{"id":"W2054765427","doi":"10.1007/s10115-011-0467-4","title":"A countably infinite mixture model for clustering and feature selection","year":2011,"lang":"en","type":"article","venue":"Knowledge and Information Systems","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":52,"is_retracted":false,"has_abstract":false,"ca_institutions":"Université de Sherbrooke; Concordia University","funders":"","keywords":"Mixture model; Cluster analysis; Model selection; Computer science; Artificial intelligence; Feature selection; Dirichlet process; Dirichlet distribution; Machine learning; Bayesian inference; Inference; Pattern recognition (psychology); Data mining; Mathematics; Bayesian probability","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":[0.0004031151,0.000118814,0.0001515694,0.000126446,0.000158266,0.0002236549,0.0001213337,0.0001288349,4.22812e-7],"category_scores_gemma":[0.00001484988,0.00009857066,0.00002465625,0.0001444443,0.00001456053,0.002750146,0.00006778618,0.00008676936,0.000004545022],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000182719,"about_ca_system_score_gemma":0.00004115783,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000008812988,"about_ca_topic_score_gemma":0.000007460337,"domain_scores_codex":[0.9993963,0.00003087386,0.0002185469,0.0001297076,0.00007045898,0.0001541486],"domain_scores_gemma":[0.9994591,0.00002739257,0.0001065288,0.0001321803,0.0001980505,0.00007672417],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00006700397,0.00003667004,0.0002848406,0.001493848,0.00005854954,3.388237e-7,0.09350681,0.0002370422,0.0003108859,0.6711775,0.01373329,0.2190932],"study_design_scores_gemma":[0.0003384,0.00004449866,0.0001425324,0.00005167727,0.000006953088,0.00004260056,0.00005797865,0.9687272,0.00006251068,0.001145852,0.02924774,0.0001320728],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0004484888,0.0006697313,0.983844,0.00003446662,0.0002879308,0.0003435014,0.000007453755,0.0000810636,0.01428341],"genre_scores_gemma":[0.5823224,0.0001579087,0.4155915,0.0003933853,0.0001491964,0.0001524996,0.00001226941,0.00001141436,0.001209377],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9684901,"threshold_uncertainty_score":0.4019595,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02864478443536663,"score_gpt":0.2546671348517391,"score_spread":0.2260223504163725,"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."}}