{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.03008532,0.00137049,0.001874651,0.006555089,0.003340812,0.008867201,0.004734683,0.004502629,0.001653156],"category_scores_gemma":[0.14199,0.001667107,0.002958882,0.006612348,0.005476108,0.02520826,0.008103885,0.006590553,0.0005514391],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002956764,"about_ca_system_score_gemma":0.002521523,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003969548,"about_ca_topic_score_gemma":0.004110037,"domain_scores_codex":[0.9589205,0.01432547,0.004288958,0.006957465,0.01389677,0.00161066],"domain_scores_gemma":[0.7574397,0.1875655,0.01875973,0.02463822,0.01017545,0.001421444],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00037464,0.0002704067,0.02161642,0.001335063,0.0006092387,0.005734085,0.004910885,0.1688358,0.00343534,0.6453401,0.01379664,0.1337413],"study_design_scores_gemma":[0.0000237688,0.00002667122,0.0008595511,0.0002400349,0.00007866685,0.001150171,0.0008776996,0.221127,0.003718928,0.7600884,0.01174739,0.00006181737],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01955126,0.0006452841,0.9691766,0.00604035,0.000150785,0.0002220041,0.001766906,0.0005155168,0.00193142],"genre_scores_gemma":[0.3586443,0.001336068,0.6269293,0.002192447,0.0007163307,0.0005353572,0.006714166,0.000211157,0.002720786],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.03008532,"threshold_uncertainty_score":0.1591082,"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."}}