{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:CM4EOR6WLBBHNOKQLZEHCISZ5F","short_pith_number":"pith:CM4EOR6W","schema_version":"1.0","canonical_sha256":"13384747d6584276b9505e48712259e96681dd9c1afa5f9b4b65a2ad3e83e295","source":{"kind":"arxiv","id":"2605.25569","version":1},"attestation_state":"computed","paper":{"title":"ControlLight: Towards Controllable, Consistent, and Generalizable Low-Light Enhancement","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jiancheng Huang, Jianzhuang Liu, Jisheng Chu, Shifeng Chen, Xianfang Zeng, Yufeng Yang, Yuqi Peng","submitted_at":"2026-05-25T08:23:56Z","abstract_excerpt":"Existing deep learning-based low-light enhancement methods are typically trained on limited datasets with single enhancement targets, which restricts their generalization ability and controllability in real-world applications. To overcome these limitations, we propose ControlLight, a controllable, consistent, and generalizable framework for low-light enhancement. We first construct a large-scale dataset of real-world degraded images with continuous illumination-strength supervision. To further ensure consistent outputs under different control strengths, we introduce a misalignment-aware weight"},"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":"2605.25569","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-25T08:23:56Z","cross_cats_sorted":[],"title_canon_sha256":"097348117c902a4f68c990c19af15dc99b101246494f33f26d10bdb19fd9fb0d","abstract_canon_sha256":"3b05dc4d174e851ca633254d61fe44e20927427c2116e8f565a407d3981ed544"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-26T02:04:43.538066Z","signature_b64":"GtRRky8yUbk+Foh85WHz4r9FYEBMNzMygmdz0qWy2MZKHzfs+4i+//rqYPYn7ecbBeNIREX2xWZUsCNPHmxMCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"13384747d6584276b9505e48712259e96681dd9c1afa5f9b4b65a2ad3e83e295","last_reissued_at":"2026-05-26T02:04:43.537311Z","signature_status":"signed_v1","first_computed_at":"2026-05-26T02:04:43.537311Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ControlLight: Towards Controllable, Consistent, and Generalizable Low-Light Enhancement","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jiancheng Huang, Jianzhuang Liu, Jisheng Chu, Shifeng Chen, Xianfang Zeng, Yufeng Yang, Yuqi Peng","submitted_at":"2026-05-25T08:23:56Z","abstract_excerpt":"Existing deep learning-based low-light enhancement methods are typically trained on limited datasets with single enhancement targets, which restricts their generalization ability and controllability in real-world applications. To overcome these limitations, we propose ControlLight, a controllable, consistent, and generalizable framework for low-light enhancement. We first construct a large-scale dataset of real-world degraded images with continuous illumination-strength supervision. To further ensure consistent outputs under different control strengths, we introduce a misalignment-aware weight"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.25569","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/2605.25569/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":"2605.25569","created_at":"2026-05-26T02:04:43.537419+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.25569v1","created_at":"2026-05-26T02:04:43.537419+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.25569","created_at":"2026-05-26T02:04:43.537419+00:00"},{"alias_kind":"pith_short_12","alias_value":"CM4EOR6WLBBH","created_at":"2026-05-26T02:04:43.537419+00:00"},{"alias_kind":"pith_short_16","alias_value":"CM4EOR6WLBBHNOKQ","created_at":"2026-05-26T02:04:43.537419+00:00"},{"alias_kind":"pith_short_8","alias_value":"CM4EOR6W","created_at":"2026-05-26T02:04:43.537419+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/CM4EOR6WLBBHNOKQLZEHCISZ5F","json":"https://pith.science/pith/CM4EOR6WLBBHNOKQLZEHCISZ5F.json","graph_json":"https://pith.science/api/pith-number/CM4EOR6WLBBHNOKQLZEHCISZ5F/graph.json","events_json":"https://pith.science/api/pith-number/CM4EOR6WLBBHNOKQLZEHCISZ5F/events.json","paper":"https://pith.science/paper/CM4EOR6W"},"agent_actions":{"view_html":"https://pith.science/pith/CM4EOR6WLBBHNOKQLZEHCISZ5F","download_json":"https://pith.science/pith/CM4EOR6WLBBHNOKQLZEHCISZ5F.json","view_paper":"https://pith.science/paper/CM4EOR6W","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.25569&json=true","fetch_graph":"https://pith.science/api/pith-number/CM4EOR6WLBBHNOKQLZEHCISZ5F/graph.json","fetch_events":"https://pith.science/api/pith-number/CM4EOR6WLBBHNOKQLZEHCISZ5F/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CM4EOR6WLBBHNOKQLZEHCISZ5F/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CM4EOR6WLBBHNOKQLZEHCISZ5F/action/storage_attestation","attest_author":"https://pith.science/pith/CM4EOR6WLBBHNOKQLZEHCISZ5F/action/author_attestation","sign_citation":"https://pith.science/pith/CM4EOR6WLBBHNOKQLZEHCISZ5F/action/citation_signature","submit_replication":"https://pith.science/pith/CM4EOR6WLBBHNOKQLZEHCISZ5F/action/replication_record"}},"created_at":"2026-05-26T02:04:43.537419+00:00","updated_at":"2026-05-26T02:04:43.537419+00:00"}