{"id":"W3152330735","doi":"10.1080/01621459.2021.1909597","title":"Balancing Inferential Integrity and Disclosure Risk Via Model Targeted Masking and Multiple Imputation","year":2021,"lang":"en","type":"article","venue":"Journal of the American Statistical Association","topic":"Privacy-Preserving Technologies in Data","field":"Computer Science","cited_by":16,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University; University of Alberta","funders":"Eunice Kennedy Shriver National Institute of Child Health and Human Development; National Cancer Institute; Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Imputation (statistics); Inference; Risk model; Econometrics; Statistics; Missing data; Mathematics; Artificial intelligence; Machine learning","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":true,"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":[0.1474679,0.00127963,0.002119868,0.002085719,0.001943655,0.006164325,0.004833904,0.003154865,0.00149063],"category_scores_gemma":[0.3638474,0.001262227,0.001960911,0.003171493,0.005389826,0.01006597,0.01195074,0.005003737,0.0004814728],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002582798,"about_ca_system_score_gemma":0.007013618,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001242492,"about_ca_topic_score_gemma":0.0009991775,"domain_scores_codex":[0.8068689,0.1607243,0.006786201,0.009137033,0.0145561,0.001927507],"domain_scores_gemma":[0.5385876,0.3106771,0.02897527,0.1101746,0.009765767,0.001819552],"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":[0.002549907,0.0003660088,0.04722594,0.00135416,0.001909518,0.0007878522,0.009016158,0.1081406,0.01132012,0.3593984,0.004842028,0.4530894],"study_design_scores_gemma":[0.0003093247,0.0006485192,0.007039525,0.0005087272,0.0006395075,0.001005149,0.000954668,0.3962874,0.02037327,0.5614627,0.01059228,0.0001789502],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03080327,0.0008391251,0.9619458,0.003605021,0.00007491512,0.0002708771,0.0001992356,0.0003987298,0.001863153],"genre_scores_gemma":[0.6469623,0.0003876431,0.3499972,0.0008631593,0.0001631753,0.0005057285,0.0002362229,0.0001167266,0.0007678196],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.1474679,"threshold_uncertainty_score":0.7798939,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01034028780123936,"score_gpt":0.2628697703301932,"score_spread":0.2525294825289539,"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."}}