{"id":"W2757054860","doi":"10.1109/ictis.2017.8047758","title":"Data-driven models for predicting delay recovery in high-speed rail","year":2017,"lang":"en","type":"article","venue":"","topic":"Railway Systems and Energy Efficiency","field":"Engineering","cited_by":15,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Dwell time; Reliability (semiconductor); Computer science; Predictive modelling; Linear regression; Random forest; Mean squared prediction error; Regression analysis; Regression; Performance prediction; Simulation; Statistics; Artificial intelligence; Machine learning; 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":[0.0002670095,0.0001151308,0.0001826889,0.00005815241,0.0001302291,0.0001136121,0.0005930318,0.00008200583,0.00001471187],"category_scores_gemma":[0.0000593917,0.0001042259,0.00003152662,0.00003137348,0.00001469602,0.0007267037,0.0001041459,0.0000721808,0.000009541069],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003918595,"about_ca_system_score_gemma":0.00001466871,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0008505844,"about_ca_topic_score_gemma":0.001127574,"domain_scores_codex":[0.9991558,0.000006609826,0.0002483377,0.000227797,0.00009428304,0.0002672339],"domain_scores_gemma":[0.9989534,0.00004689599,0.0000444685,0.0008862923,0.00002047915,0.00004846452],"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":[0.000005158579,0.000008719892,0.00033888,0.00003436762,0.00001665862,0.000002745276,0.00005923114,0.9921694,0.0003060729,0.001317677,0.002212633,0.003528504],"study_design_scores_gemma":[0.0004231628,0.00001778574,0.0005873385,0.00004216028,0.000005100319,0.000002112687,0.00003180176,0.9956631,0.0001042996,0.0003327636,0.002653017,0.000137351],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7647029,0.0001533883,0.1761266,0.00009346876,0.001751363,0.0003455604,0.0001719374,0.0003862325,0.05626853],"genre_scores_gemma":[0.9939765,0.00003077844,0.0045677,0.00001076019,0.0002033996,0.00001662902,0.00004746878,0.00003169475,0.001115108],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2292736,"threshold_uncertainty_score":0.4250209,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04137534783214578,"score_gpt":0.2489844947484076,"score_spread":0.2076091469162618,"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."}}