{"id":"W1972132022","doi":"10.1145/1046456.1046468","title":"Subspace clustering for high dimensional categorical data","year":2004,"lang":"en","type":"article","venue":"ACM SIGKDD Explorations Newsletter","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":73,"is_retracted":false,"has_abstract":true,"ca_institutions":"York University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Cluster analysis; Computer science; Clustering high-dimensional data; Categorical variable; Correlation clustering; CURE data clustering algorithm; Data mining; Subspace topology; Canopy clustering algorithm; Data stream clustering; Focus (optics); Algorithm; Pattern recognition (psychology); Artificial intelligence; Machine learning","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":[0.003667024,0.0007325431,0.0013952,0.003133809,0.001615953,0.001524821,0.001362129,0.001086037,0.001365948],"category_scores_gemma":[0.01125367,0.0003534379,0.001386236,0.004813941,0.001364131,0.001934973,0.00186994,0.001586164,0.000713491],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001175548,"about_ca_system_score_gemma":0.001714046,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003713113,"about_ca_topic_score_gemma":0.004320384,"domain_scores_codex":[0.9958442,0.001840004,0.0002245165,0.0005922827,0.00133916,0.000159775],"domain_scores_gemma":[0.9945497,0.00251713,0.0004290871,0.0009376222,0.001399775,0.0001666127],"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":[0.0001577147,0.00009320082,0.003772436,0.0005072683,0.0001755037,0.0002328453,0.0008529113,0.3639867,0.009032694,0.1766486,0.007019468,0.4375206],"study_design_scores_gemma":[0.000009494041,0.00005123314,0.0009633853,0.00002273448,0.00001552045,0.0001524013,0.0001588011,0.8882079,0.003188365,0.101581,0.005601386,0.00004775618],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.002977177,0.0001891443,0.9962111,0.00008878906,0.00001316635,0.0000216117,0.00006211713,0.0001968504,0.0002400615],"genre_scores_gemma":[0.08437975,0.00045641,0.9132391,0.00006756825,0.00006028299,0.0001528903,0.0006502906,0.0001009036,0.0008928911],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003713113,"threshold_uncertainty_score":0.01939332,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1123055424811128,"score_gpt":0.3448912619355348,"score_spread":0.232585719454422,"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."}}