{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","open_science"],"consensus_categories":[],"category_scores_codex":[0.0007347935,0.0004271327,0.0004071062,0.0005888699,0.0003678082,0.0003804206,0.008154604,0.0003802656,0.00001500891],"category_scores_gemma":[0.0001502781,0.0004031951,0.0001280287,0.0005469364,0.0004293915,0.0007626934,0.003078935,0.0005514214,0.00002589853],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002043615,"about_ca_system_score_gemma":0.0002836672,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007308959,"about_ca_topic_score_gemma":0.0001644044,"domain_scores_codex":[0.9964756,0.00001878612,0.0005122778,0.001981688,0.000474744,0.0005369278],"domain_scores_gemma":[0.9942669,0.0004088198,0.0003138053,0.004615698,0.0002339722,0.0001607514],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.000006465938,0.00003158824,0.000005768053,0.00001942124,0.000008941019,0.00000723393,0.00007235081,0.0001552914,0.0001507243,0.04051868,0.0001355982,0.9588879],"study_design_scores_gemma":[0.0001762085,0.0002941822,0.00004151831,0.00003466944,0.00001379599,0.00008013435,4.499948e-8,0.3478071,0.005265739,0.6296678,0.01608714,0.0005316859],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.000011634,0.0001424271,0.9956272,0.0003952414,0.001022452,0.0007752578,0.00002926338,0.0004120985,0.001584485],"genre_scores_gemma":[0.1400061,0.00004636315,0.8580442,0.0006272363,0.0006348921,0.0001086566,0.00002062832,0.00004650424,0.0004653923],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9583563,"threshold_uncertainty_score":0.999842,"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."}}