{"id":"W4412505633","doi":"10.70777/si.v2i3.15063","title":"Darwin Gödel Machine: Open-Ended Evolution of Self-Improving Agents","year":2025,"lang":"en","type":"article","venue":"SuperIntelligence - Robotics - Safety & Alignment","topic":"Evolutionary Algorithms and Applications","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":true,"ca_institutions":"Vector Institute; Canadian Institute for Advanced Research; University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada; Government of Canada; Canadian Institute for Advanced Research","keywords":"Darwin (ADL); Computer science; Software engineering","routes":{"ca_aff":true,"ca_fund":true,"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":[0.001167906,0.0005028654,0.0004847978,0.0005275081,0.0006906063,0.001157655,0.001595487,0.001210034,0.002358855],"category_scores_gemma":[0.006205842,0.0003869883,0.0006253699,0.0003384255,0.002719186,0.001475287,0.001455287,0.001213828,0.0004559798],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008447784,"about_ca_system_score_gemma":0.001008966,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001782578,"about_ca_topic_score_gemma":0.001360453,"domain_scores_codex":[0.9995198,0.0001527553,0.00002126816,0.0001007334,0.0001527836,0.00005277929],"domain_scores_gemma":[0.998322,0.0008145462,0.0001553633,0.0004044744,0.0002137159,0.00008992409],"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":[0.0001333462,0.0000655442,0.002987412,0.0002441497,0.0001089494,0.0003420681,0.0008348593,0.5342573,0.01822562,0.3565945,0.004208212,0.08199814],"study_design_scores_gemma":[0.00005012832,0.0001037947,0.0004460398,0.00003440079,0.00003307547,0.0001300338,0.00007659433,0.8593225,0.0060755,0.1209895,0.012701,0.00003739116],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.09733579,0.0005801345,0.8791125,0.0009115592,0.0001624408,0.0001607232,0.0001231577,0.00198833,0.01962548],"genre_scores_gemma":[0.6517857,0.0003877672,0.3398249,0.0002890339,0.00003982492,0.0002960724,0.0001670684,0.0003661104,0.006843461],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.002358855,"threshold_uncertainty_score":0.007891178,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01750147175455305,"score_gpt":0.2803470702291549,"score_spread":0.2628455984746019,"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."}}