{"id":"W207560109","doi":"10.1007/978-3-642-21881-1_42","title":"Learning Inverted Dirichlet Mixtures for Positive Data Clustering","year":2011,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":23,"is_retracted":false,"has_abstract":false,"ca_institutions":"Concordia University","funders":"","keywords":"Cluster analysis; Computer science; Dirichlet distribution; Expectation–maximization algorithm; Maximization; Model selection; Selection (genetic algorithm); Algorithm; Minimum description length; Latent Dirichlet allocation; Artificial intelligence; Data mining; Pattern recognition (psychology); Maximum likelihood; Mathematical optimization; Topic model; Mathematics; Statistics","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":["metaepi_narrow","open_science"],"consensus_categories":[],"category_scores_codex":[0.002003851,0.000664671,0.0007108958,0.0006960565,0.0004609028,0.0005722473,0.006991436,0.0004567101,0.00001230368],"category_scores_gemma":[0.000261152,0.0005944982,0.0001457917,0.0004477001,0.0006069968,0.00101616,0.005015346,0.001095915,0.00001305164],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001591975,"about_ca_system_score_gemma":0.0004440512,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004604113,"about_ca_topic_score_gemma":0.00008035868,"domain_scores_codex":[0.9952583,0.00009992693,0.000556309,0.002478437,0.0006492542,0.0009577193],"domain_scores_gemma":[0.9958187,0.000768151,0.0003763788,0.002509653,0.0002980591,0.0002290183],"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":[0.00001469043,0.00001898629,0.000008447308,0.00005147229,0.00002632807,0.0000426728,0.00118575,0.00139691,0.000176541,0.02594396,0.000078174,0.971056],"study_design_scores_gemma":[0.0002642105,0.0002208316,0.00002552782,0.0003327828,0.00001870801,0.00005791501,7.465492e-8,0.6684594,0.0008665333,0.3271483,0.001936362,0.0006693626],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.000003054334,0.0006318737,0.9920489,0.000546933,0.001666353,0.0006626924,0.00002933143,0.0002077579,0.004203108],"genre_scores_gemma":[0.0105957,0.00006731765,0.9861576,0.001831763,0.0005509696,0.00001452931,0.00004638711,0.00006035864,0.0006753837],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9703867,"threshold_uncertainty_score":0.9996507,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04864157303338876,"score_gpt":0.288367066147882,"score_spread":0.2397254931144932,"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."}}