{"id":"W3048160908","doi":"10.69554/qpbq3248","title":"Reasoning about unstructured data de-identification","year":2020,"lang":"en","type":"article","venue":"Journal of data protection & privacy.","topic":"Semantic Web and Ontologies","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Unstructured data; Identification (biology); Computer science; Data mining; Big data; Biology","routes":{"ca_aff":true,"ca_fund":false,"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":["open_science"],"consensus_categories":[],"category_scores_codex":[0.001079209,0.00009621985,0.0001751567,0.00007981558,0.0001268149,0.0003669835,0.00551725,0.00006274339,0.00001319303],"category_scores_gemma":[0.001891698,0.00008060772,0.00003047821,0.000343007,0.00002993844,0.003620357,0.001684294,0.0003386396,0.00001505195],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003596146,"about_ca_system_score_gemma":0.0002050233,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002898085,"about_ca_topic_score_gemma":0.000003816908,"domain_scores_codex":[0.998515,0.0001293527,0.0004841734,0.0003579835,0.0003519766,0.000161541],"domain_scores_gemma":[0.9972977,0.00003794553,0.0006444717,0.001768126,0.0001409147,0.0001108447],"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":[0.000149499,0.00009093183,0.001545067,0.0001292976,0.0001954437,0.000172374,0.002342261,0.0002273958,0.04783351,0.00275116,0.04223655,0.9023265],"study_design_scores_gemma":[0.001729989,0.0004232082,0.06908291,0.0002377735,0.0001342176,0.002306278,0.0003910173,0.6599336,0.01864451,0.007199592,0.2393641,0.0005527786],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01015174,0.000372486,0.9771644,0.01160485,0.0004395425,0.0001415267,0.00001769644,0.00007360047,0.00003419373],"genre_scores_gemma":[0.7356907,0.0001172926,0.2632335,0.0003693853,0.0005375873,0.000001561541,0.00002932227,0.000008299832,0.00001228434],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9017738,"threshold_uncertainty_score":0.9998634,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1440368952251863,"score_gpt":0.3265463087389853,"score_spread":0.1825094135137991,"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."}}