{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:ECUFPTAI7XONRMNCI3XM6V5ZEU","short_pith_number":"pith:ECUFPTAI","schema_version":"1.0","canonical_sha256":"20a857cc08fddcd8b1a246eecf57b9252a24caff87f2e16f2ed98c1c6054ccc7","source":{"kind":"arxiv","id":"2507.06569","version":1},"attestation_state":"computed","paper":{"title":"Edge-Boundary-Texture Loss: A Tri-Class Generalization of Weighted Binary Cross-Entropy for Enhanced Edge Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hao Shu","submitted_at":"2025-07-09T05:47:26Z","abstract_excerpt":"Edge detection (ED) remains a fundamental task in computer vision, yet its performance is often hindered by the ambiguous nature of non-edge pixels near object boundaries. The widely adopted Weighted Binary Cross-Entropy (WBCE) loss treats all non-edge pixels uniformly, overlooking the structural nuances around edges and often resulting in blurred predictions. In this paper, we propose the Edge-Boundary-Texture (EBT) loss, a novel objective that explicitly divides pixels into three categories, edge, boundary, and texture, and assigns each a distinct supervisory weight. This tri-class formulati"},"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":"2507.06569","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-07-09T05:47:26Z","cross_cats_sorted":[],"title_canon_sha256":"0e1edf966a72cdd79b3cc60ce179226e8998870da2efffdf662b99a29c87e36e","abstract_canon_sha256":"1aef4d98ab056db83cd4d07975fc29caa6d0e1733575f78d758538f8e43d65d6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:34:18.556806Z","signature_b64":"rpuA9gqCsfLFpzNLLmZXfDaU3BTNcKhkmDj+/3ePKNuvM1m0Z2Pc57ZXKZvhHo1Bibl3ZBxRomfBbqYZjA8KBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"20a857cc08fddcd8b1a246eecf57b9252a24caff87f2e16f2ed98c1c6054ccc7","last_reissued_at":"2026-07-05T11:34:18.556344Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:34:18.556344Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Edge-Boundary-Texture Loss: A Tri-Class Generalization of Weighted Binary Cross-Entropy for Enhanced Edge Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hao Shu","submitted_at":"2025-07-09T05:47:26Z","abstract_excerpt":"Edge detection (ED) remains a fundamental task in computer vision, yet its performance is often hindered by the ambiguous nature of non-edge pixels near object boundaries. The widely adopted Weighted Binary Cross-Entropy (WBCE) loss treats all non-edge pixels uniformly, overlooking the structural nuances around edges and often resulting in blurred predictions. In this paper, we propose the Edge-Boundary-Texture (EBT) loss, a novel objective that explicitly divides pixels into three categories, edge, boundary, and texture, and assigns each a distinct supervisory weight. This tri-class formulati"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.06569","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/2507.06569/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":"2507.06569","created_at":"2026-07-05T11:34:18.556412+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.06569v1","created_at":"2026-07-05T11:34:18.556412+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.06569","created_at":"2026-07-05T11:34:18.556412+00:00"},{"alias_kind":"pith_short_12","alias_value":"ECUFPTAI7XON","created_at":"2026-07-05T11:34:18.556412+00:00"},{"alias_kind":"pith_short_16","alias_value":"ECUFPTAI7XONRMNC","created_at":"2026-07-05T11:34:18.556412+00:00"},{"alias_kind":"pith_short_8","alias_value":"ECUFPTAI","created_at":"2026-07-05T11:34:18.556412+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/ECUFPTAI7XONRMNCI3XM6V5ZEU","json":"https://pith.science/pith/ECUFPTAI7XONRMNCI3XM6V5ZEU.json","graph_json":"https://pith.science/api/pith-number/ECUFPTAI7XONRMNCI3XM6V5ZEU/graph.json","events_json":"https://pith.science/api/pith-number/ECUFPTAI7XONRMNCI3XM6V5ZEU/events.json","paper":"https://pith.science/paper/ECUFPTAI"},"agent_actions":{"view_html":"https://pith.science/pith/ECUFPTAI7XONRMNCI3XM6V5ZEU","download_json":"https://pith.science/pith/ECUFPTAI7XONRMNCI3XM6V5ZEU.json","view_paper":"https://pith.science/paper/ECUFPTAI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.06569&json=true","fetch_graph":"https://pith.science/api/pith-number/ECUFPTAI7XONRMNCI3XM6V5ZEU/graph.json","fetch_events":"https://pith.science/api/pith-number/ECUFPTAI7XONRMNCI3XM6V5ZEU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ECUFPTAI7XONRMNCI3XM6V5ZEU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ECUFPTAI7XONRMNCI3XM6V5ZEU/action/storage_attestation","attest_author":"https://pith.science/pith/ECUFPTAI7XONRMNCI3XM6V5ZEU/action/author_attestation","sign_citation":"https://pith.science/pith/ECUFPTAI7XONRMNCI3XM6V5ZEU/action/citation_signature","submit_replication":"https://pith.science/pith/ECUFPTAI7XONRMNCI3XM6V5ZEU/action/replication_record"}},"created_at":"2026-07-05T11:34:18.556412+00:00","updated_at":"2026-07-05T11:34:18.556412+00:00"}