{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:F4PRYRSO5JSWLMF4DPDKASYAZ4","short_pith_number":"pith:F4PRYRSO","schema_version":"1.0","canonical_sha256":"2f1f1c464eea6565b0bc1bc6a04b00cf38811231951b7a3b029928809abb572d","source":{"kind":"arxiv","id":"2505.00580","version":2},"attestation_state":"computed","paper":{"title":"Parameter-Efficient Fine-Tuning with Circulant and Diagonal Vectors","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Lexuan Chen, Siyu Liao, Xinyu Ding, Zhongfeng Wang","submitted_at":"2025-05-01T15:11:46Z","abstract_excerpt":"Foundation models have achieved tremendous success in different domains. However, their huge computation and storage complexity make these models difficult to fine-tune and also less applicable in practice. Recent study shows training in Fourier domain can be an effective fine-tuning method in terms of both model performance and number of training parameters. In this work, we propose to further reduce the complexity by the factorization through the product of interleaved circulant and diagonal matrices. In addition, we address the case of non-square fine-tuning weights by partitioning the circ"},"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":"2505.00580","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-05-01T15:11:46Z","cross_cats_sorted":[],"title_canon_sha256":"81898d2b26e2710ad63c1c3c4f5790dd4d69f3ac3fa3085ff500fc74f08de817","abstract_canon_sha256":"e08c63fffaf86cf757b901fd192dc6a86a6f3564c2e78cea6da6186b4570e243"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:37:19.116595Z","signature_b64":"Bvg1uIWXtXODPoxWpRiNvhNbsG6KRVHpohbFDok7THpUjg/84WDhzXM688jY9/CXsiAlCtzhdpP5YWRyF15YBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2f1f1c464eea6565b0bc1bc6a04b00cf38811231951b7a3b029928809abb572d","last_reissued_at":"2026-07-05T11:37:19.116081Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:37:19.116081Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Parameter-Efficient Fine-Tuning with Circulant and Diagonal Vectors","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Lexuan Chen, Siyu Liao, Xinyu Ding, Zhongfeng Wang","submitted_at":"2025-05-01T15:11:46Z","abstract_excerpt":"Foundation models have achieved tremendous success in different domains. However, their huge computation and storage complexity make these models difficult to fine-tune and also less applicable in practice. Recent study shows training in Fourier domain can be an effective fine-tuning method in terms of both model performance and number of training parameters. In this work, we propose to further reduce the complexity by the factorization through the product of interleaved circulant and diagonal matrices. In addition, we address the case of non-square fine-tuning weights by partitioning the circ"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.00580","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/2505.00580/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":"2505.00580","created_at":"2026-07-05T11:37:19.116139+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.00580v2","created_at":"2026-07-05T11:37:19.116139+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.00580","created_at":"2026-07-05T11:37:19.116139+00:00"},{"alias_kind":"pith_short_12","alias_value":"F4PRYRSO5JSW","created_at":"2026-07-05T11:37:19.116139+00:00"},{"alias_kind":"pith_short_16","alias_value":"F4PRYRSO5JSWLMF4","created_at":"2026-07-05T11:37:19.116139+00:00"},{"alias_kind":"pith_short_8","alias_value":"F4PRYRSO","created_at":"2026-07-05T11:37:19.116139+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/F4PRYRSO5JSWLMF4DPDKASYAZ4","json":"https://pith.science/pith/F4PRYRSO5JSWLMF4DPDKASYAZ4.json","graph_json":"https://pith.science/api/pith-number/F4PRYRSO5JSWLMF4DPDKASYAZ4/graph.json","events_json":"https://pith.science/api/pith-number/F4PRYRSO5JSWLMF4DPDKASYAZ4/events.json","paper":"https://pith.science/paper/F4PRYRSO"},"agent_actions":{"view_html":"https://pith.science/pith/F4PRYRSO5JSWLMF4DPDKASYAZ4","download_json":"https://pith.science/pith/F4PRYRSO5JSWLMF4DPDKASYAZ4.json","view_paper":"https://pith.science/paper/F4PRYRSO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.00580&json=true","fetch_graph":"https://pith.science/api/pith-number/F4PRYRSO5JSWLMF4DPDKASYAZ4/graph.json","fetch_events":"https://pith.science/api/pith-number/F4PRYRSO5JSWLMF4DPDKASYAZ4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/F4PRYRSO5JSWLMF4DPDKASYAZ4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/F4PRYRSO5JSWLMF4DPDKASYAZ4/action/storage_attestation","attest_author":"https://pith.science/pith/F4PRYRSO5JSWLMF4DPDKASYAZ4/action/author_attestation","sign_citation":"https://pith.science/pith/F4PRYRSO5JSWLMF4DPDKASYAZ4/action/citation_signature","submit_replication":"https://pith.science/pith/F4PRYRSO5JSWLMF4DPDKASYAZ4/action/replication_record"}},"created_at":"2026-07-05T11:37:19.116139+00:00","updated_at":"2026-07-05T11:37:19.116139+00:00"}