{"id":"W1523280505","doi":"10.1007/11564096_63","title":"Detecting Fraud in Health Insurance Data: Learning to Model Incomplete Benford’s Law Distributions","year":2005,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Benford’s Law and Fraud Detection","field":"Mathematics","cited_by":29,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Benford's law; Computer science; Probabilistic logic; Data mining; Health insurance; Data science; Health care; Artificial intelligence; Statistics; Law; Mathematics","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"],"consensus_categories":[],"category_scores_codex":[0.00171445,0.0004884063,0.0006969269,0.0005181939,0.0006152641,0.0002348102,0.001497644,0.0003207003,0.0000150108],"category_scores_gemma":[0.0004118403,0.0004965182,0.00008258664,0.0006098999,0.000312451,0.0005656987,0.001166903,0.00174699,0.00001820839],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008536392,"about_ca_system_score_gemma":0.0003990343,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000391315,"about_ca_topic_score_gemma":0.01066603,"domain_scores_codex":[0.9961969,0.00005197571,0.0009443755,0.001264972,0.0007170842,0.0008246998],"domain_scores_gemma":[0.9973425,0.0005852983,0.000433952,0.001285606,0.000138482,0.0002141492],"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":[0.00001977177,0.00004552231,0.00009745816,0.000176233,0.00001018848,0.00001173457,0.001137297,0.4212587,0.00005116822,0.07031562,0.00002153404,0.5068548],"study_design_scores_gemma":[0.0002854833,0.0001536909,0.00007767014,0.0008624351,0.000005284524,0.00003191998,0.000001076184,0.780783,0.0001336476,0.2124196,0.004649235,0.0005969687],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001329077,0.0001336825,0.9943546,0.0004905268,0.0004835939,0.0006209027,0.0001075041,0.0001690827,0.002311029],"genre_scores_gemma":[0.6621413,0.00002520923,0.3361811,0.000916275,0.0004235519,0.00001485496,0.00003755196,0.00005654823,0.0002035934],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.6608122,"threshold_uncertainty_score":0.9997486,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07206716951578145,"score_gpt":0.3215984773727922,"score_spread":0.2495313078570107,"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."}}