{"id":"W4399317013","doi":"10.48550/arxiv.2405.20405","title":"Private Mean Estimation with Person-Level Differential Privacy","year":2024,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Privacy-Preserving Technologies in Data","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Alexander S. Onassis Public Benefit Foundation; University of Waterloo; Natural Sciences and Engineering Research Council of Canada; Canadian Institute for Advanced Research; National Science Foundation","keywords":"Differential privacy; Estimation; Internet privacy; Differential (mechanical device); Computer science; Statistics; Mathematics; Economics; Data mining; Engineering; Management","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":[0.00763661,0.001489829,0.002585795,0.0009664733,0.001165097,0.003484446,0.004525634,0.00254873,0.002885923],"category_scores_gemma":[0.03719909,0.001038555,0.001702494,0.0028081,0.003301368,0.009247982,0.006981062,0.005240942,0.0009732344],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002980191,"about_ca_system_score_gemma":0.002139112,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001757436,"about_ca_topic_score_gemma":0.001458764,"domain_scores_codex":[0.9918255,0.003101502,0.0002734994,0.002072589,0.001802425,0.0009245631],"domain_scores_gemma":[0.9770363,0.01455303,0.001731874,0.005223001,0.000967969,0.0004878183],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0010571,0.0002170749,0.004959919,0.0003086688,0.0002810644,0.0005237398,0.0006015964,0.4613597,0.005487796,0.4346142,0.004947373,0.08564174],"study_design_scores_gemma":[0.00004164303,0.00007267178,0.0004234473,0.0000194157,0.00003227304,0.0001917649,0.00005077185,0.8113598,0.002296899,0.1840128,0.001462618,0.00003572954],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01054921,0.0002645294,0.9867893,0.0006587458,0.00003439484,0.00004139151,0.000225404,0.0002189751,0.001218024],"genre_scores_gemma":[0.7313007,0.000974694,0.2575011,0.0009882948,0.0004310984,0.0003612456,0.0008535084,0.0001819411,0.007407389],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.00763661,"threshold_uncertainty_score":0.04038674,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1056821586793497,"score_gpt":0.2143883325137831,"score_spread":0.1087061738344334,"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."}}