{"id":"W4312792291","doi":"10.6028/nist.sp.800-188.3pd","title":"De-Identifying Government Data Sets","year":2022,"lang":"en","type":"report","venue":"","topic":"Electoral Systems and Political Participation","field":"Social Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Office of Planning, Research and Evaluation; Administration for Children and Families; Canadian Patient Safety Institute; Information Technology Laboratory; Harvard University; Massachusetts Institute of Technology; Millennium Challenge Corporation; National Institute of Standards and Technology; U.S. Department of Education; U.S. Department of Health and Human Services","keywords":"Government (linguistics); Computer science; Data science; Data mining; Philosophy","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.02538123,0.001141482,0.001394482,0.009913562,0.003388893,0.008802738,0.00395694,0.002055376,0.00933579],"category_scores_gemma":[0.08528095,0.00101708,0.001753173,0.01513727,0.002088065,0.008357252,0.01065556,0.004980299,0.009890758],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.004956884,"about_ca_system_score_gemma":0.01388507,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01034028,"about_ca_topic_score_gemma":0.007811234,"domain_scores_codex":[0.9522534,0.01269617,0.006978504,0.005727543,0.02028331,0.002061058],"domain_scores_gemma":[0.8701062,0.02243335,0.008486173,0.07278194,0.02506742,0.001124944],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0002942246,0.0001910343,0.01299941,0.001187648,0.0001747751,0.0004371575,0.002834085,0.007368091,0.003756225,0.2807118,0.273721,0.4163246],"study_design_scores_gemma":[0.00004094237,0.00005265935,0.005349423,0.000802903,0.00007152853,0.0004614696,0.00210296,0.01640261,0.01472923,0.07720988,0.8826643,0.0001120627],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.03299267,0.002608312,0.6621374,0.01734378,0.002723787,0.004419556,0.1070184,0.0129718,0.1577844],"genre_scores_gemma":[0.1888452,0.003725231,0.5754102,0.005349229,0.0006691525,0.004248653,0.1845724,0.002411872,0.0347681],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.02538123,"threshold_uncertainty_score":0.1342303,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.3438040697664923,"score_gpt":0.4872269256654063,"score_spread":0.143422855898914,"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."}}