{"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":"codex-gemma-dda1882f352a","candidate_categories":["open_science"],"consensus_categories":[],"category_scores_codex":[0.009776866,0.0001470646,0.0002570498,0.0003698411,0.0008884257,0.0007597383,0.007069882,0.00003997956,0.00005465556],"category_scores_gemma":[0.00140131,0.00009415863,0.00001802546,0.003037613,0.0003791521,0.003507513,0.00565687,0.0003839279,0.00001736597],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004101557,"about_ca_system_score_gemma":0.0001462005,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0008647855,"about_ca_topic_score_gemma":0.0003501672,"domain_scores_codex":[0.9970714,0.0002722957,0.0004629721,0.0009288625,0.0007991829,0.000465221],"domain_scores_gemma":[0.994402,0.0007537588,0.0001862617,0.004243769,0.00009630551,0.0003178945],"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":[0.00007280549,0.000668614,0.1139576,0.000004915212,0.0002709453,0.00001982562,0.0003006844,0.0001498803,0.0003986779,0.01178277,0.01364371,0.8587296],"study_design_scores_gemma":[0.00008789653,0.00003687949,0.444251,0.000004506081,0.00007415842,0.00002949123,0.00003298025,0.5544716,0.00001861326,0.0002257187,0.0006587137,0.0001085301],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02928215,0.00005216212,0.9673868,0.0006725916,0.0001221815,0.00007216251,0.002366836,0.00002582719,0.00001927896],"genre_scores_gemma":[0.8600723,0.00004010812,0.138541,0.0002386459,0.00009072051,0.000002271277,0.001003732,0.000004562342,0.000006724349],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8586211,"threshold_uncertainty_score":0.9983023,"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."}}