{"id":"W1648737833","doi":"","title":"The effects of randomly sampled training data on program evolution","year":2000,"lang":"en","type":"article","venue":"","topic":"Evolutionary Algorithms and Applications","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":true,"ca_institutions":"Brock University","funders":"","keywords":"Genetic programming; Sampling (signal processing); Computer science; Machine learning; Resampling; Evolutionary algorithm; Sample (material); Training (meteorology); Population; Artificial intelligence; Simple random sample; Sampling bias; Genetic algorithm; Statistics; Sample size determination; Mathematical optimization; Mathematics","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":[0.0002637165,0.00005960073,0.00007456491,0.00001760192,0.0002404032,0.00004483535,0.001000736,0.00002072545,0.00001438973],"category_scores_gemma":[0.00005295449,0.00003732791,0.00002769374,0.0002563902,0.00005365566,0.0002039411,0.0000830895,0.00005760571,0.00002988708],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001256694,"about_ca_system_score_gemma":0.00004564523,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003391257,"about_ca_topic_score_gemma":0.000008487789,"domain_scores_codex":[0.9992723,0.00004500906,0.000139862,0.0002227944,0.0001728652,0.0001471933],"domain_scores_gemma":[0.9984803,0.0005396678,0.00003556619,0.0008850312,0.00002593245,0.00003353669],"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":[0.000009384502,0.0001136055,0.00001000662,0.000004476577,0.000009845269,3.134493e-7,0.00009453529,0.00004529333,0.00009530668,0.165801,0.002192834,0.8316234],"study_design_scores_gemma":[0.002458987,0.0005364729,0.01604982,0.00005114004,0.00001650961,0.00001216151,0.00004684981,0.7945791,0.0003541303,0.02912257,0.1565422,0.0002300692],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01835419,0.0004814837,0.9574553,0.004069238,0.0002325226,0.001531172,0.00001002111,0.000490048,0.01737603],"genre_scores_gemma":[0.8740628,0.0001012385,0.1231052,0.0001317404,0.0001154619,0.0002160694,0.00002624918,0.000007127948,0.002234082],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8557086,"threshold_uncertainty_score":0.1859634,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02617905632834657,"score_gpt":0.2858960940716449,"score_spread":0.2597170377432984,"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."}}