{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01242115,0.001171246,0.002242009,0.002849916,0.00241279,0.003326257,0.004886616,0.0041568,0.004355931],"category_scores_gemma":[0.03755842,0.001622029,0.002242218,0.004614697,0.003315911,0.007045968,0.003624968,0.004672096,0.002203221],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.003132797,"about_ca_system_score_gemma":0.00226493,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.009271604,"about_ca_topic_score_gemma":0.0127812,"domain_scores_codex":[0.9911366,0.005898993,0.0003001777,0.001166496,0.001135011,0.0003627958],"domain_scores_gemma":[0.9823822,0.01396675,0.0008018018,0.001708161,0.0007886163,0.0003524554],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0004588443,0.0001879543,0.003065017,0.0003158403,0.0002881055,0.0002772039,0.00206963,0.3372981,0.001276531,0.5110251,0.01139452,0.1323432],"study_design_scores_gemma":[0.00006470121,0.00002283902,0.0003857354,0.0000376195,0.00004080008,0.00007669409,0.00007872781,0.58574,0.0002708532,0.4095612,0.00367788,0.00004298105],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.005733091,0.0006472509,0.9910261,0.0006948021,0.00005177846,0.00009863924,0.0001997518,0.0002777824,0.001270829],"genre_scores_gemma":[0.2579952,0.002029017,0.7273434,0.0007643832,0.0004688668,0.00134329,0.001793664,0.000317869,0.007944402],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01242115,"threshold_uncertainty_score":0.0656901,"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."}}