{"id":"W3184338320","doi":"10.1109/tnsm.2021.3098784","title":"TSAGen: Synthetic Time Series Generation for KPI Anomaly Detection","year":2021,"lang":"en","type":"article","venue":"IEEE Transactions on Network and Service Management","topic":"Anomaly Detection Techniques and Applications","field":"Computer Science","cited_by":38,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Victoria","funders":"National Key Research and Development Program of China; National Natural Science Foundation of China","keywords":"Anomaly detection; Computer science; Data mining; Performance indicator; Time series; Anomaly (physics); Series (stratigraphy); Overhead (engineering); Machine learning","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":[0.0001399714,0.0001427387,0.0001218899,0.0000699951,0.000593599,0.0001766091,0.0001652315,0.00006348445,0.00003077941],"category_scores_gemma":[3.885442e-7,0.0001535371,0.0000712473,0.0005419856,0.0000137625,0.0002408963,0.00000795907,0.00007761056,0.00003119462],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003681813,"about_ca_system_score_gemma":0.00001383111,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00000898138,"about_ca_topic_score_gemma":0.0001389303,"domain_scores_codex":[0.9989943,0.0000411753,0.0001961943,0.0004433414,0.0001171181,0.0002078778],"domain_scores_gemma":[0.9993328,0.00002882634,0.00005339685,0.0004261555,0.00009763071,0.0000611498],"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":[0.00004739063,0.0002677519,0.000001490828,0.0001602128,0.000203925,0.00001083972,0.0002248566,0.05882469,0.0105138,0.01428999,0.00128304,0.914172],"study_design_scores_gemma":[0.0005740271,0.0003318888,0.0001219892,0.00005095483,0.0001647883,0.00006350829,0.0001010727,0.7952775,0.09896606,0.003121028,0.1006802,0.0005469791],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001891038,0.00005216284,0.993576,0.002139291,0.000284923,0.0004477843,0.000005108464,0.0002970765,0.0013066],"genre_scores_gemma":[0.8612567,0.0007475961,0.1290845,0.002549716,0.000252744,0.001109525,0.00001128362,0.0000320965,0.004955762],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.913625,"threshold_uncertainty_score":0.6261059,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01157556854400971,"score_gpt":0.211022926873319,"score_spread":0.1994473583293093,"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."}}