{"id":"W2100163972","doi":"","title":"Sharing Clusters among Related Groups: Hierarchical Dirichlet Processes","year":2004,"lang":"en","type":"article","venue":"","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":434,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Hierarchical Dirichlet process; Computer science; Generalization; Cluster analysis; Hierarchical clustering; Dirichlet process; Nonparametric statistics; Dirichlet distribution; Latent Dirichlet allocation; Bayesian probability; Group (periodic table); Topic model; Data mining; Artificial intelligence; Mathematics; Statistics","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":[0.0003518295,0.0001542476,0.0001688101,0.0001007943,0.000124904,0.000194532,0.0009244811,0.0001041227,0.00001572787],"category_scores_gemma":[0.000079836,0.0001208519,0.00005720155,0.0006540015,0.00007161883,0.000699562,0.0003745174,0.0002521742,0.00002942343],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004203576,"about_ca_system_score_gemma":0.00008158496,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004189405,"about_ca_topic_score_gemma":0.00002572074,"domain_scores_codex":[0.9986117,0.00003798707,0.0002461472,0.0005354283,0.0002225404,0.0003461487],"domain_scores_gemma":[0.9991829,0.00006246905,0.00005521892,0.0004807938,0.00005568044,0.0001628994],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.000005439698,0.0001035604,0.0009980056,0.00006531736,0.00002889518,0.00007058447,0.002566084,0.0003927223,0.0001898845,0.9626735,0.0002217742,0.03268427],"study_design_scores_gemma":[0.0009398107,0.00010537,0.003230894,0.0001159702,0.0000115889,0.0000728511,0.00002025994,0.03075473,0.002115061,0.9617366,0.0004051359,0.0004917475],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02794317,0.00008931469,0.9489827,0.001744483,0.0001742956,0.0001367169,2.779517e-7,0.0003936999,0.02053531],"genre_scores_gemma":[0.509741,0.00001301134,0.4889354,0.0005516678,0.00003398028,0.00001063538,0.000001021905,0.00001011116,0.0007032111],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.4817978,"threshold_uncertainty_score":0.4928197,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01351625547000949,"score_gpt":0.2516143638654544,"score_spread":0.238098108395445,"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."}}