{"id":"W4226182767","doi":"10.1177/03611981221085561","title":"Using Delay Logs and Machine Learning to Support Passenger Railway Operations","year":2022,"lang":"en","type":"article","venue":"Transportation Research Record Journal of the Transportation Research Board","topic":"Railway Systems and Energy Efficiency","field":"Engineering","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Train; Computer science; Leverage (statistics); Data science; Machine learning; Data mining","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["sts","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.004236926,0.0002163325,0.0003645003,0.001085595,0.001430063,0.0001437796,0.0006538581,0.00008791583,0.0006139078],"category_scores_gemma":[0.00007060594,0.0001811923,0.0001910213,0.00202011,0.0001799003,0.0004005125,0.00001564832,0.002362652,0.000009532349],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003111399,"about_ca_system_score_gemma":0.0003059752,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.006891703,"about_ca_topic_score_gemma":0.02042891,"domain_scores_codex":[0.9943942,0.00092231,0.00105102,0.0003091958,0.002565212,0.000758008],"domain_scores_gemma":[0.9978479,0.0003281016,0.0001043525,0.0002900883,0.001023194,0.0004063997],"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":[0.0002086899,0.00008657495,0.0336217,0.0001157653,0.00009951691,0.000128115,0.004768461,0.9374304,0.01664625,0.0007995016,0.00185304,0.004241995],"study_design_scores_gemma":[0.004606783,0.004294947,0.4706491,0.0004202213,0.0001744843,0.00003810874,0.01702798,0.1773483,0.004183912,0.0007086076,0.3192286,0.001318912],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9909197,0.0003431749,0.006457743,0.0007644772,0.0006135738,0.0005892154,0.00007149349,0.00004998611,0.0001906118],"genre_scores_gemma":[0.9963955,0.0003227168,0.002131407,0.00003434853,0.0001273107,0.00009037083,0.00002079612,0.00007362792,0.000803941],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7600821,"threshold_uncertainty_score":0.999939,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09183245065545798,"score_gpt":0.3474221614683148,"score_spread":0.2555897108128568,"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."}}