{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:SZDAG57X3UXTWQ64XLC7YF4GE7","short_pith_number":"pith:SZDAG57X","schema_version":"1.0","canonical_sha256":"96460377f7dd2f3b43dcbac5fc178627c62835cb2932538f442cecb6856362c7","source":{"kind":"arxiv","id":"2505.05666","version":1},"attestation_state":"computed","paper":{"title":"Lost in OCR Translation? Vision-Based Approaches to Robust Document Retrieval","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Alexander Most, Ayan Biswas, Dan O'Malley, Joseph Winjum, Manish Bhattarai, Nishath Rajiv Ranasinghe, Shawn Jones","submitted_at":"2025-05-08T21:54:02Z","abstract_excerpt":"Retrieval-Augmented Generation (RAG) has become a popular technique for enhancing the reliability and utility of Large Language Models (LLMs) by grounding responses in external documents. Traditional RAG systems rely on Optical Character Recognition (OCR) to first process scanned documents into text. However, even state-of-the-art OCRs can introduce errors, especially in degraded or complex documents. Recent vision-language approaches, such as ColPali, propose direct visual embedding of documents, eliminating the need for OCR. This study presents a systematic comparison between a vision-based "},"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":"2505.05666","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-05-08T21:54:02Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"59e5c997b0704e60b165043b51335e2555e8a34a6bd4663ff1b1fbfa332ca5d7","abstract_canon_sha256":"4e11fbc574ce9dacb626027c2c980828ebb75a5803efdffe218725607065b886"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:00:45.545503Z","signature_b64":"UirCrTsucDGzXV69POYK/E0HlKCZ5G6ClZKmGsAmTqNsLVK7io9AMNqlFswGACD7BCY06lFX/lVbBBupLvE1AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"96460377f7dd2f3b43dcbac5fc178627c62835cb2932538f442cecb6856362c7","last_reissued_at":"2026-07-05T11:00:45.544930Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:00:45.544930Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Lost in OCR Translation? Vision-Based Approaches to Robust Document Retrieval","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Alexander Most, Ayan Biswas, Dan O'Malley, Joseph Winjum, Manish Bhattarai, Nishath Rajiv Ranasinghe, Shawn Jones","submitted_at":"2025-05-08T21:54:02Z","abstract_excerpt":"Retrieval-Augmented Generation (RAG) has become a popular technique for enhancing the reliability and utility of Large Language Models (LLMs) by grounding responses in external documents. Traditional RAG systems rely on Optical Character Recognition (OCR) to first process scanned documents into text. However, even state-of-the-art OCRs can introduce errors, especially in degraded or complex documents. Recent vision-language approaches, such as ColPali, propose direct visual embedding of documents, eliminating the need for OCR. This study presents a systematic comparison between a vision-based "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.05666","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/2505.05666/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":"2505.05666","created_at":"2026-07-05T11:00:45.545001+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.05666v1","created_at":"2026-07-05T11:00:45.545001+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.05666","created_at":"2026-07-05T11:00:45.545001+00:00"},{"alias_kind":"pith_short_12","alias_value":"SZDAG57X3UXT","created_at":"2026-07-05T11:00:45.545001+00:00"},{"alias_kind":"pith_short_16","alias_value":"SZDAG57X3UXTWQ64","created_at":"2026-07-05T11:00:45.545001+00:00"},{"alias_kind":"pith_short_8","alias_value":"SZDAG57X","created_at":"2026-07-05T11:00:45.545001+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/SZDAG57X3UXTWQ64XLC7YF4GE7","json":"https://pith.science/pith/SZDAG57X3UXTWQ64XLC7YF4GE7.json","graph_json":"https://pith.science/api/pith-number/SZDAG57X3UXTWQ64XLC7YF4GE7/graph.json","events_json":"https://pith.science/api/pith-number/SZDAG57X3UXTWQ64XLC7YF4GE7/events.json","paper":"https://pith.science/paper/SZDAG57X"},"agent_actions":{"view_html":"https://pith.science/pith/SZDAG57X3UXTWQ64XLC7YF4GE7","download_json":"https://pith.science/pith/SZDAG57X3UXTWQ64XLC7YF4GE7.json","view_paper":"https://pith.science/paper/SZDAG57X","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.05666&json=true","fetch_graph":"https://pith.science/api/pith-number/SZDAG57X3UXTWQ64XLC7YF4GE7/graph.json","fetch_events":"https://pith.science/api/pith-number/SZDAG57X3UXTWQ64XLC7YF4GE7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SZDAG57X3UXTWQ64XLC7YF4GE7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SZDAG57X3UXTWQ64XLC7YF4GE7/action/storage_attestation","attest_author":"https://pith.science/pith/SZDAG57X3UXTWQ64XLC7YF4GE7/action/author_attestation","sign_citation":"https://pith.science/pith/SZDAG57X3UXTWQ64XLC7YF4GE7/action/citation_signature","submit_replication":"https://pith.science/pith/SZDAG57X3UXTWQ64XLC7YF4GE7/action/replication_record"}},"created_at":"2026-07-05T11:00:45.545001+00:00","updated_at":"2026-07-05T11:00:45.545001+00:00"}