{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005645031,0.0005863712,0.002206029,0.00365185,0.001694816,0.002636718,0.005012058,0.001323429,0.003904595],"category_scores_gemma":[0.03422395,0.001295093,0.003067204,0.007533182,0.002215559,0.004202916,0.004341106,0.003419992,0.001949115],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002187863,"about_ca_system_score_gemma":0.001989015,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.009517566,"about_ca_topic_score_gemma":0.01025588,"domain_scores_codex":[0.9940379,0.00221733,0.0003918144,0.0008867842,0.002215981,0.0002502872],"domain_scores_gemma":[0.9900878,0.004438467,0.0003168407,0.003221375,0.001769622,0.0001659648],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001037286,0.00008394739,0.002037111,0.000416372,0.0001630244,0.0001935523,0.0009836281,0.09756324,0.002965481,0.605687,0.01473308,0.2750698],"study_design_scores_gemma":[0.00002375064,0.00004431736,0.002574195,0.00007372838,0.0000730208,0.0004425906,0.0002574454,0.4204519,0.001620027,0.5597323,0.01463775,0.00006902798],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.003151961,0.0003088859,0.9944622,0.00021459,0.00004758766,0.0000520844,0.0001934722,0.0001948294,0.001374413],"genre_scores_gemma":[0.1131278,0.001030706,0.8767855,0.0002375906,0.0002053254,0.0003745696,0.001734286,0.0002933382,0.006210853],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.009517566,"threshold_uncertainty_score":0.02985418,"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."}}