{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:RKXZBVBHRE7MX7SYFQUQWPRT7O","short_pith_number":"pith:RKXZBVBH","schema_version":"1.0","canonical_sha256":"8aaf90d427893ecbfe582c290b3e33fbac2e52ebc8c5db949c97a90ab4a3763a","source":{"kind":"arxiv","id":"2204.00631","version":2},"attestation_state":"computed","paper":{"title":"UNetFormer: A Unified Vision Transformer Model and Pre-Training Framework for 3D Medical Image Segmentation","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI","cs.CV","cs.LG"],"primary_cat":"eess.IV","authors_text":"Ali Hatamizadeh, Daguang Xu, Dong Yang, Holger Roth, Wenqi Li, Ziyue Xu","submitted_at":"2022-04-01T17:38:39Z","abstract_excerpt":"Vision Transformers (ViT)s have recently become popular due to their outstanding modeling capabilities, in particular for capturing long-range information, and scalability to dataset and model sizes which has led to state-of-the-art performance in various computer vision and medical image analysis tasks. In this work, we introduce a unified framework consisting of two architectures, dubbed UNetFormer, with a 3D Swin Transformer-based encoder and Convolutional Neural Network (CNN) and transformer-based decoders. In the proposed model, the encoder is linked to the decoder via skip connections at"},"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":"2204.00631","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"eess.IV","submitted_at":"2022-04-01T17:38:39Z","cross_cats_sorted":["cs.AI","cs.CV","cs.LG"],"title_canon_sha256":"8d94544cad4e79dafc79361adfadce6dfc8e1b441d5948db3a15d5137b7bc953","abstract_canon_sha256":"a7b21507344347dfd45d7b4ef351193947b25cb8466021e692abeab0c3a07511"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:11:31.849477Z","signature_b64":"WgRvpRCJ0oENQa3tw5s8gkTKXu3aDOD4ii4aCkxhT3tZW1iUTZAQeCKP9rzjvxAMnH1cg7pftQw/8Z5ig6hmBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8aaf90d427893ecbfe582c290b3e33fbac2e52ebc8c5db949c97a90ab4a3763a","last_reissued_at":"2026-07-05T04:11:31.849000Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:11:31.849000Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"UNetFormer: A Unified Vision Transformer Model and Pre-Training Framework for 3D Medical Image Segmentation","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI","cs.CV","cs.LG"],"primary_cat":"eess.IV","authors_text":"Ali Hatamizadeh, Daguang Xu, Dong Yang, Holger Roth, Wenqi Li, Ziyue Xu","submitted_at":"2022-04-01T17:38:39Z","abstract_excerpt":"Vision Transformers (ViT)s have recently become popular due to their outstanding modeling capabilities, in particular for capturing long-range information, and scalability to dataset and model sizes which has led to state-of-the-art performance in various computer vision and medical image analysis tasks. In this work, we introduce a unified framework consisting of two architectures, dubbed UNetFormer, with a 3D Swin Transformer-based encoder and Convolutional Neural Network (CNN) and transformer-based decoders. In the proposed model, the encoder is linked to the decoder via skip connections at"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2204.00631","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/2204.00631/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":"2204.00631","created_at":"2026-07-05T04:11:31.849052+00:00"},{"alias_kind":"arxiv_version","alias_value":"2204.00631v2","created_at":"2026-07-05T04:11:31.849052+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2204.00631","created_at":"2026-07-05T04:11:31.849052+00:00"},{"alias_kind":"pith_short_12","alias_value":"RKXZBVBHRE7M","created_at":"2026-07-05T04:11:31.849052+00:00"},{"alias_kind":"pith_short_16","alias_value":"RKXZBVBHRE7MX7SY","created_at":"2026-07-05T04:11:31.849052+00:00"},{"alias_kind":"pith_short_8","alias_value":"RKXZBVBH","created_at":"2026-07-05T04:11:31.849052+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.10281","citing_title":"MFogHub: Bridging Multi-Regional and Multi-Satellite Data for Global Marine Fog Detection and Forecasting","ref_index":8,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RKXZBVBHRE7MX7SYFQUQWPRT7O","json":"https://pith.science/pith/RKXZBVBHRE7MX7SYFQUQWPRT7O.json","graph_json":"https://pith.science/api/pith-number/RKXZBVBHRE7MX7SYFQUQWPRT7O/graph.json","events_json":"https://pith.science/api/pith-number/RKXZBVBHRE7MX7SYFQUQWPRT7O/events.json","paper":"https://pith.science/paper/RKXZBVBH"},"agent_actions":{"view_html":"https://pith.science/pith/RKXZBVBHRE7MX7SYFQUQWPRT7O","download_json":"https://pith.science/pith/RKXZBVBHRE7MX7SYFQUQWPRT7O.json","view_paper":"https://pith.science/paper/RKXZBVBH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2204.00631&json=true","fetch_graph":"https://pith.science/api/pith-number/RKXZBVBHRE7MX7SYFQUQWPRT7O/graph.json","fetch_events":"https://pith.science/api/pith-number/RKXZBVBHRE7MX7SYFQUQWPRT7O/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RKXZBVBHRE7MX7SYFQUQWPRT7O/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RKXZBVBHRE7MX7SYFQUQWPRT7O/action/storage_attestation","attest_author":"https://pith.science/pith/RKXZBVBHRE7MX7SYFQUQWPRT7O/action/author_attestation","sign_citation":"https://pith.science/pith/RKXZBVBHRE7MX7SYFQUQWPRT7O/action/citation_signature","submit_replication":"https://pith.science/pith/RKXZBVBHRE7MX7SYFQUQWPRT7O/action/replication_record"}},"created_at":"2026-07-05T04:11:31.849052+00:00","updated_at":"2026-07-05T04:11:31.849052+00:00"}