{"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":"codex-gemma-dda1882f352a","candidate_categories":["open_science"],"consensus_categories":[],"category_scores_codex":[0.0006449376,0.0001822839,0.0002886598,0.0001442714,0.0001294541,0.0001568875,0.004612544,0.00006916543,0.000005830776],"category_scores_gemma":[0.0003771349,0.0001615467,0.00002204101,0.0003431668,0.000234049,0.002905003,0.01748029,0.0002213244,0.00001294279],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002023781,"about_ca_system_score_gemma":0.0001600794,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009914489,"about_ca_topic_score_gemma":0.00007402569,"domain_scores_codex":[0.9978786,0.0001133532,0.0003270568,0.001004776,0.0002610635,0.000415215],"domain_scores_gemma":[0.9959918,0.0003258905,0.00009042482,0.003367582,0.00006336138,0.0001609281],"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":[0.00009589503,0.0004998183,0.00218884,0.0003101905,0.0001349226,0.0001715096,0.01152958,0.00001170807,0.0004464381,0.005399827,0.003187992,0.9760233],"study_design_scores_gemma":[0.0007619996,0.0002582925,0.005229628,0.0001585501,0.00002653518,0.0001248283,0.0007297426,0.9872235,0.0004315386,0.001016521,0.003525732,0.0005131421],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01382685,0.0009646261,0.981401,0.00005297152,0.0003861318,0.0001221459,0.0003998737,0.00007760885,0.00276877],"genre_scores_gemma":[0.7519178,0.0001932975,0.2464058,0.0000258155,0.0001923682,0.000009209494,0.0005461478,0.00003009534,0.0006793858],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9872118,"threshold_uncertainty_score":0.9904661,"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."}}