{"id":"W2208980899","doi":"10.1002/atr.1358","title":"A random forests approach to prioritize Highway Safety Manual (HSM) variables for data collection","year":2015,"lang":"en","type":"article","venue":"Journal of Advanced Transportation","topic":"Traffic and Road Safety","field":"Engineering","cited_by":21,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Variables; Transport engineering; Data collection; Crash; Ranking (information retrieval); Variable (mathematics); Calibration; Cluster analysis; Range (aeronautics); Computer science; Random forest; Statistics; Engineering; Mathematics; Machine learning","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01689673,0.00177596,0.002083171,0.005442733,0.001366028,0.001658907,0.002754066,0.001087061,0.003361198],"category_scores_gemma":[0.02523916,0.001057692,0.003010096,0.0042039,0.0005398206,0.001352362,0.001187214,0.002238705,0.001169238],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001369941,"about_ca_system_score_gemma":0.004027484,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01858387,"about_ca_topic_score_gemma":0.02943616,"domain_scores_codex":[0.9908102,0.005272214,0.0007876494,0.001599011,0.001089222,0.0004416522],"domain_scores_gemma":[0.9838198,0.010824,0.0009952012,0.0006932835,0.003316766,0.0003508256],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0008758607,0.001088726,0.05640873,0.001598876,0.0009088189,0.0009882202,0.001139859,0.2856443,0.005845042,0.008693204,0.03440613,0.6024023],"study_design_scores_gemma":[0.0002036922,0.0003370297,0.01019854,0.0002243578,0.0002085463,0.0001405343,0.0006392611,0.9603048,0.002537931,0.01670026,0.008430297,0.00007476185],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.04482674,0.0004746451,0.9425993,0.0006528667,0.0001179091,0.002471144,0.004780535,0.002469181,0.001607668],"genre_scores_gemma":[0.1500097,0.0001625214,0.8386974,0.0002095567,0.0001207987,0.002472941,0.007385226,0.0001530669,0.0007887628],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01858387,"threshold_uncertainty_score":0.08935946,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02212598329849988,"score_gpt":0.2587086115496983,"score_spread":0.2365826282511984,"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."}}