{"id":"W4285226597","doi":"10.18653/v1/2022.acl-long.92","title":"WatClaimCheck: A new Dataset for Claim Entailment and Inference","year":2022,"lang":"en","type":"article","venue":"Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","topic":"Topic Modeling","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"ca_institutions":"Vector Institute; University of Waterloo","funders":"Vector Institute; Natural Sciences and Engineering Research Council of Canada; Government of Canada; Canadian Institute for Advanced Research","keywords":"Premise; Inference; Computer science; Identification (biology); Task (project management); Logical consequence; Textual entailment; Information retrieval; Quality (philosophy); Data science; Artificial intelligence; Natural language processing; Epistemology; Engineering","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002182353,0.001956931,0.0009762843,0.01099814,0.002209949,0.003026732,0.003784881,0.004595951,0.01786221],"category_scores_gemma":[0.01728473,0.000726083,0.001843579,0.007404202,0.0008713146,0.005521601,0.003750074,0.002594021,0.01147526],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002276923,"about_ca_system_score_gemma":0.003662516,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0161934,"about_ca_topic_score_gemma":0.03882479,"domain_scores_codex":[0.9966419,0.0005895108,0.0007153586,0.0008979875,0.0009614221,0.0001939101],"domain_scores_gemma":[0.9887754,0.005178404,0.001352241,0.002188763,0.001884014,0.0006212268],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0005693147,0.000668478,0.01075742,0.004631947,0.0002533965,0.001485827,0.0009980442,0.003993281,0.005826803,0.01368109,0.8832647,0.07386983],"study_design_scores_gemma":[0.0005486725,0.0001806905,0.02282144,0.0006721976,0.0001904233,0.00146263,0.001189059,0.03176809,0.009332157,0.01602091,0.9156517,0.0001621653],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"dataset","genre_gemma":"empirical","genre_scores_codex":[0.0281564,0.00284756,0.0167137,0.001859645,0.000469074,0.0007746108,0.9284447,0.00833891,0.01239539],"genre_scores_gemma":[0.01592066,0.0004130008,0.02376308,0.0002452987,0.0001265614,0.0006262498,0.9561655,0.0003560559,0.002383607],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01786221,"threshold_uncertainty_score":0.05975503,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01439875458522092,"score_gpt":0.2566326457056536,"score_spread":0.2422338911204327,"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."}}