{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0005214629,0.0002854732,0.0003376216,0.0001691227,0.0004089315,0.0001400217,0.002503368,0.0001069363,0.00007027271],"category_scores_gemma":[0.00003363841,0.0002927787,0.0001366868,0.000940708,0.0001007462,0.0005766518,0.001641247,0.000197233,0.00005809612],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000611991,"about_ca_system_score_gemma":0.0004134976,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003715551,"about_ca_topic_score_gemma":0.00001814276,"domain_scores_codex":[0.9973931,0.00009314172,0.0008180709,0.0007510316,0.0004798851,0.0004647527],"domain_scores_gemma":[0.9981717,0.00009567905,0.0001755791,0.001227956,0.0001866233,0.000142402],"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":[0.0000175139,0.0008327861,0.0009451335,0.00008521036,0.000114277,0.000005175771,0.0005003161,0.09974301,0.002580495,0.8720186,0.0005345713,0.02262285],"study_design_scores_gemma":[0.000488893,0.000162206,0.007241849,0.0001277172,0.00006323025,0.00001462099,0.0003885903,0.946618,0.008902059,0.02680484,0.008665624,0.0005223814],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0006381384,0.0004769808,0.989634,0.001785999,0.0005485562,0.0008136421,0.00003089257,0.0001551281,0.005916605],"genre_scores_gemma":[0.6902934,0.0002592152,0.3083371,0.0001842254,0.00003418173,0.00007816588,0.00002054999,0.00001419162,0.0007790382],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.846875,"threshold_uncertainty_score":0.9999524,"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."}}