{"id":"W2162990323","doi":"10.1109/pst.2008.30","title":"Utility of Knowledge Extracted from Unsanitized Data when Applied to Sanitized Data","year":2008,"lang":"en","type":"article","venue":"","topic":"Privacy-Preserving Technologies in Data","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Calgary","funders":"","keywords":"Computer science; Measure (data warehouse); Data mining; Set (abstract data type); Knowledge extraction; Data science; Data set; Data modeling; Information retrieval; Artificial intelligence; Database","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":[0.01690866,0.0005736027,0.001154988,0.005446379,0.0006860463,0.003783825,0.0009525824,0.00110078,0.0005296079],"category_scores_gemma":[0.1377681,0.00034646,0.0008499313,0.004999829,0.00240979,0.004899678,0.001959816,0.001076176,0.0001875673],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009933695,"about_ca_system_score_gemma":0.001127147,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001304842,"about_ca_topic_score_gemma":0.001382556,"domain_scores_codex":[0.9837993,0.006645177,0.00156011,0.001095845,0.006275016,0.0006245419],"domain_scores_gemma":[0.8062302,0.1498553,0.009938329,0.02306505,0.009627388,0.001283822],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.002856859,0.0004924232,0.274857,0.001141153,0.001057492,0.001998066,0.003707317,0.2607971,0.01384385,0.04200719,0.001863255,0.3953784],"study_design_scores_gemma":[0.00007088409,0.0009816914,0.05888267,0.0003466385,0.0004465028,0.001632111,0.001602927,0.7724335,0.04064571,0.118888,0.003944773,0.0001246237],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8367178,0.001614329,0.1557377,0.001405588,0.00006133191,0.0001669429,0.0007836848,0.0003078965,0.003204647],"genre_scores_gemma":[0.9716464,0.0003726027,0.02712415,0.00005923409,0.00003746623,0.00003123413,0.0004525999,0.00003138384,0.0002449633],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01690866,"threshold_uncertainty_score":0.08942258,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1864789450298967,"score_gpt":0.322151514453824,"score_spread":0.1356725694239273,"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."}}