{"id":"W2003144493","doi":"10.1198/jcgs.2010.08111","title":"Combining Mixture Components for Clustering","year":2010,"lang":"en","type":"article","venue":"Journal of Computational and Graphical Statistics","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":348,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Eunice Kennedy Shriver National Institute of Child Health and Human Development; National Institute of Biomedical Imaging and Bioengineering; Natural Sciences and Engineering Research Council of Canada; National Institutes of Health","keywords":"Mixture model; Cluster analysis; Mathematics; Determining the number of clusters in a data set; Gaussian; Entropy (arrow of time); Piecewise; Cluster (spacecraft); Computer science; Statistics; Correlation clustering; CURE data clustering algorithm; Physics","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01105423,0.003871261,0.004523744,0.007891809,0.002566112,0.005266872,0.00624167,0.004184892,0.009341309],"category_scores_gemma":[0.03733569,0.001905454,0.006105283,0.008725718,0.001927446,0.003900571,0.005637564,0.006191455,0.008001325],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00256764,"about_ca_system_score_gemma":0.002912418,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008996535,"about_ca_topic_score_gemma":0.01072264,"domain_scores_codex":[0.989087,0.006018094,0.0005334021,0.002057477,0.001908851,0.0003951551],"domain_scores_gemma":[0.9885534,0.006748764,0.0005249045,0.00174798,0.002196355,0.0002286518],"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":[0.0002598591,0.0001468347,0.002366409,0.001008821,0.001030807,0.0001664379,0.0007476403,0.3137744,0.002173546,0.1576806,0.02364319,0.4970015],"study_design_scores_gemma":[0.00002499957,0.00002943804,0.0005421613,0.0001247013,0.0001203253,0.0001071302,0.00008359998,0.828815,0.001033796,0.1541746,0.0148649,0.00007940514],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0004212238,0.0003575824,0.9977407,0.00008622398,0.0000495738,0.000091212,0.0001215715,0.0006529333,0.0004788846],"genre_scores_gemma":[0.02003924,0.0006001538,0.9749457,0.0001579348,0.0001458061,0.000645762,0.001214599,0.0007597642,0.001491072],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01105423,"threshold_uncertainty_score":0.05846107,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01577668605565137,"score_gpt":0.280924284971499,"score_spread":0.2651475989158477,"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."}}