{"id":"W4411586097","doi":"10.1016/j.jrtpm.2025.100532","title":"Analysis of freight train passing a stop signal using machine learning: Application of XGBoost and SHAP","year":2025,"lang":"en","type":"article","venue":"Journal of Rail Transport Planning & Management","topic":"Railway Engineering and Dynamics","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Alberta; Canadian Pacific Railway (Canada)","funders":"Natural Sciences and Engineering Research Council of Canada; Alberta Innovates; Transport Canada","keywords":"Transport engineering; Computer science; Train; SIGNAL (programming language); Rail freight transport; Engineering; Automotive engineering; Real-time computing; Geography","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0003962571,0.0001536223,0.0004769441,0.0009556033,0.00003834851,0.00001177652,0.0001314995,0.00005899986,0.000008069651],"category_scores_gemma":[0.000003303975,0.0001529801,0.0001683219,0.0006931282,0.00003149397,0.00009093481,0.000009083496,0.0002212626,5.428243e-8],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005017136,"about_ca_system_score_gemma":0.00001067525,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001918448,"about_ca_topic_score_gemma":0.000005475617,"domain_scores_codex":[0.9988353,0.00001242247,0.0006584204,0.0001138076,0.0002322169,0.0001477857],"domain_scores_gemma":[0.9995199,0.00004390663,0.0002220296,0.0001105126,0.00005394041,0.00004972612],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00003381341,0.00002848408,0.04818761,0.0004409303,0.001694949,0.00002449895,0.0004546884,0.9388478,0.003654792,0.0002843798,0.000004195339,0.006343814],"study_design_scores_gemma":[0.0004555955,0.00003511856,0.1065961,0.0002969916,0.001751484,0.000004900284,0.0001912985,0.8896026,0.0002803722,0.00005025816,0.0006162958,0.0001189749],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4512456,0.0008555395,0.5473244,0.00001406254,0.00004856901,0.00006027472,0.00001161373,0.00002407182,0.0004158549],"genre_scores_gemma":[0.9880803,0.0001107306,0.01168823,0.000005645745,0.00001610938,0.000001513597,0.00002093124,0.00001657065,0.00005992516],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.5368348,"threshold_uncertainty_score":0.6238347,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.00800928111972635,"score_gpt":0.2242007164316662,"score_spread":0.2161914353119399,"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."}}