{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:4ZUBRLGTVWNUSMR6WFAUMH2ICX","short_pith_number":"pith:4ZUBRLGT","schema_version":"1.0","canonical_sha256":"e66818acd3ad9b49323eb141461f4815fcd851b5528df18799e1f97ec59b3f1a","source":{"kind":"arxiv","id":"2501.14859","version":1},"attestation_state":"computed","paper":{"title":"Dynamic Adaptation of LoRA Fine-Tuning for Efficient and Task-Specific Optimization of Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Chihang Wang, Hongye Zheng, Jiacheng Hu, Jia Gao, Shicheng Zhou, Xiaoxuan Liao","submitted_at":"2025-01-24T18:54:14Z","abstract_excerpt":"This paper presents a novel methodology of fine-tuning for large language models-dynamic LoRA. Building from the standard Low-Rank Adaptation framework, this methodology further adds dynamic adaptation mechanisms to improve efficiency and performance. The key contribution of dynamic LoRA lies within its adaptive weight allocation mechanism coupled with an input feature-based adaptive strategy. These enhancements allow for a more precise fine-tuning process that is more tailored to specific tasks. Traditional LoRA methods use static adapter settings, not considering the different importance of "},"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":"2501.14859","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-01-24T18:54:14Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"c52e42a9e6561e09c6bc2658660247fa7306f2936c103b4b0fa37118580e185a","abstract_canon_sha256":"f7ec779622304296425ddb6010b7eb1a0b0293281e874ab52d0164c1d197bb24"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:05:19.925863Z","signature_b64":"Ky7C2RTupnjArQ/vTVrJsv9g1GzaMYRry44n9fRQNXPSr3975b4WLFHhMLfDxkT9IMbX/CP17i4qEODte+0bCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e66818acd3ad9b49323eb141461f4815fcd851b5528df18799e1f97ec59b3f1a","last_reissued_at":"2026-07-05T10:05:19.925380Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:05:19.925380Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Dynamic Adaptation of LoRA Fine-Tuning for Efficient and Task-Specific Optimization of Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Chihang Wang, Hongye Zheng, Jiacheng Hu, Jia Gao, Shicheng Zhou, Xiaoxuan Liao","submitted_at":"2025-01-24T18:54:14Z","abstract_excerpt":"This paper presents a novel methodology of fine-tuning for large language models-dynamic LoRA. Building from the standard Low-Rank Adaptation framework, this methodology further adds dynamic adaptation mechanisms to improve efficiency and performance. The key contribution of dynamic LoRA lies within its adaptive weight allocation mechanism coupled with an input feature-based adaptive strategy. These enhancements allow for a more precise fine-tuning process that is more tailored to specific tasks. Traditional LoRA methods use static adapter settings, not considering the different importance of "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.14859","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/2501.14859/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":"2501.14859","created_at":"2026-07-05T10:05:19.925437+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.14859v1","created_at":"2026-07-05T10:05:19.925437+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.14859","created_at":"2026-07-05T10:05:19.925437+00:00"},{"alias_kind":"pith_short_12","alias_value":"4ZUBRLGTVWNU","created_at":"2026-07-05T10:05:19.925437+00:00"},{"alias_kind":"pith_short_16","alias_value":"4ZUBRLGTVWNUSMR6","created_at":"2026-07-05T10:05:19.925437+00:00"},{"alias_kind":"pith_short_8","alias_value":"4ZUBRLGT","created_at":"2026-07-05T10:05:19.925437+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4ZUBRLGTVWNUSMR6WFAUMH2ICX","json":"https://pith.science/pith/4ZUBRLGTVWNUSMR6WFAUMH2ICX.json","graph_json":"https://pith.science/api/pith-number/4ZUBRLGTVWNUSMR6WFAUMH2ICX/graph.json","events_json":"https://pith.science/api/pith-number/4ZUBRLGTVWNUSMR6WFAUMH2ICX/events.json","paper":"https://pith.science/paper/4ZUBRLGT"},"agent_actions":{"view_html":"https://pith.science/pith/4ZUBRLGTVWNUSMR6WFAUMH2ICX","download_json":"https://pith.science/pith/4ZUBRLGTVWNUSMR6WFAUMH2ICX.json","view_paper":"https://pith.science/paper/4ZUBRLGT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.14859&json=true","fetch_graph":"https://pith.science/api/pith-number/4ZUBRLGTVWNUSMR6WFAUMH2ICX/graph.json","fetch_events":"https://pith.science/api/pith-number/4ZUBRLGTVWNUSMR6WFAUMH2ICX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4ZUBRLGTVWNUSMR6WFAUMH2ICX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4ZUBRLGTVWNUSMR6WFAUMH2ICX/action/storage_attestation","attest_author":"https://pith.science/pith/4ZUBRLGTVWNUSMR6WFAUMH2ICX/action/author_attestation","sign_citation":"https://pith.science/pith/4ZUBRLGTVWNUSMR6WFAUMH2ICX/action/citation_signature","submit_replication":"https://pith.science/pith/4ZUBRLGTVWNUSMR6WFAUMH2ICX/action/replication_record"}},"created_at":"2026-07-05T10:05:19.925437+00:00","updated_at":"2026-07-05T10:05:19.925437+00:00"}