{"id":"W4416396695","doi":"10.1016/j.cor.2025.107330","title":"International travel time prediction for China–Europe Express trains via interpretable deep learning models","year":2025,"lang":"en","type":"article","venue":"Computers & Operations Research","topic":"Railway Systems and Energy Efficiency","field":"Engineering","cited_by":4,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Alberta","funders":"National Natural Science Foundation of China; China Railway","keywords":"Interpretability; Train; Deep learning; Mechanism (biology); Dual (grammatical number); Process (computing); Transfer of 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003772396,0.0006553852,0.0003020533,0.0009900989,0.0002827904,0.0006192579,0.0005479018,0.0005158082,0.002322318],"category_scores_gemma":[0.0008925641,0.0002552426,0.0005853681,0.0009685133,0.0001902284,0.0007312322,0.0004674223,0.0009103635,0.0007386263],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00109661,"about_ca_system_score_gemma":0.001016708,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.1008891,"about_ca_topic_score_gemma":0.08325119,"domain_scores_codex":[0.9998891,0.00001229166,0.000004508372,0.00003815247,0.00001429569,0.00004153891],"domain_scores_gemma":[0.9997339,0.00006571224,0.00003329134,0.00002357238,0.0000994661,0.00004407161],"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":[0.0003754838,0.0002119924,0.04587444,0.00003614743,0.0001189368,0.0001116411,0.00005687776,0.8836142,0.001256979,0.00169964,0.007450678,0.05919295],"study_design_scores_gemma":[0.000003495989,0.00000725964,0.003596438,0.000002543357,0.00001082848,0.000002681693,0.0000141052,0.995565,0.0002560537,0.0002813308,0.0002561299,0.000004075895],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9604934,0.0003553155,0.03136638,0.00044425,0.000151693,0.00001499156,0.002312162,0.0006358206,0.004225927],"genre_scores_gemma":[0.9922989,0.00005931759,0.002126836,0.0000197516,0.00001784267,0.000007798581,0.002394555,0.000032829,0.003042067],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1008891,"threshold_uncertainty_score":0.2006038,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02463949121770068,"score_gpt":0.2829072155601878,"score_spread":0.2582677243424871,"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."}}