{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.09192521,0.001128653,0.0007624806,0.001983145,0.0006460709,0.001983953,0.002804909,0.001921067,0.003645027],"category_scores_gemma":[0.2526429,0.0006168176,0.002221654,0.001660262,0.001353248,0.0009029086,0.002206088,0.001704163,0.0006929719],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001014911,"about_ca_system_score_gemma":0.002233797,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004119318,"about_ca_topic_score_gemma":0.003408729,"domain_scores_codex":[0.9645056,0.02980359,0.001682186,0.00191474,0.001839896,0.0002540256],"domain_scores_gemma":[0.6760122,0.2698392,0.007105873,0.03304581,0.01288356,0.0011134],"domain_codex":null,"domain_gemma":"reproducibility","domain_candidate":"reproducibility","domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.007271909,0.002194612,0.1231338,0.005240447,0.00450377,0.001740086,0.003304209,0.5101508,0.005918874,0.03241334,0.04275459,0.2613735],"study_design_scores_gemma":[0.001947581,0.001727377,0.02055839,0.001123149,0.0008889721,0.000944202,0.0009821247,0.8884643,0.0083327,0.0454744,0.0293193,0.000237437],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2668525,0.002065687,0.6994931,0.002527454,0.001152624,0.004876791,0.01712761,0.003086142,0.002818198],"genre_scores_gemma":[0.4995327,0.0005404021,0.4732262,0.0006740611,0.0001547023,0.005160847,0.0194182,0.000575831,0.0007170862],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9080748,"threshold_uncertainty_score":0.4861528,"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."}}