{"id":"W2120468118","doi":"10.1007/978-3-540-71701-0_5","title":"Hierarchical Density-Based Clustering of Categorical Data and a Simplification","year":2007,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":22,"is_retracted":false,"has_abstract":false,"ca_institutions":"York University","funders":"","keywords":"Categorical variable; Cluster analysis; Data mining; Computer science; CURE data clustering algorithm; Outlier; Pattern recognition (psychology); Basis (linear algebra); Hierarchical clustering; Single-linkage clustering; Canopy clustering algorithm; Artificial intelligence; Correlation clustering; Algorithm; Mathematics; Machine learning","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"],"consensus_categories":[],"category_scores_codex":[0.001614176,0.0003675794,0.0004881524,0.000963693,0.0001764714,0.0002423258,0.004508063,0.0002810569,0.000003281772],"category_scores_gemma":[0.0002488781,0.0003521568,0.00004692233,0.0006679747,0.001109181,0.000500462,0.005065698,0.000970095,0.000005550558],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000226753,"about_ca_system_score_gemma":0.0005458958,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002834072,"about_ca_topic_score_gemma":0.00007622712,"domain_scores_codex":[0.9957656,0.00004376532,0.0005630567,0.001762671,0.001236654,0.0006282444],"domain_scores_gemma":[0.9956176,0.001006063,0.0002370365,0.002628448,0.0002732165,0.0002376443],"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":[0.00001485938,0.00002846531,0.00005253729,0.0001040887,0.000006755214,0.0001047248,0.0002083755,0.03110547,0.0003313581,0.004207722,0.000002384992,0.9638333],"study_design_scores_gemma":[0.0002288412,0.000122113,0.0002145267,0.000133225,0.000003973016,0.00008918608,9.898193e-8,0.9680027,0.0008046995,0.02978299,0.0002859022,0.000331731],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0000812635,0.0001835513,0.9981917,0.000512803,0.0003698333,0.0003055176,0.00000871827,0.00008848638,0.0002581885],"genre_scores_gemma":[0.1332425,0.00002655367,0.8661403,0.0003188263,0.000183372,0.000002839317,0.00001617516,0.00002811671,0.00004135731],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9635015,"threshold_uncertainty_score":0.9998931,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06047806953614623,"score_gpt":0.3310772206294265,"score_spread":0.2705991510932803,"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."}}