{"id":"W3091951858","doi":"10.2196/23139","title":"Evaluating Identity Disclosure Risk in Fully Synthetic Health Data: Model Development and Validation","year":2020,"lang":"en","type":"article","venue":"Journal of Medical Internet Research","topic":"Data Analysis and Archiving","field":"Social Sciences","cited_by":85,"is_retracted":false,"has_abstract":true,"ca_institutions":"Children's Hospital of Eastern Ontario; University of Ottawa","funders":"Health Canada","keywords":"Computer science; Identity (music); Data science; Psychology","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"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.0435558,0.00005148806,0.0002153443,0.0001595869,0.0001964077,0.0002356977,0.00112061,0.00004970319,0.0001801642],"category_scores_gemma":[0.01452826,0.00003921139,0.00002810267,0.0003305448,0.0002001393,0.0006305191,0.0007172462,0.0009577648,0.000007334154],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001187401,"about_ca_system_score_gemma":0.001555402,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001666452,"about_ca_topic_score_gemma":0.005167991,"domain_scores_codex":[0.9932227,0.001883444,0.0006093137,0.0002052246,0.003787809,0.0002915698],"domain_scores_gemma":[0.9984285,0.0005381561,0.0002318128,0.0001248225,0.000149871,0.0005267861],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001213422,0.0002963963,0.04071645,0.0001805132,0.0001514718,0.0001115429,0.1073884,0.0005513139,0.00006892423,0.006222854,0.01337445,0.8308164],"study_design_scores_gemma":[0.001031482,0.0003589861,0.008937729,0.001399961,0.00003109692,0.0000108664,0.01922672,0.9492207,0.0000605425,0.004334478,0.01519831,0.0001891568],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.941516,0.0004817495,0.02137636,0.03620455,0.00004995585,0.00009392961,0.000007055772,0.000003768646,0.0002666568],"genre_scores_gemma":[0.9955403,0.00126372,0.002744731,0.0001448096,0.0002296447,0.000001088553,0.000007216375,0.000004378208,0.00006417907],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9486694,"threshold_uncertainty_score":0.9937728,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.3742093669327674,"score_gpt":0.5630940315766862,"score_spread":0.1888846646439189,"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."}}