{"id":"W4304208350","doi":"10.1093/jamiaopen/ooac083","title":"Validating a membership disclosure metric for synthetic health data","year":2022,"lang":"en","type":"article","venue":"JAMIA Open","topic":"Privacy-Preserving Technologies in Data","field":"Computer Science","cited_by":38,"is_retracted":false,"has_abstract":true,"ca_institutions":"Children's Hospital of Eastern Ontario; University of Ottawa","funders":"Canadian Institutes of Health Research","keywords":"Synthetic data; Metric (unit); Computer science; Benchmark (surveying); Population; Data mining; Generative model; Measure (data warehouse); Fraction (chemistry); Parametrization (atmospheric modeling); Sampling (signal processing); Ground truth; Machine learning; Generative grammar; Artificial intelligence; Geography; Medicine","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":true,"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":[0.004357202,0.0001544604,0.0002960388,0.0002091011,0.0007855026,0.0006402857,0.1347291,0.00004149384,0.00008828848],"category_scores_gemma":[0.0177949,0.0001509734,0.00004008299,0.001495707,0.00003963709,0.001365318,0.484888,0.0003539892,0.00001575523],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002779744,"about_ca_system_score_gemma":0.000331014,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005270419,"about_ca_topic_score_gemma":0.00005086866,"domain_scores_codex":[0.9973034,0.0003172882,0.0003585111,0.001045396,0.0004602529,0.0005151836],"domain_scores_gemma":[0.979643,0.000743222,0.0002977063,0.01919735,0.00003352231,0.00008520883],"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":[0.00001201579,0.0001051093,0.0003049877,0.0000658034,0.00004067558,0.000009241517,0.0001881366,0.00004782905,0.00002393693,0.01950845,0.8804228,0.09927099],"study_design_scores_gemma":[0.001009563,0.0003793236,0.0002690286,0.00005752466,0.0000181563,0.00005801442,0.0006534595,0.4319425,0.0003801636,0.3104431,0.2542431,0.0005460546],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.001722086,0.001090368,0.6374044,0.3434608,0.001626405,0.004497918,0.002146014,0.001575957,0.006475972],"genre_scores_gemma":[0.2167586,0.00001730342,0.7805971,0.001441056,0.00004495439,0.0004814389,0.0003713608,0.00003183572,0.0002563506],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.6261798,"threshold_uncertainty_score":0.9904786,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1772611440591591,"score_gpt":0.3833628589269482,"score_spread":0.2061017148677891,"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."}}