{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:4T7WIFDDOTEBYFEGYVCADJCU3S","short_pith_number":"pith:4T7WIFDD","schema_version":"1.0","canonical_sha256":"e4ff64146374c81c1486c54401a454dc9ccb90c254c560f04358e1dd08634484","source":{"kind":"arxiv","id":"2303.00690","version":1},"attestation_state":"computed","paper":{"title":"Rethinking Efficient Tuning Methods from a Unified Perspective","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chaojie Mao, Deli Zhao, Jingren Zhou, Yiliang Lv, Zeyinzi Jiang, Ziyuan Huang","submitted_at":"2023-03-01T17:38:03Z","abstract_excerpt":"Parameter-efficient transfer learning (PETL) based on large-scale pre-trained foundation models has achieved great success in various downstream applications. Existing tuning methods, such as prompt, prefix, and adapter, perform task-specific lightweight adjustments to different parts of the original architecture. However, they take effect on only some parts of the pre-trained models, i.e., only the feed-forward layers or the self-attention layers, which leaves the remaining frozen structures unable to adapt to the data distributions of downstream tasks. Further, the existing structures are st"},"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":"2303.00690","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-03-01T17:38:03Z","cross_cats_sorted":[],"title_canon_sha256":"4d4b6b4cf77a06707abaae76ea1581e5c2b31fb6400eb944667d93e04a480d4c","abstract_canon_sha256":"11aa516a5eb2dd63b8fd555d22ce84057c8d9f1f2fd268fff33fc4fa49007278"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:47:11.662981Z","signature_b64":"fZbtGgbpPj2UDYCALKrCD1Q8ksX4U1HVtmehCPQOn0y8Gbbr8K6APnyGgzCth0evsjvUltpzanN8T1A6x3gzBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e4ff64146374c81c1486c54401a454dc9ccb90c254c560f04358e1dd08634484","last_reissued_at":"2026-07-05T05:47:11.662488Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:47:11.662488Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Rethinking Efficient Tuning Methods from a Unified Perspective","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chaojie Mao, Deli Zhao, Jingren Zhou, Yiliang Lv, Zeyinzi Jiang, Ziyuan Huang","submitted_at":"2023-03-01T17:38:03Z","abstract_excerpt":"Parameter-efficient transfer learning (PETL) based on large-scale pre-trained foundation models has achieved great success in various downstream applications. Existing tuning methods, such as prompt, prefix, and adapter, perform task-specific lightweight adjustments to different parts of the original architecture. However, they take effect on only some parts of the pre-trained models, i.e., only the feed-forward layers or the self-attention layers, which leaves the remaining frozen structures unable to adapt to the data distributions of downstream tasks. Further, the existing structures are st"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.00690","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/2303.00690/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":"2303.00690","created_at":"2026-07-05T05:47:11.662556+00:00"},{"alias_kind":"arxiv_version","alias_value":"2303.00690v1","created_at":"2026-07-05T05:47:11.662556+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.00690","created_at":"2026-07-05T05:47:11.662556+00:00"},{"alias_kind":"pith_short_12","alias_value":"4T7WIFDDOTEB","created_at":"2026-07-05T05:47:11.662556+00:00"},{"alias_kind":"pith_short_16","alias_value":"4T7WIFDDOTEBYFEG","created_at":"2026-07-05T05:47:11.662556+00:00"},{"alias_kind":"pith_short_8","alias_value":"4T7WIFDD","created_at":"2026-07-05T05:47:11.662556+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/4T7WIFDDOTEBYFEGYVCADJCU3S","json":"https://pith.science/pith/4T7WIFDDOTEBYFEGYVCADJCU3S.json","graph_json":"https://pith.science/api/pith-number/4T7WIFDDOTEBYFEGYVCADJCU3S/graph.json","events_json":"https://pith.science/api/pith-number/4T7WIFDDOTEBYFEGYVCADJCU3S/events.json","paper":"https://pith.science/paper/4T7WIFDD"},"agent_actions":{"view_html":"https://pith.science/pith/4T7WIFDDOTEBYFEGYVCADJCU3S","download_json":"https://pith.science/pith/4T7WIFDDOTEBYFEGYVCADJCU3S.json","view_paper":"https://pith.science/paper/4T7WIFDD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2303.00690&json=true","fetch_graph":"https://pith.science/api/pith-number/4T7WIFDDOTEBYFEGYVCADJCU3S/graph.json","fetch_events":"https://pith.science/api/pith-number/4T7WIFDDOTEBYFEGYVCADJCU3S/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4T7WIFDDOTEBYFEGYVCADJCU3S/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4T7WIFDDOTEBYFEGYVCADJCU3S/action/storage_attestation","attest_author":"https://pith.science/pith/4T7WIFDDOTEBYFEGYVCADJCU3S/action/author_attestation","sign_citation":"https://pith.science/pith/4T7WIFDDOTEBYFEGYVCADJCU3S/action/citation_signature","submit_replication":"https://pith.science/pith/4T7WIFDDOTEBYFEGYVCADJCU3S/action/replication_record"}},"created_at":"2026-07-05T05:47:11.662556+00:00","updated_at":"2026-07-05T05:47:11.662556+00:00"}