{"id":"W2292231671","doi":"10.1007/s10115-015-0906-8","title":"Managing dimensionality in data privacy anonymization","year":2015,"lang":"en","type":"article","venue":"Knowledge and Information Systems","topic":"Privacy-Preserving Technologies in Data","field":"Computer Science","cited_by":27,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Curse of dimensionality; Computer science; Data mining; Closeness; Process (computing); Cluster analysis; Variety (cybernetics); Machine learning; Mathematics; 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":["open_science"],"category_scores_codex":[0.001332014,0.00009179235,0.000131019,0.000246678,0.00005432297,0.0002952095,0.007434627,0.00007164779,6.726069e-7],"category_scores_gemma":[0.004108274,0.00008371955,0.000006604195,0.0005245368,0.00002767148,0.01119479,0.03705124,0.00009846451,0.0001132977],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007407393,"about_ca_system_score_gemma":0.00008423943,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005447588,"about_ca_topic_score_gemma":0.000007070067,"domain_scores_codex":[0.9989586,0.0000741922,0.0003997584,0.0002020675,0.0002065282,0.0001588579],"domain_scores_gemma":[0.9953856,0.00005482613,0.0001340762,0.004218177,0.0001448784,0.00006247751],"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":[0.00001330906,0.00008477355,0.01020466,0.0003988386,0.00002261183,0.000004734227,0.004388955,0.0002485477,0.00001764948,0.09837068,0.7546239,0.1316213],"study_design_scores_gemma":[0.0003528074,0.00001039911,0.001143235,0.00006588812,0.000001219505,0.00001301867,0.0001628222,0.8252246,0.00002085715,0.007629868,0.1652644,0.0001108431],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.008936398,0.002523785,0.9468613,0.008123039,0.001650438,0.0006483804,0.0000428528,0.000859349,0.03035446],"genre_scores_gemma":[0.9725661,0.0001534149,0.02666954,0.0001254221,0.00005556662,0.00002445269,0.0003330261,0.000005505066,0.00006700661],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9636297,"threshold_uncertainty_score":0.9979357,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07068525535148379,"score_gpt":0.3013851363574971,"score_spread":0.2306998810060134,"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."}}