{"id":"W4394548503","doi":"10.6084/m9.figshare.14336802.v2","title":"Balancing Inferential Integrity and Disclosure Risk Via Model Targeted Masking and Multiple Imputation","year":2021,"lang":"en","type":"dataset","venue":"Figshare","topic":"Privacy-Preserving Technologies in Data","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Imputation (statistics); Computer science; Masking (illustration); Inference; Data mining; Missing data; Artificial intelligence; Machine learning","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.1142145,0.001233927,0.001491484,0.002410066,0.001956102,0.006296567,0.003991556,0.002477678,0.01705815],"category_scores_gemma":[0.2921542,0.001360434,0.002471942,0.003857446,0.003329235,0.0058874,0.009028139,0.004012899,0.003624248],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00183379,"about_ca_system_score_gemma":0.007941048,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002044776,"about_ca_topic_score_gemma":0.003113004,"domain_scores_codex":[0.9237701,0.06041328,0.003583476,0.004909693,0.006135565,0.001187958],"domain_scores_gemma":[0.7322342,0.179693,0.01112156,0.06900635,0.00675666,0.001188165],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.002942314,0.0003093971,0.03596664,0.002828627,0.001465726,0.001451424,0.005214121,0.0740025,0.01363896,0.2547268,0.07243893,0.5350145],"study_design_scores_gemma":[0.0007890904,0.0004783588,0.009182895,0.001237641,0.0006258477,0.001438921,0.0007982556,0.2927281,0.03595016,0.5502279,0.1062228,0.0003200634],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"dataset","genre_scores_codex":[0.01791683,0.0007710274,0.9591901,0.005208926,0.0002756471,0.000698457,0.006783162,0.003817567,0.005338238],"genre_scores_gemma":[0.3553368,0.000662347,0.6291706,0.001985977,0.0002943368,0.002635065,0.005828242,0.001271319,0.002815165],"genre_candidate":"dataset","genre_consensus":null,"teacher_disagreement_score":0.1142145,"threshold_uncertainty_score":0.604031,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03167161254001121,"score_gpt":0.269407658802737,"score_spread":0.2377360462627258,"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."}}