{"id":"W4399208560","doi":"10.14778/3659437.3659455","title":"Differentially Private Data Generation with Missing Data","year":2024,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Privacy-Preserving Technologies in Data","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Missing data; Synthetic data; Differential privacy; Computer science; Data mining; Data quality; Ground truth; Process (computing); Data modeling; Algorithm; Machine learning; Engineering; Database","routes":{"ca_aff":true,"ca_fund":false,"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":[0.01599009,0.0007255365,0.001106713,0.0008321441,0.0008811821,0.002000749,0.002643329,0.001731245,0.001339406],"category_scores_gemma":[0.05822387,0.0005080013,0.0009941933,0.001462246,0.002353849,0.003975042,0.004129956,0.002925775,0.0003943981],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001337582,"about_ca_system_score_gemma":0.00154132,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005482364,"about_ca_topic_score_gemma":0.0005333509,"domain_scores_codex":[0.9892094,0.006329082,0.0005372912,0.001390086,0.002069341,0.00046495],"domain_scores_gemma":[0.9338632,0.04156884,0.003327686,0.0176508,0.00287859,0.0007109247],"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":[0.001273781,0.0002872397,0.01222103,0.000360349,0.0002012139,0.0005091346,0.0008768094,0.6482317,0.01236256,0.157474,0.005560453,0.1606417],"study_design_scores_gemma":[0.00007191369,0.0001298102,0.0005756423,0.00003260673,0.00002147391,0.0003244028,0.0001246822,0.8756418,0.01034152,0.1104658,0.002242883,0.0000275246],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03537964,0.000205576,0.9617711,0.0007793351,0.00004674575,0.0001152229,0.0003499189,0.0004014275,0.0009510461],"genre_scores_gemma":[0.7573719,0.000172625,0.2397351,0.0004903528,0.00006685988,0.0002565108,0.0009456684,0.00009933224,0.0008616163],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01599009,"threshold_uncertainty_score":0.08456469,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08668987133323494,"score_gpt":0.2909003034966938,"score_spread":0.2042104321634589,"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."}}