{"id":"W4411282933","doi":"10.1007/s10207-025-01072-6","title":"Synthetic data: revisiting the privacy-utility trade-off","year":2025,"lang":"en","type":"article","venue":"International Journal of Information Security","topic":"Privacy-Preserving Technologies in Data","field":"Computer Science","cited_by":19,"is_retracted":false,"has_abstract":false,"ca_institutions":"Concordia University; University of Manitoba","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Cryptography; Computer security; Information privacy; Internet privacy; Data science","routes":{"ca_aff":true,"ca_fund":true,"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":["metaresearch","open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.002615,0.0001091775,0.0001548956,0.0002944128,0.0001215027,0.0006589999,0.04548853,0.00007129383,0.00002143366],"category_scores_gemma":[0.03598119,0.0000781771,0.00007752095,0.000371514,0.00009559357,0.007397539,0.03519906,0.000503583,0.00001577732],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000122299,"about_ca_system_score_gemma":0.0002118543,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000008351421,"about_ca_topic_score_gemma":0.000001042303,"domain_scores_codex":[0.9979295,0.0001053409,0.0008948777,0.00014318,0.0007749236,0.0001521979],"domain_scores_gemma":[0.9940979,0.0004492739,0.0007769184,0.004101095,0.0005393987,0.00003540285],"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":[0.00003715015,0.00004305656,0.0008714764,0.00003803746,0.0002029199,0.00001365485,0.0008017828,0.00001911124,0.00001766101,0.05856123,0.2611621,0.6782318],"study_design_scores_gemma":[0.0005181535,0.0000190844,0.007080869,0.0002941253,0.00001845349,0.0002311635,0.0002493582,0.3228143,0.0008512863,0.2502811,0.4174976,0.0001445253],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.007237799,0.0004492115,0.6778744,0.3059039,0.002447171,0.0001532837,0.00008613375,0.0001478336,0.005700206],"genre_scores_gemma":[0.9677798,0.0002493128,0.0304282,0.001357079,0.0001542989,0.000001950566,0.00002387652,0.000002123609,0.000003347513],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.960542,"threshold_uncertainty_score":0.9726041,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02532597158437543,"score_gpt":0.3101578134501034,"score_spread":0.284831841865728,"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."}}