{"id":"W1481707143","doi":"10.5555/1760894.1760948","title":"HOT: hypergraph-based outlier test for categorical data","year":2003,"lang":"en","type":"article","venue":"","topic":"Anomaly Detection Techniques and Applications","field":"Computer Science","cited_by":44,"is_retracted":false,"has_abstract":true,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Categorical variable; Outlier; Data mining; Computer science; Robustness (evolution); Anomaly detection; Hypergraph; Curse of dimensionality; Linear subspace; Missing data; Computation; Cluster analysis; Artificial intelligence; Machine learning; Algorithm; 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":[0.0023657,0.0007624348,0.001433837,0.005411025,0.0009510964,0.001473074,0.002514923,0.001729507,0.003671972],"category_scores_gemma":[0.01537478,0.000273724,0.0008149007,0.003677083,0.001406179,0.003219465,0.001937418,0.00128949,0.001042569],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007374012,"about_ca_system_score_gemma":0.00117704,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001924636,"about_ca_topic_score_gemma":0.001847319,"domain_scores_codex":[0.99634,0.001156478,0.000232002,0.0005482086,0.001414019,0.000309332],"domain_scores_gemma":[0.9849871,0.007810514,0.001482251,0.002622386,0.002280431,0.0008173456],"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":[0.003990827,0.001032173,0.06838613,0.0007373454,0.0008933362,0.001231391,0.0005850936,0.1259895,0.03105922,0.03297216,0.0306168,0.7025059],"study_design_scores_gemma":[0.0001930285,0.0007741986,0.01382556,0.0000479747,0.0001163351,0.0008448638,0.0003619092,0.9035599,0.01878327,0.05607472,0.005321043,0.00009719867],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.137739,0.0004580761,0.8424881,0.0008163863,0.0002477617,0.0003526839,0.002653701,0.01214232,0.003101945],"genre_scores_gemma":[0.7515694,0.0001637052,0.2393302,0.0002770516,0.0002703763,0.0003601534,0.005018602,0.0004799252,0.002530452],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.005411025,"threshold_uncertainty_score":0.01251113,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04766541032808504,"score_gpt":0.2906593674277747,"score_spread":0.2429939570996897,"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."}}