{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:S2CQDZZHTSCTC4WLDCHQSPZWTE","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"824b5d9c0e5ed5294a889b8f5b7b7c6d74b99c447107b3d8aaf134d3aaefd12a","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2021-08-26T05:52:32Z","title_canon_sha256":"6aea4dfa84fb24fb8bda9de400a4f99ad9cae0625a0d592fb318cde1460f285b"},"schema_version":"1.0","source":{"id":"2108.11591","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2108.11591","created_at":"2026-07-05T03:09:19Z"},{"alias_kind":"arxiv_version","alias_value":"2108.11591v2","created_at":"2026-07-05T03:09:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2108.11591","created_at":"2026-07-05T03:09:19Z"},{"alias_kind":"pith_short_12","alias_value":"S2CQDZZHTSCT","created_at":"2026-07-05T03:09:19Z"},{"alias_kind":"pith_short_16","alias_value":"S2CQDZZHTSCTC4WL","created_at":"2026-07-05T03:09:19Z"},{"alias_kind":"pith_short_8","alias_value":"S2CQDZZH","created_at":"2026-07-05T03:09:19Z"}],"graph_snapshots":[{"event_id":"sha256:77145e8b4c0eeaf477ce9138c28280c707afdececf5ef426e95aa21472315afb","target":"graph","created_at":"2026-07-05T03:09:19Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2108.11591/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Furu Wei, Jingbo Shang, Lei Cui, Yiheng Xu, Zilong Wang","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2021-08-26T05:52:32Z","title":"LayoutReader: Pre-training of Text and Layout for Reading Order Detection"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2108.11591","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:729042b118fdebb3127ac2d02ffa0b4534b2e741d4cd1cf97fd6ac85329f0111","target":"record","created_at":"2026-07-05T03:09:19Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"824b5d9c0e5ed5294a889b8f5b7b7c6d74b99c447107b3d8aaf134d3aaefd12a","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2021-08-26T05:52:32Z","title_canon_sha256":"6aea4dfa84fb24fb8bda9de400a4f99ad9cae0625a0d592fb318cde1460f285b"},"schema_version":"1.0","source":{"id":"2108.11591","kind":"arxiv","version":2}},"canonical_sha256":"968501e7279c853172cb188f093f369924ebc1da9e3c26c5938d9078aeb4f01e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"968501e7279c853172cb188f093f369924ebc1da9e3c26c5938d9078aeb4f01e","first_computed_at":"2026-07-05T03:09:19.965866Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:09:19.965866Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"vT8ClnAvM5YLBoMtoGUxXR+0HlRlamzSgOuH74dWC3SyW00mFSaX+uEY/gB//BJ+XJ89Y1slSMWjEYIP4DHKDw==","signature_status":"signed_v1","signed_at":"2026-07-05T03:09:19.966392Z","signed_message":"canonical_sha256_bytes"},"source_id":"2108.11591","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:729042b118fdebb3127ac2d02ffa0b4534b2e741d4cd1cf97fd6ac85329f0111","sha256:77145e8b4c0eeaf477ce9138c28280c707afdececf5ef426e95aa21472315afb"],"state_sha256":"1f2e7c55d4db75dce565e97ed61fd893edb7b097e3eb6a028b44c55b67d1d070"}