{"id":"W4318604488","doi":"10.1109/ssci51031.2022.10022072","title":"Bayesian Folding-In Using Generalized Dirichlet and Beta-Liouville Kernels for Information Retrieval","year":2022,"lang":"en","type":"article","venue":"2022 IEEE Symposium Series on Computational Intelligence (SSCI)","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Concordia University","funders":"","keywords":"Latent Dirichlet allocation; Probabilistic latent semantic analysis; Dirichlet distribution; Computer science; Kernel (algebra); Bayesian probability; Topic model; Mixture model; Folding (DSP implementation); Artificial intelligence; Pattern recognition (psychology); 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":[0.0005804918,0.0002337777,0.0002562477,0.0006089929,0.0006408639,0.0003606682,0.0008235708,0.0000730467,0.00004967697],"category_scores_gemma":[0.00005657001,0.0002553953,0.00008863973,0.001120541,0.0001158986,0.001585744,0.0003576494,0.0002371564,0.000009285148],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002872732,"about_ca_system_score_gemma":0.0001416329,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000313165,"about_ca_topic_score_gemma":0.000005688848,"domain_scores_codex":[0.9978163,0.0001061952,0.0006165751,0.0004887119,0.0006265027,0.0003457078],"domain_scores_gemma":[0.9988813,0.0002478139,0.0003007038,0.0003488174,0.0001485585,0.00007278655],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00014475,0.0001002694,0.0002677151,0.00003243359,0.00002589288,0.000003972441,0.001134447,0.5459478,0.001317554,0.4455093,0.0007996898,0.004716207],"study_design_scores_gemma":[0.0003693123,0.0005293095,0.0002552091,0.00001529686,0.000009670512,0.00003641282,0.0007486224,0.9274337,0.01115403,0.05082149,0.008212791,0.0004141643],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05230389,0.00008833194,0.9408935,0.004412625,0.0009873806,0.0007202415,0.00007229832,0.0002946529,0.0002270766],"genre_scores_gemma":[0.9465967,0.00005054476,0.05215905,0.0006933205,0.000046053,0.0001661219,0.00008430866,0.0000166713,0.0001872022],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8942928,"threshold_uncertainty_score":0.9999898,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0287169286179947,"score_gpt":0.2829308803661048,"score_spread":0.2542139517481101,"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."}}