{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:5CPBRG6UWW4G7HEZMBWQDWLT34","short_pith_number":"pith:5CPBRG6U","schema_version":"1.0","canonical_sha256":"e89e189bd4b5b86f9c99606d01d973df07f285bcbc63934b460b1946a8c716b4","source":{"kind":"arxiv","id":"2303.16892","version":1},"attestation_state":"computed","paper":{"title":"Multi-scale Hierarchical Vision Transformer with Cascaded Attention Decoding for Medical Image Segmentation","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Md Mostafijur Rahman, Radu Marculescu","submitted_at":"2023-03-29T17:58:40Z","abstract_excerpt":"Transformers have shown great success in medical image segmentation. However, transformers may exhibit a limited generalization ability due to the underlying single-scale self-attention (SA) mechanism. In this paper, we address this issue by introducing a Multi-scale hiERarchical vIsion Transformer (MERIT) backbone network, which improves the generalizability of the model by computing SA at multiple scales. We also incorporate an attention-based decoder, namely Cascaded Attention Decoding (CASCADE), for further refinement of multi-stage features generated by MERIT. Finally, we introduce an eff"},"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":"2303.16892","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2023-03-29T17:58:40Z","cross_cats_sorted":[],"title_canon_sha256":"0ee4b67c2f845958041b1b124559f37e7426fc78d160fdeaa549483cdd209d52","abstract_canon_sha256":"96b1c901ec42cce365d67fac38963eb40a4eb07169a982d8220a776233c86be1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:56:11.703020Z","signature_b64":"pehd/RtYGo8N/HOBF4Sj+61G+we4zvP0WMCIrRqDp71pYjcom2wj1W0tNvU1ZWwITbFi2ngEWDs2hlYHAFCdCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e89e189bd4b5b86f9c99606d01d973df07f285bcbc63934b460b1946a8c716b4","last_reissued_at":"2026-07-05T05:56:11.702603Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:56:11.702603Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Multi-scale Hierarchical Vision Transformer with Cascaded Attention Decoding for Medical Image Segmentation","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Md Mostafijur Rahman, Radu Marculescu","submitted_at":"2023-03-29T17:58:40Z","abstract_excerpt":"Transformers have shown great success in medical image segmentation. However, transformers may exhibit a limited generalization ability due to the underlying single-scale self-attention (SA) mechanism. In this paper, we address this issue by introducing a Multi-scale hiERarchical vIsion Transformer (MERIT) backbone network, which improves the generalizability of the model by computing SA at multiple scales. We also incorporate an attention-based decoder, namely Cascaded Attention Decoding (CASCADE), for further refinement of multi-stage features generated by MERIT. Finally, we introduce an eff"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.16892","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/2303.16892/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":"2303.16892","created_at":"2026-07-05T05:56:11.702667+00:00"},{"alias_kind":"arxiv_version","alias_value":"2303.16892v1","created_at":"2026-07-05T05:56:11.702667+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.16892","created_at":"2026-07-05T05:56:11.702667+00:00"},{"alias_kind":"pith_short_12","alias_value":"5CPBRG6UWW4G","created_at":"2026-07-05T05:56:11.702667+00:00"},{"alias_kind":"pith_short_16","alias_value":"5CPBRG6UWW4G7HEZ","created_at":"2026-07-05T05:56:11.702667+00:00"},{"alias_kind":"pith_short_8","alias_value":"5CPBRG6U","created_at":"2026-07-05T05:56:11.702667+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2509.05953","citing_title":"Dual Interaction Network with Cross-Image Attention for Medical Image Segmentation","ref_index":41,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5CPBRG6UWW4G7HEZMBWQDWLT34","json":"https://pith.science/pith/5CPBRG6UWW4G7HEZMBWQDWLT34.json","graph_json":"https://pith.science/api/pith-number/5CPBRG6UWW4G7HEZMBWQDWLT34/graph.json","events_json":"https://pith.science/api/pith-number/5CPBRG6UWW4G7HEZMBWQDWLT34/events.json","paper":"https://pith.science/paper/5CPBRG6U"},"agent_actions":{"view_html":"https://pith.science/pith/5CPBRG6UWW4G7HEZMBWQDWLT34","download_json":"https://pith.science/pith/5CPBRG6UWW4G7HEZMBWQDWLT34.json","view_paper":"https://pith.science/paper/5CPBRG6U","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2303.16892&json=true","fetch_graph":"https://pith.science/api/pith-number/5CPBRG6UWW4G7HEZMBWQDWLT34/graph.json","fetch_events":"https://pith.science/api/pith-number/5CPBRG6UWW4G7HEZMBWQDWLT34/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5CPBRG6UWW4G7HEZMBWQDWLT34/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5CPBRG6UWW4G7HEZMBWQDWLT34/action/storage_attestation","attest_author":"https://pith.science/pith/5CPBRG6UWW4G7HEZMBWQDWLT34/action/author_attestation","sign_citation":"https://pith.science/pith/5CPBRG6UWW4G7HEZMBWQDWLT34/action/citation_signature","submit_replication":"https://pith.science/pith/5CPBRG6UWW4G7HEZMBWQDWLT34/action/replication_record"}},"created_at":"2026-07-05T05:56:11.702667+00:00","updated_at":"2026-07-05T05:56:11.702667+00:00"}