{"id":"W3180876344","doi":"10.1093/bioinformatics/btab292","title":"Expected 10-anonymity of HyperLogLog sketches for federated queries of clinical data repositories","year":2021,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Privacy-Preserving Technologies in Data","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":true,"ca_institutions":"The Scarborough Hospital; University of Toronto","funders":"National Cancer Institute; Division of Mathematical Sciences; University of Toronto","keywords":"Anonymity; Computer science; Confidentiality; Sketch; Probabilistic logic; Aggregate (composite); Sorting; Protocol (science); Code (set theory); Information retrieval; Data mining; Computer security; Algorithm; Programming language","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":[0.0212356,0.001345634,0.002258183,0.001706812,0.002500374,0.008495756,0.003671787,0.004161785,0.008360478],"category_scores_gemma":[0.1322706,0.001681803,0.002760418,0.002028525,0.004521084,0.01611916,0.008093921,0.005522515,0.001916239],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00525926,"about_ca_system_score_gemma":0.00392827,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001461203,"about_ca_topic_score_gemma":0.001074184,"domain_scores_codex":[0.9844141,0.006163816,0.001302238,0.002628948,0.003621747,0.001869176],"domain_scores_gemma":[0.8058951,0.150467,0.006778975,0.02785072,0.005354214,0.003653915],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.002596796,0.0003177746,0.009662461,0.001030617,0.0003618307,0.0008766025,0.0021155,0.395434,0.005947082,0.5215178,0.0118468,0.04829288],"study_design_scores_gemma":[0.0001336109,0.0001271272,0.0005907344,0.0001316084,0.00007715243,0.0005121685,0.0002753266,0.5445526,0.003631766,0.4472462,0.00263407,0.00008775628],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1333955,0.001206786,0.8412032,0.008212109,0.0001640305,0.000436761,0.003913159,0.003084218,0.008384318],"genre_scores_gemma":[0.9156818,0.0006201071,0.07636975,0.001068562,0.0001555832,0.0004576031,0.001513147,0.0003729251,0.003760609],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.0212356,"threshold_uncertainty_score":0.1123059,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1350247034792257,"score_gpt":0.3642481111285533,"score_spread":0.2292234076493276,"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."}}