{"id":"W4384788087","doi":"10.1007/978-3-031-36819-6_4","title":"A Selective Supervised Latent Beta-Liouville Allocation for Document Classification","year":2023,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"ca_institutions":"Concordia University","funders":"","keywords":"Computer science; Latent Dirichlet allocation; Inference; Artificial intelligence; Bernoulli's principle; Dirichlet distribution; Machine learning; Simple (philosophy); Prior probability; Gibbs sampling; Topic model; Word (group theory); Pattern recognition (psychology); Bayesian probability; 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":[0.003439722,0.0007884504,0.002072194,0.001447525,0.00133153,0.001765022,0.003730559,0.00185714,0.006599693],"category_scores_gemma":[0.00581146,0.0006242861,0.001426027,0.00228975,0.001181635,0.00244659,0.002945446,0.002646349,0.003961762],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00119558,"about_ca_system_score_gemma":0.0023371,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003383661,"about_ca_topic_score_gemma":0.005761694,"domain_scores_codex":[0.9974464,0.001283561,0.0001248264,0.0004175065,0.000522174,0.0002054672],"domain_scores_gemma":[0.997314,0.001264908,0.00009423972,0.0006116931,0.0005716792,0.0001433034],"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":[0.0005600381,0.0004003359,0.0007224342,0.0001694193,0.0001359239,0.00006042704,0.0001612668,0.07629637,0.0120092,0.05606711,0.01652535,0.836892],"study_design_scores_gemma":[0.00004347053,0.00007595666,0.000158734,0.00001485704,0.00002272998,0.00004981839,0.0000218361,0.9624633,0.002991963,0.03113665,0.003002408,0.00001828165],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.003638808,0.0002249704,0.9942643,0.00008506833,0.00005280029,0.00004345731,0.00006741265,0.0008358881,0.0007872308],"genre_scores_gemma":[0.1286932,0.0003594326,0.8542087,0.000394741,0.0003142112,0.0005924364,0.001324623,0.0005445735,0.0135681],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.006599693,"threshold_uncertainty_score":0.02207816,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04136607743477803,"score_gpt":0.2744832432710408,"score_spread":0.2331171658362627,"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."}}