{"id":"W2160036998","doi":"10.1145/1233321.1233324","title":"Utility-based anonymization for privacy preservation with less information loss","year":2006,"lang":"en","type":"article","venue":"ACM SIGKDD Explorations Newsletter","topic":"Privacy-Preserving Technologies in Data","field":"Computer Science","cited_by":78,"is_retracted":false,"has_abstract":true,"ca_institutions":"Simon Fraser University","funders":"Chinese University of Hong Kong; National Natural Science Foundation of China","keywords":"Computer science; Data anonymization; Microdata (statistics); Categorical variable; Data mining; Identifier; Information loss; Heuristic; Set (abstract data type); Data quality; Information privacy; Machine learning; 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":["open_science"],"consensus_categories":[],"category_scores_codex":[0.000285429,0.0002380252,0.0001788607,0.0003404341,0.0003498292,0.0005911413,0.01014754,0.0001528042,0.00001092357],"category_scores_gemma":[0.00507517,0.0002182925,0.00005420535,0.0009909652,0.0001039717,0.009924433,0.005933374,0.0001685765,0.00004259977],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007718174,"about_ca_system_score_gemma":0.0001462626,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007058292,"about_ca_topic_score_gemma":0.00006767079,"domain_scores_codex":[0.9981841,0.00006765687,0.0005025461,0.0004445557,0.000425443,0.0003757299],"domain_scores_gemma":[0.9917091,0.000319205,0.0002885451,0.007208849,0.0004338577,0.00004049365],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00008173741,0.000220117,0.01680055,0.0001205185,0.0000318828,0.000003986421,0.0002729395,0.004644601,0.001047443,0.02045552,0.9409957,0.01532503],"study_design_scores_gemma":[0.001932351,0.0001765167,0.006290177,0.00005882166,0.00002683932,0.00000425732,0.00004666052,0.6446371,0.02282024,0.2002786,0.1230975,0.000630921],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01698777,0.000009203228,0.8351662,0.1457968,0.0001362703,0.0008398555,0.00004322151,0.0008591102,0.0001616273],"genre_scores_gemma":[0.3270649,0.000002279433,0.668196,0.002693144,0.0001099472,0.0005565311,0.001320923,0.00001928932,0.00003701146],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8178982,"threshold_uncertainty_score":0.995208,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04348191414472581,"score_gpt":0.2574041941641516,"score_spread":0.2139222800194258,"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."}}