{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00505355,0.0008643343,0.002021387,0.002865177,0.0009325054,0.002629866,0.002109993,0.001916407,0.001880766],"category_scores_gemma":[0.01596806,0.0007340218,0.001942171,0.003894628,0.00150427,0.005674833,0.002384468,0.001889949,0.001070555],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002673757,"about_ca_system_score_gemma":0.002291246,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00801696,"about_ca_topic_score_gemma":0.005623979,"domain_scores_codex":[0.995417,0.002055105,0.0003161781,0.0007378423,0.001148816,0.0003249878],"domain_scores_gemma":[0.996078,0.002301923,0.0002966954,0.0005343432,0.0006591377,0.0001298604],"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":[0.0003849703,0.0003406611,0.003128523,0.0004270664,0.0002305664,0.0001806015,0.0007191582,0.2541259,0.008714218,0.3024294,0.00607063,0.4232484],"study_design_scores_gemma":[0.00001859987,0.0000310693,0.0003701955,0.00001614572,0.00002444287,0.00007740979,0.00003332117,0.9191942,0.001282334,0.07642027,0.002494155,0.00003785728],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.004808304,0.0005047363,0.9933136,0.0001802965,0.00002614885,0.00004614748,0.00005525638,0.0002837418,0.0007816789],"genre_scores_gemma":[0.4247935,0.002394324,0.5638268,0.000447164,0.0003431374,0.000494034,0.0008456622,0.0002454033,0.006609989],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.00801696,"threshold_uncertainty_score":0.02672607,"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."}}