{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:ZF52M5T2DR4GGPVGZTR76X6L6M","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"cb97442cd5ea8406f45d81cefbea00cf50c1a3d1d54b9f209d008748f34751e5","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-05-13T09:41:09Z","title_canon_sha256":"8e239bc5e7bac560be607bc05357024aecbb1a540eeb5265d4d2e039656531ee"},"schema_version":"1.0","source":{"id":"2605.13258","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.13258","created_at":"2026-05-18T02:44:49Z"},{"alias_kind":"arxiv_version","alias_value":"2605.13258v1","created_at":"2026-05-18T02:44:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.13258","created_at":"2026-05-18T02:44:49Z"},{"alias_kind":"pith_short_12","alias_value":"ZF52M5T2DR4G","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"ZF52M5T2DR4GGPVG","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"ZF52M5T2","created_at":"2026-05-18T12:33:37Z"}],"graph_snapshots":[{"event_id":"sha256:56995cb3928aba96ea379290093f06f3dffcc2e0fc1a4adb3942ce59c65aff8e","target":"graph","created_at":"2026-05-18T02:44:49Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"With these strategies, our proposed method successfully ranks the 1st place in the challenge."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That the performance gain is primarily attributable to the three listed changes rather than differences in training schedule, optimizer settings, or undisclosed data filtering that were not ablated."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"X-Restormer++ wins the UG2+ all-weather image restoration challenge by combining adaptive scaling, a gradient-guided edge-aware loss, and expanded training data on top of the X-Restormer baseline."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"X-Restormer++ wins first place in all-weather image restoration by adding adaptive scaling, edge-aware loss, and extra training pairs"}],"snapshot_sha256":"dc792598c1dbfbe0368f7cd66bf5461579d06fe73a3ba131d27760116243951b"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"paper":{"abstract_excerpt":"In this work, we present our winning solution for the 8th UG2+ Challenge (CVPR 2026) Track 1: Image Restoration under All-weather Conditions. Our method is built upon the strong baseline framework X-Restormer, which effectively captures both channel-wise global dependencies and spatially-local structural information through its dual-attention design (Multi-DConv Head Transposed Attention and Overlapping Cross-Attention). To further boost the restoration performance, we propose several key improvements. First, we integrate the spatially-adaptive input scaling mechanism from Restormer-Plus to dy","authors_text":"Fengjie Zhu, Leilei Cao, Yingfang Zhu, Youwei Pan","cross_cats":["cs.AI"],"headline":"X-Restormer++ wins first place in all-weather image restoration by adding adaptive scaling, edge-aware loss, and extra training pairs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-05-13T09:41:09Z","title":"X-Restormer++: 1st Place Solution for the UG2+ CVPR 2026 All-Weather Restoration Challenge"},"references":{"count":9,"internal_anchors":0,"resolved_work":9,"sample":[{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":1,"title":"A comparative study of image restoration networks for gen eral backbone network design","work_id":"66c039c6-2486-4d30-98ef-2b3776a085e8","year":2023},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":2,"title":"Activating more pixels in image super-resolution transformer","work_id":"bd178b7c-857e-470e-b847-a70a3806d9a2","year":null},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":3,"title":"Weatherbench: A real-world bench- mark dataset for all-in-one adverse weather image restoration","work_id":"45f08c4f-8f16-4a7d-9f9c-765a36fda214","year":2025},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":4,"title":"Foundir: Unleashing million-scale training data to ad- vance foundation models for image restoration","work_id":"ba18d76b-d4f1-4b9e-8ab9-cf9afe212b89","year":2025},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":5,"title":"Diff- bir: Toward blind image restoration with generative diffusion prior","work_id":"7e0bed32-0c16-415d-a35b-1811e43367d4","year":null}],"snapshot_sha256":"6886c2d9e4ba11b1612e65e35e49b2d8b85dc71724ef16b6b9e15c3ecf3dcdcf"},"source":{"id":"2605.13258","kind":"arxiv","version":1},"verdict":{"created_at":"2026-05-14T19:58:22.540307Z","id":"1ef25422-d245-4c0f-95d7-d3705014a6f6","model_set":{"reader":"grok-4.3"},"one_line_summary":"X-Restormer++ wins the UG2+ all-weather image restoration challenge by combining adaptive scaling, a gradient-guided edge-aware loss, and expanded training data on top of the X-Restormer baseline.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"X-Restormer++ wins first place in all-weather image restoration by adding adaptive scaling, edge-aware loss, and extra training pairs","strongest_claim":"With these strategies, our proposed method successfully ranks the 1st place in the challenge.","weakest_assumption":"That the performance gain is primarily attributable to the three listed changes rather than differences in training schedule, optimizer settings, or undisclosed data filtering that were not ablated."}},"verdict_id":"1ef25422-d245-4c0f-95d7-d3705014a6f6"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:f8a961a4daa402e2f6a8c98018fe3f152bf34fc59284523f7bebc619595dda2e","target":"record","created_at":"2026-05-18T02:44:49Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"cb97442cd5ea8406f45d81cefbea00cf50c1a3d1d54b9f209d008748f34751e5","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-05-13T09:41:09Z","title_canon_sha256":"8e239bc5e7bac560be607bc05357024aecbb1a540eeb5265d4d2e039656531ee"},"schema_version":"1.0","source":{"id":"2605.13258","kind":"arxiv","version":1}},"canonical_sha256":"c97ba6767a1c78633ea6cce3ff5fcbf32967359e0dba80f42c5c287534c9157f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c97ba6767a1c78633ea6cce3ff5fcbf32967359e0dba80f42c5c287534c9157f","first_computed_at":"2026-05-18T02:44:49.374009Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T02:44:49.374009Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"+mL9CjBPW21NZVLtGpCi/xcIjhoUhdBvYNwM2y4NwoP+9Td9XUXQPbvS9zTcp5qXqnzlt5PeeLOwRUdAnC/lAw==","signature_status":"signed_v1","signed_at":"2026-05-18T02:44:49.374441Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.13258","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f8a961a4daa402e2f6a8c98018fe3f152bf34fc59284523f7bebc619595dda2e","sha256:56995cb3928aba96ea379290093f06f3dffcc2e0fc1a4adb3942ce59c65aff8e"],"state_sha256":"0d1b1caf2adf65cfe411c2b6a505004ccd7a23b79c2a563a4a71b5b17f5580e5"}