{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:S3OU2PPY6QL3TMPIZI2W3CW4MR","short_pith_number":"pith:S3OU2PPY","schema_version":"1.0","canonical_sha256":"96dd4d3df8f417b9b1e8ca356d8adc644baab05f86c02581906b81f408706e2c","source":{"kind":"arxiv","id":"2104.08836","version":3},"attestation_state":"computed","paper":{"title":"LayoutXLM: Multimodal Pre-training for Multilingual Visually-rich Document Understanding","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Cha Zhang, Dinei Florencio, Furu Wei, Guoxin Wang, Lei Cui, Tengchao Lv, Yiheng Xu, Yijuan Lu","submitted_at":"2021-04-18T12:16:00Z","abstract_excerpt":"Multimodal pre-training with text, layout, and image has achieved SOTA performance for visually-rich document understanding tasks recently, which demonstrates the great potential for joint learning across different modalities. In this paper, we present LayoutXLM, a multimodal pre-trained model for multilingual document understanding, which aims to bridge the language barriers for visually-rich document understanding. To accurately evaluate LayoutXLM, we also introduce a multilingual form understanding benchmark dataset named XFUND, which includes form understanding samples in 7 languages (Chin"},"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":"2104.08836","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2021-04-18T12:16:00Z","cross_cats_sorted":[],"title_canon_sha256":"16e8a759478b923762e43f45fa5896bbb1594cecf124b362fc2632915ab25648","abstract_canon_sha256":"e1fae405c97c4d2f0d0fdbda24c1d0cda13fbb68db478726a5769eb77fd76b2d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:12:48.460816Z","signature_b64":"On8gYI1agplF6fEQ0YIL+Ts1G5pC4D4XfBr6DR2M8aA3gm8W4iiIqWvInVlcJSEceXMcUFeHc0Ua0dm55TplDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"96dd4d3df8f417b9b1e8ca356d8adc644baab05f86c02581906b81f408706e2c","last_reissued_at":"2026-07-05T03:12:48.460272Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:12:48.460272Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LayoutXLM: Multimodal Pre-training for Multilingual Visually-rich Document Understanding","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Cha Zhang, Dinei Florencio, Furu Wei, Guoxin Wang, Lei Cui, Tengchao Lv, Yiheng Xu, Yijuan Lu","submitted_at":"2021-04-18T12:16:00Z","abstract_excerpt":"Multimodal pre-training with text, layout, and image has achieved SOTA performance for visually-rich document understanding tasks recently, which demonstrates the great potential for joint learning across different modalities. In this paper, we present LayoutXLM, a multimodal pre-trained model for multilingual document understanding, which aims to bridge the language barriers for visually-rich document understanding. To accurately evaluate LayoutXLM, we also introduce a multilingual form understanding benchmark dataset named XFUND, which includes form understanding samples in 7 languages (Chin"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2104.08836","kind":"arxiv","version":3},"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/2104.08836/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":"2104.08836","created_at":"2026-07-05T03:12:48.460346+00:00"},{"alias_kind":"arxiv_version","alias_value":"2104.08836v3","created_at":"2026-07-05T03:12:48.460346+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2104.08836","created_at":"2026-07-05T03:12:48.460346+00:00"},{"alias_kind":"pith_short_12","alias_value":"S3OU2PPY6QL3","created_at":"2026-07-05T03:12:48.460346+00:00"},{"alias_kind":"pith_short_16","alias_value":"S3OU2PPY6QL3TMPI","created_at":"2026-07-05T03:12:48.460346+00:00"},{"alias_kind":"pith_short_8","alias_value":"S3OU2PPY","created_at":"2026-07-05T03:12:48.460346+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.28796","citing_title":"Structure-Preserving Document Translation via Multi-Stage LLM Pipeline: A Case Study in Marathi","ref_index":31,"is_internal_anchor":false},{"citing_arxiv_id":"2605.12623","citing_title":"DocAtlas: Multilingual Document Understanding Across 80+ Languages","ref_index":39,"is_internal_anchor":false},{"citing_arxiv_id":"2605.12623","citing_title":"DocAtlas: Multilingual Document Understanding Across 80+ Languages","ref_index":45,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/S3OU2PPY6QL3TMPIZI2W3CW4MR","json":"https://pith.science/pith/S3OU2PPY6QL3TMPIZI2W3CW4MR.json","graph_json":"https://pith.science/api/pith-number/S3OU2PPY6QL3TMPIZI2W3CW4MR/graph.json","events_json":"https://pith.science/api/pith-number/S3OU2PPY6QL3TMPIZI2W3CW4MR/events.json","paper":"https://pith.science/paper/S3OU2PPY"},"agent_actions":{"view_html":"https://pith.science/pith/S3OU2PPY6QL3TMPIZI2W3CW4MR","download_json":"https://pith.science/pith/S3OU2PPY6QL3TMPIZI2W3CW4MR.json","view_paper":"https://pith.science/paper/S3OU2PPY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2104.08836&json=true","fetch_graph":"https://pith.science/api/pith-number/S3OU2PPY6QL3TMPIZI2W3CW4MR/graph.json","fetch_events":"https://pith.science/api/pith-number/S3OU2PPY6QL3TMPIZI2W3CW4MR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/S3OU2PPY6QL3TMPIZI2W3CW4MR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/S3OU2PPY6QL3TMPIZI2W3CW4MR/action/storage_attestation","attest_author":"https://pith.science/pith/S3OU2PPY6QL3TMPIZI2W3CW4MR/action/author_attestation","sign_citation":"https://pith.science/pith/S3OU2PPY6QL3TMPIZI2W3CW4MR/action/citation_signature","submit_replication":"https://pith.science/pith/S3OU2PPY6QL3TMPIZI2W3CW4MR/action/replication_record"}},"created_at":"2026-07-05T03:12:48.460346+00:00","updated_at":"2026-07-05T03:12:48.460346+00:00"}