{"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":"codex-gemma-dda1882f352a","candidate_categories":["open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.0006144479,0.0001783007,0.0001586296,0.00009878109,0.0001367176,0.0007187375,0.06067123,0.00005474001,0.000005852321],"category_scores_gemma":[0.002190503,0.0001087937,0.00002226658,0.000540113,0.0001087137,0.002232831,0.1880036,0.0002254338,0.000006386877],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006170615,"about_ca_system_score_gemma":0.00007356221,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002458697,"about_ca_topic_score_gemma":0.00000439566,"domain_scores_codex":[0.9979073,0.000008359325,0.0002762197,0.0009526436,0.0005804601,0.0002750224],"domain_scores_gemma":[0.9910303,0.00004155147,0.0001532198,0.00866363,0.0000705404,0.00004075168],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001625957,0.0001641962,0.00100321,0.0005199866,0.0002933775,0.000009384084,0.000225371,0.000006422483,0.2831479,0.05151263,0.49159,0.1715113],"study_design_scores_gemma":[0.000247204,0.00006831759,0.000303515,0.0005072265,0.00007080236,0.00006341887,0.00001826497,0.7458063,0.1850115,0.05108628,0.01653962,0.0002775803],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1259103,0.003258101,0.6546767,0.2030717,0.002961974,0.002106714,0.0005918669,0.003430682,0.003991972],"genre_scores_gemma":[0.5929699,0.0001266393,0.4064898,0.00009521964,0.0001368702,0.00001553975,0.00008210901,0.0000226154,0.00006137987],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7457999,"threshold_uncertainty_score":0.944411,"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."}}