{"id":"W2907794603","doi":"10.1007/s13042-018-0900-z","title":"Simultaneous clustering and feature selection via nonparametric Pitman–Yor process mixture models","year":2019,"lang":"en","type":"article","venue":"International Journal of Machine Learning and Cybernetics","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":false,"ca_institutions":"Concordia University","funders":"National Natural Science Foundation of China","keywords":"Dirichlet process; Computer science; Mixture model; Artificial intelligence; Machine learning; Cluster analysis; Model selection; Inference; Nonparametric statistics; Hierarchical Dirichlet process; Feature selection; Process (computing); Bayesian inference; Feature (linguistics); Generative model; Bayesian probability; Generative grammar; Latent Dirichlet allocation; Mathematics; Topic model; Econometrics","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":[0.0003959857,0.0001492694,0.0002084621,0.0002454288,0.00005764045,0.0002269667,0.0003727277,0.000106284,0.000007192131],"category_scores_gemma":[0.0001202451,0.0001222633,0.00005351662,0.0001777702,0.00002132088,0.0003211007,0.0001239578,0.0006794683,0.000001998368],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003087238,"about_ca_system_score_gemma":0.00003285085,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001119521,"about_ca_topic_score_gemma":0.000004631464,"domain_scores_codex":[0.9988651,0.000102511,0.0002485817,0.0002163984,0.0004190101,0.0001484551],"domain_scores_gemma":[0.9989139,0.0002254923,0.0003060082,0.00006935885,0.000384982,0.0001002232],"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":[0.0002009142,0.000121218,0.01095991,0.0000861846,0.0002579445,0.0001409392,0.002879635,0.170581,0.002494183,0.004851243,0.00008616631,0.8073406],"study_design_scores_gemma":[0.0005708704,0.0002693775,0.0003183211,0.00007586686,0.00001721298,0.001565319,0.00001278272,0.9857829,0.0001919031,0.009494615,0.001556624,0.0001442747],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.09765582,0.001421931,0.8990861,0.0008251384,0.0003911203,0.00006200292,9.412257e-7,0.00002349311,0.0005334303],"genre_scores_gemma":[0.8590794,0.0003490327,0.139234,0.0001606935,0.0001506613,5.583873e-7,0.000001052023,0.00001200196,0.001012626],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8152018,"threshold_uncertainty_score":0.4985751,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.005642067798220262,"score_gpt":0.2623153025612442,"score_spread":0.256673234763024,"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."}}