{"id":"W2224576170","doi":"10.3141/2514-15","title":"Predicting Driver Injury Severity in Single-Vehicle and Two-Vehicle Crashes with Boosted Regression Trees","year":2015,"lang":"en","type":"article","venue":"Transportation Research Record Journal of the Transportation Research Board","topic":"Traffic and Road Safety","field":"Engineering","cited_by":36,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Windsor","funders":"","keywords":"Regression analysis; Truck; Logistic regression; Statistics; Random forest; Poison control; Regression; Nonparametric regression; Linear regression; Computer science; Engineering; Mathematics; Medicine; Machine learning; Environmental health; Automotive engineering","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":[0.00264016,0.0002409558,0.000395134,0.000683246,0.0002767084,0.00007652538,0.0004716224,0.0001637299,0.00003772918],"category_scores_gemma":[0.00008703348,0.0001653031,0.0001103198,0.001516972,0.0004765328,0.000807368,0.000007618174,0.001916417,0.000004826197],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002615759,"about_ca_system_score_gemma":0.0002785065,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004101938,"about_ca_topic_score_gemma":0.09067798,"domain_scores_codex":[0.9951544,0.0006273686,0.0009057792,0.0003060545,0.002295689,0.0007107314],"domain_scores_gemma":[0.9973929,0.0004420693,0.0001639445,0.0002878156,0.001258452,0.0004548483],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.001865843,0.0001719423,0.9546873,0.0001543349,0.00007931936,0.0001420678,0.00536702,0.01681382,0.00524627,0.00008940199,0.001316566,0.01406611],"study_design_scores_gemma":[0.002708968,0.0006451699,0.9845624,0.0006496132,0.00002582504,0.000001409223,0.002875638,0.004228995,0.002228529,0.0004425177,0.001436159,0.0001948052],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9972665,0.0004555324,0.0003572216,0.000861863,0.0002152942,0.0005495786,0.00003292868,0.00007323273,0.0001878305],"genre_scores_gemma":[0.9982458,0.0005909729,0.0008350919,0.00001246968,0.0001095081,0.00002512377,0.000008894064,0.00005722329,0.0001149571],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.08657604,"threshold_uncertainty_score":0.9259148,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05870362311760013,"score_gpt":0.3267391622410502,"score_spread":0.2680355391234501,"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."}}