{"id":"W4406975757","doi":"10.48550/arxiv.2501.17719","title":"A Framework for Generating Realistic Synthetic Tabular Data in a Randomized Controlled Trial Setting","year":2025,"lang":"en","type":"preprint","venue":"ArXiv.org","topic":"demographic modeling and climate adaptation","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Randomized controlled trial; Computer science; Medicine; Surgery","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.03576867,0.0004531492,0.003405871,0.0007622589,0.0002707519,0.0005449707,0.002175428,0.0006025917,0.00005821293],"category_scores_gemma":[0.1701242,0.0003334213,0.0008768309,0.0006077559,0.0001306765,0.0001483158,0.001169639,0.0008859877,0.00001737054],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005072066,"about_ca_system_score_gemma":0.0005222122,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002680108,"about_ca_topic_score_gemma":0.0001653621,"domain_scores_codex":[0.9906214,0.002275423,0.003554974,0.001848293,0.001197767,0.0005021793],"domain_scores_gemma":[0.9530149,0.04081655,0.002095501,0.003369011,0.00058768,0.0001163184],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"randomized_trial","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.9183816,0.0002789567,0.00236853,0.0002021926,0.000578622,0.00001823061,0.001262735,0.05915725,0.00003562709,0.007788487,0.0006918007,0.009235951],"study_design_scores_gemma":[0.3751789,0.00001980146,0.00002062712,0.0005777338,0.0003182332,4.016977e-7,0.0002579703,0.5416122,0.000002195816,0.08171439,0.00007816694,0.000219374],"study_design_candidate":"randomized_trial","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4573675,0.001057775,0.5296273,0.00136727,0.002861737,0.006952302,0.0002683569,0.00009290001,0.0004048397],"genre_scores_gemma":[0.9433637,0.0002217158,0.05137737,0.0004505872,0.0006765166,0.00288018,0.0004359456,0.00003526299,0.0005587068],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.5432027,"threshold_uncertainty_score":0.9999118,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2341241304923682,"score_gpt":0.4406328326224827,"score_spread":0.2065087021301145,"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."}}