{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:S2P62PCMUFKKQHODJJZXKHCWFS","short_pith_number":"pith:S2P62PCM","schema_version":"1.0","canonical_sha256":"969fed3c4ca154a81dc34a73751c562c8ca8d969a13a228206653489b1be6d73","source":{"kind":"arxiv","id":"2404.00122","version":2},"attestation_state":"computed","paper":{"title":"AgileFormer: Spatially Agile Transformer UNet for Medical Image Segmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.IV"],"primary_cat":"cs.CV","authors_text":"Aristeidis Sotiras, Jin Yang, Peijie Qiu, Sayantan Kumar, Soumyendu Sekhar Ghosh","submitted_at":"2024-03-29T19:25:09Z","abstract_excerpt":"In the past decades, deep neural networks, particularly convolutional neural networks, have achieved state-of-the-art performance in a variety of medical image segmentation tasks. Recently, the introduction of the vision transformer (ViT) has significantly altered the landscape of deep segmentation models. There has been a growing focus on ViTs, driven by their excellent performance and scalability. However, we argue that the current design of the vision transformer-based UNet (ViT-UNet) segmentation models may not effectively handle the heterogeneous appearance (e.g., varying shapes and sizes"},"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":"2404.00122","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-03-29T19:25:09Z","cross_cats_sorted":["eess.IV"],"title_canon_sha256":"4c4fbc04e02901587ffc3a62a4df04bbfdfefcb4fafce892b202cf2d027be535","abstract_canon_sha256":"38e664a69cbdc78b871c11887c2b1c6e0e74cfd0846a00b0b9113e4054958853"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:07:46.853325Z","signature_b64":"Z1sgdEEjQA/6Bs7V8CmHLtJBzbgz7j2DrKuZdhcAAohLFWih4hHUUXc24n2rU/pngp8m+1O4IlCiG8o/+ThADA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"969fed3c4ca154a81dc34a73751c562c8ca8d969a13a228206653489b1be6d73","last_reissued_at":"2026-07-05T09:07:46.852834Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:07:46.852834Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"AgileFormer: Spatially Agile Transformer UNet for Medical Image Segmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.IV"],"primary_cat":"cs.CV","authors_text":"Aristeidis Sotiras, Jin Yang, Peijie Qiu, Sayantan Kumar, Soumyendu Sekhar Ghosh","submitted_at":"2024-03-29T19:25:09Z","abstract_excerpt":"In the past decades, deep neural networks, particularly convolutional neural networks, have achieved state-of-the-art performance in a variety of medical image segmentation tasks. Recently, the introduction of the vision transformer (ViT) has significantly altered the landscape of deep segmentation models. There has been a growing focus on ViTs, driven by their excellent performance and scalability. However, we argue that the current design of the vision transformer-based UNet (ViT-UNet) segmentation models may not effectively handle the heterogeneous appearance (e.g., varying shapes and sizes"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.00122","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/2404.00122/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":"2404.00122","created_at":"2026-07-05T09:07:46.852903+00:00"},{"alias_kind":"arxiv_version","alias_value":"2404.00122v2","created_at":"2026-07-05T09:07:46.852903+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.00122","created_at":"2026-07-05T09:07:46.852903+00:00"},{"alias_kind":"pith_short_12","alias_value":"S2P62PCMUFKK","created_at":"2026-07-05T09:07:46.852903+00:00"},{"alias_kind":"pith_short_16","alias_value":"S2P62PCMUFKKQHOD","created_at":"2026-07-05T09:07:46.852903+00:00"},{"alias_kind":"pith_short_8","alias_value":"S2P62PCM","created_at":"2026-07-05T09:07:46.852903+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/S2P62PCMUFKKQHODJJZXKHCWFS","json":"https://pith.science/pith/S2P62PCMUFKKQHODJJZXKHCWFS.json","graph_json":"https://pith.science/api/pith-number/S2P62PCMUFKKQHODJJZXKHCWFS/graph.json","events_json":"https://pith.science/api/pith-number/S2P62PCMUFKKQHODJJZXKHCWFS/events.json","paper":"https://pith.science/paper/S2P62PCM"},"agent_actions":{"view_html":"https://pith.science/pith/S2P62PCMUFKKQHODJJZXKHCWFS","download_json":"https://pith.science/pith/S2P62PCMUFKKQHODJJZXKHCWFS.json","view_paper":"https://pith.science/paper/S2P62PCM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2404.00122&json=true","fetch_graph":"https://pith.science/api/pith-number/S2P62PCMUFKKQHODJJZXKHCWFS/graph.json","fetch_events":"https://pith.science/api/pith-number/S2P62PCMUFKKQHODJJZXKHCWFS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/S2P62PCMUFKKQHODJJZXKHCWFS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/S2P62PCMUFKKQHODJJZXKHCWFS/action/storage_attestation","attest_author":"https://pith.science/pith/S2P62PCMUFKKQHODJJZXKHCWFS/action/author_attestation","sign_citation":"https://pith.science/pith/S2P62PCMUFKKQHODJJZXKHCWFS/action/citation_signature","submit_replication":"https://pith.science/pith/S2P62PCMUFKKQHODJJZXKHCWFS/action/replication_record"}},"created_at":"2026-07-05T09:07:46.852903+00:00","updated_at":"2026-07-05T09:07:46.852903+00:00"}