{"id":"W4406986127","doi":"10.32388/pjil3e","title":"SafeSynthDP: Leveraging Large Language Models for Privacy-Preserving Synthetic Data Generation Using Differential Privacy","year":2025,"lang":"en","type":"preprint","venue":"Qeios","topic":"Privacy-Preserving Technologies in Data","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Differential privacy; Computer science; Internet privacy; Computer security; Information privacy; Privacy software; Privacy protection; Data mining","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":[0.006987459,0.000733157,0.000645904,0.0007415501,0.0006097912,0.002082474,0.002056599,0.001284145,0.001337016],"category_scores_gemma":[0.03282657,0.0004578003,0.0009901688,0.0008176967,0.001711414,0.003139528,0.003905962,0.002607848,0.0007228998],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009870619,"about_ca_system_score_gemma":0.001547037,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001273256,"about_ca_topic_score_gemma":0.001790677,"domain_scores_codex":[0.993371,0.003998538,0.0003259601,0.0008256161,0.001260427,0.0002183109],"domain_scores_gemma":[0.9763753,0.01462787,0.000935464,0.00673907,0.001044462,0.0002777251],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0005793243,0.00035124,0.007785572,0.0002535209,0.0001394464,0.0004022813,0.0006760391,0.7271545,0.01246454,0.1011178,0.006927229,0.1421484],"study_design_scores_gemma":[0.0000251953,0.00005575479,0.0001683641,0.00001129356,0.000006011333,0.00007192198,0.00003778985,0.9538426,0.007335308,0.03662213,0.00181109,0.00001244647],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.04963303,0.0001996265,0.9444999,0.0007721353,0.00006537649,0.000167668,0.0008725632,0.002259976,0.001529681],"genre_scores_gemma":[0.6633342,0.0001686069,0.3308921,0.0004605505,0.0000519626,0.0004501217,0.002653433,0.0004270764,0.001561914],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.006987459,"threshold_uncertainty_score":0.03695363,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1236772230759604,"score_gpt":0.3420301906008161,"score_spread":0.2183529675248558,"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."}}