{"id":"W2015887370","doi":"10.1002/sam.11161","title":"A survey on unsupervised outlier detection in high‐dimensional numerical data","year":2012,"lang":"en","type":"article","venue":"Statistical Analysis and Data Mining The ASA Data Science Journal","topic":"Anomaly Detection Techniques and Applications","field":"Computer Science","cited_by":856,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Outlier; Curse of dimensionality; Anomaly detection; Computer science; Linear subspace; Data mining; Euclidean distance; Clustering high-dimensional data; Task (project management); Machine learning; Artificial intelligence; Mathematics; Cluster analysis","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005236827,0.001462266,0.003402622,0.00639186,0.0006947735,0.003177468,0.003650879,0.002128437,0.001004677],"category_scores_gemma":[0.02352748,0.0008746269,0.002103246,0.01176643,0.001484619,0.004021115,0.001836499,0.001803587,0.001225828],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007522406,"about_ca_system_score_gemma":0.001416149,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001050396,"about_ca_topic_score_gemma":0.0007322573,"domain_scores_codex":[0.9925261,0.00208858,0.0009426077,0.001332326,0.002879608,0.0002307806],"domain_scores_gemma":[0.9831366,0.009752234,0.001265245,0.001865668,0.003763783,0.0002165456],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0001334139,0.0002041724,0.009923363,0.00306354,0.000433328,0.0002834784,0.0003395821,0.03874382,0.003552331,0.02169715,0.008114599,0.9135113],"study_design_scores_gemma":[0.00007400278,0.0005035159,0.01419215,0.001791017,0.0003804351,0.003512056,0.0007501426,0.6975209,0.02232444,0.1112582,0.1474219,0.000271349],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"review","genre_scores_codex":[0.008357667,0.03188857,0.9557455,0.0008393864,0.0002310313,0.000105536,0.0002138745,0.0009865152,0.00163193],"genre_scores_gemma":[0.145889,0.0794744,0.7671575,0.000796696,0.001510804,0.0003702294,0.002160763,0.0004143598,0.002226245],"genre_candidate":"review","genre_consensus":null,"teacher_disagreement_score":0.00639186,"threshold_uncertainty_score":0.0276953,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09488812902028622,"score_gpt":0.3590586097123034,"score_spread":0.2641704806920172,"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."}}