{"id":"W4284669228","doi":"10.1016/j.ijtst.2022.06.006","title":"CGAN-EB: A non-parametric empirical Bayes method for crash frequency modeling using conditional generative adversarial networks as safety performance functions","year":2022,"lang":"en","type":"article","venue":"International Journal of Transportation Science and Technology","topic":"Traffic and Road Safety","field":"Engineering","cited_by":11,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Crash; Bayes' theorem; Parametric statistics; Artificial neural network; Computer science; Machine learning; Nonparametric statistics; Artificial intelligence; Algorithm; Statistics; Mathematics; Bayesian probability","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":[0.003375586,0.00110202,0.001033858,0.001417565,0.0003833051,0.000727929,0.002312805,0.001184101,0.002927829],"category_scores_gemma":[0.008405737,0.0005304656,0.0009158205,0.0006086389,0.0009780374,0.00129067,0.001433699,0.001924856,0.0006491164],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007526837,"about_ca_system_score_gemma":0.001033547,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00554746,"about_ca_topic_score_gemma":0.005024741,"domain_scores_codex":[0.9987736,0.000657405,0.00004120074,0.0001856897,0.0002660474,0.00007596348],"domain_scores_gemma":[0.9957129,0.003204854,0.0002960396,0.0002535585,0.0004328921,0.00009983846],"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":[0.00005728054,0.00004308672,0.001533948,0.00005414872,0.00007346807,0.00006740935,0.00004950802,0.9227592,0.0007299064,0.01383586,0.00142515,0.05937104],"study_design_scores_gemma":[0.000002291896,0.000009118241,0.0001210041,0.000007054577,0.000004980376,0.00001862821,0.00000371609,0.9946525,0.0002201358,0.004655573,0.000300101,0.000004795696],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.005006072,0.0002105222,0.9935012,0.0000982125,0.00002326857,0.00004140861,0.00006326802,0.000309104,0.0007469205],"genre_scores_gemma":[0.5846289,0.0007532013,0.4056651,0.0004206669,0.0001594192,0.0004849126,0.0009398116,0.000323428,0.006624548],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.00554746,"threshold_uncertainty_score":0.01785207,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01819109800104003,"score_gpt":0.3053526273259077,"score_spread":0.2871615293248677,"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."}}