{"id":"W2007500067","doi":"10.3141/2198-07","title":"Automated Analysis of Pedestrian–Vehicle Conflicts","year":2010,"lang":"en","type":"article","venue":"Transportation Research Record Journal of the Transportation Research Board","topic":"Traffic and Road Safety","field":"Engineering","cited_by":171,"is_retracted":false,"has_abstract":true,"ca_institutions":"Polytechnique Montréal; Carleton University; University of British Columbia","funders":"University of British Columbia","keywords":"Pedestrian; Collision; Conflict analysis; Computer science; Transport engineering; Chinatown; Quality (philosophy); Traffic conflict; Computer security; Data science; Engineering; Conflict resolution; Geography; Floating car data; Traffic congestion","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004143011,0.0003287973,0.0004393566,0.002310694,0.0003898277,0.0004785905,0.0005594013,0.0001967403,0.001199517],"category_scores_gemma":[0.001691105,0.0001472466,0.0002104658,0.0006939711,0.0002009064,0.0004400367,0.0005825815,0.0002446281,0.0002719663],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003681421,"about_ca_system_score_gemma":0.0005404024,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004560099,"about_ca_topic_score_gemma":0.005539965,"domain_scores_codex":[0.9993716,0.0001707255,0.00002541505,0.0001090386,0.0002682462,0.00005505049],"domain_scores_gemma":[0.9984474,0.0004721587,0.000246903,0.0001877544,0.0005792559,0.00006665887],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.000771534,0.0003246382,0.05087998,0.0002329341,0.0001213668,0.0003580716,0.0008920144,0.0302269,0.1200051,0.002726757,0.003546241,0.7899145],"study_design_scores_gemma":[0.00007923762,0.0006760953,0.1580024,0.00004692055,0.0001048614,0.0008225641,0.001122007,0.7174386,0.1069388,0.004293303,0.01032453,0.0001506501],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5146798,0.0003170836,0.4751465,0.00009838214,0.00005927906,0.0002588133,0.001044625,0.002112009,0.006283503],"genre_scores_gemma":[0.8488189,0.0001030365,0.148888,0.0000272917,0.00002810148,0.00009802976,0.0007255209,0.00006236751,0.001248796],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.004560099,"threshold_uncertainty_score":0.009067118,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05315668651212617,"score_gpt":0.3565698316706756,"score_spread":0.3034131451585494,"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."}}