{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00725258,0.0007291478,0.001306636,0.001892103,0.0004671338,0.001765875,0.002013495,0.002001717,0.001139829],"category_scores_gemma":[0.03454004,0.0008335281,0.001082102,0.001692637,0.001772773,0.005735952,0.001535429,0.003979489,0.0003108487],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001534306,"about_ca_system_score_gemma":0.00106474,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002836819,"about_ca_topic_score_gemma":0.003052704,"domain_scores_codex":[0.9982578,0.000907169,0.0001023657,0.0003037842,0.0003193821,0.0001095061],"domain_scores_gemma":[0.9707184,0.02595595,0.001065374,0.001325636,0.0007027787,0.0002318519],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002400582,0.0004480927,0.02935872,0.0002967225,0.000219848,0.0002366903,0.0006635166,0.4335741,0.001088338,0.1390292,0.01233413,0.3825105],"study_design_scores_gemma":[0.000008427006,0.00001810001,0.0007698325,0.00001968327,0.000009613725,0.00005257465,0.00002038011,0.9035159,0.0002842709,0.09474861,0.0005437855,0.000008863253],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0735573,0.001147784,0.9195392,0.003377046,0.00006129634,0.00006668627,0.000340574,0.0003089043,0.001601207],"genre_scores_gemma":[0.7801648,0.001333937,0.2136238,0.0006087506,0.0003345166,0.0001626861,0.001053015,0.00005913529,0.002659188],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.00725258,"threshold_uncertainty_score":0.03835571,"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."}}