{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:WM7PXOQBPXP7YBDWMYXLZG44UP","short_pith_number":"pith:WM7PXOQB","schema_version":"1.0","canonical_sha256":"b33efbba017ddffc0476662ebc9b9ca3edf1ce808443dd5f585bcbab7c9a861f","source":{"kind":"arxiv","id":"2607.00223","version":1},"attestation_state":"computed","paper":{"title":"Does Your ViT Still Need U-Net for Segmentation?","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hao Wang, Oana M. Dumitrascu, Wenhui Zhu, Xin Li, Xiwen Chen, Xuanzhao Dong, Yalin Wang, Yanxi Chen, Yujian Xiong","submitted_at":"2026-06-30T22:02:12Z","abstract_excerpt":"Medical image segmentation is dominated by U-Net-style encoder-decoder architectures. Vision Transformers (ViTs) overcome the limited receptive field of convolutional networks through self-attention, enabling modeling of long-range dependencies. Early ViT-based segmentation methods typically retained U-Net-style decoders because pretrained ViT representations were insufficient to support accurate dense prediction. Recent advances in large-scale pretraining have redefined the representation capability of ViTs, reducing the reliance on U-Net-style decoder architectures in modern vision models. T"},"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":"2607.00223","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-30T22:02:12Z","cross_cats_sorted":[],"title_canon_sha256":"3b3b260c1ea5de9d7419baa99bbd562b1b85fc03ec1b238a7f3087efd4175686","abstract_canon_sha256":"68c570e4194c07abe8112af88e6cb725ae441996bc2c00caf2c98cf6c8741731"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-02T00:18:39.873804Z","signature_b64":"OUiIKe5yRaoTK+OJnVmRNICLwGXoak4hvsJ5tCZuaTfC3FN805QVKr7y5vSyjxD30JvRYcnpzaxF4Id/YFUODA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b33efbba017ddffc0476662ebc9b9ca3edf1ce808443dd5f585bcbab7c9a861f","last_reissued_at":"2026-07-02T00:18:39.872752Z","signature_status":"signed_v1","first_computed_at":"2026-07-02T00:18:39.872752Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Does Your ViT Still Need U-Net for Segmentation?","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hao Wang, Oana M. Dumitrascu, Wenhui Zhu, Xin Li, Xiwen Chen, Xuanzhao Dong, Yalin Wang, Yanxi Chen, Yujian Xiong","submitted_at":"2026-06-30T22:02:12Z","abstract_excerpt":"Medical image segmentation is dominated by U-Net-style encoder-decoder architectures. Vision Transformers (ViTs) overcome the limited receptive field of convolutional networks through self-attention, enabling modeling of long-range dependencies. Early ViT-based segmentation methods typically retained U-Net-style decoders because pretrained ViT representations were insufficient to support accurate dense prediction. Recent advances in large-scale pretraining have redefined the representation capability of ViTs, reducing the reliance on U-Net-style decoder architectures in modern vision models. T"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.00223","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/2607.00223/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":"2607.00223","created_at":"2026-07-02T00:18:39.872857+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.00223v1","created_at":"2026-07-02T00:18:39.872857+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.00223","created_at":"2026-07-02T00:18:39.872857+00:00"},{"alias_kind":"pith_short_12","alias_value":"WM7PXOQBPXP7","created_at":"2026-07-02T00:18:39.872857+00:00"},{"alias_kind":"pith_short_16","alias_value":"WM7PXOQBPXP7YBDW","created_at":"2026-07-02T00:18:39.872857+00:00"},{"alias_kind":"pith_short_8","alias_value":"WM7PXOQB","created_at":"2026-07-02T00:18:39.872857+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/WM7PXOQBPXP7YBDWMYXLZG44UP","json":"https://pith.science/pith/WM7PXOQBPXP7YBDWMYXLZG44UP.json","graph_json":"https://pith.science/api/pith-number/WM7PXOQBPXP7YBDWMYXLZG44UP/graph.json","events_json":"https://pith.science/api/pith-number/WM7PXOQBPXP7YBDWMYXLZG44UP/events.json","paper":"https://pith.science/paper/WM7PXOQB"},"agent_actions":{"view_html":"https://pith.science/pith/WM7PXOQBPXP7YBDWMYXLZG44UP","download_json":"https://pith.science/pith/WM7PXOQBPXP7YBDWMYXLZG44UP.json","view_paper":"https://pith.science/paper/WM7PXOQB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.00223&json=true","fetch_graph":"https://pith.science/api/pith-number/WM7PXOQBPXP7YBDWMYXLZG44UP/graph.json","fetch_events":"https://pith.science/api/pith-number/WM7PXOQBPXP7YBDWMYXLZG44UP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WM7PXOQBPXP7YBDWMYXLZG44UP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WM7PXOQBPXP7YBDWMYXLZG44UP/action/storage_attestation","attest_author":"https://pith.science/pith/WM7PXOQBPXP7YBDWMYXLZG44UP/action/author_attestation","sign_citation":"https://pith.science/pith/WM7PXOQBPXP7YBDWMYXLZG44UP/action/citation_signature","submit_replication":"https://pith.science/pith/WM7PXOQBPXP7YBDWMYXLZG44UP/action/replication_record"}},"created_at":"2026-07-02T00:18:39.872857+00:00","updated_at":"2026-07-02T00:18:39.872857+00:00"}