{"id":"W4319835984","doi":"10.1080/19439962.2022.2164636","title":"Investigating the application of deep learning to identify pedestrian collision-prone zones","year":2023,"lang":"en","type":"article","venue":"Journal of Transportation Safety & Security","topic":"Traffic and Road Safety","field":"Engineering","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"McMaster University","funders":"Ministère des Transports","keywords":"Collision; Pedestrian; Intersection (aeronautics); Computer science; Bayes' theorem; Consistency (knowledge bases); Simulation; Artificial intelligence; Transport engineering; Bayesian probability; Engineering; Computer security","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":[0.0008738547,0.0001204602,0.0002496506,0.0001443689,0.0001469167,0.00001568888,0.0002038445,0.00007671721,0.00001319045],"category_scores_gemma":[0.00006255353,0.00009513725,0.0001367812,0.0007869524,0.00003925335,0.0001942297,0.000004712943,0.0003541515,0.00001512138],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003877695,"about_ca_system_score_gemma":0.00003355151,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002308778,"about_ca_topic_score_gemma":0.0001798877,"domain_scores_codex":[0.9984294,0.00005502336,0.0008472408,0.00009987396,0.0004066263,0.0001618557],"domain_scores_gemma":[0.9991037,0.0001747242,0.0002909956,0.0001219798,0.0001979696,0.0001106794],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"observational","study_design_scores_codex":[0.00005143293,0.00002503801,0.01019596,0.0001823496,0.00007747493,0.000005662568,0.01448973,0.9538692,0.00359429,0.0007039228,0.0001990844,0.01660588],"study_design_scores_gemma":[0.000688033,0.00008544223,0.9466171,0.0001305874,0.0001015689,0.00000889253,0.004231537,0.0382232,0.001510448,0.0008377089,0.007378137,0.0001873584],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.931075,0.0002025306,0.06737785,0.0006256465,0.0002761225,0.000217421,0.00002446009,0.0001094874,0.0000914453],"genre_scores_gemma":[0.9983763,0.0002918093,0.001113764,0.00002126974,0.0001197546,0.00000610167,0.00004167749,0.00002164338,0.000007725374],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9364211,"threshold_uncertainty_score":0.3879584,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01108033724322895,"score_gpt":0.2661065304117509,"score_spread":0.255026193168522,"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."}}