{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001258258,0.0001461158,0.0002284827,0.00006197321,0.0006446372,0.00008535005,0.001169482,0.00005126924,0.000002155827],"category_scores_gemma":[0.006750276,0.0001225196,0.0001427797,0.0002523846,0.00004056404,0.00008831806,0.001020635,0.0001792977,2.978458e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002316359,"about_ca_system_score_gemma":0.0002066333,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005642614,"about_ca_topic_score_gemma":0.000004626283,"domain_scores_codex":[0.9981107,0.00002277821,0.0005177849,0.0003352101,0.0007559209,0.00025757],"domain_scores_gemma":[0.9968277,0.0007244809,0.00114774,0.0001635709,0.001074794,0.00006176931],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001913887,0.0003548659,0.2067445,0.0007860929,0.0004734978,2.246049e-7,0.009254459,0.2863694,0.001162476,0.4290346,0.06163951,0.003988978],"study_design_scores_gemma":[0.002503756,0.0003956144,0.01887069,0.0002265388,0.0002562884,0.000005418473,0.001085517,0.7349062,0.001443526,0.1329909,0.10672,0.000595619],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5420154,0.001400263,0.3100295,0.06409097,0.02315838,0.01793945,0.03034026,0.0007716232,0.01025415],"genre_scores_gemma":[0.9475317,0.000001739513,0.05091679,0.0003813868,0.0002431982,0.00005311846,0.00007029287,0.00001525224,0.0007865205],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4485368,"threshold_uncertainty_score":0.8081199,"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."}}