{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002096708,0.0001471474,0.0001697743,0.00009004812,0.00008196358,0.0004187321,0.0006277874,0.00009484762,0.00001308805],"category_scores_gemma":[0.0000248084,0.0001589836,0.0001022218,0.00009318266,0.000005241517,0.0004206044,0.000336945,0.0001632339,0.000004846634],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001170582,"about_ca_system_score_gemma":0.0002277364,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008293459,"about_ca_topic_score_gemma":0.000009094694,"domain_scores_codex":[0.9987128,0.00003452484,0.0002458557,0.0006463451,0.0001774416,0.000183014],"domain_scores_gemma":[0.998675,0.00007617276,0.0001044674,0.0009308929,0.0001624296,0.00005097504],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001503074,0.0001595119,0.0001421255,0.0006686567,0.00006073628,0.000006834816,0.001005745,0.7209916,0.01175394,0.04197328,0.0002084597,0.2230141],"study_design_scores_gemma":[0.0001577281,0.00001111506,0.0001835007,0.00009245981,0.000007152295,7.07591e-7,0.00002167438,0.9623132,0.03562873,0.0009105198,0.0004787772,0.000194481],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04245175,0.00005153986,0.9545733,0.0007156609,0.001227123,0.0003547184,0.000003397913,0.0002706936,0.0003518693],"genre_scores_gemma":[0.5112013,0.000009742643,0.4881232,0.0001196856,0.00008618336,0.00033275,0.00007980576,0.000008133456,0.00003928861],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.4687495,"threshold_uncertainty_score":0.6483165,"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."}}