{"id":"W4410804643","doi":"10.1214/24-aoas2009","title":"A privacy-preserved and high-utility synthesis strategy for risk-based stratified subgroups of the Canadian scleroderma patient registry data","year":2025,"lang":"en","type":"article","venue":"The Annals of Applied Statistics","topic":"Privacy-Preserving Technologies in Data","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"McGill University; University of Alberta","funders":"","keywords":"Medicine; Data science; Family medicine; Computer science","routes":{"ca_aff":true,"ca_fund":false,"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":[0.001329947,0.0002086935,0.0003450581,0.00009977149,0.0003933569,0.0001319239,0.02538372,0.0001380232,0.000004921465],"category_scores_gemma":[0.01769174,0.0001464975,0.0000382371,0.0004568165,0.0006526476,0.0001338295,0.01947084,0.0002860679,4.083168e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002810245,"about_ca_system_score_gemma":0.0008313778,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.01908096,"about_ca_topic_score_gemma":0.03308171,"domain_scores_codex":[0.9979508,0.0001574333,0.0005672491,0.0005641302,0.0003606973,0.000399688],"domain_scores_gemma":[0.9822645,0.002089245,0.0005679074,0.01473918,0.0002602965,0.00007885366],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0003316024,0.0002734853,0.001513643,0.0008449687,0.0003531825,0.000003414898,0.0002140666,0.0007141818,0.0007576522,0.3462864,0.4721595,0.1765479],"study_design_scores_gemma":[0.0002880186,0.00005350661,0.02666348,0.00008220294,0.00006379693,3.058801e-7,0.00008424771,0.2496885,0.02959149,0.6927115,0.0005947034,0.0001782138],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1284513,0.0002451165,0.8019198,0.03243499,0.0002305997,0.002319039,0.03328665,0.0001664515,0.0009461251],"genre_scores_gemma":[0.8540083,0.00004092056,0.1455928,0.0002057188,0.000005836964,0.00005073424,0.00008273478,0.000009141224,0.000003811285],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.725557,"threshold_uncertainty_score":0.9905826,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1118521193370718,"score_gpt":0.3174271461467318,"score_spread":0.20557502680966,"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."}}