{"id":"W4413111174","doi":"10.1002/sim.70227","title":"A Framework for Generating Realistic Synthetic Tabular Data in a Randomized Controlled Trial Setting","year":2025,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University; McGill University Health Centre","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Randomized controlled trial; Synthetic data; Copula (linguistics); Artificial intelligence; Machine learning; Data mining; Econometrics; Medicine; Mathematics","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"],"consensus_categories":[],"category_scores_codex":[0.008428017,0.0001751612,0.001337843,0.0004074445,0.00007466012,0.00006272776,0.001328004,0.0001004816,0.000009525116],"category_scores_gemma":[0.08066683,0.0001384608,0.000032754,0.0005411077,0.0001846582,0.000120477,0.0002745841,0.0002997527,8.853417e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009263944,"about_ca_system_score_gemma":0.0002217833,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000976849,"about_ca_topic_score_gemma":0.00006720985,"domain_scores_codex":[0.9968697,0.0006077505,0.001325347,0.0005877721,0.0003119198,0.0002974451],"domain_scores_gemma":[0.9827983,0.01519305,0.0003886125,0.00145213,0.0001275015,0.00004041482],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.05648784,0.00005172073,0.000009756437,0.00007892392,0.00002852018,0.00001414023,0.0002471124,0.0000349771,0.00007867898,0.928783,0.003847193,0.01033814],"study_design_scores_gemma":[0.3462317,0.00003691098,0.00000425733,0.000412759,0.00003097243,4.65354e-7,0.00002784138,0.4361242,0.00001421154,0.2168838,0.0001630506,0.00006991584],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00005461434,0.0003026812,0.9912509,0.003063491,0.0006412484,0.004150841,0.0001635614,0.00009466779,0.000277956],"genre_scores_gemma":[0.02692925,0.0001032753,0.9702732,0.0007456649,0.0001493989,0.001380122,0.0003314169,0.00001101464,0.00007663276],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.7118992,"threshold_uncertainty_score":0.9270771,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03481874690734359,"score_gpt":0.3819513484906666,"score_spread":0.347132601583323,"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."}}