{"id":"W176952057","doi":"10.1007/978-3-642-23199-5_9","title":"Parameter-Free Anomaly Detection for Categorical Data","year":2011,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Anomaly Detection Techniques and Applications","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":false,"ca_institutions":"Université de Sherbrooke","funders":"","keywords":"Categorical variable; Anomaly detection; Computer science; Outlier; Data mining; Preprocessor; Set (abstract data type); Similarity (geometry); Artificial intelligence; Data set; Measure (data warehouse); Similarity measure; Data pre-processing; Pattern recognition (psychology); Machine learning; Image (mathematics)","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":[0.004246135,0.0008759634,0.002221336,0.001897998,0.0005650112,0.001833858,0.004229306,0.001459974,0.001605061],"category_scores_gemma":[0.02320117,0.0007204377,0.001395944,0.002707606,0.001285877,0.003969803,0.002817371,0.00315139,0.001076865],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007829496,"about_ca_system_score_gemma":0.001020103,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001265773,"about_ca_topic_score_gemma":0.00125991,"domain_scores_codex":[0.9945467,0.001283432,0.0004747793,0.001175577,0.002163458,0.0003560085],"domain_scores_gemma":[0.982538,0.008572688,0.0009880649,0.00560787,0.00203381,0.0002595015],"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":[0.0007256525,0.000258841,0.01077392,0.0003185834,0.0002797087,0.0002650168,0.000202692,0.1566911,0.02235048,0.04117403,0.01004056,0.7569194],"study_design_scores_gemma":[0.00001604142,0.00007425406,0.001028104,0.00001482077,0.00002410529,0.0003433744,0.00002500904,0.9115012,0.007960887,0.07698382,0.001993557,0.00003485505],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.007612833,0.0001585655,0.9895968,0.00009896683,0.00003654471,0.00002155227,0.0001585623,0.002050647,0.0002655027],"genre_scores_gemma":[0.3898743,0.0003056891,0.60391,0.0001664108,0.0001934095,0.0001593026,0.002077065,0.0006903806,0.002623537],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.004246135,"threshold_uncertainty_score":0.02245593,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05045130097694171,"score_gpt":0.2740340784227595,"score_spread":0.2235827774458178,"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."}}