{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:TGYCQ5DMO4BRN35MNY4RB3RAM3","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":"f178f9fb0ff55b4f1046645dcf32636a6bdf1ddf78d2cc272f8cc9048ad28925","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-11T12:13:13Z","title_canon_sha256":"1b1ba165d5f8eed9576cb4835aec70e3c3ee7550e2cbc541842ee228376ee8eb"},"schema_version":"1.0","source":{"id":"2605.12556","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.12556","created_at":"2026-05-18T03:10:02Z"},{"alias_kind":"arxiv_version","alias_value":"2605.12556v1","created_at":"2026-05-18T03:10:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.12556","created_at":"2026-05-18T03:10:02Z"},{"alias_kind":"pith_short_12","alias_value":"TGYCQ5DMO4BR","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"TGYCQ5DMO4BRN35M","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"TGYCQ5DM","created_at":"2026-05-18T12:33:37Z"}],"graph_snapshots":[{"event_id":"sha256:6cf0ad5ce8a356edb99fcfd3d510fdb3cc31f403fe2dbd8874104b593a857cb6","target":"graph","created_at":"2026-05-18T03:10:02Z","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":"Evaluations on the LOL, SID, SMID, and SDSD benchmarks demonstrate overall improvements over Retinexformer and recent state-of-the-art methods."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That depth cues, luminance priors, and semantic features extracted at multiple scales will remain reliable and provide net positive guidance without introducing new artifacts or requiring perfectly aligned auxiliary data."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"M2Retinexformer improves low-light images by progressively refining RGB data with depth, luminance, and semantic modalities through cross-attention and adaptive gating, showing gains on LOL, SID, SMID, and SDSD benchmarks."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"M2Retinexformer improves low-light image enhancement by fusing depth cues, luminance priors, and semantic features into Retinexformer through multi-scale cross-attention."}],"snapshot_sha256":"385473aefdb93c434e7e1dc0544b2511a89c9ee5ece77b1c5eb536e58591fc9b"},"formal_canon":{"evidence_count":2,"snapshot_sha256":"5dc9b458a3c4d73a67592194494f8503f53d9bd1bafe395bea5dc98989813e88"},"paper":{"abstract_excerpt":"Low-light image enhancement is challenging due to complex degradations, including amplified noise, artifacts, and color distortion. While Retinex-based deep learning methods have achieved promising results, they primarily rely on single-modality RGB information. We propose M2Retinexformer (Multi-Modal Retinexformer), a novel framework that extends Retinexformer by incorporating depth cues, luminance priors, and semantic features within a progressive refinement pipeline. Depth provides geometric context that is invariant to lighting variations, while luminance and semantic features offer explic","authors_text":"Hicham G. Elmongui, Marwan Torki, Youssef Aboelwafa","cross_cats":[],"headline":"M2Retinexformer improves low-light image enhancement by fusing depth cues, luminance priors, and semantic features into Retinexformer through multi-scale cross-attention.","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-11T12:13:13Z","title":"M2Retinexformer: Multi-Modal Retinexformer for Low-Light Image Enhancement"},"references":{"count":37,"internal_anchors":3,"resolved_work":37,"sample":[{"cited_arxiv_id":"2605.12556","doi":"","is_internal_anchor":true,"ref_index":1,"title":"M2Retinexformer: Multi-Modal Retinexformer for Low-Light Image Enhancement","work_id":"14f8cc97-37c1-410d-b13c-80932d7fa977","year":2026},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":2,"title":"Classical ap- proaches such as [8, 9, 10] rely on hand-crafted priors and assume that low-light images are corruption-free, leading to noise amplification and color distortion","work_id":"e0222fdd-7415-4a30-ad41-2e0a29c5da3f","year":null},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":3,"title":"3, we present the overall architecture of M2Retinexformer, which extends Retinexformer by incor- porating complementary multi-modal cues","work_id":"3604e6bb-3af0-409a-9fb4-60b44e82442e","year":null},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":4,"title":"EXPERIMENTS 4.1. Experimental Setup and Implementation Details Datasets.We evaluated M2Retinexformer on seven low- light benchmarks: LOL-v1 [3], LOL-v2 Real/Synthetic [29], SID [30], SMID [31], and SD","work_id":"86f4d1cc-10fd-488b-ac23-ae8070483b7b","year":null},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":5,"title":"Our key insight is that depth provides geometric context that is robust to il- lumination changes, while luminance and semantic features provide content-aware guidance","work_id":"1bfc4a58-7407-4710-adb9-63bf85013bd5","year":null}],"snapshot_sha256":"909a9f17aa6856cf87eca8b47aaa3b0a8a85198070261d6f0c299f0292b7e612"},"source":{"id":"2605.12556","kind":"arxiv","version":1},"verdict":{"created_at":"2026-05-14T21:28:28.673488Z","id":"0180f31b-e3bb-4a77-bf95-13e456a10824","model_set":{"reader":"grok-4.3"},"one_line_summary":"M2Retinexformer improves low-light images by progressively refining RGB data with depth, luminance, and semantic modalities through cross-attention and adaptive gating, showing gains on LOL, SID, SMID, and SDSD benchmarks.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"M2Retinexformer improves low-light image enhancement by fusing depth cues, luminance priors, and semantic features into Retinexformer through multi-scale cross-attention.","strongest_claim":"Evaluations on the LOL, SID, SMID, and SDSD benchmarks demonstrate overall improvements over Retinexformer and recent state-of-the-art methods.","weakest_assumption":"That depth cues, luminance priors, and semantic features extracted at multiple scales will remain reliable and provide net positive guidance without introducing new artifacts or requiring perfectly aligned auxiliary data."}},"verdict_id":"0180f31b-e3bb-4a77-bf95-13e456a10824"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:eb227988bf94f6c9cfef49f6c2071e1337a7dfaace0c76f8322ebb47ae400879","target":"record","created_at":"2026-05-18T03:10:02Z","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":"f178f9fb0ff55b4f1046645dcf32636a6bdf1ddf78d2cc272f8cc9048ad28925","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-11T12:13:13Z","title_canon_sha256":"1b1ba165d5f8eed9576cb4835aec70e3c3ee7550e2cbc541842ee228376ee8eb"},"schema_version":"1.0","source":{"id":"2605.12556","kind":"arxiv","version":1}},"canonical_sha256":"99b028746c770316efac6e3910ee2066f32018b44f1eec9d0239992a27c5dc6a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"99b028746c770316efac6e3910ee2066f32018b44f1eec9d0239992a27c5dc6a","first_computed_at":"2026-05-18T03:10:02.057752Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T03:10:02.057752Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"JoeGcHt9c5nlarRMZ7WPPWcOewhZywvOKoujxF+W3+9DyBoqXmXC7qTRZGXkf1QnQZE52yTM/75E+idnOUwMBA==","signature_status":"signed_v1","signed_at":"2026-05-18T03:10:02.058409Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.12556","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:eb227988bf94f6c9cfef49f6c2071e1337a7dfaace0c76f8322ebb47ae400879","sha256:6cf0ad5ce8a356edb99fcfd3d510fdb3cc31f403fe2dbd8874104b593a857cb6"],"state_sha256":"b3e5512734b681c1943e3e41aab37d8e3bc3cbe882634b39dd251b451b3b4e45"}