{"id":"W4387800198","doi":"10.48550/arxiv.2310.11548","title":"Differentially Private Data Generation with Missing Data","year":2023,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Privacy-Preserving Technologies in Data","field":"Computer Science","cited_by":0,"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":[0.01696392,0.0007204373,0.001090937,0.0008868352,0.0009413716,0.002207249,0.002627463,0.001847516,0.001408761],"category_scores_gemma":[0.06388702,0.0005132855,0.0009971771,0.001513506,0.002559932,0.004149779,0.004192864,0.003120493,0.0004127614],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001420379,"about_ca_system_score_gemma":0.001590505,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004894154,"about_ca_topic_score_gemma":0.0004667406,"domain_scores_codex":[0.9878395,0.00736498,0.0005671047,0.001485474,0.002268219,0.0004748149],"domain_scores_gemma":[0.9269989,0.04630942,0.003773209,0.01912471,0.003045804,0.0007479583],"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":[0.001214492,0.0002857572,0.01295196,0.0004075594,0.0002187644,0.000522812,0.0009767776,0.5955211,0.01233144,0.2149158,0.005703779,0.1549498],"study_design_scores_gemma":[0.00007992044,0.0001377325,0.0006459712,0.00004230519,0.00002408821,0.0003677476,0.0001461006,0.8294696,0.01138106,0.1549974,0.002676314,0.00003172331],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.03403743,0.0002142749,0.9628949,0.0008769526,0.00004851806,0.0001206034,0.000364238,0.0003573729,0.001085809],"genre_scores_gemma":[0.7585073,0.0001904241,0.2385291,0.000508885,0.00007055892,0.0002777523,0.0008932903,0.0001028094,0.0009198753],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01696392,"threshold_uncertainty_score":0.08971483,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.3124674934964199,"score_gpt":0.2476308599953372,"score_spread":0.06483663350108279,"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."}}