{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:2R423TZICMGUFCTPYAKJ7VCNTC","short_pith_number":"pith:2R423TZI","schema_version":"1.0","canonical_sha256":"d479adcf28130d428a6fc0149fd44d989db7b982bfa77505170a8be0978c2391","source":{"kind":"arxiv","id":"2505.14010","version":1},"attestation_state":"computed","paper":{"title":"UHD Image Dehazing via anDehazeFormer with Atmospheric-aware KV Cache","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chen Wu, Dianjie Lu, Guijuan Zhang, Pengwen Dai, Pu Wang, Yeying Jin, Youshan Zhang, Zhuoran Zheng","submitted_at":"2025-05-20T07:04:34Z","abstract_excerpt":"In this paper, we propose an efficient visual transformer framework for ultra-high-definition (UHD) image dehazing that addresses the key challenges of slow training speed and high memory consumption for existing methods. Our approach introduces two key innovations: 1) an \\textbf{a}daptive \\textbf{n}ormalization mechanism inspired by the nGPT architecture that enables ultra-fast and stable training with a network with a restricted range of parameter expressions; and 2) we devise an atmospheric scattering-aware KV caching mechanism that dynamically optimizes feature preservation based on the ph"},"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":"2505.14010","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-20T07:04:34Z","cross_cats_sorted":[],"title_canon_sha256":"41bb907191764a423d4432081972994db7fdfd573050d95807a28fba0c85a0a7","abstract_canon_sha256":"6f6ab3642f9b46f42b30cad3d4f1d678fc3b063e4f4361641cb81e93ca05855b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:05:54.685898Z","signature_b64":"XIAzkJn+YXlY6xoHysgTmfgD3tGlySF6V8k/+PlYgVog2hC8wQLu+owXJL97UlYLaujUeJ6VcgoxgoilVgj9AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d479adcf28130d428a6fc0149fd44d989db7b982bfa77505170a8be0978c2391","last_reissued_at":"2026-07-05T11:05:54.685525Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:05:54.685525Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"UHD Image Dehazing via anDehazeFormer with Atmospheric-aware KV Cache","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chen Wu, Dianjie Lu, Guijuan Zhang, Pengwen Dai, Pu Wang, Yeying Jin, Youshan Zhang, Zhuoran Zheng","submitted_at":"2025-05-20T07:04:34Z","abstract_excerpt":"In this paper, we propose an efficient visual transformer framework for ultra-high-definition (UHD) image dehazing that addresses the key challenges of slow training speed and high memory consumption for existing methods. Our approach introduces two key innovations: 1) an \\textbf{a}daptive \\textbf{n}ormalization mechanism inspired by the nGPT architecture that enables ultra-fast and stable training with a network with a restricted range of parameter expressions; and 2) we devise an atmospheric scattering-aware KV caching mechanism that dynamically optimizes feature preservation based on the ph"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.14010","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/2505.14010/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":"2505.14010","created_at":"2026-07-05T11:05:54.685578+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.14010v1","created_at":"2026-07-05T11:05:54.685578+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.14010","created_at":"2026-07-05T11:05:54.685578+00:00"},{"alias_kind":"pith_short_12","alias_value":"2R423TZICMGU","created_at":"2026-07-05T11:05:54.685578+00:00"},{"alias_kind":"pith_short_16","alias_value":"2R423TZICMGUFCTP","created_at":"2026-07-05T11:05:54.685578+00:00"},{"alias_kind":"pith_short_8","alias_value":"2R423TZI","created_at":"2026-07-05T11:05:54.685578+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/2R423TZICMGUFCTPYAKJ7VCNTC","json":"https://pith.science/pith/2R423TZICMGUFCTPYAKJ7VCNTC.json","graph_json":"https://pith.science/api/pith-number/2R423TZICMGUFCTPYAKJ7VCNTC/graph.json","events_json":"https://pith.science/api/pith-number/2R423TZICMGUFCTPYAKJ7VCNTC/events.json","paper":"https://pith.science/paper/2R423TZI"},"agent_actions":{"view_html":"https://pith.science/pith/2R423TZICMGUFCTPYAKJ7VCNTC","download_json":"https://pith.science/pith/2R423TZICMGUFCTPYAKJ7VCNTC.json","view_paper":"https://pith.science/paper/2R423TZI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.14010&json=true","fetch_graph":"https://pith.science/api/pith-number/2R423TZICMGUFCTPYAKJ7VCNTC/graph.json","fetch_events":"https://pith.science/api/pith-number/2R423TZICMGUFCTPYAKJ7VCNTC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2R423TZICMGUFCTPYAKJ7VCNTC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2R423TZICMGUFCTPYAKJ7VCNTC/action/storage_attestation","attest_author":"https://pith.science/pith/2R423TZICMGUFCTPYAKJ7VCNTC/action/author_attestation","sign_citation":"https://pith.science/pith/2R423TZICMGUFCTPYAKJ7VCNTC/action/citation_signature","submit_replication":"https://pith.science/pith/2R423TZICMGUFCTPYAKJ7VCNTC/action/replication_record"}},"created_at":"2026-07-05T11:05:54.685578+00:00","updated_at":"2026-07-05T11:05:54.685578+00:00"}