{"id":"W3044811479","doi":"10.1016/j.tre.2020.102022","title":"Modeling train operation as sequences: A study of delay prediction with operation and weather data","year":2020,"lang":"en","type":"article","venue":"Transportation Research Part E Logistics and Transportation Review","topic":"Railway Systems and Energy Efficiency","field":"Engineering","cited_by":99,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Waterloo","funders":"China Scholarship Council; National Natural Science Foundation of China","keywords":"Artificial neural network; Computer science; Sensitivity (control systems); Net (polyhedron); Performance prediction; Predictive modelling; State (computer science); Machine learning; Data mining; Artificial intelligence; Simulation; Engineering; Algorithm; Mathematics","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":[0.0006680443,0.0001696327,0.0003235225,0.00006862035,0.0001357504,0.00004753235,0.0001349349,0.00006212105,0.00004740016],"category_scores_gemma":[0.0000191907,0.0001395578,0.00001808442,0.000292861,0.00007645987,0.0003663333,0.000001872863,0.0001921861,0.000002375528],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000009908633,"about_ca_system_score_gemma":0.00005665245,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000660615,"about_ca_topic_score_gemma":0.002837945,"domain_scores_codex":[0.9981424,0.00009158271,0.0006734169,0.0003956004,0.0005136541,0.0001833144],"domain_scores_gemma":[0.9993466,0.00004107566,0.00005077041,0.0002261087,0.0001919418,0.0001435187],"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":[0.00005897116,0.0001276891,0.002702095,0.004133126,0.0001047629,0.00003050514,0.006015733,0.9797325,0.0003953475,0.002947103,0.0001315215,0.00362066],"study_design_scores_gemma":[0.001189124,0.001110751,0.004606273,0.001105456,0.0002450521,0.00000275622,0.002506074,0.9865538,0.00003440766,0.00004870912,0.002314326,0.0002832563],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8102264,0.0152686,0.1701289,0.0006121662,0.00007260039,0.002610845,0.0006820456,0.0001696652,0.000228798],"genre_scores_gemma":[0.9730927,0.02519018,0.0004073759,0.00006314235,0.00003665875,0.0001052762,0.001072616,0.0000251542,0.000006922698],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1697215,"threshold_uncertainty_score":0.5691003,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1680081681407262,"score_gpt":0.345737131622022,"score_spread":0.1777289634812958,"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."}}