{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:WJDAQ5DT3KAV6UCLOTL7LOIL6E","short_pith_number":"pith:WJDAQ5DT","schema_version":"1.0","canonical_sha256":"b246087473da815f504b74d7f5b90bf13730d7d3a4df22d55cfc9b5a2dd4d5ea","source":{"kind":"arxiv","id":"2503.17650","version":1},"attestation_state":"computed","paper":{"title":"Visual Variational Autoencoder Prompt Tuning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jihun Hamm, Min Xu, Tianyang Wang, Xiao Wang, Xingjian Li, Xi Xiao, Yanshuh Li, Yunbei Zhang","submitted_at":"2025-03-22T04:59:51Z","abstract_excerpt":"Parameter-efficient fine-tuning (PEFT) has emerged as a crucial approach for adapting large vision transformers to downstream tasks without the prohibitive computational costs of full fine-tuning. While existing visual prompt tuning (VPT) methods have made significant strides, they predominantly rely on static, domain-specific prompts that fail to capture the rich visual diversity within individual instances. This paper introduces V$^2$APT (Visual Variational Autoencoder Prompt Tuning), a novel framework that generates dynamic, input-dependent prompts using a variational autoencoder architectu"},"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":"2503.17650","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-03-22T04:59:51Z","cross_cats_sorted":[],"title_canon_sha256":"41737126f5c3e7c5e1fa5cf7fb7cbced5a490fe75dc7048c3833058f16f779e6","abstract_canon_sha256":"bd2f571dffb6a7068c999d126569b4648eebf936deb36d47a1550870022e8eb4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:37:51.386419Z","signature_b64":"qUrJGqqIY8mQ7vBLikG6wttBO3E0ZB2kt+Ha2O5VSdVMjrxc7ZRpb5BnMwZyBzEDV2hAt5SCb84Ket3YAtlOAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b246087473da815f504b74d7f5b90bf13730d7d3a4df22d55cfc9b5a2dd4d5ea","last_reissued_at":"2026-07-05T10:37:51.385520Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:37:51.385520Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Visual Variational Autoencoder Prompt Tuning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jihun Hamm, Min Xu, Tianyang Wang, Xiao Wang, Xingjian Li, Xi Xiao, Yanshuh Li, Yunbei Zhang","submitted_at":"2025-03-22T04:59:51Z","abstract_excerpt":"Parameter-efficient fine-tuning (PEFT) has emerged as a crucial approach for adapting large vision transformers to downstream tasks without the prohibitive computational costs of full fine-tuning. While existing visual prompt tuning (VPT) methods have made significant strides, they predominantly rely on static, domain-specific prompts that fail to capture the rich visual diversity within individual instances. This paper introduces V$^2$APT (Visual Variational Autoencoder Prompt Tuning), a novel framework that generates dynamic, input-dependent prompts using a variational autoencoder architectu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.17650","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/2503.17650/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":"2503.17650","created_at":"2026-07-05T10:37:51.385598+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.17650v1","created_at":"2026-07-05T10:37:51.385598+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.17650","created_at":"2026-07-05T10:37:51.385598+00:00"},{"alias_kind":"pith_short_12","alias_value":"WJDAQ5DT3KAV","created_at":"2026-07-05T10:37:51.385598+00:00"},{"alias_kind":"pith_short_16","alias_value":"WJDAQ5DT3KAV6UCL","created_at":"2026-07-05T10:37:51.385598+00:00"},{"alias_kind":"pith_short_8","alias_value":"WJDAQ5DT","created_at":"2026-07-05T10:37:51.385598+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.26379","citing_title":"Layer-Specific Prompt Fusion Discovery via Differentiable Search in Vision Foundation Models","ref_index":54,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WJDAQ5DT3KAV6UCLOTL7LOIL6E","json":"https://pith.science/pith/WJDAQ5DT3KAV6UCLOTL7LOIL6E.json","graph_json":"https://pith.science/api/pith-number/WJDAQ5DT3KAV6UCLOTL7LOIL6E/graph.json","events_json":"https://pith.science/api/pith-number/WJDAQ5DT3KAV6UCLOTL7LOIL6E/events.json","paper":"https://pith.science/paper/WJDAQ5DT"},"agent_actions":{"view_html":"https://pith.science/pith/WJDAQ5DT3KAV6UCLOTL7LOIL6E","download_json":"https://pith.science/pith/WJDAQ5DT3KAV6UCLOTL7LOIL6E.json","view_paper":"https://pith.science/paper/WJDAQ5DT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.17650&json=true","fetch_graph":"https://pith.science/api/pith-number/WJDAQ5DT3KAV6UCLOTL7LOIL6E/graph.json","fetch_events":"https://pith.science/api/pith-number/WJDAQ5DT3KAV6UCLOTL7LOIL6E/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WJDAQ5DT3KAV6UCLOTL7LOIL6E/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WJDAQ5DT3KAV6UCLOTL7LOIL6E/action/storage_attestation","attest_author":"https://pith.science/pith/WJDAQ5DT3KAV6UCLOTL7LOIL6E/action/author_attestation","sign_citation":"https://pith.science/pith/WJDAQ5DT3KAV6UCLOTL7LOIL6E/action/citation_signature","submit_replication":"https://pith.science/pith/WJDAQ5DT3KAV6UCLOTL7LOIL6E/action/replication_record"}},"created_at":"2026-07-05T10:37:51.385598+00:00","updated_at":"2026-07-05T10:37:51.385598+00:00"}