{"id":"W597590429","doi":"10.1016/j.ssci.2012.11.001","title":"A clustering regression approach: A comprehensive injury severity analysis of pedestrian–vehicle crashes in New York, US and Montreal, Canada","year":2012,"lang":"en","type":"article","venue":"Safety Science","topic":"Traffic and Road Safety","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"McGill University; Polytechnique Montréal","funders":"","keywords":"Pedestrian; Cluster analysis; Multinomial logistic regression; Probit model; Logistic regression; Computer science; Regression analysis; Statistics; Geography; Artificial intelligence; Transport engineering; Machine learning; Engineering; Mathematics","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":[0.0002513987,0.0001322619,0.000287413,0.0002004457,0.00009810841,0.00001393632,0.0001963183,0.00004786062,0.000008145334],"category_scores_gemma":[0.00002123499,0.0001130038,0.00003611316,0.001581774,0.000151661,0.0002662865,0.00009256152,0.0001279586,4.316676e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001601479,"about_ca_system_score_gemma":0.0002684191,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.2856193,"about_ca_topic_score_gemma":0.3383297,"domain_scores_codex":[0.9988292,0.00002508411,0.0002522515,0.0002053053,0.0002866289,0.0004014983],"domain_scores_gemma":[0.9994177,0.00005301186,0.00004891162,0.0002193338,0.00002624241,0.0002348515],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0001281517,0.00007624772,0.5927235,0.0001644809,0.0001385495,0.000004828713,0.004932088,0.2956133,0.004911511,0.00004364468,0.000581299,0.1006823],"study_design_scores_gemma":[0.0001556217,0.000006322928,0.7772149,0.00002255008,0.00003413045,0.000001875606,0.0003771429,0.2215893,0.0001326056,0.000002600685,0.0003534369,0.0001094926],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9953967,0.0009861782,0.001729929,0.00003797518,0.0001490939,0.0001083671,0.00002364432,0.00004116035,0.001526934],"genre_scores_gemma":[0.998719,0.0001197619,0.001076738,0.00002299608,0.00002492164,0.000001463624,0.000003635312,0.000006777148,0.00002474704],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1844914,"threshold_uncertainty_score":0.7191378,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01790277552262916,"score_gpt":0.2236960986430048,"score_spread":0.2057933231203756,"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."}}