{"id":"W1587070286","doi":"10.1007/11510888_5","title":"MML-Based Approach for Finite Dirichlet Mixture Estimation and Selection","year":2005,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":51,"is_retracted":false,"has_abstract":false,"ca_institutions":"Université de Sherbrooke","funders":"","keywords":"Minimum description length; Automatic summarization; Computer science; Dirichlet distribution; Artificial intelligence; Selection (genetic algorithm); Model selection; Unsupervised learning; Pattern recognition (psychology); Bayesian probability; Machine learning; Data mining; Algorithm; 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004895261,0.001508722,0.002723516,0.002196242,0.001170927,0.002786343,0.005311246,0.003015087,0.01343359],"category_scores_gemma":[0.01889276,0.001715541,0.002442866,0.003240531,0.001213609,0.003085604,0.004053292,0.004484666,0.008925811],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001377005,"about_ca_system_score_gemma":0.001678532,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004798003,"about_ca_topic_score_gemma":0.007281608,"domain_scores_codex":[0.9955166,0.002544099,0.0002479673,0.0004691161,0.001064582,0.0001576024],"domain_scores_gemma":[0.9917903,0.005957407,0.0001706772,0.0008315679,0.001102626,0.000147342],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0002755172,0.0001741896,0.0007189796,0.000441189,0.0003485225,0.000247662,0.0003283432,0.2175128,0.005458473,0.199009,0.01754794,0.5579374],"study_design_scores_gemma":[0.00001895822,0.00001521528,0.00008668211,0.00002042017,0.00003153726,0.00008342365,0.00001477206,0.9352305,0.001360197,0.0569583,0.006153445,0.00002650896],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0001653424,0.00009996184,0.9990896,0.00003833999,0.0000247068,0.00001230763,0.00002910076,0.0002307422,0.0003098964],"genre_scores_gemma":[0.01517425,0.0003179096,0.9783341,0.0002129393,0.0001883883,0.0003475521,0.0005533322,0.0005051267,0.004366466],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01343359,"threshold_uncertainty_score":0.04493982,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0185513968506605,"score_gpt":0.2607570820387777,"score_spread":0.2422056851881172,"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."}}