{"id":"W4240428965","doi":"10.1007/3-540-36175-8_40","title":"HOT: Hypergraph-Based Outlier Test for Categorical Data","year":2003,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Anomaly Detection Techniques and Applications","field":"Computer Science","cited_by":23,"is_retracted":false,"has_abstract":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Categorical variable; Computer science; Outlier; Data mining; Robustness (evolution); Linear subspace; Anomaly detection; Curse of dimensionality; Missing data; Computation; Hypergraph; Cluster analysis; Artificial intelligence; Algorithm; Machine learning; 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":[0.0006935174,0.0004439936,0.0004152425,0.0006031567,0.000385371,0.0004431689,0.00545389,0.0003336046,0.00001304513],"category_scores_gemma":[0.0001385907,0.0004076054,0.0001358528,0.0007574441,0.0005033056,0.0004181715,0.0009414912,0.0005326858,0.00002288848],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001720186,"about_ca_system_score_gemma":0.0004759163,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001311051,"about_ca_topic_score_gemma":0.0000285984,"domain_scores_codex":[0.9964257,0.00001567469,0.0004733286,0.001952954,0.0005724861,0.0005597916],"domain_scores_gemma":[0.9953761,0.0006860053,0.0002462355,0.003258495,0.0002559022,0.0001772784],"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":[0.000007686996,0.0001832434,0.0000753959,0.00006191058,0.00001521352,0.00002604672,0.00007703852,0.004279451,0.0003320122,0.1114873,0.002291113,0.8811635],"study_design_scores_gemma":[0.0002759438,0.0002679904,0.00003550538,0.00005899181,0.00001503413,0.00004623909,5.289372e-8,0.7124498,0.002367777,0.1809563,0.1027599,0.0007664934],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.000002180383,0.0001714228,0.9948171,0.001951743,0.0005896083,0.000739115,0.00004735832,0.00031855,0.001362922],"genre_scores_gemma":[0.03250258,0.00002767923,0.9622292,0.00412804,0.0003272754,0.0000927623,0.00004286904,0.00004982277,0.0005997713],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.880397,"threshold_uncertainty_score":0.9999271,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03384550495253059,"score_gpt":0.2738144117525889,"score_spread":0.2399689068000583,"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."}}