{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002888907,0.0002237184,0.0002080637,0.0001738008,0.0004106516,0.0003026644,0.003262907,0.00008812359,0.00001300624],"category_scores_gemma":[0.0004711494,0.0002156771,0.00005059941,0.0005390499,0.0000772248,0.002463814,0.003044442,0.0002583137,0.0002306217],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001766332,"about_ca_system_score_gemma":0.0001602932,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008112521,"about_ca_topic_score_gemma":0.00007934668,"domain_scores_codex":[0.9976661,0.00005096177,0.0003247646,0.0008815498,0.0004971441,0.000579497],"domain_scores_gemma":[0.9959775,0.0003470546,0.00007833023,0.003250398,0.0001798864,0.000166896],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001931697,0.00113489,0.0001282362,0.0001860862,0.0003356656,0.0004963474,0.004846421,0.5114476,0.06080486,0.1426964,0.1548861,0.1228442],"study_design_scores_gemma":[0.006744563,0.0006695507,0.0006657018,0.0000906792,0.00004962123,0.0002637311,0.0001640765,0.7211635,0.01955274,0.1915259,0.05702209,0.002087855],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.002734174,0.0000377446,0.9214948,0.07449408,0.0005146203,0.0004209795,0.00002487672,0.0002542343,0.00002443746],"genre_scores_gemma":[0.2055515,0.000007963334,0.7900522,0.003010029,0.0005358455,0.0002541639,0.000236514,0.00004121936,0.0003105326],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.2097159,"threshold_uncertainty_score":0.8795058,"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."}}