{"id":"W4410887344","doi":"10.1109/syscon64521.2025.11014854","title":"Calibrated Unsupervised Anomaly Detection in Multivariate Time-Series Using Reinforcement Learning","year":2025,"lang":"en","type":"article","venue":"","topic":"Anomaly Detection Techniques and Applications","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"Concordia University","funders":"","keywords":"Anomaly detection; Multivariate statistics; Series (stratigraphy); Reinforcement learning; Computer science; Artificial intelligence; Unsupervised learning; Anomaly (physics); Time series; Pattern recognition (psychology); Machine learning; Geology; 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":[0.0001433954,0.00009717156,0.0001056829,0.0002321467,0.0001812116,0.0001071275,0.000234424,0.00006533664,0.00004035037],"category_scores_gemma":[0.0000165792,0.00009545984,0.00003478639,0.00103697,0.00001941315,0.0004751004,0.0001478175,0.0001253299,0.00002000268],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008937973,"about_ca_system_score_gemma":0.00004891447,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0008375509,"about_ca_topic_score_gemma":0.00004431483,"domain_scores_codex":[0.999215,0.00004897549,0.0002422135,0.0002550239,0.00007584727,0.0001629426],"domain_scores_gemma":[0.9996123,0.00002433668,0.00005151738,0.000237709,0.000048461,0.00002563105],"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":[0.00005402836,0.0001239459,0.003219558,0.00003789394,0.00004551096,0.000007260351,0.000460228,0.06478272,0.7467771,0.1000605,0.00009021166,0.08434101],"study_design_scores_gemma":[0.0001693429,0.00003747005,0.001516126,0.00001426917,0.000002415714,0.000002075328,0.00002337778,0.825546,0.1696893,0.0006414764,0.002259234,0.00009895255],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04077335,0.000008124194,0.9526612,0.0001739991,0.00003985961,0.0002096008,1.035724e-7,0.000508466,0.005625277],"genre_scores_gemma":[0.9438946,0.000003785036,0.05205285,0.0001538561,0.00000802159,0.00004283464,0.000001069197,0.000005062391,0.003837929],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9031212,"threshold_uncertainty_score":0.3892739,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01149448844109937,"score_gpt":0.2539032243105276,"score_spread":0.2424087358694282,"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."}}