{"id":"W4225164725","doi":"10.1155/2022/4257865","title":"Predicting Freeway Traffic Crash Severity Using XGBoost-Bayesian Network Model with Consideration of Features Interaction","year":2022,"lang":"en","type":"article","venue":"Journal of Advanced Transportation","topic":"Traffic and Road Safety","field":"Engineering","cited_by":94,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"China Postdoctoral Science Foundation","keywords":"Crash; Computer science; Transport engineering; Bayesian probability; Predictive modelling; Poison control; Ranking (information retrieval); Data mining; Machine learning; Engineering; Artificial intelligence","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001541061,0.0001179387,0.0002183979,0.00009388423,0.0001463894,0.000008764937,0.00005946027,0.0000395104,0.00001480037],"category_scores_gemma":[0.000004487915,0.0001121139,0.00007830124,0.0001804867,0.00001866968,0.0004698092,0.000001462074,0.0003783301,3.992421e-8],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001078153,"about_ca_system_score_gemma":0.00006638462,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003373213,"about_ca_topic_score_gemma":0.0001608409,"domain_scores_codex":[0.9989666,0.00002845295,0.000495697,0.00008780316,0.0002899145,0.0001315661],"domain_scores_gemma":[0.9994032,0.00003992821,0.000333813,0.00006651827,0.0001112015,0.00004531385],"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":[0.00027678,0.00003279692,0.00174514,0.00005050379,0.00006390449,0.00001252396,0.002313037,0.9893445,0.003026556,0.00003766793,0.00003943988,0.003057198],"study_design_scores_gemma":[0.001437911,0.0003001235,0.07228261,0.0001766731,0.0001712522,0.000137287,0.002615096,0.9213032,0.001133298,0.0001628235,0.00006933206,0.0002104437],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8811865,0.0001710347,0.1179854,0.00002682305,0.000415751,0.0001115667,0.00002076946,0.00004651231,0.00003556968],"genre_scores_gemma":[0.9729919,0.00003794325,0.0268,0.00001248846,0.00009755779,0.000003043241,0.00002754397,0.00002443161,0.000005035259],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.09180542,"threshold_uncertainty_score":0.4571871,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.007585156580796709,"score_gpt":0.2188579439998348,"score_spread":0.2112727874190381,"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."}}