{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:ZUAVDSD43KJW3VM34GJ7C6BPFY","short_pith_number":"pith:ZUAVDSD4","schema_version":"1.0","canonical_sha256":"cd0151c87cda936dd59be193f1782f2e2df2ea05c2f3246cb49ca0574eec24a7","source":{"kind":"arxiv","id":"2408.10527","version":1},"attestation_state":"computed","paper":{"title":"EdgeNAT: Transformer for Efficient Edge Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Baojian Hua, Guixing Wu, Jinghuai Jie, Junmin Wu, Yan Guo","submitted_at":"2024-08-20T04:04:22Z","abstract_excerpt":"Transformers, renowned for their powerful feature extraction capabilities, have played an increasingly prominent role in various vision tasks. Especially, recent advancements present transformer with hierarchical structures such as Dilated Neighborhood Attention Transformer (DiNAT), demonstrating outstanding ability to efficiently capture both global and local features. However, transformers' application in edge detection has not been fully exploited. In this paper, we propose EdgeNAT, a one-stage transformer-based edge detector with DiNAT as the encoder, capable of extracting object boundarie"},"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":"2408.10527","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-08-20T04:04:22Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"f58dc9bc6433322c851715c2a2a73c5613b3cb671e0903c4e38fe61284243cd8","abstract_canon_sha256":"62de9f0986c3763bf5c15c6ef162f07f952b1dda553be0ddf25ba0fce6c847f1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:57:13.418411Z","signature_b64":"Nh+DXCupirGgIWyOZZggfG+/hjDMKxVzSQMOUlHZYhNBcmWIkgafR1wkw7w6FvOgbJpinVXrpVEfGqiFW3obBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cd0151c87cda936dd59be193f1782f2e2df2ea05c2f3246cb49ca0574eec24a7","last_reissued_at":"2026-07-05T08:57:13.417952Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:57:13.417952Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"EdgeNAT: Transformer for Efficient Edge Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Baojian Hua, Guixing Wu, Jinghuai Jie, Junmin Wu, Yan Guo","submitted_at":"2024-08-20T04:04:22Z","abstract_excerpt":"Transformers, renowned for their powerful feature extraction capabilities, have played an increasingly prominent role in various vision tasks. Especially, recent advancements present transformer with hierarchical structures such as Dilated Neighborhood Attention Transformer (DiNAT), demonstrating outstanding ability to efficiently capture both global and local features. However, transformers' application in edge detection has not been fully exploited. In this paper, we propose EdgeNAT, a one-stage transformer-based edge detector with DiNAT as the encoder, capable of extracting object boundarie"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.10527","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/2408.10527/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":"2408.10527","created_at":"2026-07-05T08:57:13.418007+00:00"},{"alias_kind":"arxiv_version","alias_value":"2408.10527v1","created_at":"2026-07-05T08:57:13.418007+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.10527","created_at":"2026-07-05T08:57:13.418007+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZUAVDSD43KJW","created_at":"2026-07-05T08:57:13.418007+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZUAVDSD43KJW3VM3","created_at":"2026-07-05T08:57:13.418007+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZUAVDSD4","created_at":"2026-07-05T08:57:13.418007+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.06569","citing_title":"Edge-Boundary-Texture Loss: A Tri-Class Generalization of Weighted Binary Cross-Entropy for Enhanced Edge Detection","ref_index":30,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZUAVDSD43KJW3VM34GJ7C6BPFY","json":"https://pith.science/pith/ZUAVDSD43KJW3VM34GJ7C6BPFY.json","graph_json":"https://pith.science/api/pith-number/ZUAVDSD43KJW3VM34GJ7C6BPFY/graph.json","events_json":"https://pith.science/api/pith-number/ZUAVDSD43KJW3VM34GJ7C6BPFY/events.json","paper":"https://pith.science/paper/ZUAVDSD4"},"agent_actions":{"view_html":"https://pith.science/pith/ZUAVDSD43KJW3VM34GJ7C6BPFY","download_json":"https://pith.science/pith/ZUAVDSD43KJW3VM34GJ7C6BPFY.json","view_paper":"https://pith.science/paper/ZUAVDSD4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2408.10527&json=true","fetch_graph":"https://pith.science/api/pith-number/ZUAVDSD43KJW3VM34GJ7C6BPFY/graph.json","fetch_events":"https://pith.science/api/pith-number/ZUAVDSD43KJW3VM34GJ7C6BPFY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZUAVDSD43KJW3VM34GJ7C6BPFY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZUAVDSD43KJW3VM34GJ7C6BPFY/action/storage_attestation","attest_author":"https://pith.science/pith/ZUAVDSD43KJW3VM34GJ7C6BPFY/action/author_attestation","sign_citation":"https://pith.science/pith/ZUAVDSD43KJW3VM34GJ7C6BPFY/action/citation_signature","submit_replication":"https://pith.science/pith/ZUAVDSD43KJW3VM34GJ7C6BPFY/action/replication_record"}},"created_at":"2026-07-05T08:57:13.418007+00:00","updated_at":"2026-07-05T08:57:13.418007+00:00"}