{"id":"W4406502827","doi":"10.1093/imaiai/iaae034","title":"Differentially private low-dimensional synthetic data from high-dimensional datasets","year":2025,"lang":"en","type":"article","venue":"Information and Inference A Journal of the IMA","topic":"Privacy-Preserving Technologies in Data","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Curse of dimensionality; Principal component analysis; Synthetic data; Intrinsic dimension; Covariance; Computer science; Clustering high-dimensional data; Key (lock); Dimension (graph theory); Algorithm; Covariance matrix; Data mining; Artificial intelligence; Mathematics; Statistics","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":["metaresearch","open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.0005116308,0.0001370398,0.0001962077,0.0001914874,0.0001766936,0.0004045377,0.01764719,0.00007802396,0.00004623055],"category_scores_gemma":[0.009698443,0.00008766248,0.00003665397,0.0002770173,0.0001395377,0.005286952,0.05199663,0.0003600628,0.00002484388],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000377506,"about_ca_system_score_gemma":0.0002531651,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004090943,"about_ca_topic_score_gemma":0.000005034688,"domain_scores_codex":[0.9984773,0.00007376762,0.0006382503,0.0001605765,0.00048049,0.0001696329],"domain_scores_gemma":[0.9944418,0.0003190845,0.0005514479,0.00444941,0.0001822997,0.00005592731],"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":[0.0001561961,0.0002120412,0.0025922,0.00008939655,0.0003363181,0.00001635491,0.0001495173,0.0003364566,0.003324782,0.02603012,0.747763,0.2189936],"study_design_scores_gemma":[0.00164366,0.00007834894,0.0524659,0.001059139,0.00006490562,0.0000985048,0.0000206843,0.5916607,0.007756595,0.3295704,0.01523762,0.0003434785],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5529721,0.000380973,0.385209,0.05693039,0.002569092,0.0002624565,0.00135742,0.0001316197,0.0001869386],"genre_scores_gemma":[0.9309999,0.00007841933,0.06696172,0.001734598,0.00002441107,0.000001420707,0.0001904278,0.000002722766,0.000006337495],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7325254,"threshold_uncertainty_score":0.9986433,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02040655346756855,"score_gpt":0.272225933458451,"score_spread":0.2518193799908824,"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."}}