{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001536174,0.00007083351,0.00007001337,0.00004969808,0.0001295239,0.00007162721,0.0008149192,0.00004117839,0.00002847771],"category_scores_gemma":[0.00006481308,0.00005914721,0.00003712124,0.0003146132,0.00002244784,0.0001635844,0.00007189833,0.00004663307,0.00003269189],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001153767,"about_ca_system_score_gemma":0.00005250469,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001356135,"about_ca_topic_score_gemma":0.000005826299,"domain_scores_codex":[0.9992956,0.000009956755,0.0001206927,0.0003445421,0.00008165388,0.0001475617],"domain_scores_gemma":[0.9986477,0.0001238677,0.00003044572,0.001084751,0.00005115316,0.00006201015],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000001262369,0.0001996023,0.0004901341,0.00000489365,0.000004546982,6.744517e-7,0.000007285904,0.000009312684,0.001029682,0.9366722,0.0452987,0.01628173],"study_design_scores_gemma":[0.000252074,0.0001180312,0.0003509871,0.000001122844,0.000006748863,0.000009075367,0.000006654888,0.1165377,0.02161561,0.01906232,0.8418285,0.0002111571],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.00007196903,0.00001452917,0.9916417,0.00101532,0.00004710317,0.0002234047,0.000009788501,0.000374365,0.006601816],"genre_scores_gemma":[0.5738581,0.000002687823,0.4240417,0.0007272346,0.00002036132,0.0001177106,0.00001080388,0.000006583585,0.001214792],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9176099,"threshold_uncertainty_score":0.2411953,"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."}}