{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:UXOZX24NZB2LHNG4LLFLKZN5IH","short_pith_number":"pith:UXOZX24N","schema_version":"1.0","canonical_sha256":"a5dd9beb8dc874b3b4dc5acab565bd41e2e6bb5feadf02b4f89b5aef1b6bee07","source":{"kind":"arxiv","id":"2111.08609","version":1},"attestation_state":"computed","paper":{"title":"Document AI: Benchmarks, Models and Applications","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Furu Wei, Lei Cui, Tengchao Lv, Yiheng Xu","submitted_at":"2021-11-16T16:43:07Z","abstract_excerpt":"Document AI, or Document Intelligence, is a relatively new research topic that refers to the techniques for automatically reading, understanding, and analyzing business documents. It is an important research direction for natural language processing and computer vision. In recent years, the popularity of deep learning technology has greatly advanced the development of Document AI, such as document layout analysis, visual information extraction, document visual question answering, document image classification, etc. This paper briefly reviews some of the representative models, tasks, and benchm"},"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":"2111.08609","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2021-11-16T16:43:07Z","cross_cats_sorted":[],"title_canon_sha256":"86bcca8f0224ee70d7d255b9fcc86e532ac8dd0654f3fed5146e26fe254e9ef0","abstract_canon_sha256":"f44b923039601c8613eff004d9d6d88a799602da011de862868e0d4fa29fccaf"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:32:35.854041Z","signature_b64":"0SW3nxdMyeS1u9xGLki+vNaRKJ93cA4LvkUj3qO+ufyvSTKAgjPoBF6qrwCYoBFUMeG33iBGPOdCKn4xKcpJDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a5dd9beb8dc874b3b4dc5acab565bd41e2e6bb5feadf02b4f89b5aef1b6bee07","last_reissued_at":"2026-07-05T03:32:35.853530Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:32:35.853530Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Document AI: Benchmarks, Models and Applications","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Furu Wei, Lei Cui, Tengchao Lv, Yiheng Xu","submitted_at":"2021-11-16T16:43:07Z","abstract_excerpt":"Document AI, or Document Intelligence, is a relatively new research topic that refers to the techniques for automatically reading, understanding, and analyzing business documents. It is an important research direction for natural language processing and computer vision. In recent years, the popularity of deep learning technology has greatly advanced the development of Document AI, such as document layout analysis, visual information extraction, document visual question answering, document image classification, etc. This paper briefly reviews some of the representative models, tasks, and benchm"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2111.08609","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/2111.08609/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":"2111.08609","created_at":"2026-07-05T03:32:35.853596+00:00"},{"alias_kind":"arxiv_version","alias_value":"2111.08609v1","created_at":"2026-07-05T03:32:35.853596+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2111.08609","created_at":"2026-07-05T03:32:35.853596+00:00"},{"alias_kind":"pith_short_12","alias_value":"UXOZX24NZB2L","created_at":"2026-07-05T03:32:35.853596+00:00"},{"alias_kind":"pith_short_16","alias_value":"UXOZX24NZB2LHNG4","created_at":"2026-07-05T03:32:35.853596+00:00"},{"alias_kind":"pith_short_8","alias_value":"UXOZX24N","created_at":"2026-07-05T03:32:35.853596+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.06170","citing_title":"The Documentation and Traceability Burden of the Indian EV Transition","ref_index":26,"is_internal_anchor":true},{"citing_arxiv_id":"2605.03903","citing_title":"CC-OCR V2: Benchmarking Large Multimodal Models for Literacy in Real-world Document Processing","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2605.07492","citing_title":"How Far Is Document Parsing from Solved? PureDocBench: A Source-TraceableBenchmark across Clean, Degraded, and Real-World Settings","ref_index":1,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/UXOZX24NZB2LHNG4LLFLKZN5IH","json":"https://pith.science/pith/UXOZX24NZB2LHNG4LLFLKZN5IH.json","graph_json":"https://pith.science/api/pith-number/UXOZX24NZB2LHNG4LLFLKZN5IH/graph.json","events_json":"https://pith.science/api/pith-number/UXOZX24NZB2LHNG4LLFLKZN5IH/events.json","paper":"https://pith.science/paper/UXOZX24N"},"agent_actions":{"view_html":"https://pith.science/pith/UXOZX24NZB2LHNG4LLFLKZN5IH","download_json":"https://pith.science/pith/UXOZX24NZB2LHNG4LLFLKZN5IH.json","view_paper":"https://pith.science/paper/UXOZX24N","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2111.08609&json=true","fetch_graph":"https://pith.science/api/pith-number/UXOZX24NZB2LHNG4LLFLKZN5IH/graph.json","fetch_events":"https://pith.science/api/pith-number/UXOZX24NZB2LHNG4LLFLKZN5IH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UXOZX24NZB2LHNG4LLFLKZN5IH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UXOZX24NZB2LHNG4LLFLKZN5IH/action/storage_attestation","attest_author":"https://pith.science/pith/UXOZX24NZB2LHNG4LLFLKZN5IH/action/author_attestation","sign_citation":"https://pith.science/pith/UXOZX24NZB2LHNG4LLFLKZN5IH/action/citation_signature","submit_replication":"https://pith.science/pith/UXOZX24NZB2LHNG4LLFLKZN5IH/action/replication_record"}},"created_at":"2026-07-05T03:32:35.853596+00:00","updated_at":"2026-07-05T03:32:35.853596+00:00"}