{"id":"W4409872401","doi":"10.1016/j.aap.2025.108065","title":"Dynamic short-term crash risk prediction from traffic conflicts at signalized intersections with emerging mixed traffic flow: A novel conflict indicator","year":2025,"lang":"en","type":"article","venue":"Accident Analysis & Prevention","topic":"Traffic and Road Safety","field":"Engineering","cited_by":23,"is_retracted":false,"has_abstract":true,"ca_institutions":"British Columbia Institute of Technology","funders":"Fundamental Research Funds for the Central Universities; Natural Science Foundation of Heilongjiang Province; National Natural Science Foundation of China","keywords":"Traffic flow (computer networking); Crash; Traffic conflict; Term (time); Poison control; Transport engineering; Engineering; Occupational safety and health; Computer science; Computer security; Traffic congestion; Floating car data; Medicine; Medical emergency","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003194672,0.0004232434,0.0006364414,0.001033231,0.0003982687,0.0001060114,0.0002881123,0.0002467048,0.0005164225],"category_scores_gemma":[0.00001805742,0.000409792,0.0006376354,0.001529984,0.00006214172,0.0003290428,0.00006809804,0.0003905305,0.00003631235],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004596572,"about_ca_system_score_gemma":0.00004002908,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000923371,"about_ca_topic_score_gemma":0.021674,"domain_scores_codex":[0.9975547,0.0001303296,0.0008624907,0.0006495101,0.0004004973,0.0004024323],"domain_scores_gemma":[0.9989673,0.0001046027,0.0002010375,0.0005072692,0.00007660275,0.0001431402],"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":[0.0001241069,0.0001931919,0.1109428,0.00001303176,0.007824473,0.000004708919,0.001212942,0.8617085,0.001962579,0.0000038877,0.000277823,0.015732],"study_design_scores_gemma":[0.001150495,0.00003899561,0.4642677,0.0001045085,0.005532215,0.000002336413,0.0002860129,0.5277289,0.0001983206,0.000003543864,0.0004186265,0.0002684321],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.790848,0.0004877686,0.2069311,0.00002830639,0.0004199616,0.0004314366,0.0000288813,0.0007133576,0.0001112004],"genre_scores_gemma":[0.9965718,0.0004906582,0.0006494648,0.00001168185,0.0000571565,0.000139411,0.001457328,0.00005034605,0.0005721335],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3533249,"threshold_uncertainty_score":0.9998354,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.007553705884174164,"score_gpt":0.2392759252801611,"score_spread":0.2317222193959869,"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."}}