{"id":"W4410294529","doi":"10.1109/tase.2025.3569178","title":"Network-Based Rail Running Band Anomaly Recognition via Recurrent Attention Graphs","year":2025,"lang":"en","type":"article","venue":"IEEE Transactions on Automation Science and Engineering","topic":"Railway Systems and Energy Efficiency","field":"Engineering","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"Natural Science Foundation of Hunan Province; China Scholarship Council; Natural Science Foundation of Hainan Province; National Natural Science Foundation of China","keywords":"Computer science; Anomaly detection; Anomaly (physics); Artificial intelligence; Computer network; Pattern recognition (psychology); Physics","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":[0.0004828917,0.0001635657,0.0001389245,0.0006045571,0.0003280887,0.0001346746,0.0001038416,0.00006987964,0.00001469562],"category_scores_gemma":[0.000007249369,0.0001724294,0.00004789127,0.001494044,0.00005663734,0.0004433909,7.822572e-7,0.0001469523,0.00001318794],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001270377,"about_ca_system_score_gemma":0.00004053909,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001389918,"about_ca_topic_score_gemma":0.000007711526,"domain_scores_codex":[0.9988852,0.000009076328,0.0002791616,0.0002475841,0.000274967,0.00030403],"domain_scores_gemma":[0.9996054,0.00003839716,0.00002857394,0.0001513242,0.00009720819,0.00007911099],"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":[0.000003423521,0.00001429334,0.00001949401,0.00006023946,0.000008511214,5.04506e-7,0.00004377515,0.8937362,0.02360943,0.00004968601,0.00003737664,0.08241705],"study_design_scores_gemma":[0.0002522211,0.00003381856,0.003160472,0.000253808,0.00001720606,0.000003603567,0.00001902711,0.9853125,0.01042578,0.0000446216,0.0002894281,0.0001875628],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2921683,0.00009035317,0.7051343,0.000038543,0.001493704,0.0001137996,0.000002425137,0.000386243,0.0005723289],"genre_scores_gemma":[0.9980324,0.0000271017,0.001778959,0.00003193701,0.00002645802,0.00005701399,0.000002915105,0.00001363124,0.00002961984],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7058641,"threshold_uncertainty_score":0.7031465,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.009738982533731743,"score_gpt":0.2078807480474237,"score_spread":0.198141765513692,"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."}}