{"id":"W4381852594","doi":"10.1016/j.neucom.2023.126483","title":"MDGAD: Meta domain generalization for distribution drift in anomaly detection","year":2023,"lang":"en","type":"article","venue":"Neurocomputing","topic":"Anomaly Detection Techniques and Applications","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":false,"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Anomaly detection; Computer science; Generalization; Artificial intelligence; Concept drift; Merge (version control); Pattern recognition (psychology); Robustness (evolution); Data mining; Test set; Metric (unit); Machine learning; Mathematics; Data stream mining","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":[0.003673977,0.001116493,0.001415569,0.001761267,0.0006217174,0.00114762,0.002228461,0.001301581,0.002990211],"category_scores_gemma":[0.007630264,0.0005884141,0.001805788,0.001088124,0.0005981193,0.001862263,0.002907551,0.003258964,0.001047524],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008111943,"about_ca_system_score_gemma":0.001601216,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003816605,"about_ca_topic_score_gemma":0.004267258,"domain_scores_codex":[0.9988738,0.0003710077,0.00009434983,0.0002794704,0.0002769874,0.0001044804],"domain_scores_gemma":[0.9979672,0.0007884629,0.0001252481,0.0006287628,0.0004004007,0.00008986497],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0004276367,0.000275807,0.005487389,0.0002103873,0.0003941836,0.0002173856,0.0001762727,0.4122652,0.006928108,0.01693834,0.01764457,0.5390348],"study_design_scores_gemma":[0.00001659867,0.00003340643,0.0002372061,0.00001169882,0.00001818264,0.00004785638,0.0000179099,0.9867764,0.001511099,0.009690405,0.001631801,0.00000748841],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.008692159,0.0002458254,0.9848593,0.0002052055,0.0001024293,0.00006433002,0.0003635865,0.004993361,0.0004737361],"genre_scores_gemma":[0.2597899,0.0002896128,0.7340816,0.0003422482,0.0001061011,0.0002840441,0.001992197,0.0009680857,0.002146107],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003816605,"threshold_uncertainty_score":0.01943004,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02926753523049013,"score_gpt":0.2756240665815084,"score_spread":0.2463565313510183,"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."}}