{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0001291785,0.0003113857,0.0003334736,0.0001520589,0.0003693143,0.000127684,0.001227088,0.000289055,0.00001092204],"category_scores_gemma":[0.000009801211,0.000330396,0.0003362601,0.0004515518,0.00007652275,0.0004234111,0.0004858556,0.0003706664,0.00001156143],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001628709,"about_ca_system_score_gemma":0.0004806918,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003459565,"about_ca_topic_score_gemma":0.00002782395,"domain_scores_codex":[0.9981214,0.00005662145,0.0002065172,0.001177186,0.00009207686,0.0003462116],"domain_scores_gemma":[0.9982975,0.00006172435,0.0001518857,0.001017258,0.0003017646,0.0001699193],"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":[0.000009080615,0.0001582431,0.00003248299,0.00006267778,0.00006376551,0.00002002336,0.0009610629,0.5286676,0.0003487742,0.4682379,0.0005065442,0.0009318247],"study_design_scores_gemma":[0.0003437191,0.00001901783,0.00008862309,0.00006403915,0.00005234242,0.000004192751,0.00008359096,0.925103,0.0004249867,0.07322198,0.0002388549,0.0003556478],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04204868,0.0001819596,0.9554307,0.0005431498,0.0002019403,0.0005589725,0.00006940334,0.0001709019,0.0007942843],"genre_scores_gemma":[0.9354528,0.0002983194,0.06042043,0.0001648364,0.0001102189,0.00002784649,0.0001071353,0.00002045933,0.003397934],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8950103,"threshold_uncertainty_score":0.9999148,"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."}}