{"id":"W3036908157","doi":"10.1155/2020/6751728","title":"A Gradient Boosting Crash Prediction Approach for Highway-Rail Grade Crossing Crash Analysis","year":2020,"lang":"en","type":"article","venue":"Journal of Advanced Transportation","topic":"Traffic and Road Safety","field":"Engineering","cited_by":41,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Mountain-Plains Consortium; North Dakota State University; U.S. Department of Transportation","keywords":"Crash; Predictive modelling; Gradient boosting; Decision tree; Boosting (machine learning); Popularity; Computer science; Transport engineering; Engineering; Machine learning; Random forest","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001329098,0.0001508336,0.0003276581,0.0001493984,0.0001408279,0.00003953149,0.00009139433,0.00007055524,0.000005109662],"category_scores_gemma":[0.00002187475,0.0001418483,0.0003203202,0.0005124129,0.00002703313,0.0004281526,9.075324e-7,0.0002088761,4.063332e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000608062,"about_ca_system_score_gemma":0.00002749964,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":8.533595e-7,"about_ca_topic_score_gemma":0.000008439108,"domain_scores_codex":[0.9987378,0.00001135152,0.0006672795,0.0001492579,0.0002412332,0.0001931354],"domain_scores_gemma":[0.9993937,0.00004822369,0.0002246164,0.00006505011,0.0001261187,0.0001422613],"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":[0.00007084288,0.00003304898,0.004024901,0.0001448528,0.000337576,0.000005327334,0.003712153,0.9810089,0.005928562,0.00004806623,0.00008307862,0.004602641],"study_design_scores_gemma":[0.003178955,0.0003367456,0.6290574,0.00008759557,0.001892801,0.00000992194,0.001879937,0.3566958,0.002787055,0.0001146894,0.003582142,0.0003769693],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4353892,0.0001775068,0.5638351,0.00008334949,0.0002112315,0.0001212618,0.00004671174,0.0001037055,0.00003192441],"genre_scores_gemma":[0.9374605,0.0000708039,0.06200344,0.00003174285,0.0002660252,0.000007581844,0.0001263178,0.00002784679,0.0000057431],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6250325,"threshold_uncertainty_score":0.5784405,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01445955858893554,"score_gpt":0.224978628993014,"score_spread":0.2105190704040784,"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."}}