{"id":"W4414458923","doi":"10.1109/acdsa65407.2025.11166156","title":"Genetic Algorithm for Subset Selection in Synthetic Tabular Data","year":2025,"lang":"en","type":"article","venue":"","topic":"Fuzzy Logic and Control Systems","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Selection (genetic algorithm); Synthetic data; Initialization; Scalability; Quality (philosophy); Genetic algorithm; Sampling (signal processing)","routes":{"ca_aff":true,"ca_fund":false,"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":[],"consensus_categories":[],"category_scores_codex":[0.0002919392,0.00007278027,0.0001243604,0.00009197467,0.00004868568,0.00008137012,0.0009483957,0.0000457447,0.000002865983],"category_scores_gemma":[0.00003050051,0.00006165356,0.00002156959,0.0003577876,0.000009778043,0.0001603938,0.0001853045,0.00004347931,0.00001329933],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003071014,"about_ca_system_score_gemma":0.00007136916,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001867087,"about_ca_topic_score_gemma":0.0001289473,"domain_scores_codex":[0.9991183,0.00004351003,0.00017603,0.0003845236,0.00008804319,0.0001895615],"domain_scores_gemma":[0.9993467,0.00008327705,0.00002477412,0.0004884772,0.00003328513,0.00002348653],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000005673027,0.0001018213,0.001681976,0.0000379135,0.00003239644,0.000006465522,0.00004843843,0.0003335296,0.0004146252,0.09053421,0.01292343,0.8938795],"study_design_scores_gemma":[0.0003979251,0.00003145804,0.002487713,0.00001493142,0.000004971756,0.000003665167,0.00001269302,0.9762306,0.00009427727,0.01125859,0.009379239,0.00008399669],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.000420204,0.0003439116,0.9937504,0.0006175296,0.0002668743,0.0003294883,0.000005156392,0.00008230701,0.00418416],"genre_scores_gemma":[0.6577504,0.00001978285,0.3383939,0.000807507,0.00009759606,0.0001529165,0.000009882759,0.000006770706,0.00276126],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.975897,"threshold_uncertainty_score":0.2514159,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01747097499206681,"score_gpt":0.2529542620145691,"score_spread":0.2354832870225023,"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."}}