{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:BUWFLXF72SEWUCOBOES7Z4ANOK","short_pith_number":"pith:BUWFLXF7","schema_version":"1.0","canonical_sha256":"0d2c55dcbfd4896a09c17125fcf00d72b3e04de23e26402541e9e689e4f4c4eb","source":{"kind":"arxiv","id":"2303.04291","version":2},"attestation_state":"computed","paper":{"title":"Diffusion in the Dark: A Diffusion Model for Low-Light Text Recognition","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"eess.IV","authors_text":"Alexander W. Bergman, Cindy M. Nguyen, Eric R. Chan, Gordon Wetzstein","submitted_at":"2023-03-07T23:52:51Z","abstract_excerpt":"Capturing images is a key part of automation for high-level tasks such as scene text recognition. Low-light conditions pose a challenge for high-level perception stacks, which are often optimized on well-lit, artifact-free images. Reconstruction methods for low-light images can produce well-lit counterparts, but typically at the cost of high-frequency details critical for downstream tasks. We propose Diffusion in the Dark (DiD), a diffusion model for low-light image reconstruction for text recognition. DiD provides qualitatively competitive reconstructions with that of state-of-the-art (SOTA),"},"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":"2303.04291","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.IV","submitted_at":"2023-03-07T23:52:51Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"6ce4297bde916efb220dbd0aca8b25ffdd9d87925959f5a7bb72248c27083689","abstract_canon_sha256":"e9f18842ac108b089c3852841aa6a2f88946749f80af2876ad6eff46ab61c84b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:07:07.849490Z","signature_b64":"jWRTeTjGT9naC0rNgtjrNWu0yzRAYJJLEdLWBkXFrI8mHJvtZYuJi4I90F2DugmmHK52vUs4jZsLi5gU9nfjBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0d2c55dcbfd4896a09c17125fcf00d72b3e04de23e26402541e9e689e4f4c4eb","last_reissued_at":"2026-07-05T07:07:07.849011Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:07:07.849011Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Diffusion in the Dark: A Diffusion Model for Low-Light Text Recognition","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"eess.IV","authors_text":"Alexander W. Bergman, Cindy M. Nguyen, Eric R. Chan, Gordon Wetzstein","submitted_at":"2023-03-07T23:52:51Z","abstract_excerpt":"Capturing images is a key part of automation for high-level tasks such as scene text recognition. Low-light conditions pose a challenge for high-level perception stacks, which are often optimized on well-lit, artifact-free images. Reconstruction methods for low-light images can produce well-lit counterparts, but typically at the cost of high-frequency details critical for downstream tasks. We propose Diffusion in the Dark (DiD), a diffusion model for low-light image reconstruction for text recognition. DiD provides qualitatively competitive reconstructions with that of state-of-the-art (SOTA),"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.04291","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/2303.04291/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":"2303.04291","created_at":"2026-07-05T07:07:07.849062+00:00"},{"alias_kind":"arxiv_version","alias_value":"2303.04291v2","created_at":"2026-07-05T07:07:07.849062+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.04291","created_at":"2026-07-05T07:07:07.849062+00:00"},{"alias_kind":"pith_short_12","alias_value":"BUWFLXF72SEW","created_at":"2026-07-05T07:07:07.849062+00:00"},{"alias_kind":"pith_short_16","alias_value":"BUWFLXF72SEWUCOB","created_at":"2026-07-05T07:07:07.849062+00:00"},{"alias_kind":"pith_short_8","alias_value":"BUWFLXF7","created_at":"2026-07-05T07:07:07.849062+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2310.19512","citing_title":"VideoCrafter1: Open Diffusion Models for High-Quality Video Generation","ref_index":37,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BUWFLXF72SEWUCOBOES7Z4ANOK","json":"https://pith.science/pith/BUWFLXF72SEWUCOBOES7Z4ANOK.json","graph_json":"https://pith.science/api/pith-number/BUWFLXF72SEWUCOBOES7Z4ANOK/graph.json","events_json":"https://pith.science/api/pith-number/BUWFLXF72SEWUCOBOES7Z4ANOK/events.json","paper":"https://pith.science/paper/BUWFLXF7"},"agent_actions":{"view_html":"https://pith.science/pith/BUWFLXF72SEWUCOBOES7Z4ANOK","download_json":"https://pith.science/pith/BUWFLXF72SEWUCOBOES7Z4ANOK.json","view_paper":"https://pith.science/paper/BUWFLXF7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2303.04291&json=true","fetch_graph":"https://pith.science/api/pith-number/BUWFLXF72SEWUCOBOES7Z4ANOK/graph.json","fetch_events":"https://pith.science/api/pith-number/BUWFLXF72SEWUCOBOES7Z4ANOK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BUWFLXF72SEWUCOBOES7Z4ANOK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BUWFLXF72SEWUCOBOES7Z4ANOK/action/storage_attestation","attest_author":"https://pith.science/pith/BUWFLXF72SEWUCOBOES7Z4ANOK/action/author_attestation","sign_citation":"https://pith.science/pith/BUWFLXF72SEWUCOBOES7Z4ANOK/action/citation_signature","submit_replication":"https://pith.science/pith/BUWFLXF72SEWUCOBOES7Z4ANOK/action/replication_record"}},"created_at":"2026-07-05T07:07:07.849062+00:00","updated_at":"2026-07-05T07:07:07.849062+00:00"}