{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:23WJ3ADH3OCGBT6HKNGBZMNO4Z","short_pith_number":"pith:23WJ3ADH","schema_version":"1.0","canonical_sha256":"d6ec9d8067db8460cfc7534c1cb1aee66d98d58a150a3462c98bc292b5e203b3","source":{"kind":"arxiv","id":"2404.04316","version":2},"attestation_state":"computed","paper":{"title":"Parameter Efficient Quasi-Orthogonal Fine-Tuning via Givens Rotation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.LG","authors_text":"Junfeng Zhao, Xin Gao, Xinyu Ma, Xu Chu, Yang Lin, Zhibang Yang","submitted_at":"2024-04-05T15:28:44Z","abstract_excerpt":"With the increasingly powerful performances and enormous scales of pretrained models, promoting parameter efficiency in fine-tuning has become a crucial need for effective and efficient adaptation to various downstream tasks. One representative line of fine-tuning methods is Orthogonal Fine-tuning (OFT), which rigorously preserves the angular distances within the parameter space to preserve the pretrained knowledge. Despite the empirical effectiveness, OFT still suffers low parameter efficiency at $\\mathcal{O}(d^2)$ and limited capability of downstream adaptation. Inspired by Givens rotation, "},"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":"2404.04316","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-04-05T15:28:44Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"c4c12b48c1c2ef82b378c19ff67b2e1c9afc1f5bff50af28da7699d8c9cf6e06","abstract_canon_sha256":"4195ffcff142b3c2f193f1b5be62d298c30f6d48fd58c50731df73da42e27128"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:28:39.891385Z","signature_b64":"8VV8EkTanzkR8kwINtBRDmSsxANy6dRiR8kpvCj2eUWHnNxhz04lFuTAQm6OfOAcEc5kqxou61Ft5ir339BVCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d6ec9d8067db8460cfc7534c1cb1aee66d98d58a150a3462c98bc292b5e203b3","last_reissued_at":"2026-07-05T08:28:39.890851Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:28:39.890851Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Parameter Efficient Quasi-Orthogonal Fine-Tuning via Givens Rotation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.LG","authors_text":"Junfeng Zhao, Xin Gao, Xinyu Ma, Xu Chu, Yang Lin, Zhibang Yang","submitted_at":"2024-04-05T15:28:44Z","abstract_excerpt":"With the increasingly powerful performances and enormous scales of pretrained models, promoting parameter efficiency in fine-tuning has become a crucial need for effective and efficient adaptation to various downstream tasks. One representative line of fine-tuning methods is Orthogonal Fine-tuning (OFT), which rigorously preserves the angular distances within the parameter space to preserve the pretrained knowledge. Despite the empirical effectiveness, OFT still suffers low parameter efficiency at $\\mathcal{O}(d^2)$ and limited capability of downstream adaptation. Inspired by Givens rotation, "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.04316","kind":"arxiv","version":2},"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/2404.04316/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":"2404.04316","created_at":"2026-07-05T08:28:39.890912+00:00"},{"alias_kind":"arxiv_version","alias_value":"2404.04316v2","created_at":"2026-07-05T08:28:39.890912+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.04316","created_at":"2026-07-05T08:28:39.890912+00:00"},{"alias_kind":"pith_short_12","alias_value":"23WJ3ADH3OCG","created_at":"2026-07-05T08:28:39.890912+00:00"},{"alias_kind":"pith_short_16","alias_value":"23WJ3ADH3OCGBT6H","created_at":"2026-07-05T08:28:39.890912+00:00"},{"alias_kind":"pith_short_8","alias_value":"23WJ3ADH","created_at":"2026-07-05T08:28:39.890912+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.22383","citing_title":"Structured Hyperedge Adaptation for Parameter-Efficient Fine-Tuning of Vision Transformers","ref_index":33,"is_internal_anchor":false},{"citing_arxiv_id":"2605.15916","citing_title":"LoCO: Low-rank Compositional Rotation Fine-tuning","ref_index":34,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/23WJ3ADH3OCGBT6HKNGBZMNO4Z","json":"https://pith.science/pith/23WJ3ADH3OCGBT6HKNGBZMNO4Z.json","graph_json":"https://pith.science/api/pith-number/23WJ3ADH3OCGBT6HKNGBZMNO4Z/graph.json","events_json":"https://pith.science/api/pith-number/23WJ3ADH3OCGBT6HKNGBZMNO4Z/events.json","paper":"https://pith.science/paper/23WJ3ADH"},"agent_actions":{"view_html":"https://pith.science/pith/23WJ3ADH3OCGBT6HKNGBZMNO4Z","download_json":"https://pith.science/pith/23WJ3ADH3OCGBT6HKNGBZMNO4Z.json","view_paper":"https://pith.science/paper/23WJ3ADH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2404.04316&json=true","fetch_graph":"https://pith.science/api/pith-number/23WJ3ADH3OCGBT6HKNGBZMNO4Z/graph.json","fetch_events":"https://pith.science/api/pith-number/23WJ3ADH3OCGBT6HKNGBZMNO4Z/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/23WJ3ADH3OCGBT6HKNGBZMNO4Z/action/timestamp_anchor","attest_storage":"https://pith.science/pith/23WJ3ADH3OCGBT6HKNGBZMNO4Z/action/storage_attestation","attest_author":"https://pith.science/pith/23WJ3ADH3OCGBT6HKNGBZMNO4Z/action/author_attestation","sign_citation":"https://pith.science/pith/23WJ3ADH3OCGBT6HKNGBZMNO4Z/action/citation_signature","submit_replication":"https://pith.science/pith/23WJ3ADH3OCGBT6HKNGBZMNO4Z/action/replication_record"}},"created_at":"2026-07-05T08:28:39.890912+00:00","updated_at":"2026-07-05T08:28:39.890912+00:00"}