{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:7X2WC3QOGBPMK2NTU7Z6JHGROH","short_pith_number":"pith:7X2WC3QO","schema_version":"1.0","canonical_sha256":"fdf5616e0e305ec569b3a7f3e49cd171d4fecd9ccf93f69aa1767c03d5dea13a","source":{"kind":"arxiv","id":"2605.07111","version":2},"attestation_state":"computed","paper":{"title":"Beyond LoRA vs. Full Fine-Tuning: Gradient-Guided Optimizer Routing for LLM Adaptation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"Gradient routing between full and LoRA tuning beats static choices","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Boxun Li, Haozhan Tang, Kevin Kuo, Virginia Smith, Xinyin Zhang, Xiuqi Zhu","submitted_at":"2026-05-08T01:38:58Z","abstract_excerpt":"Recent literature on fine-tuning Large Language Models highlights a fundamental debate. While Full Fine-Tuning (FFT) provides the representational plasticity required for high-entropy knowledge injection, Low-Rank Adaptation (LoRA) can match or surpass FFT performance because many tasks only require updates in a low-rank space and benefit from LoRA's additional regularization. Through empirical evaluation across diverse tasks (SQL, Medical QA, and Counterfactual Knowledge) and varying language models (Gemma-3-1B, Qwen2.5-1.5B, and Qwen2.5-3B), we verify both trends and demonstrate that relying"},"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":true},"canonical_record":{"source":{"id":"2605.07111","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-08T01:38:58Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"103e0cf8c60a2787cbd5b3f86bad6499148fd2bfa103ee1f751146f704ee3b64","abstract_canon_sha256":"8e5bf3075d2e1b68b45eb49719ba7ea8b7e781e48d2aac672b64f638cb815090"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:04:34.544895Z","signature_b64":"VdQ8qfqECovANhOiqQ3xl9pB1lp7CSx6ffmh5uDYFQF8wuj2QiSK/cPfv1YNgfnpFusEo+r5sA3kPpuv0CYyCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fdf5616e0e305ec569b3a7f3e49cd171d4fecd9ccf93f69aa1767c03d5dea13a","last_reissued_at":"2026-05-20T00:04:34.544123Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:04:34.544123Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Beyond LoRA vs. Full Fine-Tuning: Gradient-Guided Optimizer Routing for LLM Adaptation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"Gradient routing between full and LoRA tuning beats static choices","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Boxun Li, Haozhan Tang, Kevin Kuo, Virginia Smith, Xinyin Zhang, Xiuqi Zhu","submitted_at":"2026-05-08T01:38:58Z","abstract_excerpt":"Recent literature on fine-tuning Large Language Models highlights a fundamental debate. While Full Fine-Tuning (FFT) provides the representational plasticity required for high-entropy knowledge injection, Low-Rank Adaptation (LoRA) can match or surpass FFT performance because many tasks only require updates in a low-rank space and benefit from LoRA's additional regularization. Through empirical evaluation across diverse tasks (SQL, Medical QA, and Counterfactual Knowledge) and varying language models (Gemma-3-1B, Qwen2.5-1.5B, and Qwen2.5-3B), we verify both trends and demonstrate that relying"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"Our evaluations show that MoLF either improves on or stays within 1.5% of the better of FFT and LoRA across all settings, while MoLF-Efficient outperforms prior adaptive LoRA approaches by up to 20% on Fact and 9% on Med and SQL.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That gradient-guided routing at the optimizer level will produce stable training dynamics and that the observed performance gains on the tested models and tasks will hold for other LLMs and domains.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"MoLF routes updates between full fine-tuning and LoRA at the optimizer level to match or exceed the better of either static method, with an efficient LoRA-only variant outperforming prior adaptive approaches.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Gradient routing between full and LoRA tuning beats static choices","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"d95b4e9469b7d3d5d9293102394085b8ce920d6dfe1207dd1fbf3ec7e8b3fd31"},"source":{"id":"2605.07111","kind":"arxiv","version":2},"verdict":{"id":"238107a3-c9e5-4662-bfe5-45b7242416f9","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-11T01:06:23.765691Z","strongest_claim":"Our evaluations show that MoLF either improves on or stays within 1.5% of the better of FFT and LoRA across all settings, while MoLF-Efficient outperforms prior adaptive LoRA approaches by up to 20% on Fact and 9% on Med and SQL.","one_line_summary":"MoLF routes updates between full fine-tuning and LoRA at the optimizer level to match or exceed the better of either static method, with an efficient LoRA-only variant outperforming prior adaptive approaches.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That gradient-guided routing at the optimizer level will produce stable training dynamics and that the observed performance gains on the tested models and tasks will hold for other LLMs and domains.","pith_extraction_headline":"Gradient routing between full and LoRA tuning beats static choices"},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2605.07111/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"doi_title_agreement","ran_at":"2026-05-19T17:01:20.208246Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_compliance","ran_at":"2026-05-19T12:03:16.659944Z","status":"completed","version":"1.0.0","findings_count":0}],"snapshot_sha256":"7edae3803484477b5980f53e42edef3702145ff1dd67ae2e12af8a04c4ce6185"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":2,"snapshot_sha256":"333d7a786c5dc6498bf5f007daacde7861e685b842781fe932fe275ad1e28763"},"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":"2605.07111","created_at":"2026-05-20T00:04:34.544233+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.07111v2","created_at":"2026-05-20T00:04:34.544233+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.07111","created_at":"2026-05-20T00:04:34.544233+00:00"},{"alias_kind":"pith_short_12","alias_value":"7X2WC3QOGBPM","created_at":"2026-05-20T00:04:34.544233+00:00"},{"alias_kind":"pith_short_16","alias_value":"7X2WC3QOGBPMK2NT","created_at":"2026-05-20T00:04:34.544233+00:00"},{"alias_kind":"pith_short_8","alias_value":"7X2WC3QO","created_at":"2026-05-20T00:04:34.544233+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/7X2WC3QOGBPMK2NTU7Z6JHGROH","json":"https://pith.science/pith/7X2WC3QOGBPMK2NTU7Z6JHGROH.json","graph_json":"https://pith.science/api/pith-number/7X2WC3QOGBPMK2NTU7Z6JHGROH/graph.json","events_json":"https://pith.science/api/pith-number/7X2WC3QOGBPMK2NTU7Z6JHGROH/events.json","paper":"https://pith.science/paper/7X2WC3QO"},"agent_actions":{"view_html":"https://pith.science/pith/7X2WC3QOGBPMK2NTU7Z6JHGROH","download_json":"https://pith.science/pith/7X2WC3QOGBPMK2NTU7Z6JHGROH.json","view_paper":"https://pith.science/paper/7X2WC3QO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.07111&json=true","fetch_graph":"https://pith.science/api/pith-number/7X2WC3QOGBPMK2NTU7Z6JHGROH/graph.json","fetch_events":"https://pith.science/api/pith-number/7X2WC3QOGBPMK2NTU7Z6JHGROH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7X2WC3QOGBPMK2NTU7Z6JHGROH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7X2WC3QOGBPMK2NTU7Z6JHGROH/action/storage_attestation","attest_author":"https://pith.science/pith/7X2WC3QOGBPMK2NTU7Z6JHGROH/action/author_attestation","sign_citation":"https://pith.science/pith/7X2WC3QOGBPMK2NTU7Z6JHGROH/action/citation_signature","submit_replication":"https://pith.science/pith/7X2WC3QOGBPMK2NTU7Z6JHGROH/action/replication_record"}},"created_at":"2026-05-20T00:04:34.544233+00:00","updated_at":"2026-05-20T00:04:34.544233+00:00"}