{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005170252,0.0008726295,0.002217145,0.002212464,0.001062252,0.002115807,0.002860949,0.001716326,0.001372297],"category_scores_gemma":[0.01873899,0.001079162,0.001738452,0.001760622,0.001670036,0.002502149,0.001820354,0.00206971,0.0007915364],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001556094,"about_ca_system_score_gemma":0.001310929,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00488041,"about_ca_topic_score_gemma":0.004446501,"domain_scores_codex":[0.9970113,0.001700058,0.0001260523,0.0005348664,0.0004457402,0.0001819295],"domain_scores_gemma":[0.990514,0.007330659,0.0006169091,0.0005309993,0.0008266189,0.0001806403],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0002338636,0.00008180459,0.002291716,0.0001670109,0.000152791,0.0001534645,0.0004166243,0.8416802,0.00301616,0.04038812,0.001755197,0.1096631],"study_design_scores_gemma":[0.00000581659,0.000008125781,0.0001487384,0.000007635752,0.000006242457,0.00001290596,0.00001014058,0.988147,0.000455887,0.01094402,0.0002401022,0.00001336323],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.008314962,0.0001135603,0.9910486,0.0001249602,0.0000140209,0.00002359608,0.00003227088,0.0001304848,0.0001976047],"genre_scores_gemma":[0.3195092,0.000493832,0.6753384,0.0002055689,0.0001713262,0.0004384808,0.0008590191,0.0002565937,0.002727526],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005170252,"threshold_uncertainty_score":0.02734327,"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."}}