{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00788986,0.0008656795,0.002060821,0.0008451379,0.001394599,0.002118954,0.00316956,0.002410234,0.004177976],"category_scores_gemma":[0.01957417,0.0009090114,0.001332526,0.001636231,0.001638482,0.00444936,0.00421889,0.003541369,0.001445752],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001221165,"about_ca_system_score_gemma":0.002484262,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004194726,"about_ca_topic_score_gemma":0.0061244,"domain_scores_codex":[0.9963259,0.002211665,0.000151305,0.0006058922,0.0004441502,0.0002610155],"domain_scores_gemma":[0.9902934,0.005614437,0.0003339862,0.002316861,0.001177835,0.0002635574],"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":[0.0009273949,0.0005637128,0.003718135,0.0001741267,0.0002671286,0.0001353588,0.0004086819,0.5143079,0.003488214,0.09435849,0.01224326,0.3694077],"study_design_scores_gemma":[0.00001576742,0.00003856306,0.0001365831,0.00001025213,0.00001236463,0.00002107782,0.0000153723,0.9835346,0.0009076748,0.01453629,0.0007614149,0.00001008615],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01621665,0.0003624769,0.9808075,0.0003520248,0.0000512345,0.00003649349,0.00008763138,0.0007867596,0.001299344],"genre_scores_gemma":[0.5227696,0.0004986349,0.4584683,0.0007802807,0.00018364,0.0003497758,0.00140197,0.0005152512,0.01503253],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.00788986,"threshold_uncertainty_score":0.04172611,"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."}}