{"id":"W4399923463","doi":"10.1038/s41598-024-62102-2","title":"Synthetic data generation for a longitudinal cohort study – evaluation, method extension and reproduction of published data analysis results","year":2024,"lang":"en","type":"article","venue":"Scientific Reports","topic":"Health, Environment, Cognitive Aging","field":"Environmental Science","cited_by":17,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Canadian Institutes of Health Research; National Institutes of Health; Genentech; IXICO; Servier; Bundesministerium für Ernährung und Landwirtschaft; Eisai; Deutsche Forschungsgemeinschaft; H. Lundbeck A/S; National Institute on Aging; Ministerium für Innovation, Wissenschaft und Forschung des Landes Nordrhein-Westfalen; Bundesamt für Landwirtschaft; Northern California Institute for Research and Education; BioClinica; Biogen; Pfizer; Novartis Pharmaceuticals Corporation; University of Southern California; U.S. Department of Defense; Eli Lilly and Company; Bristol-Myers Squibb; Alzheimer's Disease Neuroimaging Initiative; Meso Scale Diagnostics; Alzheimer's Association","keywords":"Reproduction; Extension (predicate logic); Longitudinal data; Computer science; Cohort; Data science; Statistics; Data mining; Biology; Mathematics; Genetics","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[{"model":"gemma","categories":["metaresearch"],"domain":"reproducibility","study_design":"simulation_or_modeling","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"high","status":"direct model label, unvalidated"},{"model":"gpt","categories":["metaresearch"],"domain":"reproducibility","study_design":"simulation_or_modeling","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"high","status":"direct model label, unvalidated"}],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.07970741,0.0001452236,0.0002713393,0.0002780171,0.0003716906,0.000447282,0.0003479243,0.00004808661,0.0003048506],"category_scores_gemma":[0.008465514,0.000128874,0.00003965679,0.001454765,0.0002338769,0.001772774,0.0009011275,0.0000995536,0.000008673282],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001517913,"about_ca_system_score_gemma":0.0000910737,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004918436,"about_ca_topic_score_gemma":0.0006344728,"domain_scores_codex":[0.9904948,0.0004582341,0.0009373326,0.006510736,0.001358827,0.000240077],"domain_scores_gemma":[0.9904705,0.0001601158,0.0003995594,0.008761892,0.0001084902,0.00009949564],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00009566395,0.001164772,0.5035316,0.0001605632,0.001207519,0.0001711163,0.002755704,0.01795929,0.1083018,0.00001610862,0.08896815,0.2756676],"study_design_scores_gemma":[0.0001608689,0.00005172575,0.2691583,0.00002195307,0.001910527,0.00006416802,0.0001772253,0.721386,0.001486576,0.0007584167,0.004651555,0.0001727135],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9150403,0.000293185,0.07795846,0.0005664455,0.002432611,0.003246709,0.0001458769,0.00005207789,0.0002643839],"genre_scores_gemma":[0.9847011,0.00001222356,0.01129239,0.000007289798,0.00008456641,0.00007878163,0.0034394,0.00001466954,0.0003695735],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7034267,"threshold_uncertainty_score":0.9998866,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.132920756423318,"score_gpt":0.3985734879187245,"score_spread":0.2656527314954066,"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."}}