{"id":"W3091792859","doi":"10.32866/001c.17386","title":"How Data Imputation Affects Crash Modeling Results","year":2020,"lang":"en","type":"article","venue":"Findings","topic":"Traffic and Road Safety","field":"Engineering","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Missing data; Crash; Imputation (statistics); Computer science; Statistics; Econometrics; Data mining; Mathematics; Machine learning","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":[],"consensus_categories":[],"category_scores_codex":[0.00007419134,0.0000910314,0.00009163684,0.00002373876,0.00004544663,0.00005688218,0.0002156331,0.00005925362,0.000003840258],"category_scores_gemma":[0.00007433972,0.00008942661,0.00001953092,0.0001264759,0.000005902021,0.0002694392,0.00006905695,0.0001270283,0.00004857062],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001661599,"about_ca_system_score_gemma":0.00000762854,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000001640626,"about_ca_topic_score_gemma":0.000002076164,"domain_scores_codex":[0.999445,0.000005771071,0.00008829837,0.0001979808,0.0001047463,0.0001582269],"domain_scores_gemma":[0.9996953,0.00002295195,0.00001123279,0.0001861552,0.000008971897,0.00007541121],"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":[0.00002950101,0.000007276859,0.0001567788,0.0001369462,0.00004233885,0.00001733774,0.002300307,0.9218039,0.001741601,0.0003305788,0.05923531,0.01419815],"study_design_scores_gemma":[0.0003221804,0.00001397592,0.0004306473,0.00001638483,0.000009242051,0.00000141896,0.00007185648,0.9917601,0.0003008645,0.00001539786,0.006941335,0.0001165863],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6365519,0.0002891452,0.3500014,0.006263051,0.0006567403,0.0002728379,0.000314982,0.001904996,0.003744916],"genre_scores_gemma":[0.9974275,0.0000237882,0.00193327,0.00007396135,0.0001995422,0.000001446109,0.0002621193,0.00002367656,0.00005469793],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3608755,"threshold_uncertainty_score":0.3646711,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04448710579232729,"score_gpt":0.225650458825685,"score_spread":0.1811633530333577,"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."}}