{"id":"W2595008630","doi":"10.29012/jpc.v7i3.406","title":"On the Meaning and Limits of Empirical Differential Privacy","year":2017,"lang":"en","type":"article","venue":"Journal of Privacy and Confidentiality","topic":"Privacy-Preserving Technologies in Data","field":"Computer Science","cited_by":16,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia; Université Laval","funders":"Natural Sciences and Engineering Research Council of Canada; Mitacs","keywords":"Differential privacy; Computer science; Meaning (existential); Conjugate prior; Measure (data warehouse); Bayesian probability; Discretization; Empirical measure; Differential (mechanical device); Empirical research; Data mining; Posterior probability; Mathematics; Artificial intelligence; Statistics","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.03851356,0.0009697168,0.002112908,0.002438157,0.002657103,0.008844483,0.003196027,0.005105294,0.002114045],"category_scores_gemma":[0.1494421,0.001224898,0.001592881,0.002755165,0.02267446,0.02217319,0.0088197,0.01211518,0.000344192],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.005685427,"about_ca_system_score_gemma":0.002364435,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00109867,"about_ca_topic_score_gemma":0.000539474,"domain_scores_codex":[0.9681556,0.02075352,0.001180448,0.003252398,0.005465192,0.001192897],"domain_scores_gemma":[0.7941567,0.1774149,0.005844178,0.01604043,0.004949654,0.001594118],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00002720372,0.00001337817,0.0004415814,0.00005078626,0.00001481768,0.00006178811,0.000144062,0.007991998,0.0001623834,0.985084,0.0003997088,0.005608269],"study_design_scores_gemma":[0.000009982694,0.00002215788,0.0001873099,0.00008014168,0.000008839169,0.0001122335,0.00004986085,0.03561707,0.0002369109,0.9622728,0.001381023,0.00002178374],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03595337,0.005671313,0.9103178,0.01599712,0.0002369824,0.00009481363,0.0002234744,0.0001466832,0.03135845],"genre_scores_gemma":[0.8664416,0.005971594,0.1187316,0.003401301,0.00107982,0.0004809867,0.000170457,0.000163061,0.003559643],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.03851356,"threshold_uncertainty_score":0.2036816,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0786503603741271,"score_gpt":0.3423210247903177,"score_spread":0.2636706644161906,"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."}}