{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:UFZELBNBLEL6X3ELMNH4SSKLTP","short_pith_number":"pith:UFZELBNB","schema_version":"1.0","canonical_sha256":"a1724585a15917ebec8b634fc9494b9be2bc09a921160cfafa04b430c152bab3","source":{"kind":"arxiv","id":"2504.09621","version":1},"attestation_state":"computed","paper":{"title":"Tokenize Image Patches: Global Context Fusion for Effective Haze Removal in Large Images","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jiuchen Chen, Kaiqi Li, Qizhi Xu, Xinyu Yan","submitted_at":"2025-04-13T15:41:25Z","abstract_excerpt":"Global contextual information and local detail features are essential for haze removal tasks. Deep learning models perform well on small, low-resolution images, but they encounter difficulties with large, high-resolution ones due to GPU memory limitations. As a compromise, they often resort to image slicing or downsampling. The former diminishes global information, while the latter discards high-frequency details. To address these challenges, we propose DehazeXL, a haze removal method that effectively balances global context and local feature extraction, enabling end-to-end modeling of large i"},"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":"2504.09621","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-04-13T15:41:25Z","cross_cats_sorted":[],"title_canon_sha256":"78ed0c5a4a988a676d13584cf316e2a5e7ffb31c945978228e186c6574f765d5","abstract_canon_sha256":"c61626c50d3a6954a58772f9ea9662229a6ae83956a459dea79bedc7f38a0c84"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:48:40.169020Z","signature_b64":"wGIzHd3hfi25q0CFE0RORapwlmxSp8crxp7MY6e3ry7LWMGCgDJI+LkwbTCrgI0z9+73osz7F3VTyo97rDTjBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a1724585a15917ebec8b634fc9494b9be2bc09a921160cfafa04b430c152bab3","last_reissued_at":"2026-07-05T10:48:40.168579Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:48:40.168579Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Tokenize Image Patches: Global Context Fusion for Effective Haze Removal in Large Images","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jiuchen Chen, Kaiqi Li, Qizhi Xu, Xinyu Yan","submitted_at":"2025-04-13T15:41:25Z","abstract_excerpt":"Global contextual information and local detail features are essential for haze removal tasks. Deep learning models perform well on small, low-resolution images, but they encounter difficulties with large, high-resolution ones due to GPU memory limitations. As a compromise, they often resort to image slicing or downsampling. The former diminishes global information, while the latter discards high-frequency details. To address these challenges, we propose DehazeXL, a haze removal method that effectively balances global context and local feature extraction, enabling end-to-end modeling of large i"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.09621","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/2504.09621/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":"2504.09621","created_at":"2026-07-05T10:48:40.168634+00:00"},{"alias_kind":"arxiv_version","alias_value":"2504.09621v1","created_at":"2026-07-05T10:48:40.168634+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.09621","created_at":"2026-07-05T10:48:40.168634+00:00"},{"alias_kind":"pith_short_12","alias_value":"UFZELBNBLEL6","created_at":"2026-07-05T10:48:40.168634+00:00"},{"alias_kind":"pith_short_16","alias_value":"UFZELBNBLEL6X3EL","created_at":"2026-07-05T10:48:40.168634+00:00"},{"alias_kind":"pith_short_8","alias_value":"UFZELBNB","created_at":"2026-07-05T10:48:40.168634+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.14010","citing_title":"UHD Image Dehazing via anDehazeFormer with Atmospheric-aware KV Cache","ref_index":6,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/UFZELBNBLEL6X3ELMNH4SSKLTP","json":"https://pith.science/pith/UFZELBNBLEL6X3ELMNH4SSKLTP.json","graph_json":"https://pith.science/api/pith-number/UFZELBNBLEL6X3ELMNH4SSKLTP/graph.json","events_json":"https://pith.science/api/pith-number/UFZELBNBLEL6X3ELMNH4SSKLTP/events.json","paper":"https://pith.science/paper/UFZELBNB"},"agent_actions":{"view_html":"https://pith.science/pith/UFZELBNBLEL6X3ELMNH4SSKLTP","download_json":"https://pith.science/pith/UFZELBNBLEL6X3ELMNH4SSKLTP.json","view_paper":"https://pith.science/paper/UFZELBNB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2504.09621&json=true","fetch_graph":"https://pith.science/api/pith-number/UFZELBNBLEL6X3ELMNH4SSKLTP/graph.json","fetch_events":"https://pith.science/api/pith-number/UFZELBNBLEL6X3ELMNH4SSKLTP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UFZELBNBLEL6X3ELMNH4SSKLTP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UFZELBNBLEL6X3ELMNH4SSKLTP/action/storage_attestation","attest_author":"https://pith.science/pith/UFZELBNBLEL6X3ELMNH4SSKLTP/action/author_attestation","sign_citation":"https://pith.science/pith/UFZELBNBLEL6X3ELMNH4SSKLTP/action/citation_signature","submit_replication":"https://pith.science/pith/UFZELBNBLEL6X3ELMNH4SSKLTP/action/replication_record"}},"created_at":"2026-07-05T10:48:40.168634+00:00","updated_at":"2026-07-05T10:48:40.168634+00:00"}