{"id":"W2146453464","doi":"10.1186/1472-6947-12-66","title":"Estimating the re-identification risk of clinical data sets","year":2012,"lang":"en","type":"article","venue":"BMC Medical Informatics and Decision Making","topic":"Privacy-Preserving Technologies in Data","field":"Computer Science","cited_by":102,"is_retracted":false,"has_abstract":true,"ca_institutions":"Agricultural Research Institute of Ontario; University of Ottawa; Children's Hospital of Eastern Ontario","funders":"Canada Research Chairs","keywords":"Estimator; Statistics; Uniqueness; Quartile; Identification (biology); Mathematics; Data mining; Computer science; Econometrics; Confidence interval","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":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.01343681,0.00009740383,0.000225431,0.00007848233,0.0001841021,0.0001685952,0.01758174,0.0001633663,0.00001647351],"category_scores_gemma":[0.1805181,0.00005949888,0.00003824651,0.0002959617,0.0002014151,0.001433481,0.07046162,0.000398382,0.00002296785],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000007895917,"about_ca_system_score_gemma":0.00009982618,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000004485345,"about_ca_topic_score_gemma":0.000005799539,"domain_scores_codex":[0.9969744,0.000127919,0.001461682,0.000174263,0.001023954,0.0002377729],"domain_scores_gemma":[0.981672,0.008201547,0.0009913816,0.008919224,0.00007930036,0.0001364969],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000004184809,0.00002368412,0.01155966,0.00003887706,0.000009071548,3.429076e-7,0.0001370237,0.0000393446,1.47257e-7,0.0008587563,0.02958226,0.9577466],"study_design_scores_gemma":[0.0001588374,0.00001012528,0.006937996,0.0001961783,0.00001040349,0.00001428501,0.0001227153,0.9407566,0.000003717539,0.05126181,0.0004591688,0.0000681338],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.08608154,0.0002095773,0.9123386,0.0002294805,0.0007467176,0.0001017822,0.00001539645,0.00009003795,0.0001869169],"genre_scores_gemma":[0.2764018,0.0001047883,0.7232924,0.0001311333,0.00005714921,0.000002085233,0.000007268885,0.000002934824,4.373912e-7],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9576785,"threshold_uncertainty_score":0.9877336,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1848199606233114,"score_gpt":0.4447147731322799,"score_spread":0.2598948125089684,"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."}}