{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:ORMO545EA32BAKDOXDVE6UPN7K","short_pith_number":"pith:ORMO545E","schema_version":"1.0","canonical_sha256":"7458eef3a406f410286eb8ea4f51edfaa64e3ff35587aebd836ac9c52cad138c","source":{"kind":"arxiv","id":"2510.14150","version":5},"attestation_state":"computed","paper":{"title":"CodeEvolve: an open source evolutionary coding agent for algorithmic discovery and optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.NE"],"primary_cat":"cs.AI","authors_text":"Diego Ferreira, Fabricio Murai, Henrique Assump\\c{c}\\~ao, Leandro Campos","submitted_at":"2025-10-15T22:58:06Z","abstract_excerpt":"We introduce CodeEvolve, an open-source framework that couples large language models with island-based evolutionary search for end-to-end algorithmic discovery. CodeEvolve integrates inspiration-based crossover, meta-prompting, and depth-based refinement on top of a CVT-MAP-Elites archive and a weighted LLM ensemble to generate optimized solutions for complex problems. On the AlphaEvolve benchmark suite, CodeEvolve matches or surpasses the reported AlphaEvolve results on 5 of 9 problems and, under matched conditions, outperforms the open-source frameworks OpenEvolve and ShinkaEvolve on 6 of 9."},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2510.14150","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-10-15T22:58:06Z","cross_cats_sorted":["cs.LG","cs.NE"],"title_canon_sha256":"f6553ecfee2898a2aaa46e8b2f4c1c29ab6d6a60db5f3f5bd7a08b7540ce9081","abstract_canon_sha256":"0fbe613142cb9216ae224190e906db463553d572cfe71a1512a841f6398a380d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-29T02:05:37.185164Z","signature_b64":"EcqKCDG+4kk1wn275aSB/+exv0SgErhX2EJNqP5nmxH03kwPLerdNc8hcb6N0dHWCBWAQFS1i/Fb6hQizQBjAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7458eef3a406f410286eb8ea4f51edfaa64e3ff35587aebd836ac9c52cad138c","last_reissued_at":"2026-05-29T02:05:37.184614Z","signature_status":"signed_v1","first_computed_at":"2026-05-29T02:05:37.184614Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CodeEvolve: an open source evolutionary coding agent for algorithmic discovery and optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.NE"],"primary_cat":"cs.AI","authors_text":"Diego Ferreira, Fabricio Murai, Henrique Assump\\c{c}\\~ao, Leandro Campos","submitted_at":"2025-10-15T22:58:06Z","abstract_excerpt":"We introduce CodeEvolve, an open-source framework that couples large language models with island-based evolutionary search for end-to-end algorithmic discovery. CodeEvolve integrates inspiration-based crossover, meta-prompting, and depth-based refinement on top of a CVT-MAP-Elites archive and a weighted LLM ensemble to generate optimized solutions for complex problems. On the AlphaEvolve benchmark suite, CodeEvolve matches or surpasses the reported AlphaEvolve results on 5 of 9 problems and, under matched conditions, outperforms the open-source frameworks OpenEvolve and ShinkaEvolve on 6 of 9."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2510.14150","kind":"arxiv","version":5},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2510.14150/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2510.14150","created_at":"2026-05-29T02:05:37.184691+00:00"},{"alias_kind":"arxiv_version","alias_value":"2510.14150v5","created_at":"2026-05-29T02:05:37.184691+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2510.14150","created_at":"2026-05-29T02:05:37.184691+00:00"},{"alias_kind":"pith_short_12","alias_value":"ORMO545EA32B","created_at":"2026-05-29T02:05:37.184691+00:00"},{"alias_kind":"pith_short_16","alias_value":"ORMO545EA32BAKDO","created_at":"2026-05-29T02:05:37.184691+00:00"},{"alias_kind":"pith_short_8","alias_value":"ORMO545E","created_at":"2026-05-29T02:05:37.184691+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":16,"internal_anchor_count":16,"sample":[{"citing_arxiv_id":"2605.20086","citing_title":"What Do Evolutionary Coding Agents Evolve?","ref_index":5,"is_internal_anchor":true},{"citing_arxiv_id":"2605.15221","citing_title":"Effective Harness Engineering for Algorithm Discovery with Coding Agents","ref_index":15,"is_internal_anchor":true},{"citing_arxiv_id":"2605.15334","citing_title":"From I/O to Code with Discovery Agent","ref_index":1,"is_internal_anchor":true},{"citing_arxiv_id":"2605.09018","citing_title":"Evolutionary Ensemble of Agents","ref_index":9,"is_internal_anchor":true},{"citing_arxiv_id":"2605.15026","citing_title":"SemaTune: Semantic-Aware Online OS Tuning with Large Language Models","ref_index":6,"is_internal_anchor":true},{"citing_arxiv_id":"2604.03473","citing_title":"Evolutionary Search for Automated Design of Uncertainty Quantification Methods","ref_index":1,"is_internal_anchor":true},{"citing_arxiv_id":"2605.08678","citing_title":"MLS-Bench: A Holistic and Rigorous Assessment of AI Systems on Building Better AI","ref_index":5,"is_internal_anchor":true},{"citing_arxiv_id":"2605.08520","citing_title":"FlashEvolve: Accelerating Agent Self-Evolution with Asynchronous Stage Orchestration","ref_index":3,"is_internal_anchor":true},{"citing_arxiv_id":"2605.09018","citing_title":"Evolutionary Ensemble of Agents","ref_index":9,"is_internal_anchor":true},{"citing_arxiv_id":"2604.25083","citing_title":"Agentic Architect: An Agentic AI Framework for Architecture Design Exploration and Optimization","ref_index":5,"is_internal_anchor":true},{"citing_arxiv_id":"2604.18607","citing_title":"TurboEvolve: Towards Fast and Robust LLM-Driven Program Evolution","ref_index":2,"is_internal_anchor":true},{"citing_arxiv_id":"2604.07144","citing_title":"Autopoiesis: A Self-Evolving System Paradigm for LLM Serving Under Runtime Dynamics","ref_index":30,"is_internal_anchor":true},{"citing_arxiv_id":"2605.07039","citing_title":"PACEvolve++: Improving Test-time Learning for Evolutionary Search Agents","ref_index":4,"is_internal_anchor":true},{"citing_arxiv_id":"2605.07572","citing_title":"Open-Ended Task Discovery via Bayesian Optimization","ref_index":9,"is_internal_anchor":true},{"citing_arxiv_id":"2604.16625","citing_title":"AdaExplore: Failure-Driven Adaptation and Diversity-Preserving Search for Efficient Kernel Generation","ref_index":2,"is_internal_anchor":true},{"citing_arxiv_id":"2604.19341","citing_title":"Evaluation-driven Scaling for Scientific Discovery","ref_index":7,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ORMO545EA32BAKDOXDVE6UPN7K","json":"https://pith.science/pith/ORMO545EA32BAKDOXDVE6UPN7K.json","graph_json":"https://pith.science/api/pith-number/ORMO545EA32BAKDOXDVE6UPN7K/graph.json","events_json":"https://pith.science/api/pith-number/ORMO545EA32BAKDOXDVE6UPN7K/events.json","paper":"https://pith.science/paper/ORMO545E"},"agent_actions":{"view_html":"https://pith.science/pith/ORMO545EA32BAKDOXDVE6UPN7K","download_json":"https://pith.science/pith/ORMO545EA32BAKDOXDVE6UPN7K.json","view_paper":"https://pith.science/paper/ORMO545E","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2510.14150&json=true","fetch_graph":"https://pith.science/api/pith-number/ORMO545EA32BAKDOXDVE6UPN7K/graph.json","fetch_events":"https://pith.science/api/pith-number/ORMO545EA32BAKDOXDVE6UPN7K/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ORMO545EA32BAKDOXDVE6UPN7K/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ORMO545EA32BAKDOXDVE6UPN7K/action/storage_attestation","attest_author":"https://pith.science/pith/ORMO545EA32BAKDOXDVE6UPN7K/action/author_attestation","sign_citation":"https://pith.science/pith/ORMO545EA32BAKDOXDVE6UPN7K/action/citation_signature","submit_replication":"https://pith.science/pith/ORMO545EA32BAKDOXDVE6UPN7K/action/replication_record"}},"created_at":"2026-05-29T02:05:37.184691+00:00","updated_at":"2026-05-29T02:05:37.184691+00:00"}