{"id":"W4385625456","doi":"10.1007/s10489-023-04888-8","title":"Unsupervised nested Dirichlet finite mixture model for clustering","year":2023,"lang":"en","type":"article","venue":"Applied Intelligence","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":false,"ca_institutions":"Concordia University","funders":"","keywords":"Hierarchical Dirichlet process; Computer science; Dirichlet distribution; Mixture model; Generalized Dirichlet distribution; Latent Dirichlet allocation; Concentration parameter; Expectation–maximization algorithm; Feature (linguistics); Artificial intelligence; Pattern recognition (psychology); Algorithm; Mathematics; Topic model; Dirichlet's principle; Statistics; Maximum likelihood","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":[0.0005872538,0.0002530921,0.0002679162,0.0001741678,0.0001916708,0.000152706,0.001284269,0.000150593,0.000007286535],"category_scores_gemma":[0.00006907327,0.0002328773,0.0001135197,0.001016756,0.0000452774,0.0002057013,0.0003794155,0.0001888292,0.0001375855],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002643605,"about_ca_system_score_gemma":0.00006438717,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00000406251,"about_ca_topic_score_gemma":0.000005715602,"domain_scores_codex":[0.9981413,0.00003119193,0.0003436197,0.0006827909,0.0002366706,0.0005644389],"domain_scores_gemma":[0.9984545,0.0004416789,0.0000782818,0.0007914307,0.00008940838,0.0001447562],"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":[0.00002831507,0.000036206,0.000004669759,0.00008923213,0.00002408588,0.000007598798,0.002969335,0.07096064,0.006230411,0.4476979,0.002696105,0.4692555],"study_design_scores_gemma":[0.00008809265,0.00002125069,0.00000890826,0.00001578071,0.000006354221,0.000002304976,0.00002050609,0.8311871,0.006006355,0.1611182,0.001276344,0.0002488506],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0002391113,0.00005773818,0.9950361,0.0006400729,0.0002762836,0.0005602972,0.00001027684,0.000624289,0.002555829],"genre_scores_gemma":[0.2445083,0.00007255313,0.7525452,0.001275273,0.00009560735,0.0002792907,0.00001599691,0.00003414678,0.001173601],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.7602264,"threshold_uncertainty_score":0.949646,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05490856148407772,"score_gpt":0.3012650529070272,"score_spread":0.2463564914229494,"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."}}