{"id":"W2189001323","doi":"","title":"Combining Synthetic Data with Subsampling to Create Public Use Microdata Files for Large Scale Surveys","year":2012,"lang":"en","type":"article","venue":"Survey methodology","topic":"demographic modeling and climate adaptation","field":"Decision Sciences","cited_by":11,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Microdata (statistics); Confidentiality; Computer science; Scale (ratio); Sample (material); Imputation (statistics); Statistics; Sample size determination; Statistical inference; Data file; Data science; Data mining; Econometrics; Database; Missing data; Mathematics; Census; Computer security; Geography; Machine learning","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.1820991,0.0002556976,0.0006893667,0.0005373491,0.0003836248,0.0004434412,0.001749245,0.0001670499,0.0001671856],"category_scores_gemma":[0.08109479,0.0001892139,0.00007614737,0.001270708,0.0001116306,0.001279593,0.0006384425,0.0001881617,0.0000941752],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001711896,"about_ca_system_score_gemma":0.00008961422,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001153342,"about_ca_topic_score_gemma":0.009099188,"domain_scores_codex":[0.9771793,0.0187289,0.0009402788,0.001269312,0.0007121524,0.00117003],"domain_scores_gemma":[0.9328368,0.06292264,0.0003559359,0.002564587,0.0009451943,0.0003748915],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0003902788,0.0002495412,0.9633021,0.0000157522,0.0001055551,0.000001385905,0.001383909,0.0002240023,0.001194625,0.001192513,0.004748253,0.02719204],"study_design_scores_gemma":[0.00103982,0.000228498,0.9603989,0.0000353572,0.00007824395,0.00003608966,0.002112197,0.01556676,0.0003250998,0.002274395,0.01728116,0.0006235259],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4025036,0.000096107,0.5941917,0.0002124057,0.0004854666,0.0002441272,0.002172223,0.00004873278,0.0000456856],"genre_scores_gemma":[0.7030889,0.00001315734,0.294649,0.000232201,0.00006096344,0.00003335913,0.001670923,0.00003665149,0.0002148022],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.3005854,"threshold_uncertainty_score":0.9266455,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.7970682118326551,"score_gpt":0.5130019730252127,"score_spread":0.2840662388074424,"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."}}