{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003019688,0.00009048959,0.0001203073,0.0001267348,0.0001303852,0.0002090576,0.0007722382,0.00005207381,6.704764e-7],"category_scores_gemma":[0.00006553371,0.00008228589,0.00000813364,0.0004628646,0.00005023259,0.0004014554,0.002265637,0.0001004452,0.000003342126],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002015124,"about_ca_system_score_gemma":0.0000558637,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007756984,"about_ca_topic_score_gemma":0.00008431434,"domain_scores_codex":[0.9989729,0.00003735179,0.0001707562,0.0006249898,0.00005521134,0.0001387876],"domain_scores_gemma":[0.9986552,0.0001003018,0.00003172753,0.001158266,0.00001474583,0.00003978653],"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":[0.00001275813,0.0002376972,0.002395018,0.00004004362,0.0000157285,0.000004820749,0.0004959368,0.000008711675,0.0003274534,0.01409222,0.003452075,0.9789175],"study_design_scores_gemma":[0.0002546484,0.00003436705,0.009390613,0.00003372632,0.00001393925,0.00001621161,0.000220628,0.9652631,0.0003276566,0.0004242789,0.02384271,0.0001781199],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05818643,0.000779892,0.9392631,0.0002327385,0.0001370533,0.0001071108,0.00005233938,0.00008911567,0.001152223],"genre_scores_gemma":[0.9929909,0.00005371825,0.006428877,0.00004814737,0.00002940607,0.0000164956,0.00007001287,0.000003843072,0.0003585935],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9787394,"threshold_uncertainty_score":0.3355521,"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."}}