{"id":"W4410692212","doi":"10.1007/s10115-025-02417-2","title":"Providing and evaluating a model for big data anonymization streams by using in-memory processing","year":2025,"lang":"en","type":"article","venue":"Knowledge and Information Systems","topic":"Privacy-Preserving Technologies in Data","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"Regional Municipality of Niagara","funders":"","keywords":"Computer science; Big data; Data stream mining; Data mining; STREAMS; Data anonymization; Data science; Artificial intelligence; Information privacy; Computer security","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":[0.001113694,0.0001096266,0.000155299,0.0003021857,0.0002050007,0.0005631141,0.002674593,0.00009387461,4.208183e-8],"category_scores_gemma":[0.003194558,0.0001052348,0.000007018343,0.0004696945,0.00003022559,0.00656841,0.01018138,0.00007967566,5.810193e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007685055,"about_ca_system_score_gemma":0.0002162301,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002451939,"about_ca_topic_score_gemma":0.000006695203,"domain_scores_codex":[0.9989764,0.00003562296,0.000444578,0.000252193,0.0001160347,0.0001751848],"domain_scores_gemma":[0.9980811,0.00008960612,0.0001932547,0.001448837,0.0001634238,0.00002372689],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000006967442,0.00001851442,0.0005657072,0.001544032,0.000009304968,7.209192e-8,0.001588158,0.001248398,0.0005100518,0.0009782285,0.0127768,0.9807538],"study_design_scores_gemma":[0.0004393176,0.00001319173,0.00001324641,0.0004547363,0.000006127083,0.000002932276,0.0003240936,0.9961186,0.0001687569,0.001111848,0.001238936,0.0001081949],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01378547,0.002203251,0.9817787,0.0002704536,0.0002761521,0.0006610844,0.00004025012,0.0001643091,0.0008203274],"genre_scores_gemma":[0.9350904,0.00007326202,0.06443442,0.00005560295,0.00004129251,0.00008479782,0.0001553597,0.0000064525,0.00005840567],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9948702,"threshold_uncertainty_score":0.9978241,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1086372386100229,"score_gpt":0.3474931435090034,"score_spread":0.2388559048989805,"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."}}