{"id":"W2994808218","doi":"10.1002/for.2639","title":"A predictive model of train delays on a railway line","year":2019,"lang":"en","type":"article","venue":"Journal of Forecasting","topic":"Railway Systems and Energy Efficiency","field":"Engineering","cited_by":67,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"Department of Science and Technology of Sichuan Province; China Scholarship Council","keywords":"Computer science; Artificial neural network; Python (programming language); Random forest; Predictive modelling; Artificial intelligence; Machine learning","routes":{"ca_aff":true,"ca_fund":false,"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":[0.0004150551,0.0001088807,0.0002835632,0.0001603961,0.00001853662,0.000009410122,0.0001265423,0.00006142945,0.00001502718],"category_scores_gemma":[0.00006706815,0.00008609586,0.0001299501,0.0001300062,0.00001202495,0.0001204251,0.000009342201,0.0002097874,0.000003323034],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005079971,"about_ca_system_score_gemma":0.00003335389,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000004319441,"about_ca_topic_score_gemma":0.0000023711,"domain_scores_codex":[0.9989864,0.00001319703,0.0005183666,0.00006659755,0.0002436683,0.000171738],"domain_scores_gemma":[0.9994295,0.00007667595,0.0002259503,0.00009492147,0.0001085218,0.00006437684],"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":[0.00003484326,0.00002216772,0.0001015567,0.00006558938,0.00004124928,0.000005186916,0.0007772128,0.9788641,0.01274553,0.0001125252,0.0001025254,0.007127503],"study_design_scores_gemma":[0.0004555056,0.0004865551,0.00006160069,0.0004084885,0.00001326315,0.00006566342,0.0002004426,0.9949042,0.003143899,0.0001062479,0.00007511489,0.00007899907],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9415874,0.0001583455,0.04605033,0.00001236129,0.0003876247,0.00005911412,0.000006666842,0.00001934366,0.01171875],"genre_scores_gemma":[0.997615,0.0000101824,0.002047075,0.000008301729,0.0001763439,9.454014e-7,3.818803e-7,0.00002273114,0.0001189783],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.05602759,"threshold_uncertainty_score":0.3510887,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02369394031512286,"score_gpt":0.201390566858223,"score_spread":0.1776966265431001,"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."}}