{"id":"W3206238941","doi":"10.1080/19439962.2021.1988787","title":"An integrated clustering and Bayesian approach to investigate the severity of pedestrian collisions at highway-railway grade crossings collisions","year":2021,"lang":"en","type":"article","venue":"Journal of Transportation Safety & Security","topic":"Traffic and Road Safety","field":"Engineering","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"McMaster University","funders":"","keywords":"Collision; Pedestrian; Cluster analysis; Transport engineering; Bayesian probability; Warning system; Computer science; Bayes' theorem; Engineering; Computer security; Machine learning; Artificial intelligence","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":[],"consensus_categories":[],"category_scores_codex":[0.00057625,0.0002251968,0.0004523952,0.0001070145,0.0003456497,0.00006153496,0.000229872,0.0001497043,0.00002339361],"category_scores_gemma":[0.00003892211,0.0001718809,0.0001658402,0.0006287287,0.0001550039,0.0003557128,0.00001264183,0.0004637689,7.095813e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001126533,"about_ca_system_score_gemma":0.0002056253,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000730266,"about_ca_topic_score_gemma":0.001236338,"domain_scores_codex":[0.9980672,0.0001256035,0.0009655018,0.00020602,0.0003823918,0.0002533069],"domain_scores_gemma":[0.9986863,0.0001195256,0.0002339902,0.0002495515,0.0003175632,0.000393135],"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":[0.001167485,0.001016349,0.05284265,0.0009497219,0.0006574701,0.0001931507,0.09398814,0.8202001,0.01867041,0.001766022,0.002101711,0.006446743],"study_design_scores_gemma":[0.002670517,0.0002157888,0.8868629,0.0004237099,0.0003483902,0.0003049017,0.005859173,0.06955025,0.008545415,0.000352918,0.02426563,0.0006004588],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.945569,0.0003195278,0.05225908,0.0007080408,0.0002967336,0.0002054729,0.0004244592,0.00006165348,0.0001559883],"genre_scores_gemma":[0.9901887,0.0003289516,0.009180843,0.00008610627,0.00006266083,0.000003446728,0.0001014609,0.00002916661,0.00001866601],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8340202,"threshold_uncertainty_score":0.7009101,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01279833608239226,"score_gpt":0.2358621519857231,"score_spread":0.2230638159033309,"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."}}