{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:DS7CQ4VVXTR3FXVX3YPIQWCPXY","short_pith_number":"pith:DS7CQ4VV","schema_version":"1.0","canonical_sha256":"1cbe2872b5bce3b2deb7de1e88584fbe1a00738176670d64c5bf25724f3c12b7","source":{"kind":"arxiv","id":"2411.10951","version":2},"attestation_state":"computed","paper":{"title":"TSFormer: A Robust Framework for Efficient UHD Image Restoration","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chen Wu, Xin Su, Zhuoran Zheng","submitted_at":"2024-11-17T03:34:27Z","abstract_excerpt":"Ultra-high-definition (UHD) image restoration is vital for applications demanding exceptional visual fidelity, yet existing methods often face a trade-off between restoration quality and efficiency, limiting their practical deployment. In this paper, we propose TSFormer, an all-in-one framework that integrates \\textbf{T}rusted learning with \\textbf{S}parsification to boost both generalization capability and computational efficiency in UHD image restoration. The key is that only a small amount of token movement is allowed within the model. To efficiently filter tokens, we use Min-$p$ with rando"},"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":"2411.10951","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-11-17T03:34:27Z","cross_cats_sorted":[],"title_canon_sha256":"3ee7c8a768c33a4cbdb0c8139a15a4fc7962507c8ea4364e2c0dceeedf52b5e0","abstract_canon_sha256":"f90522c3013b10e1c3486ece9afe55d74ec74542de7dcd962415dbcae4bdc238"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:37:58.556852Z","signature_b64":"s8t5UxMy4C/k9kojzGzDjhZ9s/dtJQPCXlH22aDWig/UzTpt3bGFZX7OACs6X+IsG5YFt8gn83Wu/y0CoQ7HAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1cbe2872b5bce3b2deb7de1e88584fbe1a00738176670d64c5bf25724f3c12b7","last_reissued_at":"2026-07-05T09:37:58.556359Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:37:58.556359Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"TSFormer: A Robust Framework for Efficient UHD Image Restoration","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chen Wu, Xin Su, Zhuoran Zheng","submitted_at":"2024-11-17T03:34:27Z","abstract_excerpt":"Ultra-high-definition (UHD) image restoration is vital for applications demanding exceptional visual fidelity, yet existing methods often face a trade-off between restoration quality and efficiency, limiting their practical deployment. In this paper, we propose TSFormer, an all-in-one framework that integrates \\textbf{T}rusted learning with \\textbf{S}parsification to boost both generalization capability and computational efficiency in UHD image restoration. The key is that only a small amount of token movement is allowed within the model. To efficiently filter tokens, we use Min-$p$ with rando"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.10951","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/2411.10951/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":"2411.10951","created_at":"2026-07-05T09:37:58.556415+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.10951v2","created_at":"2026-07-05T09:37:58.556415+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.10951","created_at":"2026-07-05T09:37:58.556415+00:00"},{"alias_kind":"pith_short_12","alias_value":"DS7CQ4VVXTR3","created_at":"2026-07-05T09:37:58.556415+00:00"},{"alias_kind":"pith_short_16","alias_value":"DS7CQ4VVXTR3FXVX","created_at":"2026-07-05T09:37:58.556415+00:00"},{"alias_kind":"pith_short_8","alias_value":"DS7CQ4VV","created_at":"2026-07-05T09:37:58.556415+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.16161","citing_title":"Deep Learning-Driven Ultra-High-Definition Image Restoration: A Survey","ref_index":51,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DS7CQ4VVXTR3FXVX3YPIQWCPXY","json":"https://pith.science/pith/DS7CQ4VVXTR3FXVX3YPIQWCPXY.json","graph_json":"https://pith.science/api/pith-number/DS7CQ4VVXTR3FXVX3YPIQWCPXY/graph.json","events_json":"https://pith.science/api/pith-number/DS7CQ4VVXTR3FXVX3YPIQWCPXY/events.json","paper":"https://pith.science/paper/DS7CQ4VV"},"agent_actions":{"view_html":"https://pith.science/pith/DS7CQ4VVXTR3FXVX3YPIQWCPXY","download_json":"https://pith.science/pith/DS7CQ4VVXTR3FXVX3YPIQWCPXY.json","view_paper":"https://pith.science/paper/DS7CQ4VV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.10951&json=true","fetch_graph":"https://pith.science/api/pith-number/DS7CQ4VVXTR3FXVX3YPIQWCPXY/graph.json","fetch_events":"https://pith.science/api/pith-number/DS7CQ4VVXTR3FXVX3YPIQWCPXY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DS7CQ4VVXTR3FXVX3YPIQWCPXY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DS7CQ4VVXTR3FXVX3YPIQWCPXY/action/storage_attestation","attest_author":"https://pith.science/pith/DS7CQ4VVXTR3FXVX3YPIQWCPXY/action/author_attestation","sign_citation":"https://pith.science/pith/DS7CQ4VVXTR3FXVX3YPIQWCPXY/action/citation_signature","submit_replication":"https://pith.science/pith/DS7CQ4VVXTR3FXVX3YPIQWCPXY/action/replication_record"}},"created_at":"2026-07-05T09:37:58.556415+00:00","updated_at":"2026-07-05T09:37:58.556415+00:00"}