{"id":"W4405186637","doi":"10.1016/j.jsr.2024.12.001","title":"Conditional Generative Adversarial Network-Based roadway crash risk prediction considering heterogeneity with dynamic data","year":2024,"lang":"en","type":"article","venue":"Journal of Safety Research","topic":"Traffic and Road Safety","field":"Engineering","cited_by":12,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Windsor","funders":"Korea Agency for Infrastructure Technology Advancement; Ministry of Land, Infrastructure and Transport","keywords":"Crash; Poison control; Generative grammar; Generative adversarial network; Computer science; Adversarial system; Transport engineering; Engineering; Data mining; Machine learning; Artificial intelligence; Medical emergency; Medicine; Deep 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":[0.002456776,0.0001628977,0.0002541107,0.000230667,0.0002909355,0.0001117339,0.000356538,0.0001199032,0.0001341832],"category_scores_gemma":[0.00007948872,0.0001246372,0.00008612875,0.000423371,0.0001858697,0.0004811356,0.00009175362,0.001374133,0.00002337982],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003332883,"about_ca_system_score_gemma":0.0004998784,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000007337684,"about_ca_topic_score_gemma":0.0001196127,"domain_scores_codex":[0.9976462,0.0002657677,0.000509283,0.0002447744,0.0009148059,0.0004191692],"domain_scores_gemma":[0.99863,0.000525646,0.00006709897,0.0003187892,0.0002758834,0.0001826219],"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":[0.0003448147,0.00003713418,0.001812054,0.00006184446,0.0004895285,0.000202808,0.0000840093,0.9826518,0.0003518579,0.0001202874,0.009273056,0.004570825],"study_design_scores_gemma":[0.001258273,0.0003559635,0.02092306,0.0003210137,0.00007934292,0.0002263714,0.00007374153,0.9588517,0.0002503598,0.0002025763,0.01729127,0.0001663407],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3033348,0.006329211,0.6813226,0.001147891,0.003101788,0.0006213556,0.002374569,0.0003813826,0.001386337],"genre_scores_gemma":[0.9926376,0.0008658039,0.004990997,0.00001097458,0.001228535,0.00000373396,0.0001857983,0.00004232453,0.00003416956],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6893029,"threshold_uncertainty_score":0.5970001,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04963040726369076,"score_gpt":0.3260743185035714,"score_spread":0.2764439112398806,"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."}}