{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:4TZ3RWFY4YUNRXZDRHBU4QWBXN","short_pith_number":"pith:4TZ3RWFY","schema_version":"1.0","canonical_sha256":"e4f3b8d8b8e628d8df2389c34e42c1bb6858967182d0c392ae44719addf25ed4","source":{"kind":"arxiv","id":"2605.14386","version":1},"attestation_state":"computed","paper":{"title":"Darwin Family: MRI-Trust-Weighted Evolutionary Merging for Training-Free Scaling of Language-Model Reasoning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"Evolutionary merging of existing language model checkpoints produces superior reasoning performance without any training.","cross_cats":["cs.AI"],"primary_cat":"cs.NE","authors_text":"Jaewon Jang, Junghoon Shin, Minseo Kim, Minsik Kim, Sunyoung Choi, Taebong Kim, Youngsik Hong","submitted_at":"2026-05-14T05:09:12Z","abstract_excerpt":"We present Darwin Family, a framework for training-free evolutionary merging of large language models via gradient-free weight-space recombination. We ask whether frontier-level reasoning performance can be improved without additional training, by reorganizing latent capabilities already encoded in existing checkpoints. Darwin introduces three key ideas: (i) a 14-dimensional adaptive merge genome enabling fine-grained component- and block-level recombination; (ii) MRI-Trust Fusion, which adaptively balances diagnostic layer-importance signals with evolutionary search through a learnable trust "},"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":true,"formal_links_present":true},"canonical_record":{"source":{"id":"2605.14386","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.NE","submitted_at":"2026-05-14T05:09:12Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"c461aa8820472e61db747a2d0a7182cb1675e71409a9b4300174836fc1f5f49f","abstract_canon_sha256":"b2edeca0f92cfa052adfac5ff244477531547f1ea36f88c4a7da21f1c172fd40"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:39:07.668642Z","signature_b64":"HEdNLvwcdclQU/WGQp1f2qmGYFY9UX5py1oE+tqPj+4ySEDZ5gewBw7I46N8fqnL4VsVIYg7TjIrRc1S/Ua5BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e4f3b8d8b8e628d8df2389c34e42c1bb6858967182d0c392ae44719addf25ed4","last_reissued_at":"2026-05-17T23:39:07.667925Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:39:07.667925Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Darwin Family: MRI-Trust-Weighted Evolutionary Merging for Training-Free Scaling of Language-Model Reasoning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"Evolutionary merging of existing language model checkpoints produces superior reasoning performance without any training.","cross_cats":["cs.AI"],"primary_cat":"cs.NE","authors_text":"Jaewon Jang, Junghoon Shin, Minseo Kim, Minsik Kim, Sunyoung Choi, Taebong Kim, Youngsik Hong","submitted_at":"2026-05-14T05:09:12Z","abstract_excerpt":"We present Darwin Family, a framework for training-free evolutionary merging of large language models via gradient-free weight-space recombination. We ask whether frontier-level reasoning performance can be improved without additional training, by reorganizing latent capabilities already encoded in existing checkpoints. Darwin introduces three key ideas: (i) a 14-dimensional adaptive merge genome enabling fine-grained component- and block-level recombination; (ii) MRI-Trust Fusion, which adaptively balances diagnostic layer-importance signals with evolutionary search through a learnable trust "},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"The flagship Darwin-27B-Opus achieves 86.9% on GPQA Diamond, ranking #6 among 1,252 evaluated models, and outperforming its fully trained foundation model without any gradient-based training.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That the evolutionary recombination guided by the 14-dimensional merge genome and MRI-Trust Fusion can reliably reorganize latent reasoning capabilities already present in existing checkpoints without loss of coherence or introduction of new failure modes.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"Evolutionary merging with a 14-dimensional genome and MRI-Trust Fusion produces models that outperform their trained parents on reasoning benchmarks without any gradient updates.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Evolutionary merging of existing language model checkpoints produces superior reasoning performance without any training.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"1af84823694f7a281e48c186708ad9561a9f66045af0732bb7e0fd0dc86cd152"},"source":{"id":"2605.14386","kind":"arxiv","version":1},"verdict":{"id":"8c66b9a3-a779-4915-a734-ece30b7ba831","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-15T02:09:01.351243Z","strongest_claim":"The flagship Darwin-27B-Opus achieves 86.9% on GPQA Diamond, ranking #6 among 1,252 evaluated models, and outperforming its fully trained foundation model without any gradient-based training.","one_line_summary":"Evolutionary merging with a 14-dimensional genome and MRI-Trust Fusion produces models that outperform their trained parents on reasoning benchmarks without any gradient updates.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That the evolutionary recombination guided by the 14-dimensional merge genome and MRI-Trust Fusion can reliably reorganize latent reasoning capabilities already present in existing checkpoints without loss of coherence or introduction of new failure modes.","pith_extraction_headline":"Evolutionary merging of existing language model checkpoints produces superior reasoning performance without any training."},"references":{"count":31,"sample":[{"doi":"","year":2022,"title":"Chain-of-thought prompting elicits reason- ing in large language models","work_id":"59e16d6c-e56a-4398-a4a3-f1d086439c8d","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2022,"title":"Takeshi Kojima, Shixiang Gu, M. Reid, et al. Large language models are zero-shot reasoners. InNeural Information Processing Systems, 2022","work_id":"5c4ef5d3-b983-49db-86d1-2ef46e73e9d8","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2023,"title":"Self-consistency improves chain-of-thought reasoning in language models","work_id":"f088816e-1c6c-4ac4-8a4e-0b209da8ab9a","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2023,"title":"Least-to-most prompting enables complex rea- soning in large language models","work_id":"87a0882f-6eb8-47cf-aa5e-41759cd0d615","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2019,"title":"Bert rediscovers the classical nlp pipeline","work_id":"c9de2a65-5b4c-48bc-98de-2b89d1846e02","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":31,"snapshot_sha256":"26e9066885c73f9ad8cefc80e611f0979829f320fdeeb33805dd4f4b2726617a","internal_anchors":3},"formal_canon":{"evidence_count":2,"snapshot_sha256":"d02bb810824e18a774590e3eb05bec50099351a9e375f14abcd36dd734e52090"},"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":"2605.14386","created_at":"2026-05-17T23:39:07.668021+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.14386v1","created_at":"2026-05-17T23:39:07.668021+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.14386","created_at":"2026-05-17T23:39:07.668021+00:00"},{"alias_kind":"pith_short_12","alias_value":"4TZ3RWFY4YUN","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_16","alias_value":"4TZ3RWFY4YUNRXZD","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_8","alias_value":"4TZ3RWFY","created_at":"2026-05-18T12:33:37.589309+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":2,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4TZ3RWFY4YUNRXZDRHBU4QWBXN","json":"https://pith.science/pith/4TZ3RWFY4YUNRXZDRHBU4QWBXN.json","graph_json":"https://pith.science/api/pith-number/4TZ3RWFY4YUNRXZDRHBU4QWBXN/graph.json","events_json":"https://pith.science/api/pith-number/4TZ3RWFY4YUNRXZDRHBU4QWBXN/events.json","paper":"https://pith.science/paper/4TZ3RWFY"},"agent_actions":{"view_html":"https://pith.science/pith/4TZ3RWFY4YUNRXZDRHBU4QWBXN","download_json":"https://pith.science/pith/4TZ3RWFY4YUNRXZDRHBU4QWBXN.json","view_paper":"https://pith.science/paper/4TZ3RWFY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.14386&json=true","fetch_graph":"https://pith.science/api/pith-number/4TZ3RWFY4YUNRXZDRHBU4QWBXN/graph.json","fetch_events":"https://pith.science/api/pith-number/4TZ3RWFY4YUNRXZDRHBU4QWBXN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4TZ3RWFY4YUNRXZDRHBU4QWBXN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4TZ3RWFY4YUNRXZDRHBU4QWBXN/action/storage_attestation","attest_author":"https://pith.science/pith/4TZ3RWFY4YUNRXZDRHBU4QWBXN/action/author_attestation","sign_citation":"https://pith.science/pith/4TZ3RWFY4YUNRXZDRHBU4QWBXN/action/citation_signature","submit_replication":"https://pith.science/pith/4TZ3RWFY4YUNRXZDRHBU4QWBXN/action/replication_record"}},"created_at":"2026-05-17T23:39:07.668021+00:00","updated_at":"2026-05-17T23:39:07.668021+00:00"}