{"id":"W2612562696","doi":"10.1109/icit.2017.7915513","title":"Unsupervised learning of finite mixtures using scaled dirichlet distribution and its application to software modules categorization","year":2017,"lang":"en","type":"article","venue":"","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":46,"is_retracted":false,"has_abstract":true,"ca_institutions":"Concordia University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Dirichlet distribution; Mixture model; Computer science; Expectation–maximization algorithm; Latent Dirichlet allocation; Artificial intelligence; Flexibility (engineering); Machine learning; Dirichlet process; Data mining; Pattern recognition (psychology); Algorithm; Topic model; Mathematics; Maximum likelihood; Statistics","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0003064203,0.0001039192,0.0001502798,0.00004854998,0.0003660076,0.0001511508,0.0003742473,0.00007086417,0.000001781739],"category_scores_gemma":[0.0003185041,0.00009170837,0.00002721652,0.0001192236,0.00002324633,0.0004325535,0.000211825,0.0000708204,0.000001827313],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000176944,"about_ca_system_score_gemma":0.00001870619,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006603626,"about_ca_topic_score_gemma":0.000004498734,"domain_scores_codex":[0.9991543,0.00007157757,0.0001853828,0.0003048034,0.0001409798,0.0001429504],"domain_scores_gemma":[0.9991505,0.00005979156,0.0001577807,0.0003916193,0.0001605572,0.0000797095],"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":[0.00002282724,0.00006559285,0.005467482,0.0001177397,0.0000236272,0.000001683745,0.0008167227,0.006531163,0.1495672,0.2550696,0.00005309634,0.5822634],"study_design_scores_gemma":[0.0002189064,0.00003690677,0.01130484,0.00002725112,0.00001146699,0.000002427087,0.000003859838,0.930183,0.04615112,0.0117226,0.0001738202,0.0001637898],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0547843,0.00007783601,0.9445021,0.0002333503,0.0000524122,0.0002059264,0.000005894189,0.00006348812,0.00007473082],"genre_scores_gemma":[0.7034687,0.00001127722,0.2963875,0.00003253493,0.00002537142,0.00000743314,0.00001368916,0.000004889667,0.00004866615],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9236518,"threshold_uncertainty_score":0.3739759,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02167367406103386,"score_gpt":0.2850443828201396,"score_spread":0.2633707087591057,"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."}}