{"id":"W4386320385","doi":"10.1109/access.2023.3310653","title":"An Interactive Threshold-Setting Procedure for Improved Multivariate Anomaly Detection in Time Series","year":2023,"lang":"en","type":"article","venue":"IEEE Access","topic":"Anomaly Detection Techniques and Applications","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"Ontario Tech University","funders":"Knowledge Foundation","keywords":"Computer science; Anomaly detection; Benchmark (surveying); Multivariate statistics; Artificial intelligence; Data mining; Context (archaeology); Series (stratigraphy); Machine learning; Schema (genetic algorithms); Ground truth; Pattern recognition (psychology)","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":[0.0002449523,0.0001193849,0.0001209883,0.0002168223,0.0001872356,0.0003738813,0.000845365,0.000078545,0.000003474945],"category_scores_gemma":[0.00002653565,0.0001180272,0.0000458363,0.000859579,0.00001907107,0.002129303,0.0001246494,0.0001231547,0.0000206594],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004892433,"about_ca_system_score_gemma":0.00003408963,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009058796,"about_ca_topic_score_gemma":0.0001123388,"domain_scores_codex":[0.9990295,0.00002205486,0.0002114981,0.0004224522,0.00007846237,0.0002360733],"domain_scores_gemma":[0.9993447,0.00005568259,0.000120044,0.0003373304,0.00009461431,0.00004764281],"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":[0.000143808,0.000207329,0.00158051,0.00006550331,0.00002857418,0.000004999849,0.001213375,0.000790113,0.8198606,0.001035447,0.0006010155,0.1744687],"study_design_scores_gemma":[0.0002701282,0.0001602376,0.01172999,0.00001980069,0.000003623984,0.000006762198,0.00003195287,0.5445856,0.4353451,0.007078674,0.0005626646,0.0002054709],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3377118,0.000003479953,0.659692,0.0004547435,0.0001606518,0.0008230705,0.00001011771,0.001039885,0.0001043218],"genre_scores_gemma":[0.990563,0.00000373908,0.008141968,0.0001165272,0.00009316757,0.0008534138,0.000006921553,0.00001666641,0.000204572],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6528513,"threshold_uncertainty_score":0.481301,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01759907759539784,"score_gpt":0.3243480003963526,"score_spread":0.3067489228009548,"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."}}