{"id":"W4200376038","doi":"10.1080/15472450.2021.2014833","title":"Modeling vehicle collision instincts over road midblock using deep learning","year":2021,"lang":"en","type":"article","venue":"Journal of Intelligent Transportation Systems","topic":"Traffic and Road Safety","field":"Engineering","cited_by":15,"is_retracted":false,"has_abstract":true,"ca_institutions":"Toronto Metropolitan University","funders":"Mitacs","keywords":"Trajectory; Collision; Computer science; Instinct; Active safety; Development (topology); Simulation; Transport engineering; Computer security; Artificial intelligence; Engineering; Automotive engineering; Mathematics","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0002994749,0.0001545524,0.00032032,0.0001341516,0.00009242284,0.00005265131,0.00009252966,0.0001172699,0.00003607893],"category_scores_gemma":[0.00002353984,0.0001433039,0.0001710034,0.0002690841,0.000009308466,0.0002517085,0.00000219801,0.0003455656,0.000007328133],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001333136,"about_ca_system_score_gemma":0.00006856908,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003722931,"about_ca_topic_score_gemma":0.00005107377,"domain_scores_codex":[0.9982263,0.00005456699,0.001004413,0.0001157397,0.000409719,0.0001892577],"domain_scores_gemma":[0.9992025,0.00003904843,0.0001609389,0.00008936155,0.0003855011,0.0001226244],"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":[0.00002409477,0.00002682221,0.002007446,0.0001312642,0.00008659994,0.0001106021,0.001423402,0.9889647,0.00450486,0.00005031922,0.00001251109,0.002657415],"study_design_scores_gemma":[0.0003381829,0.00003145647,0.002014164,0.0004439665,0.00006396903,0.00008354711,0.002362833,0.9900348,0.002833597,0.00000379206,0.00163078,0.0001589293],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6693404,0.003220792,0.3262287,0.000005286937,0.001020054,0.00005706355,0.000002691894,0.00004497308,0.00008001575],"genre_scores_gemma":[0.9980449,0.0006930396,0.0009321371,0.000007421087,0.0002295386,0.000001073646,0.00001359614,0.00003510649,0.0000431735],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3287045,"threshold_uncertainty_score":0.5843764,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02119038587126769,"score_gpt":0.239942421319155,"score_spread":0.2187520354478873,"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."}}