{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:CEOX6CQXFD423F45FBAA6CK62E","short_pith_number":"pith:CEOX6CQX","schema_version":"1.0","canonical_sha256":"111d7f0a1728f9ad979d28400f095ed1069f387850929fd1cb7bc308d8a93bac","source":{"kind":"arxiv","id":"2606.22383","version":1},"attestation_state":"computed","paper":{"title":"Structured Hyperedge Adaptation for Parameter-Efficient Fine-Tuning of Vision Transformers","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Edwin Kwadwo Tenagyei, Jun Zhou, Lei Wang, Ugochukwu Ejike Akpudo, Yongsheng Gao","submitted_at":"2026-06-21T08:09:08Z","abstract_excerpt":"Parameter-efficient fine-tuning (PEFT) has become a practical solution for adapting large pretrained vision transformers (ViTs) to downstream tasks while updating only a small subset of parameters. However, existing adapter-based methods perform adaptation independently for each token, implicitly assuming that token refinements should be learned in isolation. This token-wise formulation overlooks the structured relationships among tokens that naturally arise in visual scenes, potentially leading to redundant updates and spatially inconsistent feature refinement. In this work, we revisit the de"},"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":"2606.22383","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-06-21T08:09:08Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"c83b3ff75b844f6ccb8220c9cbe4bc7cf3678a7fa38f3ce5d59e87b1b5cae376","abstract_canon_sha256":"e686ecaef62c1f606d74b941b92f750f83e5e9b079df04a808f880c735518ab5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-23T02:13:36.979715Z","signature_b64":"Og6o1HSUPk2a9qJ+qXPsj9YFytyxTyWMocJ1hrL+sEqRkKELRzNISmjLRYqex6q3FBd4axXnj8UB4KxjrVOdBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"111d7f0a1728f9ad979d28400f095ed1069f387850929fd1cb7bc308d8a93bac","last_reissued_at":"2026-06-23T02:13:36.979247Z","signature_status":"signed_v1","first_computed_at":"2026-06-23T02:13:36.979247Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Structured Hyperedge Adaptation for Parameter-Efficient Fine-Tuning of Vision Transformers","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Edwin Kwadwo Tenagyei, Jun Zhou, Lei Wang, Ugochukwu Ejike Akpudo, Yongsheng Gao","submitted_at":"2026-06-21T08:09:08Z","abstract_excerpt":"Parameter-efficient fine-tuning (PEFT) has become a practical solution for adapting large pretrained vision transformers (ViTs) to downstream tasks while updating only a small subset of parameters. However, existing adapter-based methods perform adaptation independently for each token, implicitly assuming that token refinements should be learned in isolation. This token-wise formulation overlooks the structured relationships among tokens that naturally arise in visual scenes, potentially leading to redundant updates and spatially inconsistent feature refinement. In this work, we revisit the de"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.22383","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/2606.22383/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":"2606.22383","created_at":"2026-06-23T02:13:36.979307+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.22383v1","created_at":"2026-06-23T02:13:36.979307+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.22383","created_at":"2026-06-23T02:13:36.979307+00:00"},{"alias_kind":"pith_short_12","alias_value":"CEOX6CQXFD42","created_at":"2026-06-23T02:13:36.979307+00:00"},{"alias_kind":"pith_short_16","alias_value":"CEOX6CQXFD423F45","created_at":"2026-06-23T02:13:36.979307+00:00"},{"alias_kind":"pith_short_8","alias_value":"CEOX6CQX","created_at":"2026-06-23T02:13:36.979307+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/CEOX6CQXFD423F45FBAA6CK62E","json":"https://pith.science/pith/CEOX6CQXFD423F45FBAA6CK62E.json","graph_json":"https://pith.science/api/pith-number/CEOX6CQXFD423F45FBAA6CK62E/graph.json","events_json":"https://pith.science/api/pith-number/CEOX6CQXFD423F45FBAA6CK62E/events.json","paper":"https://pith.science/paper/CEOX6CQX"},"agent_actions":{"view_html":"https://pith.science/pith/CEOX6CQXFD423F45FBAA6CK62E","download_json":"https://pith.science/pith/CEOX6CQXFD423F45FBAA6CK62E.json","view_paper":"https://pith.science/paper/CEOX6CQX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.22383&json=true","fetch_graph":"https://pith.science/api/pith-number/CEOX6CQXFD423F45FBAA6CK62E/graph.json","fetch_events":"https://pith.science/api/pith-number/CEOX6CQXFD423F45FBAA6CK62E/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CEOX6CQXFD423F45FBAA6CK62E/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CEOX6CQXFD423F45FBAA6CK62E/action/storage_attestation","attest_author":"https://pith.science/pith/CEOX6CQXFD423F45FBAA6CK62E/action/author_attestation","sign_citation":"https://pith.science/pith/CEOX6CQXFD423F45FBAA6CK62E/action/citation_signature","submit_replication":"https://pith.science/pith/CEOX6CQXFD423F45FBAA6CK62E/action/replication_record"}},"created_at":"2026-06-23T02:13:36.979307+00:00","updated_at":"2026-06-23T02:13:36.979307+00:00"}