc9b0:acceptability-prediction-rating_votes", "kind": "soft", "fresh": true, "reasoning_source": false, "source": "acceptability-prediction/rating_votes", "v2_readout_p_gold": 0.5755470442244556}
{"id": "ts:strategy-qa-44f34e040f:train:1676", "kind": "hard", "fresh": true, "reasoning_source": true, "source": "strategy-qa", "v2_readout_p_gold": 0.4073334000459302}
{"id": "ts:head-qa-en-243fd89f57:train:1371:noul-label-verification", "kind": "hard", "fresh": true, "reasoning_source": false, "source": "head_qa/en", "v2_readout_p_gold": 0.7310585727705126}
{"id": "ts:SpaRTUN-ae090fe669:train:25103", "kind": "hard", "fresh": true, "reasoning_source": true, "source": "SpaRTUN", "v2_readout_p_gold": 0.5926665999540697}
{"id": "ts:prm800k-dpo-solution-2e795c25ed:train:2031", "kind": "hard", "fresh": true, "reasoning_source": false, "source": "prm800k_dpo/solution", "v2_readout_p_gold": 0.7057850278370112}
{"id": "ts:discovery-discovery-4cdfae9f6c:train:28761:noul-label-verification", "kind": "hard", "fresh": true, "reasoning_source": false, "source": "discovery/discovery", "v2_readout_p_gold": 0.743167997235783}
{"id": "ts:contract-nli-contractnli-b-full-1b955ccb0f:train:4270", "kind": "hard", "fresh": true, "reasoning_source": true, "source": "contract-nli/contractnli_b/full", "v2_readout_p_gold": 0.7101709987649409}
{"id": "ts:mindgames-dfe4fff9e3:train:5183", "kind": "hard", "fresh": false, "base_correct_of_4": 3, "v2_readout_p_gold": 0.8991213806488609}
{"id": "ts:HelpSteer-complexity-e85ef65ed9:train:pack-03f41d566638:exists-1", "kind": "hard", "fresh": true, "reasoning_source": false, "source": "HelpSteer/complexity", "v2_readout_p_gold": 0.4073334000459302}
{"id": "ts:tasksource-sick-9e0850a4d0:train:2c0e1f657fccfed4:sick-relatedness", "kind": "soft", "fresh": false, "base_correct_of_4": 1, "v2_readout_p_gold": 0.3699402509220153}
{"id": "ts:blog-authorship-corpus-age-8880d04019:train:13084", "kind": "hard", "fresh": false, "base_correct_of_4": 2, "v2_readout_p_gold": 0.5186607557201841}
{"id": "ts:lsat-ar-eb3f507971:train:923", "kind": "hard", "fresh": true, "reasoning_source": true, "source": "lsat-ar", "v2_readout_p_gold": 0.1768212776556384}
{"id": "ts:tweet-eval-stance-feminist-3a6e00fe00:train:193", "kind": "hard", "fresh": false, "base_correct_of_4": 2, "v2_readout_p_gold": 0.531019680912676}
{"id": "ts:parade-28e532d56b:train:4084", "kind": "hard", "fresh": true, "reasoning_source": false, "source": "parade", "v2_readout_p_gold": 0.3486451285660856}
{"id": "ts:spartqa-yn-a9b30ae554:train:1882", "kind": "hard", "fresh": true, "reasoning_source": true, "source": "spartqa-yn", "v2_readout_p_gold": 0.31407205832030843}
{"id": "ts:spartqa-mchoice-d5acb91813:train:1600:choice-instruction-paraphrase", "kind": "hard", "fresh": true, "reasoning_source": true, "source": "spartqa-mchoice", "v2_readout_p_gold": 0.18507327540639396}
{"id": "ts:monotonicity-entailment-5b266929a5:train:2959", "kind": "hard", "fresh": true, "reasoning_source": true, "source": "monotonicity-entailment", "v2_readout_p_gold": 0.743167997235783}
{"id": "ts:AmbigNQ-clarifying-question-7df26f7ebb:train:8488", "kind": "hard", "fresh": false, "base_correct_of_4": 3, "v2_readout_p_gold": 0.4073334000459302}
{"id": "ts:logical-fallacy-49ee8e577f:train:2363", "kind": "hard", "fresh": true, "reasoning_source": true, "source": "logical-fallacy", "v2_readout_p_gold": 0.25056526938334506}
{"id": "ts:agent-action-safety-d817396454:train:9331", "kind": "hard", "fresh": true, "reasoning_source": true, "source": "agent_action_safety", "v2_readout_p_gold": 0.7310585727705126}
{"id": "ts:spartqa-mchoice-d5acb91813:train:1796", "kind": "hard", "fresh": true, "reasoning_source": true, "source": "spartqa-mchoice", "v2_readout_p_gold": 0.3133594177292867}
{"id": "proc:graph_navigation:train:11393:first_hop", "kind": "exact", "fresh": false, "base_correct_of_4": 3, "v2_readout_p_gold": 0.5462290299824759}
{"id": "ts:spartqa-yn-a9b30ae554:train:20138", "kind": "hard", "fresh": true, "reasoning_source": true, "source": "spartqa-yn", "v2_readout_p_gold": 0.46476106775653725}
{"id": "ts:tasksource-oasst2-dense-flat-90075f7000:train:dcbf12bf7ec445d9:oasst2-creativity", "kind": "soft", "fresh": true, "reasoning_source": false, "source": "oasst2/creativity", "v2_readout_p_gold": 0.3471213576436481}
{"id": "ts:HelpSteer3-edit-quality-998a96cfe4:train:656", "kind": "hard", "fresh": true, "reasoning_source": false, "source": "HelpSteer3/edit_quality", "v2_readout_p_gold": 0.48438008427698437}
{"id": "ts:tasksource-sts-companion-fbb4266f83:train:ff94631dfa5675fe:sts-companion", "kind": "soft", "fresh": false, "base_correct_of_4": 1, "v2_readout_p_gold": 0.4715658819974978}
{"id": "proc:event_triggered_execution:train:15569:total_firings", "kind": "exact", "fresh": false, "base_correct_of_4": 3, "v2_readout_p_gold": 0.05360733458369889}
{"id": "ts:stepgame-1cc74264d9:train:16871", "kind": "hard", "fresh": true, "reasoning_source": true, "source": "stepgame", "v2_readout_p_gold": 0.17926048576281567}
{"id": "ts:defeasible-nli-social-7479767344:train:pack-8460dd55f3f6:count-1", "kind": "hard", "fresh": true, "reasoning_source": false, "source": "defeasible-nli/social", "v2_readout_p_gold": 0.3743880928056293}
{"id": "proc:graph_navigation:train:3656:shortest_cost", "kind": "exact", "fresh": false, "base_correct_of_4": 3, "v2_readout_p_gold": 0.9258103868436756}
{"id": "ts:FOL-nli-3deb6ff51f:train:16138", "kind": "hard", "fresh": true, "reasoning_source": true, "source": "FOL-nli", "v2_readout_p_gold": 0.553310439444504}
{"id": "ts:blog-authorship-corpus-gender-5fe8900d6d:train:pack-622304fa4c84:count-0", "kind": "hard", "fresh": true, "reasoning_source": false, "source": "blog_authorship_corpus/gender", "v2_readout_p_gold": 0.3743880928056293}
{"id": "ts:FOL-nli-3deb6ff51f:train:10682", "kind": "hard", "fresh": true, "reasoning_source": true, "source": "FOL-nli", "v2_readout_p_gold": 0.32631809696700254}
{"id": "ts:monotonicity-entailment-5b266929a5:train:343", "kind": "hard", "fresh": true, "reasoning_source": true, "source": "monotonicity-entailment", "v2_readout_p_gold": 0.798186775339273}
{"id": "ts:yelp-review-full-yelp-review-full-ec5d40cd31:train:16331", "kind": "hard", "fresh": false, "base_correct_of_4": 3, "v2_readout_p_gold": 0.448825089102203}
{"id": "ts:multilingual-xcsr-X-CSQA-hi-d29b131c3a:train:52", "kind": "hard", "fresh": false, "base_correct_of_4": 3, "v2_readout_p_gold": 0.7884949134956961}
{"id": "ts:nli4ct-semeval2024-4a16101db5:train:603", "kind": "hard", "fresh": false, "base_correct_of_4": 3, "v2_readout_p_gold": 0.5}
{"id": "ts:babi-nli-counting-e9dfb27722:train:11", "kind": "hard", "fresh": true, "reasoning_source": true, "source": "babi_nli/counting", "v2_readout_p_gold": 0.4073334000459302}
{"id": "ts:cebab-noise-23431204a6:train:2075", "kind": "hard", "fresh": true, "reasoning_source": false, "source": "cebab/noise", "v2_readout_p_gold": 0.8269788833558432}
{"id": "ts:spartqa-mchoice-d5acb91813:train:14916", "kind": "hard", "fresh": true, "reasoning_source": true, "source": "spartqa-mchoice", "v2_readout_p_gold": 0.21132270148970364}
{"id": "ts:babi-nli-single-supporting-fact-64e2c2137a:train:275", "kind": "hard", "fresh": true, "reasoning_source": true, "source": "babi_nli/single-supporting-fact", "v2_readout_p_gold": 0.6370308082623217}
{"id": "proc:event_state_reconstruction:train:10487:is_open", "kind": "exact", "fresh": false, "base_correct_of_4": 3, "v2_readout_p_gold": 0.8933094110250331}
{"id": "ts:lsat-rc-094f659543:train:1826", "kind": "hard", "fresh": true, "reasoning_source": true, "source": "lsat-rc", "v2_readout_p_gold": 0.540004432158194}
{"id": "ts:temporal-nli-0d8184c0f1:train:22524", "kind": "hard", "fresh": true, "reasoning_source": true, "source": "temporal-nli", "v2_readout_p_gold": 0.6920457536882559}
{"id": "proc:state_perturbation:train:7497:risk_direction", "kind": "exact", "fresh": false, "base_correct_of_4": 1, "v2_readout_p_gold": 0.17782546944550048}
{"id": "ts:monotonicity-entailment-5b266929a5:train:1035", "kind": "hard", "fresh": true, "reasoning_source": true, "source": "monotonicity-entailment", "v2_readout_p_gold": 0.6513548714339145}
{"id": "ts:dataset-train-nli-91e59a492d:train:15791", "kind": "hard", "fresh": false, "base_correct_of_4": 3, "v2_readout_p_gold": 0.8740772335247531}
{"id": "ts:silicone-dyda-da-da8e77cb4c:train:7561", "kind": "hard", "fresh": true, "reasoning_source": false, "source": "silicone/dyda_da", "v2_readout_p_gold": 0.8252202004518269}
{"id": "ts:silicone-sem-a8f3a16c15:train:2089", "kind": "hard", "fresh": false, "base_correct_of_4": 2, "v2_readout_p_gold": 0.6148271584146803}
{"id": "ts:emo-emo2019-286304f33c:train:6883", "kind": "hard", "fresh": false, "base_correct_of_4": 2, "v2_readout_p_gold": 0.8098558395448049}
{"id": "ts:feasibilityQA-421371c2a3:train:2903:choice-instruction-paraphrase", "kind": "hard", "fresh": false, "base_correct_of_4": 3, "v2_readout_p_gold": 0.4073334000459302}
{"id": "ts:community-datasets-proto-qa-proto-qa-1bbafc24d1:train:c91acf8c9444c298:proto_qa-proto_qa", "kind": "soft", "fresh": false, "base_correct_of_4": 2, "v2_readout_p_gold": 0.18357646536167585}
{"id": "ts:tweet-eval-stance-abortion-a1a5658e1a:train:392", "kind": "hard", "fresh": true, "reasoning_source": false, "source": "tweet_eval/stance_abortion", "v2_readout_p_gold": 0.8212129992959543}
{"id": "ts:reclor-3f0b326481:train:529", "kind": "hard", "fresh": true, "reasoning_source": true, "source": "reclor", "v2_readout_p_gold": 0.615017885437464}

Xet Storage Details

Size:
85.1 kB
·
Xet hash:
1bece99ba820edcebbb31a87e558e97c97f37c955c233f892b495f06bc6d3fe9

Xet efficiently stores files, intelligently splitting them into unique chunks and accelerating uploads and downloads. More info.