{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:S2CQDZZHTSCTC4WLDCHQSPZWTE","short_pith_number":"pith:S2CQDZZH","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"},"canonical_sha256":"968501e7279c853172cb188f093f369924ebc1da9e3c26c5938d9078aeb4f01e","source":{"kind":"arxiv","id":"2108.11591","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:S2CQDZZHTSCTC4WLDCHQSPZWTE","target":"record","payload":{"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"},"canonical_sha256":"968501e7279c853172cb188f093f369924ebc1da9e3c26c5938d9078aeb4f01e","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"},"source_kind":"arxiv","source_id":"2108.11591","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T03:09:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wlSTDbCPW3DbQLVpjNck6Nm0udHs/0zWEIc7prvW6gWw5HuqwZy5r6S5cmBMl5sCht3n2MZCeO4lebTX3FPhBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T18:05:29.892734Z"},"content_sha256":"729042b118fdebb3127ac2d02ffa0b4534b2e741d4cd1cf97fd6ac85329f0111","schema_version":"1.0","event_id":"sha256:729042b118fdebb3127ac2d02ffa0b4534b2e741d4cd1cf97fd6ac85329f0111"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:S2CQDZZHTSCTC4WLDCHQSPZWTE","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T03:09:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0JipBsLQLtnE2U6v2benCC8drwNk4fiyPFNwdSuaZsW0P+rXNuLzz1mIDuNIFsPMbBnjqFSCSBSqc9bcTmUZCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T18:05:29.893063Z"},"content_sha256":"77145e8b4c0eeaf477ce9138c28280c707afdececf5ef426e95aa21472315afb","schema_version":"1.0","event_id":"sha256:77145e8b4c0eeaf477ce9138c28280c707afdececf5ef426e95aa21472315afb"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/S2CQDZZHTSCTC4WLDCHQSPZWTE/bundle.json","state_url":"https://pith.science/pith/S2CQDZZHTSCTC4WLDCHQSPZWTE/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/S2CQDZZHTSCTC4WLDCHQSPZWTE/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-06T18:05:29Z","links":{"resolver":"https://pith.science/pith/S2CQDZZHTSCTC4WLDCHQSPZWTE","bundle":"https://pith.science/pith/S2CQDZZHTSCTC4WLDCHQSPZWTE/bundle.json","state":"https://pith.science/pith/S2CQDZZHTSCTC4WLDCHQSPZWTE/state.json","well_known_bundle":"https://pith.science/.well-known/pith/S2CQDZZHTSCTC4WLDCHQSPZWTE/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vZ58XUUTuvXI7v5BMIPWOvvZ8F/8wQz5IKyLu91yZ/Y5wQ0lJ2+flkkcCPf/Xc1PZe92peUlnN9Fffn2502QCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T18:05:29.896654Z","bundle_sha256":"798ddb323ec25e84d9f8686da9a4906bfb5731b406e6cc651412219d32972f65"}}