{"id":"W2096784803","doi":"10.1109/tpami.2007.1095","title":"High-Dimensional Unsupervised Selection and Estimation of a Finite Generalized Dirichlet Mixture Model Based on Minimum Message Length","year":2007,"lang":"en","type":"article","venue":"IEEE Transactions on Pattern Analysis and Machine Intelligence","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":169,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Sherbrooke; Concordia University","funders":"University of California, Irvine","keywords":"Minimum description length; Generalized Dirichlet distribution; Mixture model; Hierarchical Dirichlet process; Dirichlet distribution; Cluster analysis; Latent Dirichlet allocation; Mathematics; Computer science; Model selection; Algorithm; Determining the number of clusters in a data set; Automatic summarization; Pattern recognition (psychology); Artificial intelligence; Topic model; Dirichlet's principle; Correlation clustering; CURE data clustering algorithm","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":[0.0006693006,0.0002657941,0.0004084686,0.000726112,0.0001771576,0.000061388,0.0002063495,0.0001236152,0.0000463726],"category_scores_gemma":[0.000009429482,0.000222647,0.0001876271,0.0009953924,0.00005245326,0.0001721356,0.000004952339,0.0002621909,0.000001729318],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002279483,"about_ca_system_score_gemma":0.00002988353,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003437356,"about_ca_topic_score_gemma":0.000389992,"domain_scores_codex":[0.9982287,0.0001490855,0.0004659922,0.0005672296,0.0003575029,0.0002314718],"domain_scores_gemma":[0.9989521,0.0002958413,0.0001490703,0.0003566839,0.000104867,0.0001414752],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00005524016,0.000151339,0.00002465885,0.00001786088,0.0001272141,0.000002793861,0.0001357116,0.588766,0.001765587,0.0005046509,0.000002771386,0.4084461],"study_design_scores_gemma":[0.0002274704,0.0001512443,0.0001650407,0.00002615636,0.0002583931,0.000003123486,0.000002295287,0.8608004,0.1370116,0.001164152,0.000001809434,0.0001882728],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0203106,0.00005636992,0.9790038,0.0002835246,0.00008138119,0.0001486111,0.00004145832,0.00005164169,0.00002261688],"genre_scores_gemma":[0.7654629,0.00005032983,0.2338655,0.000527448,0.000009125491,0.000008462421,0.00000861118,0.000009987315,0.0000575995],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7451523,"threshold_uncertainty_score":0.9079282,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01552536188303195,"score_gpt":0.2702911791012604,"score_spread":0.2547658172182285,"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."}}