{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:TS7BKHO66ZGGN7WWHY2AOTDEXE","short_pith_number":"pith:TS7BKHO6","schema_version":"1.0","canonical_sha256":"9cbe151ddef64c66fed63e34074c64b910e783dc8017e59d12ebea377a214067","source":{"kind":"arxiv","id":"2410.19694","version":1},"attestation_state":"computed","paper":{"title":"Less is More: Extreme Gradient Boost Rank-1 Adaption for Efficient Finetuning of LLMs","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Aiwei Liu, Han Yu, Hao Zhu, Irwin King, Piotr Koniusz, Yifei Zhang","submitted_at":"2024-10-25T17:07:13Z","abstract_excerpt":"Fine-tuning Large Language Models (LLMs) has become a crucial technique for adapting pre-trained models to downstream tasks. However, the enormous size of LLMs poses significant challenges in terms of computational complexity and resource requirements. Low-Rank Adaptation (LoRA) has emerged as a promising solution. However, there exists a gap between the practical performance of low-rank adaptations and its theoretical optimum. In this work, we propose eXtreme Gradient Boosting LoRA (XGBLoRA), a novel framework that bridges this gap by leveraging the power of ensemble learning. Inspired by gra"},"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":"2410.19694","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-25T17:07:13Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"fdbdc58a03f450f04a17389d4001ae93e649d4ed87b6f96e39b2398b069e5bbe","abstract_canon_sha256":"3cca692fe3fcf06647cbf5f73fe51da5fad9b47d8a79ddeeaac58636dec25b24"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:26:00.300921Z","signature_b64":"b8IVcAaHRu5qkQsmkHWLXPx9saLsM+TNUTzOkIpSJOAIumBeadtvQS5ik+gtJArFU0eLTVN6D+nHBufnp8FhBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9cbe151ddef64c66fed63e34074c64b910e783dc8017e59d12ebea377a214067","last_reissued_at":"2026-07-05T09:26:00.300449Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:26:00.300449Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Less is More: Extreme Gradient Boost Rank-1 Adaption for Efficient Finetuning of LLMs","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Aiwei Liu, Han Yu, Hao Zhu, Irwin King, Piotr Koniusz, Yifei Zhang","submitted_at":"2024-10-25T17:07:13Z","abstract_excerpt":"Fine-tuning Large Language Models (LLMs) has become a crucial technique for adapting pre-trained models to downstream tasks. However, the enormous size of LLMs poses significant challenges in terms of computational complexity and resource requirements. Low-Rank Adaptation (LoRA) has emerged as a promising solution. However, there exists a gap between the practical performance of low-rank adaptations and its theoretical optimum. In this work, we propose eXtreme Gradient Boosting LoRA (XGBLoRA), a novel framework that bridges this gap by leveraging the power of ensemble learning. Inspired by gra"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.19694","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/2410.19694/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":"2410.19694","created_at":"2026-07-05T09:26:00.300506+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.19694v1","created_at":"2026-07-05T09:26:00.300506+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.19694","created_at":"2026-07-05T09:26:00.300506+00:00"},{"alias_kind":"pith_short_12","alias_value":"TS7BKHO66ZGG","created_at":"2026-07-05T09:26:00.300506+00:00"},{"alias_kind":"pith_short_16","alias_value":"TS7BKHO66ZGGN7WW","created_at":"2026-07-05T09:26:00.300506+00:00"},{"alias_kind":"pith_short_8","alias_value":"TS7BKHO6","created_at":"2026-07-05T09:26:00.300506+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.21901","citing_title":"GiVA: Gradient-Informed Bases for Vector-Based Adaptation","ref_index":55,"is_internal_anchor":false},{"citing_arxiv_id":"2604.18867","citing_title":"Hierarchically Robust Zero-shot Vision-language Models","ref_index":51,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TS7BKHO66ZGGN7WWHY2AOTDEXE","json":"https://pith.science/pith/TS7BKHO66ZGGN7WWHY2AOTDEXE.json","graph_json":"https://pith.science/api/pith-number/TS7BKHO66ZGGN7WWHY2AOTDEXE/graph.json","events_json":"https://pith.science/api/pith-number/TS7BKHO66ZGGN7WWHY2AOTDEXE/events.json","paper":"https://pith.science/paper/TS7BKHO6"},"agent_actions":{"view_html":"https://pith.science/pith/TS7BKHO66ZGGN7WWHY2AOTDEXE","download_json":"https://pith.science/pith/TS7BKHO66ZGGN7WWHY2AOTDEXE.json","view_paper":"https://pith.science/paper/TS7BKHO6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.19694&json=true","fetch_graph":"https://pith.science/api/pith-number/TS7BKHO66ZGGN7WWHY2AOTDEXE/graph.json","fetch_events":"https://pith.science/api/pith-number/TS7BKHO66ZGGN7WWHY2AOTDEXE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TS7BKHO66ZGGN7WWHY2AOTDEXE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TS7BKHO66ZGGN7WWHY2AOTDEXE/action/storage_attestation","attest_author":"https://pith.science/pith/TS7BKHO66ZGGN7WWHY2AOTDEXE/action/author_attestation","sign_citation":"https://pith.science/pith/TS7BKHO66ZGGN7WWHY2AOTDEXE/action/citation_signature","submit_replication":"https://pith.science/pith/TS7BKHO66ZGGN7WWHY2AOTDEXE/action/replication_record"}},"created_at":"2026-07-05T09:26:00.300506+00:00","updated_at":"2026-07-05T09:26:00.300506+00:00"}