{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:MA4EOZV7MXDW47YGJKJXPVLNCW","short_pith_number":"pith:MA4EOZV7","schema_version":"1.0","canonical_sha256":"60384766bf65c76e7f064a9377d56d1581f295bf0b30cefb171d08859050ccb9","source":{"kind":"arxiv","id":"2410.22952","version":1},"attestation_state":"computed","paper":{"title":"Efficient Adaptation of Pre-trained Vision Transformer via Householder Transformation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Haokui Zhang, Hengtao Shen, Peng Wang, Qingsen Yan, Wei Dong, Xing Zhang, Yang Yang, Yiting Yang, Yuan Sun, Zhijun Lin","submitted_at":"2024-10-30T12:08:30Z","abstract_excerpt":"A common strategy for Parameter-Efficient Fine-Tuning (PEFT) of pre-trained Vision Transformers (ViTs) involves adapting the model to downstream tasks by learning a low-rank adaptation matrix. This matrix is decomposed into a product of down-projection and up-projection matrices, with the bottleneck dimensionality being crucial for reducing the number of learnable parameters, as exemplified by prevalent methods like LoRA and Adapter. However, these low-rank strategies typically employ a fixed bottleneck dimensionality, which limits their flexibility in handling layer-wise variations. To addres"},"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":"2410.22952","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-10-30T12:08:30Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"2662faf6a1575fbef5ed3ec8b2d71831f411c6fbca39b1528069b7884252f0f8","abstract_canon_sha256":"f10a49ccf30f9695afb029775bb82f38b98197333f6c73d8751a26eee90648bc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:28:38.888522Z","signature_b64":"0H7ubkjmiCF0HSpnBWyyxmYCai8uNn9Zda0dhoXQQgusiLTGReSIkvh4G3BWpOI1aToyKTiZbQqYotF10HThCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"60384766bf65c76e7f064a9377d56d1581f295bf0b30cefb171d08859050ccb9","last_reissued_at":"2026-07-05T09:28:38.888095Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:28:38.888095Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Efficient Adaptation of Pre-trained Vision Transformer via Householder Transformation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Haokui Zhang, Hengtao Shen, Peng Wang, Qingsen Yan, Wei Dong, Xing Zhang, Yang Yang, Yiting Yang, Yuan Sun, Zhijun Lin","submitted_at":"2024-10-30T12:08:30Z","abstract_excerpt":"A common strategy for Parameter-Efficient Fine-Tuning (PEFT) of pre-trained Vision Transformers (ViTs) involves adapting the model to downstream tasks by learning a low-rank adaptation matrix. This matrix is decomposed into a product of down-projection and up-projection matrices, with the bottleneck dimensionality being crucial for reducing the number of learnable parameters, as exemplified by prevalent methods like LoRA and Adapter. However, these low-rank strategies typically employ a fixed bottleneck dimensionality, which limits their flexibility in handling layer-wise variations. To addres"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.22952","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/2410.22952/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":"2410.22952","created_at":"2026-07-05T09:28:38.888155+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.22952v1","created_at":"2026-07-05T09:28:38.888155+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.22952","created_at":"2026-07-05T09:28:38.888155+00:00"},{"alias_kind":"pith_short_12","alias_value":"MA4EOZV7MXDW","created_at":"2026-07-05T09:28:38.888155+00:00"},{"alias_kind":"pith_short_16","alias_value":"MA4EOZV7MXDW47YG","created_at":"2026-07-05T09:28:38.888155+00:00"},{"alias_kind":"pith_short_8","alias_value":"MA4EOZV7","created_at":"2026-07-05T09:28:38.888155+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.20745","citing_title":"Regularizing Subspace Redundancy of Low-Rank Adaptation","ref_index":17,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MA4EOZV7MXDW47YGJKJXPVLNCW","json":"https://pith.science/pith/MA4EOZV7MXDW47YGJKJXPVLNCW.json","graph_json":"https://pith.science/api/pith-number/MA4EOZV7MXDW47YGJKJXPVLNCW/graph.json","events_json":"https://pith.science/api/pith-number/MA4EOZV7MXDW47YGJKJXPVLNCW/events.json","paper":"https://pith.science/paper/MA4EOZV7"},"agent_actions":{"view_html":"https://pith.science/pith/MA4EOZV7MXDW47YGJKJXPVLNCW","download_json":"https://pith.science/pith/MA4EOZV7MXDW47YGJKJXPVLNCW.json","view_paper":"https://pith.science/paper/MA4EOZV7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.22952&json=true","fetch_graph":"https://pith.science/api/pith-number/MA4EOZV7MXDW47YGJKJXPVLNCW/graph.json","fetch_events":"https://pith.science/api/pith-number/MA4EOZV7MXDW47YGJKJXPVLNCW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MA4EOZV7MXDW47YGJKJXPVLNCW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MA4EOZV7MXDW47YGJKJXPVLNCW/action/storage_attestation","attest_author":"https://pith.science/pith/MA4EOZV7MXDW47YGJKJXPVLNCW/action/author_attestation","sign_citation":"https://pith.science/pith/MA4EOZV7MXDW47YGJKJXPVLNCW/action/citation_signature","submit_replication":"https://pith.science/pith/MA4EOZV7MXDW47YGJKJXPVLNCW/action/replication_record"}},"created_at":"2026-07-05T09:28:38.888155+00:00","updated_at":"2026-07-05T09:28:38.888155+00:00"}