{"id":"W4392748476","doi":"10.2139/ssrn.4757427","title":"Harnessing Contrastive Learning and Neural Transformation for Time Series Anomaly Detection","year":2024,"lang":"en","type":"preprint","venue":"SSRN Electronic Journal","topic":"Anomaly Detection Techniques and Applications","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Anomaly detection; Transformation (genetics); Anomaly (physics); Series (stratigraphy); Computer science; Artificial intelligence; Pattern recognition (psychology); 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":["research_integrity"],"consensus_categories":[],"category_scores_codex":[0.000866672,0.0002167794,0.0002172387,0.0002087373,0.0005388017,0.0006613025,0.0002651785,0.0001841279,0.000001875954],"category_scores_gemma":[0.00001985044,0.0002078116,0.0001559421,0.0001626222,0.00004208408,0.0004416678,0.0001624209,0.002739384,0.000004705368],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004605866,"about_ca_system_score_gemma":0.0006346075,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000168135,"about_ca_topic_score_gemma":0.00005659641,"domain_scores_codex":[0.9982619,0.00006482682,0.0003304192,0.0003601275,0.0001412849,0.0008414908],"domain_scores_gemma":[0.999407,0.00004316183,0.0002373486,0.0001178663,0.0001364549,0.00005817443],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00005225219,0.00001949615,0.0000131336,0.0001049538,0.0001563341,0.000001262076,0.000685571,0.00044147,0.005832897,0.1263595,0.00001192446,0.8663211],"study_design_scores_gemma":[0.0002557434,0.0005572761,0.00004690244,0.00009011378,0.00008936663,0.0009830158,0.0003469012,0.3093359,0.00512451,0.6803001,0.002510418,0.0003596994],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02896209,0.001825206,0.9666823,0.001352148,0.0002092513,0.0004337837,0.00000428777,0.0003614063,0.0001695428],"genre_scores_gemma":[0.9943494,0.001075955,0.003386491,0.00002031213,0.0002405811,0.0001305422,0.000006459766,0.00002156536,0.0007686443],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9653873,"threshold_uncertainty_score":0.9995613,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.005769316081706288,"score_gpt":0.2428188506840665,"score_spread":0.2370495346023603,"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."}}