{"id":"W3175526646","doi":"10.48550/arxiv.2106.14131","title":"SymbolicGPT: A Generative Transformer Model for Symbolic Regression","year":2021,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Evolutionary Algorithms and Applications","field":"Computer Science","cited_by":37,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Symbolic regression; Computer science; Probabilistic logic; Transformer; Artificial intelligence; Machine learning; Regression; Generative grammar; Exploit; Generative model; Regression analysis; Genetic programming; Mathematics; Statistics; Engineering","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001547332,0.000935348,0.001129404,0.001256129,0.000426345,0.002051622,0.002649311,0.001437936,0.006835673],"category_scores_gemma":[0.009530395,0.0005601763,0.001810402,0.001741472,0.00144775,0.002899625,0.002330379,0.002202457,0.00247714],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001096955,"about_ca_system_score_gemma":0.001648457,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003681467,"about_ca_topic_score_gemma":0.004918275,"domain_scores_codex":[0.9990413,0.000289308,0.00005642962,0.0002411923,0.0002912233,0.00008062014],"domain_scores_gemma":[0.9979243,0.001345618,0.0001500067,0.0002721911,0.0002215986,0.00008617136],"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":[0.0001097596,0.00006908243,0.001260383,0.0001460702,0.00007972052,0.000227315,0.0001363789,0.731614,0.002853635,0.1589102,0.00580717,0.09878623],"study_design_scores_gemma":[0.000006167705,0.00001046461,0.0000299389,0.000006855342,0.000005432028,0.00003647136,0.000004632271,0.9651891,0.0003880121,0.03314567,0.001171243,0.000006037466],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.003586579,0.0001199891,0.9932279,0.0002071877,0.00003230266,0.00003048678,0.00034505,0.00097332,0.001477287],"genre_scores_gemma":[0.4110611,0.0007916384,0.568956,0.000693679,0.0001342325,0.0005650272,0.002926197,0.001763748,0.01310834],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.006835673,"threshold_uncertainty_score":0.02286762,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08461084795732692,"score_gpt":0.2156237108939364,"score_spread":0.1310128629366095,"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."}}