{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:H3K4M6MEBBA4PNUMVDRJMEPQDE","short_pith_number":"pith:H3K4M6ME","schema_version":"1.0","canonical_sha256":"3ed5c679840841c7b68ca8e29611f019216e101e1df7970b353bf94d481c2db7","source":{"kind":"arxiv","id":"2207.14552","version":1},"attestation_state":"computed","paper":{"title":"ScaleFormer: Revisiting the Transformer-based Backbones from a Scale-wise Perspective for Medical Image Segmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Huimin Huang, Lanfen Lin, Ruofeng Tong, Shiao Xie1, Xianhua Han, Yen-Wei Chen, Yutaro Iwamoto","submitted_at":"2022-07-29T08:55:00Z","abstract_excerpt":"Recently, a variety of vision transformers have been developed as their capability of modeling long-range dependency. In current transformer-based backbones for medical image segmentation, convolutional layers were replaced with pure transformers, or transformers were added to the deepest encoder to learn global context. However, there are mainly two challenges in a scale-wise perspective: (1) intra-scale problem: the existing methods lacked in extracting local-global cues in each scale, which may impact the signal propagation of small objects; (2) inter-scale problem: the existing methods fai"},"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":"2207.14552","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-07-29T08:55:00Z","cross_cats_sorted":[],"title_canon_sha256":"f8c7d52362a6e3497dec3be54772685f3a91d67beb140833fdae2c13fb0c31ab","abstract_canon_sha256":"d330babd0e3d0e1e5da20ba11e0ecaf5197445eb76f4e51b7547fce7ba70966f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:44:35.409885Z","signature_b64":"G7aumDavWxk13+XmTsk61u04FEd5TbJlIVah2QAgodXMyDjIQNWVR7xYusra7DS45pp420sVTGaKw7uAhxRkBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3ed5c679840841c7b68ca8e29611f019216e101e1df7970b353bf94d481c2db7","last_reissued_at":"2026-07-05T04:44:35.409248Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:44:35.409248Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ScaleFormer: Revisiting the Transformer-based Backbones from a Scale-wise Perspective for Medical Image Segmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Huimin Huang, Lanfen Lin, Ruofeng Tong, Shiao Xie1, Xianhua Han, Yen-Wei Chen, Yutaro Iwamoto","submitted_at":"2022-07-29T08:55:00Z","abstract_excerpt":"Recently, a variety of vision transformers have been developed as their capability of modeling long-range dependency. In current transformer-based backbones for medical image segmentation, convolutional layers were replaced with pure transformers, or transformers were added to the deepest encoder to learn global context. However, there are mainly two challenges in a scale-wise perspective: (1) intra-scale problem: the existing methods lacked in extracting local-global cues in each scale, which may impact the signal propagation of small objects; (2) inter-scale problem: the existing methods fai"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2207.14552","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/2207.14552/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":"2207.14552","created_at":"2026-07-05T04:44:35.409334+00:00"},{"alias_kind":"arxiv_version","alias_value":"2207.14552v1","created_at":"2026-07-05T04:44:35.409334+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2207.14552","created_at":"2026-07-05T04:44:35.409334+00:00"},{"alias_kind":"pith_short_12","alias_value":"H3K4M6MEBBA4","created_at":"2026-07-05T04:44:35.409334+00:00"},{"alias_kind":"pith_short_16","alias_value":"H3K4M6MEBBA4PNUM","created_at":"2026-07-05T04:44:35.409334+00:00"},{"alias_kind":"pith_short_8","alias_value":"H3K4M6ME","created_at":"2026-07-05T04:44:35.409334+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.30577","citing_title":"APRIL-MedSeg: A Modular Medical Image Segmentation Toolbox Embracing Modern Paradigms","ref_index":92,"is_internal_anchor":false},{"citing_arxiv_id":"2606.30577","citing_title":"APRIL-MedSeg: A Modular Medical Image Segmentation Toolbox Embracing Modern Paradigms","ref_index":97,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/H3K4M6MEBBA4PNUMVDRJMEPQDE","json":"https://pith.science/pith/H3K4M6MEBBA4PNUMVDRJMEPQDE.json","graph_json":"https://pith.science/api/pith-number/H3K4M6MEBBA4PNUMVDRJMEPQDE/graph.json","events_json":"https://pith.science/api/pith-number/H3K4M6MEBBA4PNUMVDRJMEPQDE/events.json","paper":"https://pith.science/paper/H3K4M6ME"},"agent_actions":{"view_html":"https://pith.science/pith/H3K4M6MEBBA4PNUMVDRJMEPQDE","download_json":"https://pith.science/pith/H3K4M6MEBBA4PNUMVDRJMEPQDE.json","view_paper":"https://pith.science/paper/H3K4M6ME","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2207.14552&json=true","fetch_graph":"https://pith.science/api/pith-number/H3K4M6MEBBA4PNUMVDRJMEPQDE/graph.json","fetch_events":"https://pith.science/api/pith-number/H3K4M6MEBBA4PNUMVDRJMEPQDE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/H3K4M6MEBBA4PNUMVDRJMEPQDE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/H3K4M6MEBBA4PNUMVDRJMEPQDE/action/storage_attestation","attest_author":"https://pith.science/pith/H3K4M6MEBBA4PNUMVDRJMEPQDE/action/author_attestation","sign_citation":"https://pith.science/pith/H3K4M6MEBBA4PNUMVDRJMEPQDE/action/citation_signature","submit_replication":"https://pith.science/pith/H3K4M6MEBBA4PNUMVDRJMEPQDE/action/replication_record"}},"created_at":"2026-07-05T04:44:35.409334+00:00","updated_at":"2026-07-05T04:44:35.409334+00:00"}