{"id":"W4393106948","doi":"10.1007/978-981-99-8413-8_10","title":"The OpenELM Library: Leveraging Progress in Language Models for Novel Evolutionary Algorithms","year":2024,"lang":"en","type":"book-chapter","venue":"Genetic and evolutionary computation","topic":"Evolutionary Algorithms and Applications","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":false,"ca_institutions":"Queen's University","funders":"","keywords":"Implementation; Computer science; Leverage (statistics); Python (programming language); Genetic programming; Evolutionary algorithm; Artificial intelligence; Inference; Machine learning; Programming language; Data science","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":[0.0001788487,0.0003847024,0.0002762566,0.000268536,0.0006189395,0.0002986783,0.000633381,0.0002276222,0.000006170717],"category_scores_gemma":[0.000003868512,0.0003428686,0.0001382277,0.0002013968,0.0002258509,0.0006117367,0.0005330553,0.0003243448,0.00002981269],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001562067,"about_ca_system_score_gemma":0.0003328208,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001165418,"about_ca_topic_score_gemma":0.000003399384,"domain_scores_codex":[0.9977352,0.00002160968,0.0005695047,0.0008978656,0.0003781858,0.000397617],"domain_scores_gemma":[0.9989045,0.0002732759,0.0001845125,0.0004042446,0.0001184983,0.0001150256],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0000145465,0.0000591941,0.00002417324,0.00008406134,0.00007836459,0.00001357007,0.0004147412,0.03342266,0.00000276382,0.8695639,0.007308127,0.08901384],"study_design_scores_gemma":[0.0002502802,0.00004485308,0.001370375,0.0001026974,0.00002124433,0.00006736419,0.00003290528,0.6029698,4.466839e-7,0.3678739,0.02700095,0.0002651046],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00007727089,0.0757587,0.9016662,0.004753434,0.000645826,0.001519613,0.0002079797,0.0003251738,0.01504579],"genre_scores_gemma":[0.02036049,0.003188217,0.7873487,0.0003269183,0.001234896,0.001077361,0.001073527,0.0001911224,0.1851987],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.5695472,"threshold_uncertainty_score":0.9999023,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02034067460913992,"score_gpt":0.2482385159854312,"score_spread":0.2278978413762913,"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."}}