{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:454ZODQ5DR7G4R7WZZZYWOGIVZ","short_pith_number":"pith:454ZODQ5","schema_version":"1.0","canonical_sha256":"e779970e1d1c7e6e47f6ce738b38c8ae7facf9f01fbe84fb81be22319f85cb55","source":{"kind":"arxiv","id":"2103.06104","version":2},"attestation_state":"computed","paper":{"title":"U-Net Transformer: Self and Cross Attention for Medical Image Segmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"eess.IV","authors_text":"Cl\\'ement Rambour, Luc Soler, Nicolas Thome, Olivier Petit","submitted_at":"2021-03-10T14:58:31Z","abstract_excerpt":"Medical image segmentation remains particularly challenging for complex and low-contrast anatomical structures. In this paper, we introduce the U-Transformer network, which combines a U-shaped architecture for image segmentation with self- and cross-attention from Transformers. U-Transformer overcomes the inability of U-Nets to model long-range contextual interactions and spatial dependencies, which are arguably crucial for accurate segmentation in challenging contexts. To this end, attention mechanisms are incorporated at two main levels: a self-attention module leverages global interactions "},"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":"2103.06104","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.IV","submitted_at":"2021-03-10T14:58:31Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"01a74c4b19515629e6340acb3b9663b157df736283d6febc546cae9458b6b44a","abstract_canon_sha256":"c904b3825b1dd04f1e8cd1be6625aa203036b684af9e8bd3bb13fdcfb721aa6b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:22:26.299271Z","signature_b64":"A1c5bKNvza3F16egSTQ/5syfkKiI7lUYxl6ZlRbK7AFB4MzqX+q/7AQqVV9UNruvH6ASO08oBalCMyZDvu8oAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e779970e1d1c7e6e47f6ce738b38c8ae7facf9f01fbe84fb81be22319f85cb55","last_reissued_at":"2026-07-05T02:22:26.298877Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:22:26.298877Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"U-Net Transformer: Self and Cross Attention for Medical Image Segmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"eess.IV","authors_text":"Cl\\'ement Rambour, Luc Soler, Nicolas Thome, Olivier Petit","submitted_at":"2021-03-10T14:58:31Z","abstract_excerpt":"Medical image segmentation remains particularly challenging for complex and low-contrast anatomical structures. In this paper, we introduce the U-Transformer network, which combines a U-shaped architecture for image segmentation with self- and cross-attention from Transformers. U-Transformer overcomes the inability of U-Nets to model long-range contextual interactions and spatial dependencies, which are arguably crucial for accurate segmentation in challenging contexts. To this end, attention mechanisms are incorporated at two main levels: a self-attention module leverages global interactions "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2103.06104","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/2103.06104/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":"2103.06104","created_at":"2026-07-05T02:22:26.298930+00:00"},{"alias_kind":"arxiv_version","alias_value":"2103.06104v2","created_at":"2026-07-05T02:22:26.298930+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2103.06104","created_at":"2026-07-05T02:22:26.298930+00:00"},{"alias_kind":"pith_short_12","alias_value":"454ZODQ5DR7G","created_at":"2026-07-05T02:22:26.298930+00:00"},{"alias_kind":"pith_short_16","alias_value":"454ZODQ5DR7G4R7W","created_at":"2026-07-05T02:22:26.298930+00:00"},{"alias_kind":"pith_short_8","alias_value":"454ZODQ5","created_at":"2026-07-05T02:22:26.298930+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.07925","citing_title":"A Comparative Study of U-Net Architectures for Change Detection in Satellite Images","ref_index":14,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/454ZODQ5DR7G4R7WZZZYWOGIVZ","json":"https://pith.science/pith/454ZODQ5DR7G4R7WZZZYWOGIVZ.json","graph_json":"https://pith.science/api/pith-number/454ZODQ5DR7G4R7WZZZYWOGIVZ/graph.json","events_json":"https://pith.science/api/pith-number/454ZODQ5DR7G4R7WZZZYWOGIVZ/events.json","paper":"https://pith.science/paper/454ZODQ5"},"agent_actions":{"view_html":"https://pith.science/pith/454ZODQ5DR7G4R7WZZZYWOGIVZ","download_json":"https://pith.science/pith/454ZODQ5DR7G4R7WZZZYWOGIVZ.json","view_paper":"https://pith.science/paper/454ZODQ5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2103.06104&json=true","fetch_graph":"https://pith.science/api/pith-number/454ZODQ5DR7G4R7WZZZYWOGIVZ/graph.json","fetch_events":"https://pith.science/api/pith-number/454ZODQ5DR7G4R7WZZZYWOGIVZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/454ZODQ5DR7G4R7WZZZYWOGIVZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/454ZODQ5DR7G4R7WZZZYWOGIVZ/action/storage_attestation","attest_author":"https://pith.science/pith/454ZODQ5DR7G4R7WZZZYWOGIVZ/action/author_attestation","sign_citation":"https://pith.science/pith/454ZODQ5DR7G4R7WZZZYWOGIVZ/action/citation_signature","submit_replication":"https://pith.science/pith/454ZODQ5DR7G4R7WZZZYWOGIVZ/action/replication_record"}},"created_at":"2026-07-05T02:22:26.298930+00:00","updated_at":"2026-07-05T02:22:26.298930+00:00"}