{"id":"W6891549042","doi":"10.48448/y8zy-ce22","title":"WatClaimCheck: A new Dataset for Claim Entailment and Inference","year":2022,"lang":"en","type":"other","venue":"Underline Science Inc.","topic":"","field":"","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Premise; Inference; Identification (biology); Task (project management); Logical consequence; Quality (philosophy)","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.001236434,0.0005162701,0.0004774846,0.001035486,0.0005060453,0.0003154131,0.001664906,0.0001575287,0.01298174],"category_scores_gemma":[0.0003542134,0.000481488,0.00005258568,0.001127684,0.001289924,0.0003231557,0.001408269,0.0004124899,0.0008119044],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005618641,"about_ca_system_score_gemma":0.002157647,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001384466,"about_ca_topic_score_gemma":0.002324678,"domain_scores_codex":[0.9958339,0.00005488246,0.0004032771,0.001486077,0.001298875,0.0009229495],"domain_scores_gemma":[0.9976413,0.000144872,0.0004154281,0.001201631,0.0000634973,0.0005333054],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00001853459,0.00008614102,0.0001518247,0.00004651267,0.00002690712,0.000006180669,0.00009571952,0.00001488478,0.0006896188,0.003756968,0.9876873,0.007419338],"study_design_scores_gemma":[0.0009403751,0.0002279861,0.00002648098,0.0000577764,0.00007164189,0.00001688665,0.0002360909,0.002411806,0.0000889619,0.001611174,0.9937172,0.0005936203],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"other","genre_gemma":"other","genre_scores_codex":[0.0006012112,0.008636948,0.03469592,0.008905292,0.006927925,0.02094934,0.4042481,0.00399046,0.5110449],"genre_scores_gemma":[0.002807318,0.0004680361,0.1101924,0.003333688,0.001675737,0.0006617297,0.06179212,0.002604523,0.8164644],"genre_candidate":"other","genre_consensus":"other","teacher_disagreement_score":0.3424559,"threshold_uncertainty_score":0.9999661,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04992216363888007,"score_gpt":0.3634655141163872,"score_spread":0.3135433504775071,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}