{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:IS23CIWQNY4VHTYF37XADJLZL2","short_pith_number":"pith:IS23CIWQ","schema_version":"1.0","canonical_sha256":"44b5b122d06e3953cf05dfee01a5795ea3d8f3d412d6eedb02bdcaeb8cf8defa","source":{"kind":"arxiv","id":"2412.02592","version":4},"attestation_state":"computed","paper":{"title":"OCR Hinders RAG: Evaluating the Cascading Impact of OCR on Retrieval-Augmented Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bin Wang, Conghui He, Junyuan Zhang, Ka-Ho Chow, Linke Ouyang, Qintong Zhang, Wentao Zhang, Ying Li, Zichen Wen","submitted_at":"2024-12-03T17:23:47Z","abstract_excerpt":"Retrieval-augmented Generation (RAG) enhances Large Language Models (LLMs) by integrating external knowledge to reduce hallucinations and incorporate up-to-date information without retraining. As an essential part of RAG, external knowledge bases are commonly built by extracting structured data from unstructured PDF documents using Optical Character Recognition (OCR). However, given the imperfect prediction of OCR and the inherent non-uniform representation of structured data, knowledge bases inevitably contain various OCR noises. In this paper, we introduce OHRBench, the first benchmark for u"},"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":"2412.02592","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-03T17:23:47Z","cross_cats_sorted":[],"title_canon_sha256":"d3fe6b63a6ca77e62e05b5bdcc636b4e87c99b5526228157db4924523211a205","abstract_canon_sha256":"9525e720cfa0fca7dd27846c0b5a7e5191aab2a57d1b658edb76fb0e1d64e12d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:01:56.119715Z","signature_b64":"riQsASV3P6w8p1B3O2fZ1M8zYpwndw0gSKYCM21b86Qk/HBTq+X8ZxUrPzqEVqYqiCKJYQ5jGLxNX+ByZVT1AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"44b5b122d06e3953cf05dfee01a5795ea3d8f3d412d6eedb02bdcaeb8cf8defa","last_reissued_at":"2026-07-05T12:01:56.119205Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:01:56.119205Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"OCR Hinders RAG: Evaluating the Cascading Impact of OCR on Retrieval-Augmented Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bin Wang, Conghui He, Junyuan Zhang, Ka-Ho Chow, Linke Ouyang, Qintong Zhang, Wentao Zhang, Ying Li, Zichen Wen","submitted_at":"2024-12-03T17:23:47Z","abstract_excerpt":"Retrieval-augmented Generation (RAG) enhances Large Language Models (LLMs) by integrating external knowledge to reduce hallucinations and incorporate up-to-date information without retraining. As an essential part of RAG, external knowledge bases are commonly built by extracting structured data from unstructured PDF documents using Optical Character Recognition (OCR). However, given the imperfect prediction of OCR and the inherent non-uniform representation of structured data, knowledge bases inevitably contain various OCR noises. In this paper, we introduce OHRBench, the first benchmark for u"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.02592","kind":"arxiv","version":4},"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/2412.02592/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":"2412.02592","created_at":"2026-07-05T12:01:56.119270+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.02592v4","created_at":"2026-07-05T12:01:56.119270+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.02592","created_at":"2026-07-05T12:01:56.119270+00:00"},{"alias_kind":"pith_short_12","alias_value":"IS23CIWQNY4V","created_at":"2026-07-05T12:01:56.119270+00:00"},{"alias_kind":"pith_short_16","alias_value":"IS23CIWQNY4VHTYF","created_at":"2026-07-05T12:01:56.119270+00:00"},{"alias_kind":"pith_short_8","alias_value":"IS23CIWQ","created_at":"2026-07-05T12:01:56.119270+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.23539","citing_title":"LightSTAR: Efficient Visual Document Retrieval via Lightweight Selection with Vision-Adaptive Refinement","ref_index":52,"is_internal_anchor":false},{"citing_arxiv_id":"2410.21169","citing_title":"Document Parsing Unveiled: Techniques, Challenges, and Prospects for Structured Information Extraction","ref_index":290,"is_internal_anchor":false},{"citing_arxiv_id":"2509.22186","citing_title":"MinerU2.5: A Decoupled Vision-Language Model for Efficient High-Resolution Document Parsing","ref_index":56,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/IS23CIWQNY4VHTYF37XADJLZL2","json":"https://pith.science/pith/IS23CIWQNY4VHTYF37XADJLZL2.json","graph_json":"https://pith.science/api/pith-number/IS23CIWQNY4VHTYF37XADJLZL2/graph.json","events_json":"https://pith.science/api/pith-number/IS23CIWQNY4VHTYF37XADJLZL2/events.json","paper":"https://pith.science/paper/IS23CIWQ"},"agent_actions":{"view_html":"https://pith.science/pith/IS23CIWQNY4VHTYF37XADJLZL2","download_json":"https://pith.science/pith/IS23CIWQNY4VHTYF37XADJLZL2.json","view_paper":"https://pith.science/paper/IS23CIWQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.02592&json=true","fetch_graph":"https://pith.science/api/pith-number/IS23CIWQNY4VHTYF37XADJLZL2/graph.json","fetch_events":"https://pith.science/api/pith-number/IS23CIWQNY4VHTYF37XADJLZL2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IS23CIWQNY4VHTYF37XADJLZL2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IS23CIWQNY4VHTYF37XADJLZL2/action/storage_attestation","attest_author":"https://pith.science/pith/IS23CIWQNY4VHTYF37XADJLZL2/action/author_attestation","sign_citation":"https://pith.science/pith/IS23CIWQNY4VHTYF37XADJLZL2/action/citation_signature","submit_replication":"https://pith.science/pith/IS23CIWQNY4VHTYF37XADJLZL2/action/replication_record"}},"created_at":"2026-07-05T12:01:56.119270+00:00","updated_at":"2026-07-05T12:01:56.119270+00:00"}