{"id":"W3084688615","doi":"10.1109/tnse.2020.3022869","title":"FAST-ODT: A Lightweight Outlier Detection Scheme for Categorical Data Sets","year":2020,"lang":"en","type":"article","venue":"IEEE Transactions on Network Science and Engineering","topic":"Anomaly Detection Techniques and Applications","field":"Computer Science","cited_by":20,"is_retracted":false,"has_abstract":true,"ca_institutions":"Dalhousie University","funders":"Natural Sciences and Engineering Research Council of Canada; National Natural Science Foundation of China","keywords":"Categorical variable; Anomaly detection; Computer science; Outlier; Data mining; Data set; Tree (set theory); Pattern recognition (psychology); Artificial intelligence; Intrusion detection system; Local outlier factor; Machine learning; Mathematics","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0002771315,0.0001298297,0.0001154762,0.0000926308,0.0005060317,0.0001861871,0.0007546309,0.00005626492,0.000002615626],"category_scores_gemma":[0.00001016963,0.0001253035,0.00003414237,0.001292206,0.00005730496,0.0007471067,0.0000180124,0.0001797826,0.00000823275],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004279686,"about_ca_system_score_gemma":0.00006236388,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005196127,"about_ca_topic_score_gemma":0.000003069109,"domain_scores_codex":[0.9987155,0.000005351836,0.0001660623,0.0005682158,0.0002265424,0.0003183194],"domain_scores_gemma":[0.9991769,0.00004958268,0.0000332433,0.0004575272,0.00007764404,0.0002050998],"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":[0.00003564869,0.0001218247,0.000008622275,0.00007960427,0.00004825805,0.000004690051,0.000658852,0.2151898,0.06290886,0.01091415,0.00214639,0.7078832],"study_design_scores_gemma":[0.0001041173,0.0001052089,0.0000300334,0.000006440326,0.00000738828,0.00001109639,0.000007380953,0.9693084,0.01540762,0.0001042963,0.01474984,0.0001581999],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001181585,0.00003938035,0.9966896,0.001042511,0.0002964349,0.0002514081,0.000006786366,0.0004377788,0.00005453725],"genre_scores_gemma":[0.9090452,0.00004048158,0.09035582,0.0002933603,0.0001340245,0.00009995325,8.907173e-7,0.00001092676,0.00001939424],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9078636,"threshold_uncertainty_score":0.5109729,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02952475362360477,"score_gpt":0.2452707000399205,"score_spread":0.2157459464163158,"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."}}