{"id":"W4408175168","doi":"10.1007/s10618-024-01084-1","title":"Efficient outlier detection in numerical and categorical data","year":2025,"lang":"en","type":"article","venue":"Data Mining and Knowledge Discovery","topic":"Anomaly Detection Techniques and Applications","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"Conselho Nacional de Desenvolvimento Científico e Tecnológico; Coordenação de Aperfeiçoamento de Pessoal de Nível Superior; Fundação de Amparo à Pesquisa do Estado de São Paulo; Carnegie Mellon University","keywords":"Categorical variable; Anomaly detection; Outlier; Computer science; Data mining; Artificial intelligence; Pattern recognition (psychology); Machine learning","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":[0.002319105,0.0008010081,0.001732998,0.003314694,0.0005712726,0.001835923,0.002182402,0.001029799,0.001025085],"category_scores_gemma":[0.01265806,0.0003461011,0.001033088,0.003601987,0.0007336323,0.001816557,0.001733969,0.001639634,0.0009160505],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007080211,"about_ca_system_score_gemma":0.001090802,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002984393,"about_ca_topic_score_gemma":0.003051393,"domain_scores_codex":[0.9965414,0.0007152933,0.0002886851,0.0008199353,0.001378929,0.0002557964],"domain_scores_gemma":[0.9915295,0.003505219,0.001140232,0.001207139,0.002256103,0.0003617849],"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":[0.0007788211,0.0004618866,0.05017883,0.0008298702,0.0004818234,0.0006470408,0.0003748667,0.189986,0.03207624,0.01410832,0.02496569,0.6851107],"study_design_scores_gemma":[0.00002218203,0.00007385336,0.003295305,0.00002987154,0.00002239073,0.0002696,0.0001757893,0.9690149,0.00919436,0.01431685,0.003555957,0.00002889099],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1038752,0.001151969,0.884253,0.0008388481,0.0002338018,0.0001195896,0.001508223,0.006576526,0.001442814],"genre_scores_gemma":[0.525085,0.0003125083,0.4689063,0.0001794079,0.0001327879,0.0001018397,0.003634019,0.0002408339,0.001407339],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.003314694,"threshold_uncertainty_score":0.01226473,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03590234063653296,"score_gpt":0.3165941644719431,"score_spread":0.2806918238354101,"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."}}