{"id":"W4395078077","doi":"10.2196/49646","title":"A Scalable Pseudonymization Tool for Rapid Deployment in Large Biomedical Research Networks: Development and Evaluation Study","year":2024,"lang":"en","type":"article","venue":"JMIR Medical Informatics","topic":"Genetics, Bioinformatics, and Biomedical Research","field":"Biochemistry, Genetics and Molecular Biology","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Computer science; Interoperability; Identifier; Context (archaeology); Software deployment; Data science; Scalability; World Wide Web; Software engineering; Database","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.009621451,0.0001905236,0.0002262177,0.0003705944,0.0001720658,0.0001740692,0.0003105976,0.0004032563,0.0001039689],"category_scores_gemma":[0.001010714,0.0001509337,0.00004927787,0.0005249745,0.0002392138,0.00002752878,0.0004162008,0.0004191597,0.00002569471],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001144551,"about_ca_system_score_gemma":0.001000069,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003586487,"about_ca_topic_score_gemma":0.00005573938,"domain_scores_codex":[0.9956397,0.0001822057,0.001029188,0.0002659707,0.002151033,0.0007318605],"domain_scores_gemma":[0.9987971,0.0001710742,0.00005937058,0.0002721896,0.0003190628,0.0003812158],"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":[0.0002740702,0.001438361,0.002656262,0.001561696,0.0001957143,0.00001394321,0.008340082,0.00005351991,0.0002823137,0.0001726397,0.03252266,0.9524887],"study_design_scores_gemma":[0.003841841,0.001871957,0.002539909,0.0003632597,0.00002276241,0.00001809331,0.006028214,0.6852717,0.0007110406,0.00008765041,0.2988805,0.0003630069],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9544189,0.001138214,0.0393197,0.000545049,0.0004216025,0.003572828,0.00002090086,0.00004231515,0.000520464],"genre_scores_gemma":[0.9918133,0.0007579859,0.004328208,0.0003437198,0.0004258546,0.001250807,0.0006682252,0.00003038456,0.0003814934],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9521257,"threshold_uncertainty_score":0.6154898,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04460671209727822,"score_gpt":0.388735928012577,"score_spread":0.3441292159152988,"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."}}