{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.006036815,0.0009104893,0.001446586,0.001823855,0.001644006,0.00163193,0.002726887,0.002048505,0.005229065],"category_scores_gemma":[0.01916748,0.00113037,0.001560242,0.001573774,0.002174704,0.003089919,0.003432098,0.003858297,0.001791526],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001223848,"about_ca_system_score_gemma":0.002289227,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002590694,"about_ca_topic_score_gemma":0.003214995,"domain_scores_codex":[0.9954781,0.002498612,0.0001673707,0.0006402982,0.001071008,0.0001447111],"domain_scores_gemma":[0.9947569,0.003652781,0.0002247108,0.0006266129,0.0005545372,0.00018446],"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":[0.0003406987,0.0001601397,0.001961703,0.0002697139,0.0002559416,0.0002325594,0.0008318924,0.2716902,0.005602613,0.4526477,0.006194894,0.2598119],"study_design_scores_gemma":[0.00005971825,0.00003552068,0.0002792362,0.00003200908,0.00003823051,0.0001418121,0.00004131788,0.8528287,0.00295329,0.1344462,0.009085727,0.00005819574],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0009630109,0.00005930826,0.9983194,0.00005517008,0.00001501264,0.0000441407,0.00002023394,0.0001755532,0.0003481406],"genre_scores_gemma":[0.03137666,0.0001193398,0.9668705,0.00007138548,0.00004137934,0.000274892,0.0001490519,0.0001773364,0.0009195658],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.006036815,"threshold_uncertainty_score":0.03192616,"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."}}