{"id":"W3129019366","doi":"10.1101/2021.01.30.428918","title":"Expected 10-anonymity of HyperLogLog sketches for federated queries of clinical data repositories","year":2021,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Privacy-Preserving Technologies in Data","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"The Scarborough Hospital; University of Toronto","funders":"","keywords":"Anonymity; Computer science; Confidentiality; Sketch; Aggregate (composite); Protocol (science); Probabilistic logic; Code (set theory); Sorting; Information retrieval; Computer security; Algorithm; Programming language","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01801432,0.001168446,0.002095696,0.001908199,0.002225547,0.00785874,0.003237865,0.003723843,0.009028113],"category_scores_gemma":[0.1166783,0.001401472,0.002581524,0.002023102,0.004010878,0.01270636,0.006845058,0.004488446,0.001783429],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.005143426,"about_ca_system_score_gemma":0.003187555,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001475123,"about_ca_topic_score_gemma":0.001043582,"domain_scores_codex":[0.986106,0.005598473,0.001121408,0.00232909,0.00329151,0.00155347],"domain_scores_gemma":[0.8169866,0.1394984,0.006194665,0.02832585,0.005437603,0.003556927],"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":[0.0022135,0.0002606045,0.009445988,0.0007772378,0.0003081481,0.0008556336,0.001452433,0.3861641,0.005112426,0.537584,0.01404959,0.04177616],"study_design_scores_gemma":[0.0001114941,0.00009927542,0.0005996451,0.0001051179,0.00006175402,0.0003651664,0.0002207705,0.5828905,0.003368666,0.4096757,0.002422274,0.00007962071],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1843081,0.00127081,0.7867305,0.008313251,0.0001856696,0.0004341008,0.005053981,0.003490909,0.01021263],"genre_scores_gemma":[0.9364871,0.0004805712,0.0561562,0.0008101455,0.0001280491,0.0003562915,0.00147029,0.0003343832,0.0037769],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01801432,"threshold_uncertainty_score":0.09526998,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08127991661387701,"score_gpt":0.3163676613310802,"score_spread":0.2350877447172032,"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."}}