{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:3M4U2GLMEAUDZMHF2Y5FW3VGVW","short_pith_number":"pith:3M4U2GLM","schema_version":"1.0","canonical_sha256":"db394d196c20283cb0e5d63a5b6ea6ad90b7d6e3f6e23b0fbc15f533ec17f3dc","source":{"kind":"arxiv","id":"2109.03201","version":6},"attestation_state":"computed","paper":{"title":"nnFormer: Interleaved Transformer for Volumetric Segmentation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hong-Yu Zhou, Jiansen Guo, Lequan Yu, Liansheng Wang, Yinghao Zhang, Yizhou Yu","submitted_at":"2021-09-07T17:08:24Z","abstract_excerpt":"Transformer, the model of choice for natural language processing, has drawn scant attention from the medical imaging community. Given the ability to exploit long-term dependencies, transformers are promising to help atypical convolutional neural networks to overcome their inherent shortcomings of spatial inductive bias. However, most of recently proposed transformer-based segmentation approaches simply treated transformers as assisted modules to help encode global context into convolutional representations. To address this issue, we introduce nnFormer, a 3D transformer for volumetric medical i"},"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":"2109.03201","kind":"arxiv","version":6},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-09-07T17:08:24Z","cross_cats_sorted":[],"title_canon_sha256":"509a086ec4a108a350950b6079c65a26137ae9b6cc06a467938e9e8d9b47dcef","abstract_canon_sha256":"2d46fe81e6cf5de405d652ebae231d95ce61ba31e2d1d1c537a66ee9f504ded3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:54:01.873616Z","signature_b64":"bzCU5ooaDVQG+0iBku/E3TCKwuwagtksON+jZFsY+A8A/02qBgSUZg5TG/RFaW1G9YleV+jbrBjUG2jfh41wAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"db394d196c20283cb0e5d63a5b6ea6ad90b7d6e3f6e23b0fbc15f533ec17f3dc","last_reissued_at":"2026-07-05T03:54:01.873120Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:54:01.873120Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"nnFormer: Interleaved Transformer for Volumetric Segmentation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hong-Yu Zhou, Jiansen Guo, Lequan Yu, Liansheng Wang, Yinghao Zhang, Yizhou Yu","submitted_at":"2021-09-07T17:08:24Z","abstract_excerpt":"Transformer, the model of choice for natural language processing, has drawn scant attention from the medical imaging community. Given the ability to exploit long-term dependencies, transformers are promising to help atypical convolutional neural networks to overcome their inherent shortcomings of spatial inductive bias. However, most of recently proposed transformer-based segmentation approaches simply treated transformers as assisted modules to help encode global context into convolutional representations. To address this issue, we introduce nnFormer, a 3D transformer for volumetric medical i"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2109.03201","kind":"arxiv","version":6},"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/2109.03201/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":"2109.03201","created_at":"2026-07-05T03:54:01.873177+00:00"},{"alias_kind":"arxiv_version","alias_value":"2109.03201v6","created_at":"2026-07-05T03:54:01.873177+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2109.03201","created_at":"2026-07-05T03:54:01.873177+00:00"},{"alias_kind":"pith_short_12","alias_value":"3M4U2GLMEAUD","created_at":"2026-07-05T03:54:01.873177+00:00"},{"alias_kind":"pith_short_16","alias_value":"3M4U2GLMEAUDZMHF","created_at":"2026-07-05T03:54:01.873177+00:00"},{"alias_kind":"pith_short_8","alias_value":"3M4U2GLM","created_at":"2026-07-05T03:54:01.873177+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.23100","citing_title":"A Positron Range Correction with Texture Preservation Framework in PET Imaging","ref_index":44,"is_internal_anchor":false},{"citing_arxiv_id":"2606.06103","citing_title":"MS-DKC: A Dataset Knowledge Card Framework for Designing and Adapting Medical Image Segmentation Models","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2605.16464","citing_title":"MHMamba: Multi-Head Mamba for 3D Brain Tumor Segmentation","ref_index":44,"is_internal_anchor":false},{"citing_arxiv_id":"2605.15997","citing_title":"Segmentation, Detection and Explanation: A Unified Framework for CT Appearance Reasoning","ref_index":50,"is_internal_anchor":false},{"citing_arxiv_id":"2506.14844","citing_title":"Improving Prostate Gland Segmentation Using Transformer based Architectures","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2510.20933","citing_title":"Focal Modulation and Bidirectional Feature Fusion Network for Medical Image Segmentation","ref_index":70,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3M4U2GLMEAUDZMHF2Y5FW3VGVW","json":"https://pith.science/pith/3M4U2GLMEAUDZMHF2Y5FW3VGVW.json","graph_json":"https://pith.science/api/pith-number/3M4U2GLMEAUDZMHF2Y5FW3VGVW/graph.json","events_json":"https://pith.science/api/pith-number/3M4U2GLMEAUDZMHF2Y5FW3VGVW/events.json","paper":"https://pith.science/paper/3M4U2GLM"},"agent_actions":{"view_html":"https://pith.science/pith/3M4U2GLMEAUDZMHF2Y5FW3VGVW","download_json":"https://pith.science/pith/3M4U2GLMEAUDZMHF2Y5FW3VGVW.json","view_paper":"https://pith.science/paper/3M4U2GLM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2109.03201&json=true","fetch_graph":"https://pith.science/api/pith-number/3M4U2GLMEAUDZMHF2Y5FW3VGVW/graph.json","fetch_events":"https://pith.science/api/pith-number/3M4U2GLMEAUDZMHF2Y5FW3VGVW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3M4U2GLMEAUDZMHF2Y5FW3VGVW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3M4U2GLMEAUDZMHF2Y5FW3VGVW/action/storage_attestation","attest_author":"https://pith.science/pith/3M4U2GLMEAUDZMHF2Y5FW3VGVW/action/author_attestation","sign_citation":"https://pith.science/pith/3M4U2GLMEAUDZMHF2Y5FW3VGVW/action/citation_signature","submit_replication":"https://pith.science/pith/3M4U2GLMEAUDZMHF2Y5FW3VGVW/action/replication_record"}},"created_at":"2026-07-05T03:54:01.873177+00:00","updated_at":"2026-07-05T03:54:01.873177+00:00"}