{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:2E5QTHK6O4CTTEXKQIR7PXTGAS","short_pith_number":"pith:2E5QTHK6","schema_version":"1.0","canonical_sha256":"d13b099d5e77053992ea8223f7de6604bb01f558c8c8fd42773697cf3b877074","source":{"kind":"arxiv","id":"1912.13318","version":5},"attestation_state":"computed","paper":{"title":"LayoutLM: Pre-training of Text and Layout for Document Image Understanding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Furu Wei, Lei Cui, Minghao Li, Ming Zhou, Shaohan Huang, Yiheng Xu","submitted_at":"2019-12-31T14:31:29Z","abstract_excerpt":"Pre-training techniques have been verified successfully in a variety of NLP tasks in recent years. Despite the widespread use of pre-training models for NLP applications, they almost exclusively focus on text-level manipulation, while neglecting layout and style information that is vital for document image understanding. In this paper, we propose the \\textbf{LayoutLM} to jointly model interactions between text and layout information across scanned document images, which is beneficial for a great number of real-world document image understanding tasks such as information extraction from scanned"},"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":"1912.13318","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-12-31T14:31:29Z","cross_cats_sorted":[],"title_canon_sha256":"ad5c5ce48b641ad9ed0e12a3c8b8f236e8f62bf822b50b61e59c6d9da1ba6de9","abstract_canon_sha256":"66121ab176c3b9213650c1ebe3322afcecf510590e0b77a239a432830936566c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:10:31.768551Z","signature_b64":"BMZ8AVsPgfEpXoNn5lPOuiVU75DexC8LUe5Pc3GXMonrPQLjhXeLKSbY5b8lHceleV70s/G7WnMZp6xuGhbUAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d13b099d5e77053992ea8223f7de6604bb01f558c8c8fd42773697cf3b877074","last_reissued_at":"2026-07-05T01:10:31.767965Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:10:31.767965Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LayoutLM: Pre-training of Text and Layout for Document Image Understanding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Furu Wei, Lei Cui, Minghao Li, Ming Zhou, Shaohan Huang, Yiheng Xu","submitted_at":"2019-12-31T14:31:29Z","abstract_excerpt":"Pre-training techniques have been verified successfully in a variety of NLP tasks in recent years. Despite the widespread use of pre-training models for NLP applications, they almost exclusively focus on text-level manipulation, while neglecting layout and style information that is vital for document image understanding. In this paper, we propose the \\textbf{LayoutLM} to jointly model interactions between text and layout information across scanned document images, which is beneficial for a great number of real-world document image understanding tasks such as information extraction from scanned"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1912.13318","kind":"arxiv","version":5},"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/1912.13318/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":"1912.13318","created_at":"2026-07-05T01:10:31.768034+00:00"},{"alias_kind":"arxiv_version","alias_value":"1912.13318v5","created_at":"2026-07-05T01:10:31.768034+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1912.13318","created_at":"2026-07-05T01:10:31.768034+00:00"},{"alias_kind":"pith_short_12","alias_value":"2E5QTHK6O4CT","created_at":"2026-07-05T01:10:31.768034+00:00"},{"alias_kind":"pith_short_16","alias_value":"2E5QTHK6O4CTTEXK","created_at":"2026-07-05T01:10:31.768034+00:00"},{"alias_kind":"pith_short_8","alias_value":"2E5QTHK6","created_at":"2026-07-05T01:10:31.768034+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"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":28,"is_internal_anchor":false},{"citing_arxiv_id":"2605.17159","citing_title":"MADP: A Multi-Agent Pipeline for Sustainable Document Processing with Human-in-the-Loop","ref_index":33,"is_internal_anchor":false},{"citing_arxiv_id":"2604.04936","citing_title":"Web Retrieval-Aware Chunking (W-RAC) for Efficient and Cost-Effective Retrieval-Augmented Generation Systems","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2604.25927","citing_title":"Information Extraction from Electricity Invoices with General-Purpose Large Language Models","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2604.16504","citing_title":"From Handwriting to Structured Data: Benchmarking AI Digitisation of Handwritten Forms","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2604.11042","citing_title":"Improving Layout Representation Learning Across Inconsistently Annotated Datasets via Agentic Harmonization","ref_index":38,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2E5QTHK6O4CTTEXKQIR7PXTGAS","json":"https://pith.science/pith/2E5QTHK6O4CTTEXKQIR7PXTGAS.json","graph_json":"https://pith.science/api/pith-number/2E5QTHK6O4CTTEXKQIR7PXTGAS/graph.json","events_json":"https://pith.science/api/pith-number/2E5QTHK6O4CTTEXKQIR7PXTGAS/events.json","paper":"https://pith.science/paper/2E5QTHK6"},"agent_actions":{"view_html":"https://pith.science/pith/2E5QTHK6O4CTTEXKQIR7PXTGAS","download_json":"https://pith.science/pith/2E5QTHK6O4CTTEXKQIR7PXTGAS.json","view_paper":"https://pith.science/paper/2E5QTHK6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1912.13318&json=true","fetch_graph":"https://pith.science/api/pith-number/2E5QTHK6O4CTTEXKQIR7PXTGAS/graph.json","fetch_events":"https://pith.science/api/pith-number/2E5QTHK6O4CTTEXKQIR7PXTGAS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2E5QTHK6O4CTTEXKQIR7PXTGAS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2E5QTHK6O4CTTEXKQIR7PXTGAS/action/storage_attestation","attest_author":"https://pith.science/pith/2E5QTHK6O4CTTEXKQIR7PXTGAS/action/author_attestation","sign_citation":"https://pith.science/pith/2E5QTHK6O4CTTEXKQIR7PXTGAS/action/citation_signature","submit_replication":"https://pith.science/pith/2E5QTHK6O4CTTEXKQIR7PXTGAS/action/replication_record"}},"created_at":"2026-07-05T01:10:31.768034+00:00","updated_at":"2026-07-05T01:10:31.768034+00:00"}