{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:LLFYXIIKOM45P3HC3IEP6HILI4","short_pith_number":"pith:LLFYXIIK","schema_version":"1.0","canonical_sha256":"5acb8ba10a7339d7ece2da08ff1d0b471cc65d799704169b27261f01732d2648","source":{"kind":"arxiv","id":"2304.14610","version":2},"attestation_state":"computed","paper":{"title":"ALL-E: Aesthetics-guided Low-light Image Enhancement","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dong Liang, Ling Li, Sheng-Jun Huang, Songcan Chen, Yuanhang Gao","submitted_at":"2023-04-28T03:34:10Z","abstract_excerpt":"Evaluating the performance of low-light image enhancement (LLE) is highly subjective, thus making integrating human preferences into image enhancement a necessity. Existing methods fail to consider this and present a series of potentially valid heuristic criteria for training enhancement models. In this paper, we propose a new paradigm, i.e., aesthetics-guided low-light image enhancement (ALL-E), which introduces aesthetic preferences to LLE and motivates training in a reinforcement learning framework with an aesthetic reward. Each pixel, functioning as an agent, refines itself by recursive ac"},"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":"2304.14610","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-04-28T03:34:10Z","cross_cats_sorted":[],"title_canon_sha256":"702b99348bdfba9e6201468643f4b530babbcea14ff6386fbf244151cb34cc50","abstract_canon_sha256":"6023f7609b74ea7293a8b973b1afbd5ba927b1077c0ed798b7a81054c662ad4e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:06:19.628778Z","signature_b64":"WU/P5/cbRRGgY5glcM6dJqYJ0gEYGJ20URTBxhkaKvJ4e8TS1RflIbbdg5Stw+NwJgsMlUpfUB8oCjr62TzBAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5acb8ba10a7339d7ece2da08ff1d0b471cc65d799704169b27261f01732d2648","last_reissued_at":"2026-07-05T06:06:19.628288Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:06:19.628288Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ALL-E: Aesthetics-guided Low-light Image Enhancement","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dong Liang, Ling Li, Sheng-Jun Huang, Songcan Chen, Yuanhang Gao","submitted_at":"2023-04-28T03:34:10Z","abstract_excerpt":"Evaluating the performance of low-light image enhancement (LLE) is highly subjective, thus making integrating human preferences into image enhancement a necessity. Existing methods fail to consider this and present a series of potentially valid heuristic criteria for training enhancement models. In this paper, we propose a new paradigm, i.e., aesthetics-guided low-light image enhancement (ALL-E), which introduces aesthetic preferences to LLE and motivates training in a reinforcement learning framework with an aesthetic reward. Each pixel, functioning as an agent, refines itself by recursive ac"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.14610","kind":"arxiv","version":2},"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/2304.14610/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":"2304.14610","created_at":"2026-07-05T06:06:19.628356+00:00"},{"alias_kind":"arxiv_version","alias_value":"2304.14610v2","created_at":"2026-07-05T06:06:19.628356+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.14610","created_at":"2026-07-05T06:06:19.628356+00:00"},{"alias_kind":"pith_short_12","alias_value":"LLFYXIIKOM45","created_at":"2026-07-05T06:06:19.628356+00:00"},{"alias_kind":"pith_short_16","alias_value":"LLFYXIIKOM45P3HC","created_at":"2026-07-05T06:06:19.628356+00:00"},{"alias_kind":"pith_short_8","alias_value":"LLFYXIIK","created_at":"2026-07-05T06:06:19.628356+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.22216","citing_title":"ReF-LLE: Personalized Low-Light Enhancement via Reference-Guided Deep Reinforcement Learning","ref_index":13,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LLFYXIIKOM45P3HC3IEP6HILI4","json":"https://pith.science/pith/LLFYXIIKOM45P3HC3IEP6HILI4.json","graph_json":"https://pith.science/api/pith-number/LLFYXIIKOM45P3HC3IEP6HILI4/graph.json","events_json":"https://pith.science/api/pith-number/LLFYXIIKOM45P3HC3IEP6HILI4/events.json","paper":"https://pith.science/paper/LLFYXIIK"},"agent_actions":{"view_html":"https://pith.science/pith/LLFYXIIKOM45P3HC3IEP6HILI4","download_json":"https://pith.science/pith/LLFYXIIKOM45P3HC3IEP6HILI4.json","view_paper":"https://pith.science/paper/LLFYXIIK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2304.14610&json=true","fetch_graph":"https://pith.science/api/pith-number/LLFYXIIKOM45P3HC3IEP6HILI4/graph.json","fetch_events":"https://pith.science/api/pith-number/LLFYXIIKOM45P3HC3IEP6HILI4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LLFYXIIKOM45P3HC3IEP6HILI4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LLFYXIIKOM45P3HC3IEP6HILI4/action/storage_attestation","attest_author":"https://pith.science/pith/LLFYXIIKOM45P3HC3IEP6HILI4/action/author_attestation","sign_citation":"https://pith.science/pith/LLFYXIIKOM45P3HC3IEP6HILI4/action/citation_signature","submit_replication":"https://pith.science/pith/LLFYXIIKOM45P3HC3IEP6HILI4/action/replication_record"}},"created_at":"2026-07-05T06:06:19.628356+00:00","updated_at":"2026-07-05T06:06:19.628356+00:00"}