{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:VXS2PN65FYPPRIKZBATMMY5OEH","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":"15c4c8c080e88f0ba294f57261a57c6c830a06f7f4830a0fd47b1fdfb8934146","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-11-30T18:55:19Z","title_canon_sha256":"8b6320ce9a458a9a71aa2db0f360c803b6cbc4f1ee12324aa996e41cbb140d6c"},"schema_version":"1.0","source":{"id":"2111.15664","kind":"arxiv","version":5}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2111.15664","created_at":"2026-07-05T05:03:49Z"},{"alias_kind":"arxiv_version","alias_value":"2111.15664v5","created_at":"2026-07-05T05:03:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2111.15664","created_at":"2026-07-05T05:03:49Z"},{"alias_kind":"pith_short_12","alias_value":"VXS2PN65FYPP","created_at":"2026-07-05T05:03:49Z"},{"alias_kind":"pith_short_16","alias_value":"VXS2PN65FYPPRIKZ","created_at":"2026-07-05T05:03:49Z"},{"alias_kind":"pith_short_8","alias_value":"VXS2PN65","created_at":"2026-07-05T05:03:49Z"}],"graph_snapshots":[{"event_id":"sha256:ed0ec1b04ea5421caa7fdf3b2d08a43cf1fdd5ec2cf6e99952032b52c2742378","target":"graph","created_at":"2026-07-05T05:03:49Z","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/2111.15664/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Understanding document images (e.g., invoices) is a core but challenging task since it requires complex functions such as reading text and a holistic understanding of the document. Current Visual Document Understanding (VDU) methods outsource the task of reading text to off-the-shelf Optical Character Recognition (OCR) engines and focus on the understanding task with the OCR outputs. Although such OCR-based approaches have shown promising performance, they suffer from 1) high computational costs for using OCR; 2) inflexibility of OCR models on languages or types of document; 3) OCR error propa","authors_text":"Dongyoon Han, Geewook Kim, Jeongyeon Nam, Jinyeong Yim, Jinyoung Park, Moonbin Yim, Sangdoo Yun, Seunghyun Park, Teakgyu Hong, Wonseok Hwang","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-11-30T18:55:19Z","title":"OCR-free Document Understanding Transformer"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2111.15664","kind":"arxiv","version":5},"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":"sha256:73e5296be5e5e149d8998c4f70b61c4680c451094dd5ae8d3c8e5c3d8065a6b2","target":"record","created_at":"2026-07-05T05:03:49Z","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":"15c4c8c080e88f0ba294f57261a57c6c830a06f7f4830a0fd47b1fdfb8934146","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-11-30T18:55:19Z","title_canon_sha256":"8b6320ce9a458a9a71aa2db0f360c803b6cbc4f1ee12324aa996e41cbb140d6c"},"schema_version":"1.0","source":{"id":"2111.15664","kind":"arxiv","version":5}},"canonical_sha256":"ade5a7b7dd2e1ef8a1590826c663ae21c1781eb86d73db881f31a2d416b1269e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ade5a7b7dd2e1ef8a1590826c663ae21c1781eb86d73db881f31a2d416b1269e","first_computed_at":"2026-07-05T05:03:49.955162Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:03:49.955162Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"B3rOXBJoAxg9rX233MHNBiWCoCQUj2vpc9UHAvGOW0ggWrp7UtsmkvxDPtYJpJyYkMvWS4A0LMsI1d9nv9ujAw==","signature_status":"signed_v1","signed_at":"2026-07-05T05:03:49.955650Z","signed_message":"canonical_sha256_bytes"},"source_id":"2111.15664","source_kind":"arxiv","source_version":5}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:73e5296be5e5e149d8998c4f70b61c4680c451094dd5ae8d3c8e5c3d8065a6b2","sha256:ed0ec1b04ea5421caa7fdf3b2d08a43cf1fdd5ec2cf6e99952032b52c2742378"],"state_sha256":"312dba3080c653e84b9db0675d6df23c499375dfb130fbb8655a0cc726cb7cb0"}