{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.05951569,0.001165035,0.001544688,0.001813459,0.000496288,0.002034599,0.003042061,0.002747238,0.01121965],"category_scores_gemma":[0.1361879,0.001001864,0.002450975,0.001504178,0.001821269,0.00175018,0.002198359,0.003589951,0.001410685],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00150154,"about_ca_system_score_gemma":0.003771282,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002495504,"about_ca_topic_score_gemma":0.002511491,"domain_scores_codex":[0.9653245,0.03112243,0.0007866045,0.001295046,0.001131015,0.0003403867],"domain_scores_gemma":[0.8142125,0.1675187,0.006241622,0.007749356,0.003085882,0.001191935],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0008524158,0.0002180214,0.003141126,0.0007721151,0.0003313786,0.0003124709,0.0005701506,0.5464572,0.000779409,0.3648292,0.007528446,0.07420809],"study_design_scores_gemma":[0.000564926,0.0003377704,0.0003725612,0.0002087192,0.00008273694,0.0001194962,0.00005149325,0.7752157,0.0005079028,0.2159626,0.006528941,0.00004707987],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.003603745,0.0003180647,0.9920792,0.001011573,0.0001111185,0.0006802024,0.0007939331,0.000401396,0.001000814],"genre_scores_gemma":[0.1533191,0.0005843645,0.8377731,0.000945031,0.0001843699,0.004301527,0.001187177,0.0001683851,0.001536953],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.05951569,"threshold_uncertainty_score":0.3147528,"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."}}