{"id":"W4401837480","doi":"10.1016/j.aap.2024.107752","title":"Analyzing the heterogenous effects of factors on high-range speeding likelihood of taxi speeders: Does explainable deep learning provides more insights than random parameter approach?","year":2024,"lang":"en","type":"article","venue":"Accident Analysis & Prevention","topic":"Traffic and Road Safety","field":"Engineering","cited_by":7,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of British Columbia","funders":"National Natural Science Foundation of China","keywords":"Range (aeronautics); Computer science; Artificial intelligence; Machine learning; Engineering; Aerospace engineering","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":[0.000397386,0.000296559,0.0006167281,0.0006555479,0.0001454888,0.0001066136,0.0002294293,0.0001222813,0.00002635916],"category_scores_gemma":[0.00007802749,0.0001785265,0.0007981707,0.001129955,0.00004382012,0.0003693147,0.00005241078,0.0002941766,0.000003911612],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008577001,"about_ca_system_score_gemma":0.0000105039,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000171883,"about_ca_topic_score_gemma":0.0003193918,"domain_scores_codex":[0.9982099,0.0001879119,0.0005753341,0.0003528091,0.0003699308,0.0003041117],"domain_scores_gemma":[0.9989758,0.0004539897,0.0001841629,0.0002760489,0.0000516184,0.00005838867],"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":[0.0001665784,0.0003406197,0.2469469,0.0009729353,0.0155248,0.00002710379,0.01768324,0.6794999,0.006537534,0.0002021889,0.00002937465,0.03206883],"study_design_scores_gemma":[0.002389782,0.0005595498,0.2777229,0.001390912,0.01575056,0.000004429458,0.008785396,0.6020919,0.08903481,0.001090147,0.00008776498,0.001091796],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9317255,0.003920362,0.06341873,0.00001334491,0.0002058664,0.0004601526,3.336667e-7,0.000187068,0.00006861338],"genre_scores_gemma":[0.9988471,0.0005105094,0.0003421582,0.000001720531,0.0000861416,0.00003479303,0.00006293471,0.00004142836,0.0000731787],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.08249728,"threshold_uncertainty_score":0.7280102,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.006983238422048242,"score_gpt":0.2183676624079825,"score_spread":0.2113844239859343,"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."}}