{"id":"W4318980282","doi":"10.1111/jori.12418","title":"Enhancing claim classification with feature extraction from anomaly‐detection‐derived routine and peculiarity profiles","year":2023,"lang":"en","type":"article","venue":"Journal of Risk & Insurance","topic":"Anomaly Detection Techniques and Applications","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université du Québec à Montréal","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Anomaly (physics); Anomaly detection; Computer science; Feature (linguistics); TRIPS architecture; Data mining; Degree (music)","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0003619262,0.0001235417,0.0001831615,0.0001570537,0.0003066107,0.0001271159,0.0002523877,0.00009610882,0.000003011853],"category_scores_gemma":[0.00006061839,0.00009886587,0.00006098844,0.0006992539,0.00004841679,0.0007165825,0.00003963389,0.0004364584,0.000007844489],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006768897,"about_ca_system_score_gemma":0.0000410601,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001005522,"about_ca_topic_score_gemma":0.00007909966,"domain_scores_codex":[0.9989737,0.00007703772,0.0003069206,0.0002479564,0.0002532552,0.0001410732],"domain_scores_gemma":[0.9985669,0.0001190027,0.0007034511,0.0002683333,0.0002648673,0.00007743564],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","study_design_scores_codex":[0.0002114131,0.0001409088,0.09206657,0.00003028944,0.00009292149,0.00002989928,0.001318933,0.0002322228,0.7036532,0.001480434,0.0004948796,0.2002484],"study_design_scores_gemma":[0.000307256,0.0001302094,0.865393,0.00005602152,0.00001612664,0.00009917122,0.0001669851,0.005520822,0.1258148,0.001146054,0.001223484,0.0001260564],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6046823,0.0001111882,0.3943385,0.0005330056,0.00009633225,0.00008678056,0.000009165393,0.0001194678,0.00002316866],"genre_scores_gemma":[0.9620449,0.0006321714,0.03704276,0.00002737792,0.0001790503,0.00001885821,0.000002229635,0.000009577671,0.00004308493],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7733264,"threshold_uncertainty_score":0.4031633,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.011034947559507,"score_gpt":0.2488976909789315,"score_spread":0.2378627434194245,"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."}}