{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:VOOBLHYCUY3UCYDXXBVBWJ2KNH","short_pith_number":"pith:VOOBLHYC","schema_version":"1.0","canonical_sha256":"ab9c159f02a637416077b86a1b274a69c5e5e5062dae6c36de28cdc31e9a4953","source":{"kind":"arxiv","id":"2504.14075","version":1},"attestation_state":"computed","paper":{"title":"Towards Scale-Aware Low-Light Enhancement via Structure-Guided Transformer Design","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Han Zhou, Jun Chen, Wei Dong, Yan Min","submitted_at":"2025-04-18T20:57:16Z","abstract_excerpt":"Current Low-light Image Enhancement (LLIE) techniques predominantly rely on either direct Low-Light (LL) to Normal-Light (NL) mappings or guidance from semantic features or illumination maps. Nonetheless, the intrinsic ill-posedness of LLIE and the difficulty in retrieving robust semantics from heavily corrupted images hinder their effectiveness in extremely low-light environments. To tackle this challenge, we present SG-LLIE, a new multi-scale CNN-Transformer hybrid framework guided by structure priors. Different from employing pre-trained models for the extraction of semantics or illuminatio"},"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":"2504.14075","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-04-18T20:57:16Z","cross_cats_sorted":[],"title_canon_sha256":"51524e05fdfabddf57c3d4472d41a997b469cf13db3f63084e601c9f2a321c12","abstract_canon_sha256":"3b29a01c034dbfccbe68e6a54e994e4e6b14fb5a082d5b1a4a448911671624fe"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:51:10.543007Z","signature_b64":"VH0KaqXfxB6ZofouZ5XudV+39L7iy2cg/Jxon0HcfKDfEjO8y6kOfecLHYUVyTy5PZxw5JabiZMQBvgfLNu6CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ab9c159f02a637416077b86a1b274a69c5e5e5062dae6c36de28cdc31e9a4953","last_reissued_at":"2026-07-05T10:51:10.542452Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:51:10.542452Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Towards Scale-Aware Low-Light Enhancement via Structure-Guided Transformer Design","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Han Zhou, Jun Chen, Wei Dong, Yan Min","submitted_at":"2025-04-18T20:57:16Z","abstract_excerpt":"Current Low-light Image Enhancement (LLIE) techniques predominantly rely on either direct Low-Light (LL) to Normal-Light (NL) mappings or guidance from semantic features or illumination maps. Nonetheless, the intrinsic ill-posedness of LLIE and the difficulty in retrieving robust semantics from heavily corrupted images hinder their effectiveness in extremely low-light environments. To tackle this challenge, we present SG-LLIE, a new multi-scale CNN-Transformer hybrid framework guided by structure priors. Different from employing pre-trained models for the extraction of semantics or illuminatio"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.14075","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/2504.14075/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":"2504.14075","created_at":"2026-07-05T10:51:10.542517+00:00"},{"alias_kind":"arxiv_version","alias_value":"2504.14075v1","created_at":"2026-07-05T10:51:10.542517+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.14075","created_at":"2026-07-05T10:51:10.542517+00:00"},{"alias_kind":"pith_short_12","alias_value":"VOOBLHYCUY3U","created_at":"2026-07-05T10:51:10.542517+00:00"},{"alias_kind":"pith_short_16","alias_value":"VOOBLHYCUY3UCYDX","created_at":"2026-07-05T10:51:10.542517+00:00"},{"alias_kind":"pith_short_8","alias_value":"VOOBLHYC","created_at":"2026-07-05T10:51:10.542517+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/VOOBLHYCUY3UCYDXXBVBWJ2KNH","json":"https://pith.science/pith/VOOBLHYCUY3UCYDXXBVBWJ2KNH.json","graph_json":"https://pith.science/api/pith-number/VOOBLHYCUY3UCYDXXBVBWJ2KNH/graph.json","events_json":"https://pith.science/api/pith-number/VOOBLHYCUY3UCYDXXBVBWJ2KNH/events.json","paper":"https://pith.science/paper/VOOBLHYC"},"agent_actions":{"view_html":"https://pith.science/pith/VOOBLHYCUY3UCYDXXBVBWJ2KNH","download_json":"https://pith.science/pith/VOOBLHYCUY3UCYDXXBVBWJ2KNH.json","view_paper":"https://pith.science/paper/VOOBLHYC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2504.14075&json=true","fetch_graph":"https://pith.science/api/pith-number/VOOBLHYCUY3UCYDXXBVBWJ2KNH/graph.json","fetch_events":"https://pith.science/api/pith-number/VOOBLHYCUY3UCYDXXBVBWJ2KNH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VOOBLHYCUY3UCYDXXBVBWJ2KNH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VOOBLHYCUY3UCYDXXBVBWJ2KNH/action/storage_attestation","attest_author":"https://pith.science/pith/VOOBLHYCUY3UCYDXXBVBWJ2KNH/action/author_attestation","sign_citation":"https://pith.science/pith/VOOBLHYCUY3UCYDXXBVBWJ2KNH/action/citation_signature","submit_replication":"https://pith.science/pith/VOOBLHYCUY3UCYDXXBVBWJ2KNH/action/replication_record"}},"created_at":"2026-07-05T10:51:10.542517+00:00","updated_at":"2026-07-05T10:51:10.542517+00:00"}