{"id":"W6910469056","doi":"10.48448/mspe-2p79","title":"Exploring Decomposition for Table-based Fact Verification","year":2021,"lang":"en","type":"other","venue":"Underline Science Inc.","topic":"","field":"","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Queen's University","funders":"","keywords":"Decomposition; Simple (philosophy); Natural language; Formal verification; Semantics (computer science); Functional verification; Runtime verification; Data modeling","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":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0008527124,0.0003418668,0.0003261149,0.001124089,0.000350026,0.0002845545,0.0006963848,0.0001395529,0.0009536528],"category_scores_gemma":[0.0002229703,0.0003589743,0.00008360349,0.001743099,0.00047767,0.0004161735,0.0000681403,0.0001826773,0.0004733974],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006240825,"about_ca_system_score_gemma":0.001306653,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002112988,"about_ca_topic_score_gemma":0.000273765,"domain_scores_codex":[0.997158,0.000049104,0.0003247163,0.001029466,0.0008283468,0.000610362],"domain_scores_gemma":[0.9981939,0.00009890759,0.0003851632,0.0008052728,0.0003379493,0.0001788419],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0001280821,0.0009122769,0.000224432,0.0007771524,0.0001081104,0.00001704282,0.0002331004,0.00907593,0.7646165,0.00934408,0.1666499,0.04791331],"study_design_scores_gemma":[0.001697624,0.0002007226,0.0003065456,0.001146495,0.0001217937,0.000008579058,0.000253727,0.1371031,0.08655714,0.0002313551,0.771031,0.001341901],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.004950859,0.001650689,0.6587017,0.0009447985,0.007079167,0.006097494,0.002544841,0.003703472,0.314327],"genre_scores_gemma":[0.2689187,0.000193307,0.5319142,0.0008331473,0.003772625,0.003034239,0.01490085,0.005068836,0.1713641],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.6780594,"threshold_uncertainty_score":0.9999596,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2119253523274232,"score_gpt":0.3703793420201934,"score_spread":0.1584539896927702,"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."}}