{"id":"W2163067442","doi":"10.1109/icdm.2009.118","title":"A New MCA-Based Divisive Hierarchical Algorithm for Clustering Categorical Data","year":2009,"lang":"en","type":"article","venue":"","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":16,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Sherbrooke","funders":"","keywords":"Categorical variable; Cluster analysis; Computer science; Similarity (geometry); Hierarchical clustering; Data mining; Pattern recognition (psychology); Algorithm; Canopy clustering algorithm; Single-linkage clustering; Subspace topology; Artificial intelligence; Linear subspace; CURE data clustering algorithm; Correlation clustering; 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":[],"consensus_categories":[],"category_scores_codex":[0.0003998132,0.0002459116,0.0002850157,0.0001803915,0.0002121048,0.000328328,0.003760504,0.0001009463,0.00002244162],"category_scores_gemma":[0.0001796456,0.0002187153,0.00008124608,0.0005543637,0.00004194257,0.000840147,0.001345727,0.0003243526,0.00004191597],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000119392,"about_ca_system_score_gemma":0.0003566504,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005520573,"about_ca_topic_score_gemma":0.000009681426,"domain_scores_codex":[0.997094,0.00006088536,0.0003263052,0.00107531,0.0006164918,0.0008269763],"domain_scores_gemma":[0.9969199,0.0004295545,0.00005844249,0.001992867,0.0001219527,0.0004772247],"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":[0.000009900257,0.00005881342,0.000002089066,0.000006418381,0.000008714765,0.00003734448,0.00004752297,0.001038213,0.0001197584,0.002885302,0.003377188,0.9924088],"study_design_scores_gemma":[0.001049837,0.0003415542,0.000147136,0.0000101546,0.000003896152,0.00002616411,0.000005593478,0.9774343,0.0005361,0.01070186,0.009457848,0.0002855935],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00001185912,0.00005567262,0.9918634,0.006386007,0.0002403548,0.0005018696,0.00001755159,0.0004269624,0.0004963821],"genre_scores_gemma":[0.006545194,0.00000456095,0.9906198,0.0009968262,0.0004241408,0.00002117631,0.00004700411,0.00001960603,0.001321671],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9921231,"threshold_uncertainty_score":0.8918951,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05942537267736089,"score_gpt":0.3551315825387727,"score_spread":0.2957062098614118,"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."}}