{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:WIHBHPZGKTOASNC4TOM3OT3SC5","short_pith_number":"pith:WIHBHPZG","canonical_record":{"source":{"id":"2505.23694","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-29T17:31:26Z","cross_cats_sorted":[],"title_canon_sha256":"b532906d7355c78f3352cfd274caa5c41ccbcf78e4be948aeb4b1fc1a36f6886","abstract_canon_sha256":"73ee45bc89e3fb4bd0248717a796cc11150a7cd0a7c6ad4209004005767c286f"},"schema_version":"1.0"},"canonical_sha256":"b20e13bf2654dc09345c9b99b74f72175a81fe780989a7075337d32b647ad62a","source":{"kind":"arxiv","id":"2505.23694","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.23694","created_at":"2026-07-05T11:13:27Z"},{"alias_kind":"arxiv_version","alias_value":"2505.23694v2","created_at":"2026-07-05T11:13:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.23694","created_at":"2026-07-05T11:13:27Z"},{"alias_kind":"pith_short_12","alias_value":"WIHBHPZGKTOA","created_at":"2026-07-05T11:13:27Z"},{"alias_kind":"pith_short_16","alias_value":"WIHBHPZGKTOASNC4","created_at":"2026-07-05T11:13:27Z"},{"alias_kind":"pith_short_8","alias_value":"WIHBHPZG","created_at":"2026-07-05T11:13:27Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:WIHBHPZGKTOASNC4TOM3OT3SC5","target":"record","payload":{"canonical_record":{"source":{"id":"2505.23694","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-29T17:31:26Z","cross_cats_sorted":[],"title_canon_sha256":"b532906d7355c78f3352cfd274caa5c41ccbcf78e4be948aeb4b1fc1a36f6886","abstract_canon_sha256":"73ee45bc89e3fb4bd0248717a796cc11150a7cd0a7c6ad4209004005767c286f"},"schema_version":"1.0"},"canonical_sha256":"b20e13bf2654dc09345c9b99b74f72175a81fe780989a7075337d32b647ad62a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:13:27.873057Z","signature_b64":"lG1fPZBdsdv49As9XLQkwIbHAoeZb3j2QlHceo0IwITHqQHAQa+q7iQK+7Pa8oeucm9p2kql3PNidCDxlSINBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b20e13bf2654dc09345c9b99b74f72175a81fe780989a7075337d32b647ad62a","last_reissued_at":"2026-07-05T11:13:27.872591Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:13:27.872591Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2505.23694","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:13:27Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MGKQq5cN/JIM/alNou4f+lx678gyh7hh5nc6SRXwwO4V3+dyZhY/16tdDOJ3CH3hhBLM7Xy+5W6DtQ13RTM7CA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T00:35:32.340053Z"},"content_sha256":"4a86a870c76e31494ce1afeac956d0fa7f83c895a81527772c2fbd9892c6e2eb","schema_version":"1.0","event_id":"sha256:4a86a870c76e31494ce1afeac956d0fa7f83c895a81527772c2fbd9892c6e2eb"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:WIHBHPZGKTOASNC4TOM3OT3SC5","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"DA-VPT: Semantic-Guided Visual Prompt Tuning for Vision Transformers","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chen Chen, Kien Hua, Liqiang Wang, Li Ren","submitted_at":"2025-05-29T17:31:26Z","abstract_excerpt":"Visual Prompt Tuning (VPT) has become a promising solution for Parameter-Efficient Fine-Tuning (PEFT) approach for Vision Transformer (ViT) models by partially fine-tuning learnable tokens while keeping most model parameters frozen. Recent research has explored modifying the connection structures of the prompts. However, the fundamental correlation and distribution between the prompts and image tokens remain unexplored. In this paper, we leverage metric learning techniques to investigate how the distribution of prompts affects fine-tuning performance. Specifically, we propose a novel framework"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.23694","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/2505.23694/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:13:27Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Uc7UYcgJdaIcHgsRx4jKn/6x07jt3PNIgSJl+RN/PAODtbEeGIRgp3oLR1R3Cs8i9tOlEXa3yTjXt3MO6JMbAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T00:35:32.340415Z"},"content_sha256":"ec4473cd9f3b2dfe09a178b6bf652076fbd1abcc397ecb0d4bdf688af7c03c22","schema_version":"1.0","event_id":"sha256:ec4473cd9f3b2dfe09a178b6bf652076fbd1abcc397ecb0d4bdf688af7c03c22"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/WIHBHPZGKTOASNC4TOM3OT3SC5/bundle.json","state_url":"https://pith.science/pith/WIHBHPZGKTOASNC4TOM3OT3SC5/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/WIHBHPZGKTOASNC4TOM3OT3SC5/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-08T00:35:32Z","links":{"resolver":"https://pith.science/pith/WIHBHPZGKTOASNC4TOM3OT3SC5","bundle":"https://pith.science/pith/WIHBHPZGKTOASNC4TOM3OT3SC5/bundle.json","state":"https://pith.science/pith/WIHBHPZGKTOASNC4TOM3OT3SC5/state.json","well_known_bundle":"https://pith.science/.well-known/pith/WIHBHPZGKTOASNC4TOM3OT3SC5/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:WIHBHPZGKTOASNC4TOM3OT3SC5","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"73ee45bc89e3fb4bd0248717a796cc11150a7cd0a7c6ad4209004005767c286f","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-29T17:31:26Z","title_canon_sha256":"b532906d7355c78f3352cfd274caa5c41ccbcf78e4be948aeb4b1fc1a36f6886"},"schema_version":"1.0","source":{"id":"2505.23694","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.23694","created_at":"2026-07-05T11:13:27Z"},{"alias_kind":"arxiv_version","alias_value":"2505.23694v2","created_at":"2026-07-05T11:13:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.23694","created_at":"2026-07-05T11:13:27Z"},{"alias_kind":"pith_short_12","alias_value":"WIHBHPZGKTOA","created_at":"2026-07-05T11:13:27Z"},{"alias_kind":"pith_short_16","alias_value":"WIHBHPZGKTOASNC4","created_at":"2026-07-05T11:13:27Z"},{"alias_kind":"pith_short_8","alias_value":"WIHBHPZG","created_at":"2026-07-05T11:13:27Z"}],"graph_snapshots":[{"event_id":"sha256:ec4473cd9f3b2dfe09a178b6bf652076fbd1abcc397ecb0d4bdf688af7c03c22","target":"graph","created_at":"2026-07-05T11:13:27Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2505.23694/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Visual Prompt Tuning (VPT) has become a promising solution for Parameter-Efficient Fine-Tuning (PEFT) approach for Vision Transformer (ViT) models by partially fine-tuning learnable tokens while keeping most model parameters frozen. Recent research has explored modifying the connection structures of the prompts. However, the fundamental correlation and distribution between the prompts and image tokens remain unexplored. In this paper, we leverage metric learning techniques to investigate how the distribution of prompts affects fine-tuning performance. Specifically, we propose a novel framework","authors_text":"Chen Chen, Kien Hua, Liqiang Wang, Li Ren","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-29T17:31:26Z","title":"DA-VPT: Semantic-Guided Visual Prompt Tuning for Vision Transformers"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.23694","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:4a86a870c76e31494ce1afeac956d0fa7f83c895a81527772c2fbd9892c6e2eb","target":"record","created_at":"2026-07-05T11:13:27Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"73ee45bc89e3fb4bd0248717a796cc11150a7cd0a7c6ad4209004005767c286f","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-29T17:31:26Z","title_canon_sha256":"b532906d7355c78f3352cfd274caa5c41ccbcf78e4be948aeb4b1fc1a36f6886"},"schema_version":"1.0","source":{"id":"2505.23694","kind":"arxiv","version":2}},"canonical_sha256":"b20e13bf2654dc09345c9b99b74f72175a81fe780989a7075337d32b647ad62a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b20e13bf2654dc09345c9b99b74f72175a81fe780989a7075337d32b647ad62a","first_computed_at":"2026-07-05T11:13:27.872591Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:13:27.872591Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"lG1fPZBdsdv49As9XLQkwIbHAoeZb3j2QlHceo0IwITHqQHAQa+q7iQK+7Pa8oeucm9p2kql3PNidCDxlSINBw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:13:27.873057Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.23694","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4a86a870c76e31494ce1afeac956d0fa7f83c895a81527772c2fbd9892c6e2eb","sha256:ec4473cd9f3b2dfe09a178b6bf652076fbd1abcc397ecb0d4bdf688af7c03c22"],"state_sha256":"eb916f49d386dbe7d899cfc37167ff25e87377fc371bf9620862dc4ef17d7ff7"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Tqfo3e3g/E6++UGd4hpMB2J9waVm/eAI3uJMvziJkp5DacR/DVL7iPBXhbATi13DGbTR7tRstyGnwsxcL6gzCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T00:35:32.343127Z","bundle_sha256":"0ed7d8305a57e3c0a14379525450b10f9927583977ce53008e05f1e0ae6b3a37"}}