{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:S3OU2PPY6QL3TMPIZI2W3CW4MR","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":"e1fae405c97c4d2f0d0fdbda24c1d0cda13fbb68db478726a5769eb77fd76b2d","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2021-04-18T12:16:00Z","title_canon_sha256":"16e8a759478b923762e43f45fa5896bbb1594cecf124b362fc2632915ab25648"},"schema_version":"1.0","source":{"id":"2104.08836","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2104.08836","created_at":"2026-07-05T03:12:48Z"},{"alias_kind":"arxiv_version","alias_value":"2104.08836v3","created_at":"2026-07-05T03:12:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2104.08836","created_at":"2026-07-05T03:12:48Z"},{"alias_kind":"pith_short_12","alias_value":"S3OU2PPY6QL3","created_at":"2026-07-05T03:12:48Z"},{"alias_kind":"pith_short_16","alias_value":"S3OU2PPY6QL3TMPI","created_at":"2026-07-05T03:12:48Z"},{"alias_kind":"pith_short_8","alias_value":"S3OU2PPY","created_at":"2026-07-05T03:12:48Z"}],"graph_snapshots":[{"event_id":"sha256:ea2f488451f44f6597e1b2e0a295717fe4d5f4d6ae1deea83b5fd1ae89c37817","target":"graph","created_at":"2026-07-05T03:12:48Z","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/2104.08836/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 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","authors_text":"Cha Zhang, Dinei Florencio, Furu Wei, Guoxin Wang, Lei Cui, Tengchao Lv, Yiheng Xu, Yijuan Lu","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2021-04-18T12:16:00Z","title":"LayoutXLM: Multimodal Pre-training for Multilingual Visually-rich Document Understanding"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2104.08836","kind":"arxiv","version":3},"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":"sha256:0e6b5df3c3a24a35e0035ab2a661040c19ef6febac5da99d5423c11d7d5f5107","target":"record","created_at":"2026-07-05T03:12:48Z","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":"e1fae405c97c4d2f0d0fdbda24c1d0cda13fbb68db478726a5769eb77fd76b2d","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2021-04-18T12:16:00Z","title_canon_sha256":"16e8a759478b923762e43f45fa5896bbb1594cecf124b362fc2632915ab25648"},"schema_version":"1.0","source":{"id":"2104.08836","kind":"arxiv","version":3}},"canonical_sha256":"96dd4d3df8f417b9b1e8ca356d8adc644baab05f86c02581906b81f408706e2c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"96dd4d3df8f417b9b1e8ca356d8adc644baab05f86c02581906b81f408706e2c","first_computed_at":"2026-07-05T03:12:48.460272Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:12:48.460272Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"On8gYI1agplF6fEQ0YIL+Ts1G5pC4D4XfBr6DR2M8aA3gm8W4iiIqWvInVlcJSEceXMcUFeHc0Ua0dm55TplDw==","signature_status":"signed_v1","signed_at":"2026-07-05T03:12:48.460816Z","signed_message":"canonical_sha256_bytes"},"source_id":"2104.08836","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0e6b5df3c3a24a35e0035ab2a661040c19ef6febac5da99d5423c11d7d5f5107","sha256:ea2f488451f44f6597e1b2e0a295717fe4d5f4d6ae1deea83b5fd1ae89c37817"],"state_sha256":"a6a085eb10a55e7d5b86824d482392d1b7b871fad6e5a96a80f3fb075c08e871"}