{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:YCYD7KAKMIAA3DVYV33VC6GHVE","short_pith_number":"pith:YCYD7KAK","schema_version":"1.0","canonical_sha256":"c0b03fa80a62000d8eb8aef75178c7a911b6c0756c8e98fd50e5ec5fbf68f8eb","source":{"kind":"arxiv","id":"2507.07796","version":1},"attestation_state":"computed","paper":{"title":"Visual Instance-aware Prompt Tuning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Jihun Hamm, Min Xu, Tianyang Wang, Xiao Wang, Xingjian Li, Xi Xiao, Yunbei Zhang, Yuxiang Wei","submitted_at":"2025-07-10T14:23:15Z","abstract_excerpt":"Visual Prompt Tuning (VPT) has emerged as a parameter-efficient fine-tuning paradigm for vision transformers, with conventional approaches utilizing dataset-level prompts that remain the same across all input instances. We observe that this strategy results in sub-optimal performance due to high variance in downstream datasets. To address this challenge, we propose Visual Instance-aware Prompt Tuning (ViaPT), which generates instance-aware prompts based on each individual input and fuses them with dataset-level prompts, leveraging Principal Component Analysis (PCA) to retain important promptin"},"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":"2507.07796","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-07-10T14:23:15Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"7e11b1cfd4c7a9aea474653167b817f092abca12803397f49f7036d9d19727e7","abstract_canon_sha256":"837bdad4d9e68c1937905cf5397de623d3256a0fc8020b2c9e4a7e96d8e789ce"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:35:05.301662Z","signature_b64":"M4vYplGA+LrP9eD+4pbw5LrCiglIwXwULr9ytkwa99Jnt93Uz1RHQ3TUDiNjcki2dNXMPH8qsWcJTX7kVwhvAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c0b03fa80a62000d8eb8aef75178c7a911b6c0756c8e98fd50e5ec5fbf68f8eb","last_reissued_at":"2026-07-05T11:35:05.300656Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:35:05.300656Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Visual Instance-aware Prompt Tuning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Jihun Hamm, Min Xu, Tianyang Wang, Xiao Wang, Xingjian Li, Xi Xiao, Yunbei Zhang, Yuxiang Wei","submitted_at":"2025-07-10T14:23:15Z","abstract_excerpt":"Visual Prompt Tuning (VPT) has emerged as a parameter-efficient fine-tuning paradigm for vision transformers, with conventional approaches utilizing dataset-level prompts that remain the same across all input instances. We observe that this strategy results in sub-optimal performance due to high variance in downstream datasets. To address this challenge, we propose Visual Instance-aware Prompt Tuning (ViaPT), which generates instance-aware prompts based on each individual input and fuses them with dataset-level prompts, leveraging Principal Component Analysis (PCA) to retain important promptin"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.07796","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/2507.07796/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":"2507.07796","created_at":"2026-07-05T11:35:05.300717+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.07796v1","created_at":"2026-07-05T11:35:05.300717+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.07796","created_at":"2026-07-05T11:35:05.300717+00:00"},{"alias_kind":"pith_short_12","alias_value":"YCYD7KAKMIAA","created_at":"2026-07-05T11:35:05.300717+00:00"},{"alias_kind":"pith_short_16","alias_value":"YCYD7KAKMIAA3DVY","created_at":"2026-07-05T11:35:05.300717+00:00"},{"alias_kind":"pith_short_8","alias_value":"YCYD7KAK","created_at":"2026-07-05T11:35:05.300717+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2511.21760","citing_title":"fMRI-LM: Towards a Universal Foundation Model for Language-Aligned fMRI Understanding","ref_index":37,"is_internal_anchor":false},{"citing_arxiv_id":"2605.08181","citing_title":"Text-Guided Multi-Scale Frequency Representation Adaptation","ref_index":47,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YCYD7KAKMIAA3DVYV33VC6GHVE","json":"https://pith.science/pith/YCYD7KAKMIAA3DVYV33VC6GHVE.json","graph_json":"https://pith.science/api/pith-number/YCYD7KAKMIAA3DVYV33VC6GHVE/graph.json","events_json":"https://pith.science/api/pith-number/YCYD7KAKMIAA3DVYV33VC6GHVE/events.json","paper":"https://pith.science/paper/YCYD7KAK"},"agent_actions":{"view_html":"https://pith.science/pith/YCYD7KAKMIAA3DVYV33VC6GHVE","download_json":"https://pith.science/pith/YCYD7KAKMIAA3DVYV33VC6GHVE.json","view_paper":"https://pith.science/paper/YCYD7KAK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.07796&json=true","fetch_graph":"https://pith.science/api/pith-number/YCYD7KAKMIAA3DVYV33VC6GHVE/graph.json","fetch_events":"https://pith.science/api/pith-number/YCYD7KAKMIAA3DVYV33VC6GHVE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YCYD7KAKMIAA3DVYV33VC6GHVE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YCYD7KAKMIAA3DVYV33VC6GHVE/action/storage_attestation","attest_author":"https://pith.science/pith/YCYD7KAKMIAA3DVYV33VC6GHVE/action/author_attestation","sign_citation":"https://pith.science/pith/YCYD7KAKMIAA3DVYV33VC6GHVE/action/citation_signature","submit_replication":"https://pith.science/pith/YCYD7KAKMIAA3DVYV33VC6GHVE/action/replication_record"}},"created_at":"2026-07-05T11:35:05.300717+00:00","updated_at":"2026-07-05T11:35:05.300717+00:00"}