{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:VRYE4SQ5TVGI523DFZDN5XZZXB","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":"212214bd24fc5ddd218388139ab14f8a0b28b525135774642a9b98478fe37840","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2021-10-16T09:17:28Z","title_canon_sha256":"00f4868c1375561e757a98811d1c5b94e5092501459f4ea77fc93cadfca5ccd5"},"schema_version":"1.0","source":{"id":"2110.08518","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2110.08518","created_at":"2026-07-05T04:03:53Z"},{"alias_kind":"arxiv_version","alias_value":"2110.08518v2","created_at":"2026-07-05T04:03:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.08518","created_at":"2026-07-05T04:03:53Z"},{"alias_kind":"pith_short_12","alias_value":"VRYE4SQ5TVGI","created_at":"2026-07-05T04:03:53Z"},{"alias_kind":"pith_short_16","alias_value":"VRYE4SQ5TVGI523D","created_at":"2026-07-05T04:03:53Z"},{"alias_kind":"pith_short_8","alias_value":"VRYE4SQ5","created_at":"2026-07-05T04:03:53Z"}],"graph_snapshots":[{"event_id":"sha256:5bf523107507336ff4dbfdd019fd9ba8cda2b270549100900c3537afd80373ce","target":"graph","created_at":"2026-07-05T04:03:53Z","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/2110.08518/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Multimodal pre-training with text, layout, and image has made significant progress for Visually Rich Document Understanding (VRDU), especially the fixed-layout documents such as scanned document images. While, there are still a large number of digital documents where the layout information is not fixed and needs to be interactively and dynamically rendered for visualization, making existing layout-based pre-training approaches not easy to apply. In this paper, we propose MarkupLM for document understanding tasks with markup languages as the backbone, such as HTML/XML-based documents, where tex","authors_text":"Furu Wei, Junlong Li, Lei Cui, Yiheng Xu","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2021-10-16T09:17:28Z","title":"MarkupLM: Pre-training of Text and Markup Language for Visually-rich Document Understanding"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.08518","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":"sha256:00135eec48ca97e779210da89d522c704c787d1da83eabb9f767d183077cd98e","target":"record","created_at":"2026-07-05T04:03:53Z","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":"212214bd24fc5ddd218388139ab14f8a0b28b525135774642a9b98478fe37840","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2021-10-16T09:17:28Z","title_canon_sha256":"00f4868c1375561e757a98811d1c5b94e5092501459f4ea77fc93cadfca5ccd5"},"schema_version":"1.0","source":{"id":"2110.08518","kind":"arxiv","version":2}},"canonical_sha256":"ac704e4a1d9d4c8eeb632e46dedf39b8474fcd5a18ebdc85762668fd41ec64cb","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ac704e4a1d9d4c8eeb632e46dedf39b8474fcd5a18ebdc85762668fd41ec64cb","first_computed_at":"2026-07-05T04:03:53.785175Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:03:53.785175Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"d03PziwddeG4m3KQg22WXWtEnA38s+zL2pfs72oAxspIkMokUVOdcsah6u0P8iPuwihH6jLENDTf7zb5+GcHDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T04:03:53.785634Z","signed_message":"canonical_sha256_bytes"},"source_id":"2110.08518","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:00135eec48ca97e779210da89d522c704c787d1da83eabb9f767d183077cd98e","sha256:5bf523107507336ff4dbfdd019fd9ba8cda2b270549100900c3537afd80373ce"],"state_sha256":"84a7cab23ebe53db8307f9d62cc6491f1d51e5cd71d8ee9d4ff9e51606a6677e"}