{"id":"W4401164363","doi":"10.1109/csp62567.2024.00010","title":"Linkage Deanonymization Risks, Data-Matching and Privacy: A Case Study","year":2024,"lang":"en","type":"article","venue":"","topic":"Names, Identity, and Discrimination Research","field":"Social Sciences","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"New York Institute of Technology","funders":"","keywords":"Computer science; Linkage (software); Record linkage; Matching (statistics); Information privacy; Computer security; Internet privacy; Statistics; Environmental health; Mathematics; Genetics; Medicine","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":[],"consensus_categories":[],"category_scores_codex":[0.001642994,0.00005346894,0.00006680922,0.0001284052,0.0006384874,0.0009725529,0.0002176193,0.00003577403,0.0003664671],"category_scores_gemma":[0.0003969017,0.00004666437,0.0000125878,0.0003201972,0.00008209898,0.0007709705,0.0002826865,0.0001065055,0.00004392835],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003610949,"about_ca_system_score_gemma":0.000168001,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.05447053,"about_ca_topic_score_gemma":0.04830143,"domain_scores_codex":[0.9988118,0.0002380851,0.0001235567,0.0002731886,0.0003957708,0.0001576322],"domain_scores_gemma":[0.9994142,0.0001979213,0.00001458998,0.0002145679,0.00006192268,0.00009677657],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"qualitative","study_design_gemma":"qualitative","study_design_scores_codex":[0.00001339549,0.001002094,0.2484197,0.0004207315,0.0001807766,0.008547677,0.3481508,0.00002500748,0.00004696624,0.1883419,0.02346386,0.181387],"study_design_scores_gemma":[0.001404242,0.0002329426,0.02286418,0.0001069541,0.0003195129,0.0002329984,0.7975977,0.01563881,0.00001807019,0.05111478,0.1096261,0.0008437326],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9699402,0.0005484475,0.00523554,0.001312613,0.0002421185,0.0004745119,0.00001225348,0.0001841763,0.02205008],"genre_scores_gemma":[0.9935238,0.0001802126,0.0003459715,0.00003423114,0.000171278,0.00000763105,0.00001264531,0.000006823295,0.005717379],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4494468,"threshold_uncertainty_score":0.9690646,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2251580555565904,"score_gpt":0.4977252111921275,"score_spread":0.2725671556355372,"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."}}