{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:PCCFPPXDIYWACFVQDATK4FETHK","short_pith_number":"pith:PCCFPPXD","schema_version":"1.0","canonical_sha256":"788457bee3462c0116b01826ae14933a903f3eb7bb80ad2405872eec373ec08b","source":{"kind":"arxiv","id":"2403.14252","version":1},"attestation_state":"computed","paper":{"title":"LayoutLLM: Large Language Model Instruction Tuning for Visually Rich Document Understanding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV","cs.LG"],"primary_cat":"cs.CL","authors_text":"Masato Fujitake","submitted_at":"2024-03-21T09:25:24Z","abstract_excerpt":"This paper proposes LayoutLLM, a more flexible document analysis method for understanding imaged documents. Visually Rich Document Understanding tasks, such as document image classification and information extraction, have gained significant attention due to their importance. Existing methods have been developed to enhance document comprehension by incorporating pre-training awareness of images, text, and layout structure. However, these methods require fine-tuning for each task and dataset, and the models are expensive to train and operate. To overcome this limitation, we propose a new Layout"},"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":"2403.14252","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-03-21T09:25:24Z","cross_cats_sorted":["cs.AI","cs.CV","cs.LG"],"title_canon_sha256":"0f70316c703702d192739d882c76afa9a9d2fb593535f050c6640e96c2852a2f","abstract_canon_sha256":"19d632aa796097ea3d8cdc565e9273b41be3fc675cb8784e782c9898d28987c7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:58:56.838781Z","signature_b64":"KeG2JeTGk11DJLBVQqs8cIO/lsKLig/9eH3h+ohXKhv88tDbRH5PZ3prCLVQGz4urMu38AbzOMQJfis6apRBBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"788457bee3462c0116b01826ae14933a903f3eb7bb80ad2405872eec373ec08b","last_reissued_at":"2026-07-05T07:58:56.838116Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:58:56.838116Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LayoutLLM: Large Language Model Instruction Tuning for Visually Rich Document Understanding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV","cs.LG"],"primary_cat":"cs.CL","authors_text":"Masato Fujitake","submitted_at":"2024-03-21T09:25:24Z","abstract_excerpt":"This paper proposes LayoutLLM, a more flexible document analysis method for understanding imaged documents. Visually Rich Document Understanding tasks, such as document image classification and information extraction, have gained significant attention due to their importance. Existing methods have been developed to enhance document comprehension by incorporating pre-training awareness of images, text, and layout structure. However, these methods require fine-tuning for each task and dataset, and the models are expensive to train and operate. To overcome this limitation, we propose a new Layout"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.14252","kind":"arxiv","version":1},"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/2403.14252/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":"2403.14252","created_at":"2026-07-05T07:58:56.838171+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.14252v1","created_at":"2026-07-05T07:58:56.838171+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.14252","created_at":"2026-07-05T07:58:56.838171+00:00"},{"alias_kind":"pith_short_12","alias_value":"PCCFPPXDIYWA","created_at":"2026-07-05T07:58:56.838171+00:00"},{"alias_kind":"pith_short_16","alias_value":"PCCFPPXDIYWACFVQ","created_at":"2026-07-05T07:58:56.838171+00:00"},{"alias_kind":"pith_short_8","alias_value":"PCCFPPXD","created_at":"2026-07-05T07:58:56.838171+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2501.02235","citing_title":"Survey on Question Answering over Visually Rich Documents: Methods, Challenges, and Trends","ref_index":30,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PCCFPPXDIYWACFVQDATK4FETHK","json":"https://pith.science/pith/PCCFPPXDIYWACFVQDATK4FETHK.json","graph_json":"https://pith.science/api/pith-number/PCCFPPXDIYWACFVQDATK4FETHK/graph.json","events_json":"https://pith.science/api/pith-number/PCCFPPXDIYWACFVQDATK4FETHK/events.json","paper":"https://pith.science/paper/PCCFPPXD"},"agent_actions":{"view_html":"https://pith.science/pith/PCCFPPXDIYWACFVQDATK4FETHK","download_json":"https://pith.science/pith/PCCFPPXDIYWACFVQDATK4FETHK.json","view_paper":"https://pith.science/paper/PCCFPPXD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.14252&json=true","fetch_graph":"https://pith.science/api/pith-number/PCCFPPXDIYWACFVQDATK4FETHK/graph.json","fetch_events":"https://pith.science/api/pith-number/PCCFPPXDIYWACFVQDATK4FETHK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PCCFPPXDIYWACFVQDATK4FETHK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PCCFPPXDIYWACFVQDATK4FETHK/action/storage_attestation","attest_author":"https://pith.science/pith/PCCFPPXDIYWACFVQDATK4FETHK/action/author_attestation","sign_citation":"https://pith.science/pith/PCCFPPXDIYWACFVQDATK4FETHK/action/citation_signature","submit_replication":"https://pith.science/pith/PCCFPPXDIYWACFVQDATK4FETHK/action/replication_record"}},"created_at":"2026-07-05T07:58:56.838171+00:00","updated_at":"2026-07-05T07:58:56.838171+00:00"}