{"id":"W4316035893","doi":"10.1007/s10489-022-04378-3","title":"Cross-collection latent Beta-Liouville allocation model training with privacy protection and applications","year":2023,"lang":"en","type":"article","venue":"Applied Intelligence","topic":"Privacy-Preserving Technologies in Data","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":false,"ca_institutions":"Concordia University","funders":"Natural Sciences and Engineering Research Council of Canada; National Natural Science Foundation of China","keywords":"Computer science; Latent Dirichlet allocation; Inference; Topic model; Data collection; Leverage (statistics); Differential privacy; Data mining; Hierarchical Dirichlet process; Artificial intelligence; Machine learning; Statistics","routes":{"ca_aff":true,"ca_fund":true,"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":[],"consensus_categories":[],"category_scores_codex":[0.0004188563,0.0001820062,0.0001488155,0.0002775087,0.0004079708,0.0002537802,0.004757917,0.0001245246,0.000004103821],"category_scores_gemma":[0.0003747938,0.0001691401,0.00002176516,0.001925424,0.0001702395,0.000533075,0.007336174,0.0002600908,0.00008565782],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009966661,"about_ca_system_score_gemma":0.00008923972,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004240019,"about_ca_topic_score_gemma":0.00001156282,"domain_scores_codex":[0.9983271,0.00001433976,0.0002761623,0.0007398804,0.0003008407,0.0003416952],"domain_scores_gemma":[0.9968666,0.00006611132,0.0001349106,0.002770139,0.0001004339,0.00006180262],"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":[0.00004192421,0.00009080475,0.0003845183,0.00009590895,0.00006104034,0.000003162766,0.001728051,0.0289462,0.01079338,0.182489,0.002254368,0.7731116],"study_design_scores_gemma":[0.00007781984,0.00004800113,0.0005953054,0.00001595117,0.00000566259,0.00001210051,0.00007617482,0.7549572,0.02992742,0.2136549,0.0004221885,0.0002073447],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01437298,0.00002347824,0.9791408,0.002644387,0.00004620938,0.001019773,0.000003491507,0.001781552,0.0009673943],"genre_scores_gemma":[0.836569,0.0001107255,0.1616365,0.00005446853,0.00002493709,0.001463864,0.00001557151,0.00001870369,0.0001062929],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.822196,"threshold_uncertainty_score":0.9144015,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07963119710981355,"score_gpt":0.3006370116237224,"score_spread":0.2210058145139089,"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."}}