{"id":"W2797647106","doi":"10.1145/3190577","title":"InfoClean","year":2017,"lang":"en","type":"article","venue":"Journal of Data and Information Quality","topic":"Privacy-Preserving Technologies in Data","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"ca_institutions":"McMaster University","funders":"","keywords":"Computer science; Confidentiality; Information sensitivity; Data mining; Process (computing); Data quality; Set (abstract data type); Information privacy; Information loss; Data set; Database; Data science; Computer security; Artificial intelligence","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":["metaresearch","scholarly_communication","open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.002214273,0.00005036779,0.0001153354,0.00008019911,0.0002130966,0.0008078361,0.02972539,0.00004399081,0.000004408269],"category_scores_gemma":[0.02812174,0.00003932069,0.00001563508,0.00004138452,0.0000776688,0.04651909,0.05689732,0.0001665868,0.00001179596],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000127698,"about_ca_system_score_gemma":0.00005348599,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001650431,"about_ca_topic_score_gemma":0.000001731292,"domain_scores_codex":[0.9990594,0.00002895773,0.0005021872,0.00006085863,0.0002627324,0.00008582795],"domain_scores_gemma":[0.9907627,0.00006267646,0.00112653,0.007860795,0.0001384678,0.00004887313],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00001063374,0.0000140624,0.004101779,0.00003683812,0.00002090883,0.000001939977,0.0001884517,3.248371e-7,0.00001970282,0.02400916,0.2527832,0.7188129],"study_design_scores_gemma":[0.001235881,0.0001370272,0.2327377,0.00008287722,0.00001108801,0.0001586977,0.0002823566,0.04984324,0.0005220816,0.1533345,0.5613782,0.0002764145],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04777244,0.00007527477,0.8783711,0.06789869,0.0005975274,0.00007191343,0.0001685528,0.00008250752,0.004961994],"genre_scores_gemma":[0.6067118,0.0004306412,0.3919497,0.0008021715,0.00006564482,3.219892e-7,0.00003260436,0.000001720799,0.000005415297],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7185366,"threshold_uncertainty_score":0.9800648,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1247884661779293,"score_gpt":0.3855261588859472,"score_spread":0.2607376927080179,"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."}}