{"id":"W3174432697","doi":"10.18653/v1/2021.acl-short.51","title":"Exploring Listwise Evidence Reasoning with T5 for Fact Verification","year":2021,"lang":"en","type":"article","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":44,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; Canada First Research Excellence Fund","keywords":"Computer science; Computational linguistics; Volume (thermodynamics); Natural language processing; Joint (building); Artificial intelligence; Cognitive science; Psychology; Engineering","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001575341,0.00006175187,0.00006962292,0.00002345495,0.00008063966,0.0001476642,0.000270843,0.00001409783,0.000007620295],"category_scores_gemma":[0.0001449961,0.00005278247,0.00002348611,0.0001623387,0.000006359662,0.001169098,0.00007137893,0.00004375819,0.000007882638],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003232684,"about_ca_system_score_gemma":0.00008786609,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002754119,"about_ca_topic_score_gemma":0.00001230755,"domain_scores_codex":[0.9992639,0.00001732966,0.0001037494,0.0003296665,0.0001396035,0.0001457413],"domain_scores_gemma":[0.9992008,0.0001092067,0.0000335103,0.0004895722,0.0001226745,0.00004419178],"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":[0.00003066728,0.00006349957,0.004178332,0.000140154,0.00003425976,0.0000405066,0.005391798,0.008819276,0.01370617,0.4526463,0.0002355591,0.5147135],"study_design_scores_gemma":[0.0004094675,0.00008512534,0.01079547,0.0005165261,0.00001332223,0.00004265123,0.0004270425,0.8742723,0.1055418,0.001166661,0.006307872,0.0004217749],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.08217613,0.0001178469,0.9159438,0.0008259333,0.0001260108,0.00008166856,1.534046e-7,0.0001249938,0.0006034577],"genre_scores_gemma":[0.5956262,0.00002523564,0.4038026,0.00008278364,0.00003835361,0.0000475605,5.667582e-7,0.000003837567,0.0003728504],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.865453,"threshold_uncertainty_score":0.2152407,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2909852846843825,"score_gpt":0.3030645874900807,"score_spread":0.01207930280569819,"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."}}