{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001614124,0.0005583559,0.0006095248,0.0006340575,0.0008711237,0.001199522,0.001945828,0.001167956,0.002662271],"category_scores_gemma":[0.008004766,0.0003923482,0.000701958,0.0004245371,0.001922734,0.001506676,0.001594627,0.001289425,0.0006756609],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009185602,"about_ca_system_score_gemma":0.0010486,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002172123,"about_ca_topic_score_gemma":0.001632861,"domain_scores_codex":[0.9992946,0.0002310289,0.0000371519,0.0001624643,0.0002086818,0.00006600374],"domain_scores_gemma":[0.9971958,0.001378143,0.0002149857,0.0006521545,0.0004039682,0.0001548209],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0002258952,0.0001559612,0.007231729,0.0002746017,0.0001621451,0.0004599691,0.0009354519,0.6617514,0.01632185,0.1123681,0.009260422,0.1908525],"study_design_scores_gemma":[0.00005245203,0.00010124,0.0005009976,0.00002648875,0.00003000418,0.0001062758,0.00004636319,0.9510317,0.004821648,0.03247148,0.01078196,0.00002932932],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1375382,0.0006645439,0.8360327,0.001049227,0.000264905,0.0002563603,0.0002258377,0.006995827,0.01697247],"genre_scores_gemma":[0.6330335,0.0002748676,0.3583154,0.0004067875,0.00005835677,0.0003968374,0.00039708,0.0006773843,0.006439795],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.002662271,"threshold_uncertainty_score":0.008906186,"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."}}