{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.000701657,0.0000888159,0.0002288658,0.00004911796,0.0001434193,0.0001642611,0.001319029,0.00004852525,0.00000110056],"category_scores_gemma":[0.04980594,0.00006571352,0.00003758876,0.0002813192,0.00008050392,0.0003875174,0.004976555,0.0006008736,3.980617e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002146437,"about_ca_system_score_gemma":0.00009755035,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007533052,"about_ca_topic_score_gemma":0.00003297166,"domain_scores_codex":[0.9986365,0.0003062275,0.0003236533,0.0001711724,0.0003959768,0.0001664652],"domain_scores_gemma":[0.997146,0.001005251,0.001034845,0.0005211033,0.0002460497,0.0000467167],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00005573973,0.0001438937,0.6920136,0.00003354908,0.0003007639,0.00003185769,0.0005769155,0.00271831,0.006765893,0.003032796,0.01487916,0.2794476],"study_design_scores_gemma":[0.0001857319,0.00003296715,0.1756267,0.00001498873,0.0000297673,0.00001668614,0.0000357979,0.6576316,0.0004154172,0.1659433,0.000008364828,0.00005856144],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2865448,0.00002997298,0.7076175,0.005591787,0.0001113644,0.00002898281,0.00004985452,0.00002128029,0.000004464192],"genre_scores_gemma":[0.6465213,0.0000694214,0.3533083,0.00006588372,0.00002596361,3.799436e-7,0.000002610873,0.00000347182,0.000002653955],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.6549134,"threshold_uncertainty_score":0.958198,"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."}}