{"id":"W4385573173","doi":"10.18653/v1/2022.sustainlp-1.7","title":"Data-Efficient Auto-Regressive Document Retrieval for Fact Verification","year":2022,"lang":"en","type":"article","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"Kootenay Association for Science & Technology","funders":"Institute for Information and Communications Technology Promotion; Ministry of Science and ICT, South Korea; Korea Advanced Institute of Science and Technology","keywords":"Computer science; Annotation; Information retrieval; Task (project management); Context (archaeology); Question answering; Precision and recall; Sequence (biology); Natural language processing; Document retrieval; Code (set theory); Artificial intelligence; Component (thermodynamics); Programming language","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":[0.0005167285,0.00007028101,0.00007757304,0.00004917816,0.0002615747,0.00009383505,0.00150464,0.00001441309,0.0001066188],"category_scores_gemma":[0.00004619332,0.00006382783,0.00002836323,0.0001628122,0.000008805632,0.0001848447,0.001041029,0.00007854441,0.0000137629],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001192455,"about_ca_system_score_gemma":0.00009527818,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000017923,"about_ca_topic_score_gemma":8.710606e-7,"domain_scores_codex":[0.998771,0.00004284342,0.0001761285,0.0004820775,0.0003505938,0.000177415],"domain_scores_gemma":[0.9985551,0.00006647792,0.00007922875,0.001216586,0.00004006506,0.00004255406],"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":[0.00007190915,0.0002921584,0.00006786765,0.0000347797,0.00005638315,0.0000110249,0.002239181,0.1768543,0.003883999,0.6386288,0.02203571,0.155824],"study_design_scores_gemma":[0.0002120471,0.00004106808,0.00009907575,0.000001378662,0.000003288006,0.000003533355,0.00006438713,0.9370872,0.000918475,0.0009676617,0.06051349,0.00008836183],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.008555713,0.00005239281,0.9876363,0.00200678,0.0006429326,0.0003521047,0.00003661694,0.0001419221,0.0005752321],"genre_scores_gemma":[0.878851,0.000001677341,0.1190981,0.0003756636,0.00006151319,0.00005647272,0.00008206781,0.000006954753,0.001466584],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8702953,"threshold_uncertainty_score":0.279602,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06656082727731734,"score_gpt":0.3146764219294113,"score_spread":0.248115594652094,"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."}}