{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:VRYE4SQ5TVGI523DFZDN5XZZXB","short_pith_number":"pith:VRYE4SQ5","schema_version":"1.0","canonical_sha256":"ac704e4a1d9d4c8eeb632e46dedf39b8474fcd5a18ebdc85762668fd41ec64cb","source":{"kind":"arxiv","id":"2110.08518","version":2},"attestation_state":"computed","paper":{"title":"MarkupLM: Pre-training of Text and Markup Language for Visually-rich Document Understanding","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Furu Wei, Junlong Li, Lei Cui, Yiheng Xu","submitted_at":"2021-10-16T09:17:28Z","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"},"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":"2110.08518","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2021-10-16T09:17:28Z","cross_cats_sorted":[],"title_canon_sha256":"00f4868c1375561e757a98811d1c5b94e5092501459f4ea77fc93cadfca5ccd5","abstract_canon_sha256":"212214bd24fc5ddd218388139ab14f8a0b28b525135774642a9b98478fe37840"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:03:53.785634Z","signature_b64":"d03PziwddeG4m3KQg22WXWtEnA38s+zL2pfs72oAxspIkMokUVOdcsah6u0P8iPuwihH6jLENDTf7zb5+GcHDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ac704e4a1d9d4c8eeb632e46dedf39b8474fcd5a18ebdc85762668fd41ec64cb","last_reissued_at":"2026-07-05T04:03:53.785175Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:03:53.785175Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MarkupLM: Pre-training of Text and Markup Language for Visually-rich Document Understanding","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Furu Wei, Junlong Li, Lei Cui, Yiheng Xu","submitted_at":"2021-10-16T09:17:28Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.08518","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/2110.08518/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":"2110.08518","created_at":"2026-07-05T04:03:53.785230+00:00"},{"alias_kind":"arxiv_version","alias_value":"2110.08518v2","created_at":"2026-07-05T04:03:53.785230+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.08518","created_at":"2026-07-05T04:03:53.785230+00:00"},{"alias_kind":"pith_short_12","alias_value":"VRYE4SQ5TVGI","created_at":"2026-07-05T04:03:53.785230+00:00"},{"alias_kind":"pith_short_16","alias_value":"VRYE4SQ5TVGI523D","created_at":"2026-07-05T04:03:53.785230+00:00"},{"alias_kind":"pith_short_8","alias_value":"VRYE4SQ5","created_at":"2026-07-05T04:03:53.785230+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.23533","citing_title":"POTracker: Optimizing Large Language Models for Standard-Compliant Power Outage Report Generation","ref_index":35,"is_internal_anchor":false},{"citing_arxiv_id":"2606.23533","citing_title":"POTracker: Optimizing Large Language Models for Standard-Compliant Power Outage Report Generation","ref_index":35,"is_internal_anchor":false},{"citing_arxiv_id":"2604.04353","citing_title":"ReFinE: Streamlining UI Mockup Iteration with Research Findings","ref_index":33,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VRYE4SQ5TVGI523DFZDN5XZZXB","json":"https://pith.science/pith/VRYE4SQ5TVGI523DFZDN5XZZXB.json","graph_json":"https://pith.science/api/pith-number/VRYE4SQ5TVGI523DFZDN5XZZXB/graph.json","events_json":"https://pith.science/api/pith-number/VRYE4SQ5TVGI523DFZDN5XZZXB/events.json","paper":"https://pith.science/paper/VRYE4SQ5"},"agent_actions":{"view_html":"https://pith.science/pith/VRYE4SQ5TVGI523DFZDN5XZZXB","download_json":"https://pith.science/pith/VRYE4SQ5TVGI523DFZDN5XZZXB.json","view_paper":"https://pith.science/paper/VRYE4SQ5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2110.08518&json=true","fetch_graph":"https://pith.science/api/pith-number/VRYE4SQ5TVGI523DFZDN5XZZXB/graph.json","fetch_events":"https://pith.science/api/pith-number/VRYE4SQ5TVGI523DFZDN5XZZXB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VRYE4SQ5TVGI523DFZDN5XZZXB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VRYE4SQ5TVGI523DFZDN5XZZXB/action/storage_attestation","attest_author":"https://pith.science/pith/VRYE4SQ5TVGI523DFZDN5XZZXB/action/author_attestation","sign_citation":"https://pith.science/pith/VRYE4SQ5TVGI523DFZDN5XZZXB/action/citation_signature","submit_replication":"https://pith.science/pith/VRYE4SQ5TVGI523DFZDN5XZZXB/action/replication_record"}},"created_at":"2026-07-05T04:03:53.785230+00:00","updated_at":"2026-07-05T04:03:53.785230+00:00"}