{"id":"W4394658390","doi":"10.66573/001c.144283","title":"Synthesizing Property & Casualty Ratemaking Datasets using Generative Adversarial Networks","year":2025,"lang":"en","type":"preprint","venue":"Variance","topic":"Autopsy Techniques and Outcomes","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université Laval","funders":"University of Waterloo; Alliance de recherche numérique du Canada; Brigham Young University","keywords":"Categorical variable; Computer science; Generative grammar; Confidentiality; Data mining; Differential privacy; Generative adversarial network; Property (philosophy); Adversarial system; Transparency (behavior); Generative model; Machine learning; Artificial intelligence; Deep learning; Computer security","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005784885,0.000718964,0.0005672751,0.0007783014,0.0002810238,0.001090992,0.001316071,0.001093221,0.002870585],"category_scores_gemma":[0.02018097,0.0003212065,0.0008776167,0.0006770623,0.001283507,0.001473025,0.001683128,0.002331224,0.0004584527],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001187593,"about_ca_system_score_gemma":0.0005936549,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001750177,"about_ca_topic_score_gemma":0.002281373,"domain_scores_codex":[0.9982336,0.001025947,0.00005531421,0.0002954203,0.0002939892,0.00009565189],"domain_scores_gemma":[0.9896131,0.006961712,0.0008294545,0.001965064,0.0004013253,0.0002293133],"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":[0.0001377585,0.00007686267,0.005527074,0.00007834652,0.00006745665,0.0001897604,0.0001449534,0.8864492,0.001084353,0.0597638,0.004555164,0.04192534],"study_design_scores_gemma":[0.00001920128,0.00003363932,0.0009879549,0.00002238728,0.000007473084,0.00005365166,0.00002211125,0.93655,0.0009865116,0.05974014,0.001564016,0.0000129103],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1018692,0.0003542904,0.8876979,0.001619465,0.00008317322,0.0001495956,0.0018079,0.00071392,0.005704684],"genre_scores_gemma":[0.9011756,0.0002840469,0.09135891,0.0003285084,0.00007325798,0.0002087668,0.002896114,0.0001303398,0.003544456],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.005784885,"threshold_uncertainty_score":0.03059375,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08169857589428087,"score_gpt":0.3641907366714952,"score_spread":0.2824921607772143,"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."}}