{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:SIA5KUTCHGCSXGRE5C3X24FA7H","short_pith_number":"pith:SIA5KUTC","schema_version":"1.0","canonical_sha256":"9201d5526239852b9a24e8b77d70a0f9df9223a81cf6e132278d1bbef8f76444","source":{"kind":"arxiv","id":"2410.13305","version":3},"attestation_state":"computed","paper":{"title":"Reference-Based Post-OCR Processing with LLM for Precise Diacritic Text in Historical Document Recognition","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.CL","authors_text":"An Vo, Daeyoung Kim, Dinh Phu Tran, Thao Do","submitted_at":"2024-10-17T08:05:02Z","abstract_excerpt":"Extracting fine-grained OCR text from aged documents in diacritic languages remains challenging due to unexpected artifacts, time-induced degradation, and lack of datasets. While standalone spell correction approaches have been proposed, they show limited performance for historical documents due to numerous possible OCR error combinations and differences between modern and classical corpus distributions. We propose a method utilizing available content-focused ebooks as a reference base to correct imperfect OCR-generated text, supported by large language models. This technique generates high-pr"},"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":"2410.13305","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-17T08:05:02Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"01e9de03a9db3000164be397a5e181ca2e99a0c7e01fa3203c60b026435519e2","abstract_canon_sha256":"f05c0684423c81895348adbbc192801c777750343f6a0b595992ee4645a8a93f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:20:40.780003Z","signature_b64":"uVmbkQ/yvIxJWWWpv2wSgcWSXrwThy7CWKfThtx/QOmF9qui8Td6dENZd2GtyimIYW9JlZhtrmz7mHM0bLfzDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9201d5526239852b9a24e8b77d70a0f9df9223a81cf6e132278d1bbef8f76444","last_reissued_at":"2026-07-05T10:20:40.779492Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:20:40.779492Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Reference-Based Post-OCR Processing with LLM for Precise Diacritic Text in Historical Document Recognition","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.CL","authors_text":"An Vo, Daeyoung Kim, Dinh Phu Tran, Thao Do","submitted_at":"2024-10-17T08:05:02Z","abstract_excerpt":"Extracting fine-grained OCR text from aged documents in diacritic languages remains challenging due to unexpected artifacts, time-induced degradation, and lack of datasets. While standalone spell correction approaches have been proposed, they show limited performance for historical documents due to numerous possible OCR error combinations and differences between modern and classical corpus distributions. We propose a method utilizing available content-focused ebooks as a reference base to correct imperfect OCR-generated text, supported by large language models. This technique generates high-pr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.13305","kind":"arxiv","version":3},"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/2410.13305/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":"2410.13305","created_at":"2026-07-05T10:20:40.779555+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.13305v3","created_at":"2026-07-05T10:20:40.779555+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.13305","created_at":"2026-07-05T10:20:40.779555+00:00"},{"alias_kind":"pith_short_12","alias_value":"SIA5KUTCHGCS","created_at":"2026-07-05T10:20:40.779555+00:00"},{"alias_kind":"pith_short_16","alias_value":"SIA5KUTCHGCSXGRE","created_at":"2026-07-05T10:20:40.779555+00:00"},{"alias_kind":"pith_short_8","alias_value":"SIA5KUTC","created_at":"2026-07-05T10:20:40.779555+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/SIA5KUTCHGCSXGRE5C3X24FA7H","json":"https://pith.science/pith/SIA5KUTCHGCSXGRE5C3X24FA7H.json","graph_json":"https://pith.science/api/pith-number/SIA5KUTCHGCSXGRE5C3X24FA7H/graph.json","events_json":"https://pith.science/api/pith-number/SIA5KUTCHGCSXGRE5C3X24FA7H/events.json","paper":"https://pith.science/paper/SIA5KUTC"},"agent_actions":{"view_html":"https://pith.science/pith/SIA5KUTCHGCSXGRE5C3X24FA7H","download_json":"https://pith.science/pith/SIA5KUTCHGCSXGRE5C3X24FA7H.json","view_paper":"https://pith.science/paper/SIA5KUTC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.13305&json=true","fetch_graph":"https://pith.science/api/pith-number/SIA5KUTCHGCSXGRE5C3X24FA7H/graph.json","fetch_events":"https://pith.science/api/pith-number/SIA5KUTCHGCSXGRE5C3X24FA7H/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SIA5KUTCHGCSXGRE5C3X24FA7H/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SIA5KUTCHGCSXGRE5C3X24FA7H/action/storage_attestation","attest_author":"https://pith.science/pith/SIA5KUTCHGCSXGRE5C3X24FA7H/action/author_attestation","sign_citation":"https://pith.science/pith/SIA5KUTCHGCSXGRE5C3X24FA7H/action/citation_signature","submit_replication":"https://pith.science/pith/SIA5KUTCHGCSXGRE5C3X24FA7H/action/replication_record"}},"created_at":"2026-07-05T10:20:40.779555+00:00","updated_at":"2026-07-05T10:20:40.779555+00:00"}