{"id":"W2123094878","doi":"","title":"Tree-Structured Stick Breaking for Hierarchical Data","year":2010,"lang":"en","type":"article","venue":"Neural Information Processing Systems","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":137,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Markov chain Monte Carlo; Hierarchical database model; Tree structure; Cluster analysis; Tree (set theory); Hierarchical clustering; Bayesian inference; Data mining; Algorithm; Bayesian probability; Theoretical computer science; Mathematics; Artificial intelligence; Binary tree","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":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0006692196,0.0001504575,0.0001894879,0.0001197456,0.0002721427,0.001203386,0.001345998,0.0001258127,0.000001656245],"category_scores_gemma":[0.0001986914,0.0001186932,0.00003456381,0.000234063,0.0000387472,0.005284132,0.0002148401,0.0002882918,0.000005566268],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001003675,"about_ca_system_score_gemma":0.0001158998,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001650438,"about_ca_topic_score_gemma":0.000008229025,"domain_scores_codex":[0.9986669,0.00004531028,0.0004837115,0.0002485148,0.00027976,0.0002757923],"domain_scores_gemma":[0.998578,0.00009548951,0.0002866503,0.0007376051,0.0001970061,0.0001053108],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000008552557,0.000006245245,0.00001664724,0.0002516727,0.000004628752,5.239289e-7,0.001000651,0.00005574284,0.001270003,0.04611196,0.001368679,0.9499047],"study_design_scores_gemma":[0.0002966162,0.00002248079,0.0001326442,0.00003402929,0.000006430737,0.0001056325,0.00001904734,0.9771347,0.0002319321,0.003097704,0.01875703,0.0001617232],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001467369,0.00004410333,0.9944399,0.0005430471,0.001729994,0.0003699114,0.0000268501,0.0002313771,0.001147466],"genre_scores_gemma":[0.6035504,5.026927e-7,0.3956171,0.0003759789,0.0002877887,0.00003141219,0.00007129092,0.000007481575,0.00005799459],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.977079,"threshold_uncertainty_score":0.9998335,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03733069654240435,"score_gpt":0.3100610288616286,"score_spread":0.2727303323192243,"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."}}