{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003778135,0.001123847,0.002012877,0.004490767,0.001326787,0.001947834,0.003050068,0.00130203,0.001346684],"category_scores_gemma":[0.0168641,0.0003691595,0.001487333,0.00469326,0.001008507,0.004096051,0.003484946,0.002032684,0.0009904192],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001334262,"about_ca_system_score_gemma":0.002061791,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00307236,"about_ca_topic_score_gemma":0.002884001,"domain_scores_codex":[0.9950579,0.0005692226,0.0006981041,0.0008092927,0.002511206,0.0003543041],"domain_scores_gemma":[0.9905596,0.002536182,0.001494493,0.002257863,0.002733622,0.0004181439],"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":[0.001363585,0.000367585,0.02221858,0.0003990797,0.0003008006,0.0006585469,0.0006003393,0.09127229,0.03010542,0.02057654,0.01177335,0.820364],"study_design_scores_gemma":[0.00008792688,0.0003131805,0.003865464,0.00003839542,0.00006273815,0.0007266327,0.0001411907,0.942124,0.01767525,0.02578995,0.009052397,0.0001228693],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01683707,0.0002758231,0.9772816,0.0002016814,0.00009770205,0.0001836693,0.0007158789,0.004001998,0.0004045924],"genre_scores_gemma":[0.3492963,0.0003582348,0.6436521,0.0002926051,0.0001663828,0.0004681955,0.00376472,0.0002804787,0.001720995],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.004490767,"threshold_uncertainty_score":0.01998091,"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."}}