{"id":"W2113334100","doi":"10.1016/j.jbi.2008.11.004","title":"Efficient layered density-based clustering of categorical data","year":2008,"lang":"en","type":"article","venue":"Journal of Biomedical Informatics","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":false,"ca_institutions":"York University","funders":"","keywords":"Cluster analysis; Computer science; Categorical variable; Data mining; Scalability; CURE data clustering algorithm; Single-linkage clustering; Clustering high-dimensional data; Correlation clustering; Artificial intelligence; Pattern recognition (psychology); Machine learning; Database","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":[0.003695514,0.0008459445,0.002440226,0.002556375,0.001212391,0.00255129,0.004327216,0.001579321,0.001803912],"category_scores_gemma":[0.01941756,0.001275064,0.002176781,0.003119443,0.0008752475,0.00259129,0.004714425,0.002397372,0.00157032],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00218263,"about_ca_system_score_gemma":0.003488312,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01867349,"about_ca_topic_score_gemma":0.01979134,"domain_scores_codex":[0.9965023,0.001248696,0.0002619196,0.0003177566,0.001323441,0.0003458225],"domain_scores_gemma":[0.9918814,0.003696398,0.0003894038,0.001465726,0.00223701,0.0003300836],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0005669314,0.0002833341,0.006224526,0.0002809181,0.0002715307,0.0001251258,0.0006562417,0.4504653,0.009701112,0.02307684,0.007709224,0.500639],"study_design_scores_gemma":[0.00001263964,0.00002063168,0.0004532759,0.000009695768,0.00001410411,0.00004097215,0.00003854035,0.9893987,0.001266056,0.008375354,0.0003538092,0.00001613165],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01013243,0.0001124775,0.988239,0.0001009222,0.0000169761,0.0000499674,0.0001422658,0.0009991287,0.0002066868],"genre_scores_gemma":[0.2177405,0.0002292437,0.7782068,0.0001060298,0.00004617172,0.000247516,0.001833674,0.0002379233,0.00135205],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01867349,"threshold_uncertainty_score":0.03712958,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06798969841812494,"score_gpt":0.3235346120781342,"score_spread":0.2555449136600092,"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."}}