{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:S2CQDZZHTSCTC4WLDCHQSPZWTE","short_pith_number":"pith:S2CQDZZH","schema_version":"1.0","canonical_sha256":"968501e7279c853172cb188f093f369924ebc1da9e3c26c5938d9078aeb4f01e","source":{"kind":"arxiv","id":"2108.11591","version":2},"attestation_state":"computed","paper":{"title":"LayoutReader: Pre-training of Text and Layout for Reading Order Detection","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Furu Wei, Jingbo Shang, Lei Cui, Yiheng Xu, Zilong Wang","submitted_at":"2021-08-26T05:52:32Z","abstract_excerpt":"Reading order detection is the cornerstone to understanding visually-rich documents (e.g., receipts and forms). Unfortunately, no existing work took advantage of advanced deep learning models because it is too laborious to annotate a large enough dataset. We observe that the reading order of WORD documents is embedded in their XML metadata; meanwhile, it is easy to convert WORD documents to PDFs or images. Therefore, in an automated manner, we construct ReadingBank, a benchmark dataset that contains reading order, text, and layout information for 500,000 document images covering a wide spectru"},"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":"2108.11591","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2021-08-26T05:52:32Z","cross_cats_sorted":[],"title_canon_sha256":"6aea4dfa84fb24fb8bda9de400a4f99ad9cae0625a0d592fb318cde1460f285b","abstract_canon_sha256":"824b5d9c0e5ed5294a889b8f5b7b7c6d74b99c447107b3d8aaf134d3aaefd12a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:09:19.966392Z","signature_b64":"vT8ClnAvM5YLBoMtoGUxXR+0HlRlamzSgOuH74dWC3SyW00mFSaX+uEY/gB//BJ+XJ89Y1slSMWjEYIP4DHKDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"968501e7279c853172cb188f093f369924ebc1da9e3c26c5938d9078aeb4f01e","last_reissued_at":"2026-07-05T03:09:19.965866Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:09:19.965866Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LayoutReader: Pre-training of Text and Layout for Reading Order Detection","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Furu Wei, Jingbo Shang, Lei Cui, Yiheng Xu, Zilong Wang","submitted_at":"2021-08-26T05:52:32Z","abstract_excerpt":"Reading order detection is the cornerstone to understanding visually-rich documents (e.g., receipts and forms). Unfortunately, no existing work took advantage of advanced deep learning models because it is too laborious to annotate a large enough dataset. We observe that the reading order of WORD documents is embedded in their XML metadata; meanwhile, it is easy to convert WORD documents to PDFs or images. Therefore, in an automated manner, we construct ReadingBank, a benchmark dataset that contains reading order, text, and layout information for 500,000 document images covering a wide spectru"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2108.11591","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/2108.11591/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":"2108.11591","created_at":"2026-07-05T03:09:19.965924+00:00"},{"alias_kind":"arxiv_version","alias_value":"2108.11591v2","created_at":"2026-07-05T03:09:19.965924+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2108.11591","created_at":"2026-07-05T03:09:19.965924+00:00"},{"alias_kind":"pith_short_12","alias_value":"S2CQDZZHTSCT","created_at":"2026-07-05T03:09:19.965924+00:00"},{"alias_kind":"pith_short_16","alias_value":"S2CQDZZHTSCTC4WL","created_at":"2026-07-05T03:09:19.965924+00:00"},{"alias_kind":"pith_short_8","alias_value":"S2CQDZZH","created_at":"2026-07-05T03:09:19.965924+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2607.00596","citing_title":"Semantic-Guided Reading Order Reconstruction in Historical Armenian Newspapers with LLMs","ref_index":17,"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":50,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/S2CQDZZHTSCTC4WLDCHQSPZWTE","json":"https://pith.science/pith/S2CQDZZHTSCTC4WLDCHQSPZWTE.json","graph_json":"https://pith.science/api/pith-number/S2CQDZZHTSCTC4WLDCHQSPZWTE/graph.json","events_json":"https://pith.science/api/pith-number/S2CQDZZHTSCTC4WLDCHQSPZWTE/events.json","paper":"https://pith.science/paper/S2CQDZZH"},"agent_actions":{"view_html":"https://pith.science/pith/S2CQDZZHTSCTC4WLDCHQSPZWTE","download_json":"https://pith.science/pith/S2CQDZZHTSCTC4WLDCHQSPZWTE.json","view_paper":"https://pith.science/paper/S2CQDZZH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2108.11591&json=true","fetch_graph":"https://pith.science/api/pith-number/S2CQDZZHTSCTC4WLDCHQSPZWTE/graph.json","fetch_events":"https://pith.science/api/pith-number/S2CQDZZHTSCTC4WLDCHQSPZWTE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/S2CQDZZHTSCTC4WLDCHQSPZWTE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/S2CQDZZHTSCTC4WLDCHQSPZWTE/action/storage_attestation","attest_author":"https://pith.science/pith/S2CQDZZHTSCTC4WLDCHQSPZWTE/action/author_attestation","sign_citation":"https://pith.science/pith/S2CQDZZHTSCTC4WLDCHQSPZWTE/action/citation_signature","submit_replication":"https://pith.science/pith/S2CQDZZHTSCTC4WLDCHQSPZWTE/action/replication_record"}},"created_at":"2026-07-05T03:09:19.965924+00:00","updated_at":"2026-07-05T03:09:19.965924+00:00"}