{"id":"W6979357642","doi":"","title":"Darwin Godel Machine: Open-Ended Evolution of Self-Improving Agents","year":2025,"lang":"en","type":"article","venue":"arXiv (Cornell University)","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; Government of Canada; Canadian Institute for Advanced Research","keywords":"Darwin (ADL); Coding (social sciences); Code (set theory); Polyglot; Reinforcement learning; Source code; Tree (set theory); Artificial life","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002977067,0.0001068816,0.0001364824,0.0002088551,0.0001673666,0.00007960597,0.001634161,0.00006158192,0.00001610026],"category_scores_gemma":[0.00006430532,0.0001188558,0.00004833122,0.0009596407,0.00003214062,0.0007598648,0.0008222776,0.0001486701,0.00003068014],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001635789,"about_ca_system_score_gemma":0.0001663878,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000566954,"about_ca_topic_score_gemma":0.00003874558,"domain_scores_codex":[0.9989958,0.0001345073,0.0001495611,0.0004935528,0.00006043121,0.000166085],"domain_scores_gemma":[0.9988725,0.00005683905,0.0001521174,0.000777819,0.00008560159,0.0000551829],"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":[0.00002313773,0.0001669212,0.01910994,0.00004758995,0.00003606671,0.00001069819,0.00009923278,0.007397399,0.0007473749,0.9662583,0.0008544049,0.005248893],"study_design_scores_gemma":[0.0006198232,0.00003260242,0.03282459,0.00002224402,0.00002593296,9.225229e-7,0.00004317811,0.958645,0.0001742008,0.00571198,0.00177698,0.0001225799],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05104113,0.00003525268,0.9225252,0.0001788514,0.0001679186,0.0001585691,0.000006297787,0.000174192,0.0257126],"genre_scores_gemma":[0.9929024,0.00001369092,0.004618979,0.00006284531,0.000007437543,4.271049e-7,0.00001111422,0.00000400102,0.002379105],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9605464,"threshold_uncertainty_score":0.4846797,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04046442298126716,"score_gpt":0.2077637585698182,"score_spread":0.167299335588551,"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."}}