{"id":"W7116778047","doi":"10.3390/ai7010001","title":"A Responsible Generative Artificial Intelligence Based Multi-Agent Framework for Preserving Data Utility and Privacy","year":2025,"lang":"en","type":"article","venue":"AI","topic":"Privacy-Preserving Technologies in Data","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"York University","funders":"Natural Resources Canada; Natural Sciences and Engineering Research Council of Canada","keywords":"Differential privacy; Interpretability; Embedding; Generative grammar; Generative model; Operationalization; Semantics (computer science); Fidelity; Data-driven","routes":{"ca_aff":true,"ca_fund":true,"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","open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.001202244,0.0001857785,0.0002125853,0.0001766154,0.000290115,0.0003674515,0.02599048,0.0001757203,0.00001283571],"category_scores_gemma":[0.06984539,0.0001808898,0.00003401484,0.0006982174,0.0001664454,0.0008249273,0.09868012,0.0003446283,0.000006571479],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004956573,"about_ca_system_score_gemma":0.0003287296,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004528812,"about_ca_topic_score_gemma":0.00004915827,"domain_scores_codex":[0.9978309,0.0001513993,0.0003489152,0.001085187,0.0001977221,0.000385887],"domain_scores_gemma":[0.984013,0.001406819,0.00009721185,0.01428604,0.0001341666,0.00006273874],"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":[0.0002192016,0.0005272509,0.002583343,0.000294087,0.0001296689,0.00002197931,0.0004315031,0.0001062803,0.002001849,0.3566294,0.2153165,0.4217389],"study_design_scores_gemma":[0.00005102281,0.00002330774,0.00038296,0.00006011227,0.000005975503,3.927714e-7,0.00001683387,0.5408185,0.01475331,0.4405196,0.003270091,0.00009791485],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00167902,0.0003502998,0.9203303,0.07611815,0.0003661962,0.00057238,0.0001272096,0.0004216165,0.0000347686],"genre_scores_gemma":[0.1112082,0.00002311643,0.8873956,0.001200581,0.00002749201,0.00007393049,0.00003242234,0.000008091638,0.00003054848],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.5407122,"threshold_uncertainty_score":0.9792794,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.172779699038435,"score_gpt":0.3980101424371431,"score_spread":0.2252304433987081,"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."}}