{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:YOJ2H3RCVRZ6OF6SMRRKPEE37E","short_pith_number":"pith:YOJ2H3RC","schema_version":"1.0","canonical_sha256":"c393a3ee22ac73e717d26462a7909bf9149eba78fb0c2e4e5ab2362dc8e52998","source":{"kind":"arxiv","id":"2503.01155","version":1},"attestation_state":"computed","paper":{"title":"Nature-Inspired Population-Based Evolution of Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.MA"],"primary_cat":"cs.CL","authors_text":"Lei Bai, Peng Ye, Shi Feng, Shufei Zhang, Shuyue Hu, Wanli Ouyang, Xiaocui Yang, Yiqun Zhang","submitted_at":"2025-03-03T04:03:31Z","abstract_excerpt":"Evolution, the engine behind the survival and growth of life on Earth, operates through the population-based process of reproduction. Inspired by this principle, this paper formally defines a newly emerging problem -- the population-based evolution of large language models (LLMs) -- and introduces a novel framework. Starting with a population of parent LLMs, our framework enables the population to evolve through four key operations: (i) crossover, merging the weights of different parents to create offspring LLMs, (ii) mutation, introducing small, random changes to model weights to foster diver"},"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":"2503.01155","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-03-03T04:03:31Z","cross_cats_sorted":["cs.MA"],"title_canon_sha256":"d6d26f9d0b3f0d7fd6fafb3477fe8bc268f8a05502c97ddb0dbf5a3f7b8fc593","abstract_canon_sha256":"b3e83c31dd6988cec410595c920927c15492cda5c87e82bf8426c892266818d9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:26:15.554258Z","signature_b64":"TaL04wbhSAwhNKRHRaf9Lki/DrU+4ux32B2zkcTAqTWA2cxDDYbL8Ff6Z0of0ztM0/yOZs47bsKtngStzPe3DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c393a3ee22ac73e717d26462a7909bf9149eba78fb0c2e4e5ab2362dc8e52998","last_reissued_at":"2026-07-05T10:26:15.553286Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:26:15.553286Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Nature-Inspired Population-Based Evolution of Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.MA"],"primary_cat":"cs.CL","authors_text":"Lei Bai, Peng Ye, Shi Feng, Shufei Zhang, Shuyue Hu, Wanli Ouyang, Xiaocui Yang, Yiqun Zhang","submitted_at":"2025-03-03T04:03:31Z","abstract_excerpt":"Evolution, the engine behind the survival and growth of life on Earth, operates through the population-based process of reproduction. Inspired by this principle, this paper formally defines a newly emerging problem -- the population-based evolution of large language models (LLMs) -- and introduces a novel framework. Starting with a population of parent LLMs, our framework enables the population to evolve through four key operations: (i) crossover, merging the weights of different parents to create offspring LLMs, (ii) mutation, introducing small, random changes to model weights to foster diver"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.01155","kind":"arxiv","version":1},"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/2503.01155/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":"2503.01155","created_at":"2026-07-05T10:26:15.553442+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.01155v1","created_at":"2026-07-05T10:26:15.553442+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.01155","created_at":"2026-07-05T10:26:15.553442+00:00"},{"alias_kind":"pith_short_12","alias_value":"YOJ2H3RCVRZ6","created_at":"2026-07-05T10:26:15.553442+00:00"},{"alias_kind":"pith_short_16","alias_value":"YOJ2H3RCVRZ6OF6S","created_at":"2026-07-05T10:26:15.553442+00:00"},{"alias_kind":"pith_short_8","alias_value":"YOJ2H3RC","created_at":"2026-07-05T10:26:15.553442+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.28373","citing_title":"Model Merging to Evolution: Parameter Space Exploration for Expert Models","ref_index":36,"is_internal_anchor":false},{"citing_arxiv_id":"2605.16727","citing_title":"PopuLoRA: Co-Evolving LLM Populations for Reasoning Self-Play","ref_index":51,"is_internal_anchor":false},{"citing_arxiv_id":"2507.21046","citing_title":"A Survey of Self-Evolving Agents: What, When, How, and Where to Evolve on the Path to Artificial Super Intelligence","ref_index":184,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YOJ2H3RCVRZ6OF6SMRRKPEE37E","json":"https://pith.science/pith/YOJ2H3RCVRZ6OF6SMRRKPEE37E.json","graph_json":"https://pith.science/api/pith-number/YOJ2H3RCVRZ6OF6SMRRKPEE37E/graph.json","events_json":"https://pith.science/api/pith-number/YOJ2H3RCVRZ6OF6SMRRKPEE37E/events.json","paper":"https://pith.science/paper/YOJ2H3RC"},"agent_actions":{"view_html":"https://pith.science/pith/YOJ2H3RCVRZ6OF6SMRRKPEE37E","download_json":"https://pith.science/pith/YOJ2H3RCVRZ6OF6SMRRKPEE37E.json","view_paper":"https://pith.science/paper/YOJ2H3RC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.01155&json=true","fetch_graph":"https://pith.science/api/pith-number/YOJ2H3RCVRZ6OF6SMRRKPEE37E/graph.json","fetch_events":"https://pith.science/api/pith-number/YOJ2H3RCVRZ6OF6SMRRKPEE37E/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YOJ2H3RCVRZ6OF6SMRRKPEE37E/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YOJ2H3RCVRZ6OF6SMRRKPEE37E/action/storage_attestation","attest_author":"https://pith.science/pith/YOJ2H3RCVRZ6OF6SMRRKPEE37E/action/author_attestation","sign_citation":"https://pith.science/pith/YOJ2H3RCVRZ6OF6SMRRKPEE37E/action/citation_signature","submit_replication":"https://pith.science/pith/YOJ2H3RCVRZ6OF6SMRRKPEE37E/action/replication_record"}},"created_at":"2026-07-05T10:26:15.553442+00:00","updated_at":"2026-07-05T10:26:15.553442+00:00"}