{"id":"W2086829791","doi":"10.1007/s10618-011-0221-2","title":"DHCC: Divisive hierarchical clustering of categorical data","year":2011,"lang":"en","type":"article","venue":"Data Mining and Knowledge Discovery","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":77,"is_retracted":false,"has_abstract":false,"ca_institutions":"Université de Sherbrooke","funders":"","keywords":"Categorical variable; Cluster analysis; Computer science; Data mining; Initialization; Similarity (geometry); Linear subspace; Single-linkage clustering; Hierarchical clustering; Artificial intelligence; Pattern recognition (psychology); CURE data clustering algorithm; Correlation clustering; Machine learning; Mathematics","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":[0.003186143,0.001350303,0.001641656,0.005162863,0.001626792,0.002618825,0.003455608,0.001392419,0.006119874],"category_scores_gemma":[0.01450486,0.0008620228,0.00202511,0.007430254,0.0006719409,0.001627894,0.00278945,0.002248004,0.004251963],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001201059,"about_ca_system_score_gemma":0.003998428,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01226791,"about_ca_topic_score_gemma":0.01728992,"domain_scores_codex":[0.9966754,0.001123483,0.000236967,0.0005648898,0.001192503,0.0002068261],"domain_scores_gemma":[0.9951391,0.001474113,0.0002268712,0.00158372,0.001367019,0.0002092161],"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":[0.000424089,0.0002477535,0.003628014,0.0007672905,0.0004126163,0.0001602235,0.000566676,0.04784878,0.005984741,0.02416062,0.06596284,0.8498363],"study_design_scores_gemma":[0.0001696962,0.0001659042,0.003628456,0.000129551,0.0001926012,0.0003882017,0.0002982659,0.839159,0.0140065,0.07377815,0.06792869,0.0001550078],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.003337046,0.0003346055,0.9810245,0.0001645491,0.0001614567,0.0004255908,0.002433635,0.01115917,0.0009594607],"genre_scores_gemma":[0.02977494,0.000206044,0.961478,0.0001240128,0.00007489182,0.0005166616,0.00520127,0.0008726419,0.001751508],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01226791,"threshold_uncertainty_score":0.02439302,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1924145629485619,"score_gpt":0.3565834104161071,"score_spread":0.1641688474675453,"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."}}