{"id":"W2068406209","doi":"10.1016/j.patcog.2008.06.022","title":"Discrete data clustering using finite mixture models","year":2008,"lang":"en","type":"article","venue":"Pattern Recognition","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":48,"is_retracted":false,"has_abstract":false,"ca_institutions":"Concordia University","funders":"","keywords":"Mixture model; Automatic summarization; Computer science; Robustness (evolution); Cluster analysis; Pattern recognition (psychology); Artificial intelligence; Dirichlet distribution; Algorithm; Data mining; Mathematics","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":[0.0003161053,0.0001760668,0.0001795522,0.00009723824,0.0002078479,0.0000989122,0.000864499,0.00009643199,0.00001818507],"category_scores_gemma":[0.00002574243,0.0001656489,0.00005369152,0.000192553,0.00003124669,0.00158731,0.0006157476,0.0001941245,0.00003407901],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002461067,"about_ca_system_score_gemma":0.0000351683,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007376144,"about_ca_topic_score_gemma":0.0000145163,"domain_scores_codex":[0.9984859,0.0001488731,0.0002425853,0.0005944733,0.0002291451,0.0002990329],"domain_scores_gemma":[0.9986951,0.00007948957,0.0001073138,0.0009531822,0.00006432794,0.0001005723],"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":[0.000007700733,0.00004217686,0.0001847406,0.00004696879,0.00002767824,0.0001080823,0.0009952293,0.0006686983,0.0008986818,0.00006882894,0.0003444266,0.9966068],"study_design_scores_gemma":[0.0002310784,0.00001895444,0.0001114304,0.00008086656,0.00001331933,0.0001863547,0.000004008501,0.9807253,0.0005566116,0.01770055,0.0001173282,0.0002541456],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.008617554,0.0001127988,0.989397,0.0002061172,0.0003894278,0.0001483595,0.00006197329,0.0001405268,0.0009262408],"genre_scores_gemma":[0.377831,0.00008531745,0.6210182,0.0006917504,0.0002070728,0.000006462443,0.0001045128,0.00001853678,0.00003712383],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9963526,"threshold_uncertainty_score":0.6754968,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1837551475213755,"score_gpt":0.3141076386796353,"score_spread":0.1303524911582598,"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."}}