{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:MRWBTX6ANSALCH2ALUNUDRRNUM","short_pith_number":"pith:MRWBTX6A","schema_version":"1.0","canonical_sha256":"646c19dfc06c80b11f405d1b41c62da33bf7c529cf62a53523b492dc102f7538","source":{"kind":"arxiv","id":"2605.12623","version":1},"attestation_state":"computed","paper":{"title":"DocAtlas: Multilingual Document Understanding Across 80+ Languages","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"Direct preference optimization with rendering-derived ground truth improves multilingual document understanding across 82 languages without base-language degradation.","cross_cats":["cs.CV","cs.LG"],"primary_cat":"cs.CL","authors_text":"Abdullah Sohail, Ahmed Heakl, Ahmed Nassar, Fahad Shahbaz Khan, Imran Razzak, Peter W. J. Staar, Rania Elbadry, Salman Khan, Youssef Mohamed","submitted_at":"2026-05-12T18:09:38Z","abstract_excerpt":"Multilingual document understanding remains limited for low-resource languages due to scarce training data and model-based annotation pipelines that perpetuate existing biases. We introduce DocAtlas, a framework that constructs high-fidelity OCR datasets and benchmarks covering 82 languages and 9 evaluation tasks. Our dual pipelines, differential rendering of native DOCX documents and synthetic LaTeX-based generation for right-to-left scripts produce precise structural annotations in a unified DocTag format encoding layout, text, and component types, without learned models for core annotation."},"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":true,"formal_links_present":true},"canonical_record":{"source":{"id":"2605.12623","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-12T18:09:38Z","cross_cats_sorted":["cs.CV","cs.LG"],"title_canon_sha256":"fc124a2f6bfc9f9191983bcdf92128c854775df7e9d78a1b75184569c9a8918c","abstract_canon_sha256":"a95951fe49943af07040052cbe2b31c810d39c9c6e61cca1684157a13fe4133d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T03:10:00.376703Z","signature_b64":"3IRLEK5g+ubeimdwOlKjtdKIujOVqaI0CAl6j/8VxRWJkW3kn5lNaUJvQy8UKrVA8xqelw2Kd66Pxz5fIFvXBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"646c19dfc06c80b11f405d1b41c62da33bf7c529cf62a53523b492dc102f7538","last_reissued_at":"2026-05-18T03:10:00.376172Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T03:10:00.376172Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DocAtlas: Multilingual Document Understanding Across 80+ Languages","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"Direct preference optimization with rendering-derived ground truth improves multilingual document understanding across 82 languages without base-language degradation.","cross_cats":["cs.CV","cs.LG"],"primary_cat":"cs.CL","authors_text":"Abdullah Sohail, Ahmed Heakl, Ahmed Nassar, Fahad Shahbaz Khan, Imran Razzak, Peter W. J. Staar, Rania Elbadry, Salman Khan, Youssef Mohamed","submitted_at":"2026-05-12T18:09:38Z","abstract_excerpt":"Multilingual document understanding remains limited for low-resource languages due to scarce training data and model-based annotation pipelines that perpetuate existing biases. We introduce DocAtlas, a framework that constructs high-fidelity OCR datasets and benchmarks covering 82 languages and 9 evaluation tasks. Our dual pipelines, differential rendering of native DOCX documents and synthetic LaTeX-based generation for right-to-left scripts produce precise structural annotations in a unified DocTag format encoding layout, text, and component types, without learned models for core annotation."},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"Direct Preference Optimization (DPO) using rendering-derived ground truth as positive signal achieves stable multilingual adaptation, improving both in-domain (+1.9%) and out-of-domain (+1.8%) accuracy without measurable base-language degradation, where supervised fine-tuning degrades out-of-domain performance by up to 21%.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"The differential rendering of native DOCX documents and synthetic LaTeX-based generation produce precise structural annotations that accurately represent real-world document distributions across all 82 languages without introducing new biases or distribution shifts.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"DocAtlas creates multilingual document datasets across 82 languages and shows DPO with rendered ground truth improves model accuracy by 1.7-1.9% without degrading base-language performance, unlike supervised fine-tuning.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Direct preference optimization with rendering-derived ground truth improves multilingual document understanding across 82 languages without base-language degradation.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"38e7ff549c4cd97f2b79d1de71759e2cb5273a209f9b54a81f96523094dc1f0f"},"source":{"id":"2605.12623","kind":"arxiv","version":1},"verdict":{"id":"08b03706-e999-40f7-97fc-16d1abfacb79","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-14T20:58:47.305197Z","strongest_claim":"Direct Preference Optimization (DPO) using rendering-derived ground truth as positive signal achieves stable multilingual adaptation, improving both in-domain (+1.9%) and out-of-domain (+1.8%) accuracy without measurable base-language degradation, where supervised fine-tuning degrades out-of-domain performance by up to 21%.","one_line_summary":"DocAtlas creates multilingual document datasets across 82 languages and shows DPO with rendered ground truth improves model accuracy by 1.7-1.9% without degrading base-language performance, unlike supervised fine-tuning.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"The differential rendering of native DOCX documents and synthetic LaTeX-based generation produce precise structural annotations that accurately represent real-world document distributions across all 82 languages without introducing new biases or distribution shifts.","pith_extraction_headline":"Direct preference optimization with rendering-derived ground truth improves multilingual document understanding across 82 languages without base-language degradation."},"references":{"count":85,"sample":[{"doi":"","year":null,"title":"FirstName LastName , title =","work_id":"d9cab501-317f-4237-9e32-b5ead5964402","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"FirstName Alpher , title =","work_id":"42297990-8783-41a1-b0fa-8ccdbf630852","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"Journal of Foo , volume = 13, number = 1, pages =","work_id":"65a8b3d0-af84-4f68-87eb-101c85ab18b2","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"Journal of Foo , volume = 14, number = 1, pages =","work_id":"b3089947-bd36-4a24-9199-cc535e299537","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"FirstName Alpher and FirstName Gamow , title =","work_id":"caed320b-7cdc-41ca-bb08-00fb14feec62","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":85,"snapshot_sha256":"6c0e904e1734960766610409aa89dcf852a4115c9170d7aea2f25766027f1c43","internal_anchors":14},"formal_canon":{"evidence_count":2,"snapshot_sha256":"de605d39aaae8914b8445ffd563e90faab484cae48c46f137c0e77f8d585e400"},"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":"2605.12623","created_at":"2026-05-18T03:10:00.376251+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.12623v1","created_at":"2026-05-18T03:10:00.376251+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.12623","created_at":"2026-05-18T03:10:00.376251+00:00"},{"alias_kind":"pith_short_12","alias_value":"MRWBTX6ANSAL","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_16","alias_value":"MRWBTX6ANSALCH2A","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_8","alias_value":"MRWBTX6A","created_at":"2026-05-18T12:33:37.589309+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":2,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MRWBTX6ANSALCH2ALUNUDRRNUM","json":"https://pith.science/pith/MRWBTX6ANSALCH2ALUNUDRRNUM.json","graph_json":"https://pith.science/api/pith-number/MRWBTX6ANSALCH2ALUNUDRRNUM/graph.json","events_json":"https://pith.science/api/pith-number/MRWBTX6ANSALCH2ALUNUDRRNUM/events.json","paper":"https://pith.science/paper/MRWBTX6A"},"agent_actions":{"view_html":"https://pith.science/pith/MRWBTX6ANSALCH2ALUNUDRRNUM","download_json":"https://pith.science/pith/MRWBTX6ANSALCH2ALUNUDRRNUM.json","view_paper":"https://pith.science/paper/MRWBTX6A","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.12623&json=true","fetch_graph":"https://pith.science/api/pith-number/MRWBTX6ANSALCH2ALUNUDRRNUM/graph.json","fetch_events":"https://pith.science/api/pith-number/MRWBTX6ANSALCH2ALUNUDRRNUM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MRWBTX6ANSALCH2ALUNUDRRNUM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MRWBTX6ANSALCH2ALUNUDRRNUM/action/storage_attestation","attest_author":"https://pith.science/pith/MRWBTX6ANSALCH2ALUNUDRRNUM/action/author_attestation","sign_citation":"https://pith.science/pith/MRWBTX6ANSALCH2ALUNUDRRNUM/action/citation_signature","submit_replication":"https://pith.science/pith/MRWBTX6ANSALCH2ALUNUDRRNUM/action/replication_record"}},"created_at":"2026-05-18T03:10:00.376251+00:00","updated_at":"2026-05-18T03:10:00.376251+00:00"}