{"id":"W4394987665","doi":"10.1016/j.asoc.2024.111640","title":"Railway network delay evolution: A heterogeneous graph neural network approach","year":2024,"lang":"en","type":"article","venue":"Applied Soft Computing","topic":"Railway Systems and Energy Efficiency","field":"Engineering","cited_by":20,"is_retracted":false,"has_abstract":false,"ca_institutions":"Canadian Pacific Railway (Canada)","funders":"","keywords":"Train; Computer science; Scalability; Robustness (evolution); Artificial neural network; Graph; Network architecture; Distributed computing; Artificial intelligence; Theoretical computer science; Computer network","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":[0.0007828149,0.0005677987,0.0007297237,0.001006908,0.0003855851,0.0010195,0.001769017,0.00135732,0.002588553],"category_scores_gemma":[0.00336833,0.0005242562,0.0007346699,0.001177151,0.0005770001,0.001620246,0.0008796255,0.001098258,0.0002372405],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001343885,"about_ca_system_score_gemma":0.0007261404,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01666273,"about_ca_topic_score_gemma":0.01262009,"domain_scores_codex":[0.9997566,0.0000698037,0.0000104301,0.00007797204,0.00004715022,0.00003789982],"domain_scores_gemma":[0.9988707,0.0007050975,0.0001175416,0.00007629432,0.0001775148,0.00005281604],"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":[0.00001289077,0.00001294706,0.0002373616,0.000009280932,0.00001749723,0.0000165941,0.00001031699,0.9872802,0.0002284403,0.005402275,0.0001873375,0.006584925],"study_design_scores_gemma":[5.96735e-7,0.00000121056,0.00002295628,5.102986e-7,0.000002097266,0.000001099621,9.915149e-7,0.9989059,0.00003048958,0.0009996857,0.00003363841,7.865056e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05897989,0.0003645722,0.9345014,0.0004571959,0.00009248867,0.00003603909,0.0001680869,0.0002696529,0.005130616],"genre_scores_gemma":[0.9226285,0.0003501166,0.0680973,0.0001444749,0.00009711109,0.00006531977,0.000243255,0.0001489483,0.008224959],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01666273,"threshold_uncertainty_score":0.03313154,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.007382969826896788,"score_gpt":0.1888585971402182,"score_spread":0.1814756273133214,"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."}}