{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:GXS7GZTP4G26CD6BM2FAW7NFXC","short_pith_number":"pith:GXS7GZTP","schema_version":"1.0","canonical_sha256":"35e5f3666fe1b5e10fc1668a0b7da5b89cfef701c42a226569827fb96a663be5","source":{"kind":"arxiv","id":"2307.07929","version":1},"attestation_state":"computed","paper":{"title":"DocTr: Document Transformer for Structured Information Extraction in Documents","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Ankan Bansal, Aruni RoyChowdhury, Haofu Liao, Ravi Kumar Satzoda, R. Manmatha, Vijay Mahadevan, Weijian Li, Yuting Zhang, Zhuowen Tu","submitted_at":"2023-07-16T02:59:30Z","abstract_excerpt":"We present a new formulation for structured information extraction (SIE) from visually rich documents. It aims to address the limitations of existing IOB tagging or graph-based formulations, which are either overly reliant on the correct ordering of input text or struggle with decoding a complex graph. Instead, motivated by anchor-based object detectors in vision, we represent an entity as an anchor word and a bounding box, and represent entity linking as the association between anchor words. This is more robust to text ordering, and maintains a compact graph for entity linking. The formulatio"},"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":"2307.07929","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-07-16T02:59:30Z","cross_cats_sorted":[],"title_canon_sha256":"c9304e4627cb1a7b7785d7d2c1a8aaf8105efdb2fe744636b84c80c24c6f9a48","abstract_canon_sha256":"615924671035ed1422010989bc1789a81d943484624ab72eb894149846c0fa4c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:31:17.733147Z","signature_b64":"fCHljMvQWvWe7M3YU0yGJ3kxFubYblxGubQ7nY4vP9jEaOxYyiKlOityi2m9o6u9GFiCJtZkGp9jfV6nfSZPCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"35e5f3666fe1b5e10fc1668a0b7da5b89cfef701c42a226569827fb96a663be5","last_reissued_at":"2026-07-05T06:31:17.732651Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:31:17.732651Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DocTr: Document Transformer for Structured Information Extraction in Documents","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Ankan Bansal, Aruni RoyChowdhury, Haofu Liao, Ravi Kumar Satzoda, R. Manmatha, Vijay Mahadevan, Weijian Li, Yuting Zhang, Zhuowen Tu","submitted_at":"2023-07-16T02:59:30Z","abstract_excerpt":"We present a new formulation for structured information extraction (SIE) from visually rich documents. It aims to address the limitations of existing IOB tagging or graph-based formulations, which are either overly reliant on the correct ordering of input text or struggle with decoding a complex graph. Instead, motivated by anchor-based object detectors in vision, we represent an entity as an anchor word and a bounding box, and represent entity linking as the association between anchor words. This is more robust to text ordering, and maintains a compact graph for entity linking. The formulatio"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.07929","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/2307.07929/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":"2307.07929","created_at":"2026-07-05T06:31:17.732712+00:00"},{"alias_kind":"arxiv_version","alias_value":"2307.07929v1","created_at":"2026-07-05T06:31:17.732712+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.07929","created_at":"2026-07-05T06:31:17.732712+00:00"},{"alias_kind":"pith_short_12","alias_value":"GXS7GZTP4G26","created_at":"2026-07-05T06:31:17.732712+00:00"},{"alias_kind":"pith_short_16","alias_value":"GXS7GZTP4G26CD6B","created_at":"2026-07-05T06:31:17.732712+00:00"},{"alias_kind":"pith_short_8","alias_value":"GXS7GZTP","created_at":"2026-07-05T06:31:17.732712+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":58,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GXS7GZTP4G26CD6BM2FAW7NFXC","json":"https://pith.science/pith/GXS7GZTP4G26CD6BM2FAW7NFXC.json","graph_json":"https://pith.science/api/pith-number/GXS7GZTP4G26CD6BM2FAW7NFXC/graph.json","events_json":"https://pith.science/api/pith-number/GXS7GZTP4G26CD6BM2FAW7NFXC/events.json","paper":"https://pith.science/paper/GXS7GZTP"},"agent_actions":{"view_html":"https://pith.science/pith/GXS7GZTP4G26CD6BM2FAW7NFXC","download_json":"https://pith.science/pith/GXS7GZTP4G26CD6BM2FAW7NFXC.json","view_paper":"https://pith.science/paper/GXS7GZTP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2307.07929&json=true","fetch_graph":"https://pith.science/api/pith-number/GXS7GZTP4G26CD6BM2FAW7NFXC/graph.json","fetch_events":"https://pith.science/api/pith-number/GXS7GZTP4G26CD6BM2FAW7NFXC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GXS7GZTP4G26CD6BM2FAW7NFXC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GXS7GZTP4G26CD6BM2FAW7NFXC/action/storage_attestation","attest_author":"https://pith.science/pith/GXS7GZTP4G26CD6BM2FAW7NFXC/action/author_attestation","sign_citation":"https://pith.science/pith/GXS7GZTP4G26CD6BM2FAW7NFXC/action/citation_signature","submit_replication":"https://pith.science/pith/GXS7GZTP4G26CD6BM2FAW7NFXC/action/replication_record"}},"created_at":"2026-07-05T06:31:17.732712+00:00","updated_at":"2026-07-05T06:31:17.732712+00:00"}