{"id":"W3198948523","doi":"10.18653/v1/2021.findings-emnlp.90","title":"Exploring Decomposition for Table-based Fact Verification","year":2021,"lang":"en","type":"preprint","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":15,"is_retracted":false,"has_abstract":true,"ca_institutions":"Queen's University","funders":"","keywords":"Computer science; Benchmark (surveying); Decomposition; Table (database); Parsing; Simple (philosophy); Artificial intelligence; Programming language; Natural language; Machine learning; Formal verification; Natural language processing; Theoretical computer science; Data mining","routes":{"ca_aff":true,"ca_fund":false,"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":[0.002351296,0.001149488,0.0008410849,0.001986208,0.0006811179,0.002039846,0.001549946,0.001115221,0.004651885],"category_scores_gemma":[0.01380191,0.0006216084,0.002357765,0.001570731,0.001021359,0.006097562,0.002557079,0.00228821,0.00186023],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001242794,"about_ca_system_score_gemma":0.002740812,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00493911,"about_ca_topic_score_gemma":0.008531386,"domain_scores_codex":[0.9979234,0.0006105371,0.0001735945,0.0006303945,0.0004861113,0.0001759704],"domain_scores_gemma":[0.9920416,0.005073508,0.0005637443,0.001404266,0.0007231838,0.0001936395],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0009788891,0.0005321973,0.02142217,0.001330434,0.0002813176,0.001125259,0.001397974,0.2130715,0.03574247,0.06977389,0.02906865,0.6252753],"study_design_scores_gemma":[0.0000370401,0.00007719776,0.0009898242,0.00006636944,0.00004884708,0.000184275,0.0001703329,0.9118425,0.01207919,0.06675914,0.007723446,0.00002193704],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05569416,0.0004984189,0.9241939,0.000919083,0.00007059571,0.0002410858,0.003766848,0.01316474,0.001451198],"genre_scores_gemma":[0.4072933,0.0003624834,0.5696101,0.000323272,0.00008649706,0.000287439,0.01946895,0.0009210691,0.00164696],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.00493911,"threshold_uncertainty_score":0.01556206,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2193518661080649,"score_gpt":0.3194389970665212,"score_spread":0.1000871309584563,"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."}}