{"id":"W2162021827","doi":"10.1198/1061860043001","title":"A Split-Merge Markov chain Monte Carlo Procedure for the Dirichlet Process Mixture Model","year":2004,"lang":"en","type":"article","venue":"Journal of Computational and Graphical Statistics","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":475,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Gibbs sampling; Markov chain Monte Carlo; Metropolis–Hastings algorithm; Hierarchical Dirichlet process; Dirichlet distribution; Rejection sampling; Dirichlet process; Markov chain; Slice sampling; Computer science; Algorithm; Monte Carlo method; Merge (version control); Hybrid Monte Carlo; Mathematics; Bayesian probability; Artificial intelligence; Latent Dirichlet allocation; Machine learning; Statistics; Topic model","routes":{"ca_aff":true,"ca_fund":true,"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":[0.000533215,0.0001602078,0.0002509512,0.0000929427,0.0002325008,0.0001246344,0.0004054726,0.00007843803,8.961514e-7],"category_scores_gemma":[0.0001547017,0.0000978698,0.0001029805,0.0002779221,0.0001035469,0.0001900417,0.00004586494,0.0003021274,1.571832e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001764943,"about_ca_system_score_gemma":0.000251496,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002483643,"about_ca_topic_score_gemma":0.000004454103,"domain_scores_codex":[0.9986659,0.00004307498,0.000430394,0.0001939945,0.0004587141,0.0002078824],"domain_scores_gemma":[0.9982944,0.0005357487,0.0002871034,0.00009981736,0.0006210398,0.0001619088],"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":[0.00007410368,0.0001033606,0.00004695313,0.00009069731,0.00007770558,0.00001857869,0.0006759507,0.1643252,0.000007320963,0.8034155,0.001639788,0.02952489],"study_design_scores_gemma":[0.0004559327,0.0001078303,0.0009492292,0.00002413578,0.00002496358,0.00009606746,0.000006923928,0.4646638,0.000003281443,0.5334821,0.0001080475,0.00007762013],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.004489921,0.000765975,0.9869781,0.007298457,0.0001393472,0.0002099695,0.00009284593,0.00001156237,0.00001378097],"genre_scores_gemma":[0.3112903,0.00006376345,0.6876686,0.0008304665,0.0001061962,0.000008544285,0.000002019278,0.000007758885,0.00002239802],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.3068003,"threshold_uncertainty_score":0.3991015,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01124520141011327,"score_gpt":0.2784303576061979,"score_spread":0.2671851561960846,"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."}}