{"id":"W2000219982","doi":"10.1109/icde.2014.6816641","title":"Scalable distance-based outlier detection over high-volume data streams","year":2014,"lang":"en","type":"article","venue":"","topic":"Anomaly Detection Techniques and Applications","field":"Computer Science","cited_by":119,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Ministère de l'Économie, de la Science et de l'Innovation - Québec; National Science Foundation","keywords":"Anomaly detection; Outlier; Computer science; Scalability; Data mining; Data stream mining; Ranging; Data point; Cluster analysis; Scale (ratio); Big data; Process (computing); Credit card fraud; Object (grammar); Artificial intelligence; Credit card; Database","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002140761,0.0001063752,0.0001015629,0.00005836173,0.0001906051,0.0001693633,0.001021821,0.0000614682,0.0001342201],"category_scores_gemma":[0.00001736237,0.00009430935,0.00003171173,0.0003532445,0.00003612615,0.0005033141,0.0002508354,0.00009001168,0.0001682166],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003938044,"about_ca_system_score_gemma":0.00002258194,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003295889,"about_ca_topic_score_gemma":0.0001691875,"domain_scores_codex":[0.99894,0.0000310879,0.0001697374,0.0004926752,0.0001794256,0.0001870961],"domain_scores_gemma":[0.9980195,0.00003315449,0.00007045591,0.001749856,0.00004994382,0.00007710055],"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":[0.000008787462,0.00020697,0.002005195,0.00001539163,0.00001395084,7.358485e-7,0.00001496841,0.0002693253,0.003825435,0.1527963,0.02426684,0.8165761],"study_design_scores_gemma":[0.0001670699,0.00006255346,0.003059517,0.000004038318,0.00000468974,0.000001161803,0.00000206902,0.7184916,0.01840877,0.003463312,0.256176,0.0001592512],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.00344425,0.000005674101,0.990861,0.0006473613,0.0001146542,0.0001382001,0.000009599684,0.0007673822,0.004011896],"genre_scores_gemma":[0.9153566,0.000002170526,0.08135697,0.0003984295,0.00007296508,0.00004069547,0.00001664849,0.000009234127,0.002746292],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9119123,"threshold_uncertainty_score":0.3845824,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01346393922891818,"score_gpt":0.2376409428860461,"score_spread":0.2241770036571279,"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."}}