{"id":"W4407120710","doi":"10.1016/j.eswa.2025.126667","title":"Graph-enhanced anomaly detection framework in multivariate time series using Graph Attention and Enhanced Generative Adversarial Networks","year":2025,"lang":"en","type":"article","venue":"Expert Systems with Applications","topic":"Anomaly Detection Techniques and Applications","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":false,"ca_institutions":"McGill University; Université de Montréal","funders":"Key Science and Technology Program of Shaanxi Province; National Key Research and Development Program of China; National Natural Science Foundation of China; Department of Science and Technology of Sichuan Province; Organization Department of Sichuan Provincial Party Committee; Ministry of Science and Technology of the People's Republic of China","keywords":"Computer science; Multivariate statistics; Graph; Anomaly detection; Adversarial system; Generative grammar; Series (stratigraphy); Generative adversarial network; Anomaly (physics); Time series; Theoretical computer science; Artificial intelligence; Machine learning; Image (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":[0.0001729696,0.0002310296,0.000270256,0.0003275788,0.0005513201,0.0002068677,0.000305409,0.0001978261,0.000002748711],"category_scores_gemma":[0.000009502674,0.0002187065,0.00005503532,0.001755916,0.0001041573,0.0005034166,0.00009789698,0.0002122055,0.000004928928],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001176731,"about_ca_system_score_gemma":0.00005355074,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004641654,"about_ca_topic_score_gemma":0.00007916474,"domain_scores_codex":[0.9983984,0.0001070027,0.0004176502,0.0006702546,0.0001426376,0.0002640024],"domain_scores_gemma":[0.9988657,0.00008220887,0.0002248028,0.0005952836,0.0001599994,0.00007204664],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001867025,0.0003936688,0.0004110178,0.00008275308,0.0002289111,0.000002391805,0.001933569,0.02736847,0.6993289,0.2451558,0.0001500362,0.0247578],"study_design_scores_gemma":[0.002213314,0.0003949731,0.005931444,0.0007728092,0.00007750151,0.00005692564,0.001166478,0.8086501,0.1590998,0.01602334,0.003984843,0.001628447],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.009560843,0.0003443387,0.9873996,0.0001443861,0.0001458888,0.001637971,0.000003798688,0.0003707267,0.0003924182],"genre_scores_gemma":[0.8912129,0.00006503484,0.104764,0.00006640577,0.0001219817,0.003516192,0.000007719247,0.00001535813,0.0002303731],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8826357,"threshold_uncertainty_score":0.8918594,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.006834604503249495,"score_gpt":0.2524976791206107,"score_spread":0.2456630746173612,"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."}}