{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001656819,0.0006685497,0.0008062407,0.001071695,0.0004750553,0.0009579148,0.00208995,0.0008553475,0.00443054],"category_scores_gemma":[0.005499366,0.0005549446,0.001107279,0.0008970039,0.000534257,0.00266466,0.001120671,0.001390694,0.004762524],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008077307,"about_ca_system_score_gemma":0.001349695,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01036136,"about_ca_topic_score_gemma":0.01809683,"domain_scores_codex":[0.9993951,0.0001221991,0.00003796279,0.0002361343,0.0001512991,0.00005719121],"domain_scores_gemma":[0.9980934,0.000834263,0.0001364237,0.0005498012,0.0003208965,0.00006514841],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0006212937,0.0004764105,0.003649203,0.0004429098,0.0001804941,0.0003251964,0.0003495238,0.2284496,0.05569944,0.01925742,0.03547919,0.6550693],"study_design_scores_gemma":[0.00001664903,0.0000300755,0.0004274273,0.000008265574,0.00001459037,0.00008690112,0.00001789223,0.9824442,0.009648837,0.004612705,0.002678776,0.00001367844],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02226583,0.0004910891,0.9578327,0.0002067259,0.00005628917,0.0001347798,0.001191,0.01645339,0.001368185],"genre_scores_gemma":[0.3424962,0.0004271123,0.6419122,0.0001504185,0.0001114824,0.0002533152,0.006687038,0.0009351633,0.007027032],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01036136,"threshold_uncertainty_score":0.02060211,"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."}}