{"id":"W2084938070","doi":"10.3141/2279-07","title":"Use of Computer Vision to Identify Pedestrians' Nonconforming Behavior at Urban Intersections","year":2012,"lang":"en","type":"article","venue":"Transportation Research Record Journal of the Transportation Research Board","topic":"Traffic and Road Safety","field":"Engineering","cited_by":24,"is_retracted":false,"has_abstract":true,"ca_institutions":"Carleton University; University of British Columbia","funders":"","keywords":"Intersection (aeronautics); Pedestrian; Computer science; Identification (biology); Downtown; Pedestrian crossing; Transport engineering; Computer security; Artificial intelligence; Engineering; Geography","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002282531,0.0002202159,0.0003937944,0.001270062,0.0003839718,0.00007752314,0.0006287569,0.0001615501,0.0002239803],"category_scores_gemma":[0.00006151923,0.0001753056,0.0003502698,0.001809655,0.0001927712,0.0009797362,0.00001363583,0.001243782,0.00006359183],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003678054,"about_ca_system_score_gemma":0.0001333021,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001949329,"about_ca_topic_score_gemma":0.01319363,"domain_scores_codex":[0.9950863,0.0003510582,0.001291986,0.0002196512,0.002188653,0.0008624041],"domain_scores_gemma":[0.9966212,0.000572561,0.0001646523,0.0003941046,0.001520667,0.000726839],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.001991117,0.0006183957,0.7784258,0.0004626799,0.0003166004,0.00007313801,0.02169929,0.06507917,0.04649488,0.0006438312,0.05221955,0.03197554],"study_design_scores_gemma":[0.0005377525,0.0005222394,0.9702542,0.0003279538,0.0000548847,0.000001541878,0.0007735633,0.0002884465,0.003583813,0.00001123426,0.02346968,0.0001746672],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9854903,0.00006269635,0.01137204,0.0004768369,0.0013904,0.001011669,0.00009300925,0.00004809959,0.00005495358],"genre_scores_gemma":[0.9943513,0.0001470076,0.004684083,0.00002559773,0.0003038691,0.00005910995,0.00001552782,0.00006084415,0.0003526355],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1918284,"threshold_uncertainty_score":0.7362356,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1034091569817617,"score_gpt":0.3916977104503231,"score_spread":0.2882885534685614,"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."}}