{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.000951001,0.0004833589,0.0004561729,0.001233545,0.0003593407,0.00065717,0.002986335,0.0004125882,0.0000095175],"category_scores_gemma":[0.0001451208,0.0004478585,0.0001726618,0.001099067,0.000424973,0.000785225,0.0007616151,0.0004718207,0.000113183],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006552235,"about_ca_system_score_gemma":0.0005036987,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000160788,"about_ca_topic_score_gemma":0.00005520373,"domain_scores_codex":[0.9960753,0.00002838894,0.0006522808,0.001741381,0.0008767145,0.0006258818],"domain_scores_gemma":[0.9969337,0.0005346711,0.0004045327,0.001506802,0.0005102267,0.0001100961],"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":[0.000009641351,0.00003346741,0.00004940703,0.00005072176,0.00002550186,0.000003405136,0.0005024795,0.00291819,0.0008902133,0.3738523,0.0002561769,0.6214085],"study_design_scores_gemma":[0.0005518047,0.0003169584,0.00103291,0.0001959999,0.00001840894,0.000006590604,0.000001389335,0.4282601,0.008812909,0.5574574,0.002539144,0.0008064136],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00005634531,0.0001270818,0.9885377,0.006805224,0.001278955,0.001283668,0.000008137548,0.0009522107,0.000950698],"genre_scores_gemma":[0.4670009,0.0003108339,0.5258436,0.001145759,0.0004620603,0.0006546789,0.0001074007,0.0001175621,0.004357164],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.620602,"threshold_uncertainty_score":0.9997973,"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."}}