{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:XPEMGAQ3NLIMVSNB6R3IR5BICW","short_pith_number":"pith:XPEMGAQ3","schema_version":"1.0","canonical_sha256":"bbc8c3021b6ad0cac9a1f47688f42815adee68d0123c270be3d07989dcd6413b","source":{"kind":"arxiv","id":"2501.08727","version":2},"attestation_state":"computed","paper":{"title":"Transformed Low-rank Adaptation via Tensor Decomposition and Its Applications to Text-to-image Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Naoki Murata, Qibin Zhao, Yuhta Takida, Yuki Mitsufuji, Zerui Tao","submitted_at":"2025-01-15T11:10:37Z","abstract_excerpt":"Parameter-Efficient Fine-Tuning (PEFT) of text-to-image models has become an increasingly popular technique with many applications. Among the various PEFT methods, Low-Rank Adaptation (LoRA) and its variants have gained significant attention due to their effectiveness, enabling users to fine-tune models with limited computational resources. However, the approximation gap between the low-rank assumption and desired fine-tuning weights prevents the simultaneous acquisition of ultra-parameter-efficiency and better performance. To reduce this gap and further improve the power of LoRA, we propose a"},"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":"2501.08727","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-01-15T11:10:37Z","cross_cats_sorted":[],"title_canon_sha256":"298e7a025c1ad0485ae9fe7c5c1df3ca01d816bda404b89a4287f7edd8d10bc3","abstract_canon_sha256":"0238b4f9939e1aa1a84396f44e7210d9221750a40118bb6d33e2671c696d4283"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:45:55.374164Z","signature_b64":"5iUspP5oVrJSZhJm5wd4dIqqXslfpTqFH9A86env4ZM9b2tK4Dx6ekz4s4VN9RuUeAZFlLnA1Qro8dFLbRNFAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bbc8c3021b6ad0cac9a1f47688f42815adee68d0123c270be3d07989dcd6413b","last_reissued_at":"2026-07-05T11:45:55.373474Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:45:55.373474Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Transformed Low-rank Adaptation via Tensor Decomposition and Its Applications to Text-to-image Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Naoki Murata, Qibin Zhao, Yuhta Takida, Yuki Mitsufuji, Zerui Tao","submitted_at":"2025-01-15T11:10:37Z","abstract_excerpt":"Parameter-Efficient Fine-Tuning (PEFT) of text-to-image models has become an increasingly popular technique with many applications. Among the various PEFT methods, Low-Rank Adaptation (LoRA) and its variants have gained significant attention due to their effectiveness, enabling users to fine-tune models with limited computational resources. However, the approximation gap between the low-rank assumption and desired fine-tuning weights prevents the simultaneous acquisition of ultra-parameter-efficiency and better performance. To reduce this gap and further improve the power of LoRA, we propose a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.08727","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/2501.08727/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":"2501.08727","created_at":"2026-07-05T11:45:55.373555+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.08727v2","created_at":"2026-07-05T11:45:55.373555+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.08727","created_at":"2026-07-05T11:45:55.373555+00:00"},{"alias_kind":"pith_short_12","alias_value":"XPEMGAQ3NLIM","created_at":"2026-07-05T11:45:55.373555+00:00"},{"alias_kind":"pith_short_16","alias_value":"XPEMGAQ3NLIMVSNB","created_at":"2026-07-05T11:45:55.373555+00:00"},{"alias_kind":"pith_short_8","alias_value":"XPEMGAQ3","created_at":"2026-07-05T11:45:55.373555+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/XPEMGAQ3NLIMVSNB6R3IR5BICW","json":"https://pith.science/pith/XPEMGAQ3NLIMVSNB6R3IR5BICW.json","graph_json":"https://pith.science/api/pith-number/XPEMGAQ3NLIMVSNB6R3IR5BICW/graph.json","events_json":"https://pith.science/api/pith-number/XPEMGAQ3NLIMVSNB6R3IR5BICW/events.json","paper":"https://pith.science/paper/XPEMGAQ3"},"agent_actions":{"view_html":"https://pith.science/pith/XPEMGAQ3NLIMVSNB6R3IR5BICW","download_json":"https://pith.science/pith/XPEMGAQ3NLIMVSNB6R3IR5BICW.json","view_paper":"https://pith.science/paper/XPEMGAQ3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.08727&json=true","fetch_graph":"https://pith.science/api/pith-number/XPEMGAQ3NLIMVSNB6R3IR5BICW/graph.json","fetch_events":"https://pith.science/api/pith-number/XPEMGAQ3NLIMVSNB6R3IR5BICW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XPEMGAQ3NLIMVSNB6R3IR5BICW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XPEMGAQ3NLIMVSNB6R3IR5BICW/action/storage_attestation","attest_author":"https://pith.science/pith/XPEMGAQ3NLIMVSNB6R3IR5BICW/action/author_attestation","sign_citation":"https://pith.science/pith/XPEMGAQ3NLIMVSNB6R3IR5BICW/action/citation_signature","submit_replication":"https://pith.science/pith/XPEMGAQ3NLIMVSNB6R3IR5BICW/action/replication_record"}},"created_at":"2026-07-05T11:45:55.373555+00:00","updated_at":"2026-07-05T11:45:55.373555+00:00"}