{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:23Q4F6GOJ6M6DZOEXWGG7DWFSB","short_pith_number":"pith:23Q4F6GO","schema_version":"1.0","canonical_sha256":"d6e1c2f8ce4f99e1e5c4bd8c6f8ec59078f4f8b2617101caf1d380bf8ac888bc","source":{"kind":"arxiv","id":"2104.06468","version":1},"attestation_state":"computed","paper":{"title":"ViT-V-Net: Vision Transformer for Unsupervised Volumetric Medical Image Registration","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"eess.IV","authors_text":"Eric C. Frey, Junyu Chen, Ye Li, Yong Du, Yufan He","submitted_at":"2021-04-13T19:18:19Z","abstract_excerpt":"In the last decade, convolutional neural networks (ConvNets) have dominated and achieved state-of-the-art performances in a variety of medical imaging applications. However, the performances of ConvNets are still limited by lacking the understanding of long-range spatial relations in an image. The recently proposed Vision Transformer (ViT) for image classification uses a purely self-attention-based model that learns long-range spatial relations to focus on the relevant parts of an image. Nevertheless, ViT emphasizes the low-resolution features because of the consecutive downsamplings, result 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":"2104.06468","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.IV","submitted_at":"2021-04-13T19:18:19Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"d363acbb329c415842526c374e9d893b028e9ed0d92176c397a3ce15e90da961","abstract_canon_sha256":"4651000e1eb99960cd49120d09cafb18489fd0ce0202464b9a7f4aa912182c6b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:32:06.078159Z","signature_b64":"CWgVRIlPwe0qoiwxHJsuHtVEd/uJbCHkMPQZCZU22QOOULzIT1jF3D3akOFq5fUvcfuZ+O4vkpcpikchsQoNCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d6e1c2f8ce4f99e1e5c4bd8c6f8ec59078f4f8b2617101caf1d380bf8ac888bc","last_reissued_at":"2026-07-05T02:32:06.077654Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:32:06.077654Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ViT-V-Net: Vision Transformer for Unsupervised Volumetric Medical Image Registration","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"eess.IV","authors_text":"Eric C. Frey, Junyu Chen, Ye Li, Yong Du, Yufan He","submitted_at":"2021-04-13T19:18:19Z","abstract_excerpt":"In the last decade, convolutional neural networks (ConvNets) have dominated and achieved state-of-the-art performances in a variety of medical imaging applications. However, the performances of ConvNets are still limited by lacking the understanding of long-range spatial relations in an image. The recently proposed Vision Transformer (ViT) for image classification uses a purely self-attention-based model that learns long-range spatial relations to focus on the relevant parts of an image. Nevertheless, ViT emphasizes the low-resolution features because of the consecutive downsamplings, result i"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2104.06468","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/2104.06468/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":"2104.06468","created_at":"2026-07-05T02:32:06.077715+00:00"},{"alias_kind":"arxiv_version","alias_value":"2104.06468v1","created_at":"2026-07-05T02:32:06.077715+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2104.06468","created_at":"2026-07-05T02:32:06.077715+00:00"},{"alias_kind":"pith_short_12","alias_value":"23Q4F6GOJ6M6","created_at":"2026-07-05T02:32:06.077715+00:00"},{"alias_kind":"pith_short_16","alias_value":"23Q4F6GOJ6M6DZOE","created_at":"2026-07-05T02:32:06.077715+00:00"},{"alias_kind":"pith_short_8","alias_value":"23Q4F6GO","created_at":"2026-07-05T02:32:06.077715+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/23Q4F6GOJ6M6DZOEXWGG7DWFSB","json":"https://pith.science/pith/23Q4F6GOJ6M6DZOEXWGG7DWFSB.json","graph_json":"https://pith.science/api/pith-number/23Q4F6GOJ6M6DZOEXWGG7DWFSB/graph.json","events_json":"https://pith.science/api/pith-number/23Q4F6GOJ6M6DZOEXWGG7DWFSB/events.json","paper":"https://pith.science/paper/23Q4F6GO"},"agent_actions":{"view_html":"https://pith.science/pith/23Q4F6GOJ6M6DZOEXWGG7DWFSB","download_json":"https://pith.science/pith/23Q4F6GOJ6M6DZOEXWGG7DWFSB.json","view_paper":"https://pith.science/paper/23Q4F6GO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2104.06468&json=true","fetch_graph":"https://pith.science/api/pith-number/23Q4F6GOJ6M6DZOEXWGG7DWFSB/graph.json","fetch_events":"https://pith.science/api/pith-number/23Q4F6GOJ6M6DZOEXWGG7DWFSB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/23Q4F6GOJ6M6DZOEXWGG7DWFSB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/23Q4F6GOJ6M6DZOEXWGG7DWFSB/action/storage_attestation","attest_author":"https://pith.science/pith/23Q4F6GOJ6M6DZOEXWGG7DWFSB/action/author_attestation","sign_citation":"https://pith.science/pith/23Q4F6GOJ6M6DZOEXWGG7DWFSB/action/citation_signature","submit_replication":"https://pith.science/pith/23Q4F6GOJ6M6DZOEXWGG7DWFSB/action/replication_record"}},"created_at":"2026-07-05T02:32:06.077715+00:00","updated_at":"2026-07-05T02:32:06.077715+00:00"}