{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:PO4CLVS6SEDJYE7EDKLR4HPDCE","short_pith_number":"pith:PO4CLVS6","schema_version":"1.0","canonical_sha256":"7bb825d65e91069c13e41a971e1de3113402ef5df4abde195f494645349cd5ad","source":{"kind":"arxiv","id":"2203.16618","version":3},"attestation_state":"computed","paper":{"title":"End-to-end Document Recognition and Understanding with Dessurt","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Brian Davis, Bryan Morse, Bryan Price, Chris Tensmeyer, Curtis Wigington, Vlad Morariu","submitted_at":"2022-03-30T19:02:53Z","abstract_excerpt":"We introduce Dessurt, a relatively simple document understanding transformer capable of being fine-tuned on a greater variety of document tasks than prior methods. It receives a document image and task string as input and generates arbitrary text autoregressively as output. Because Dessurt is an end-to-end architecture that performs text recognition in addition to the document understanding, it does not require an external recognition model as prior methods do. Dessurt is a more flexible model than prior methods and is able to handle a variety of document domains and tasks. We show that this m"},"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":"2203.16618","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-03-30T19:02:53Z","cross_cats_sorted":[],"title_canon_sha256":"a7a196c905dd371acb0a1fc3465d3b4344186d8f64a02c1cd13bd58f416daf20","abstract_canon_sha256":"af4c990318fabd2779fbf1fb0472b919a92924c3f2a9b120204cd3f63c14001a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:32:15.898023Z","signature_b64":"cc/qk8hMSrVZZqmtFPdnHMn/NqbKegSOlZWFGBBODncyLacpagcqd1k7PnWK962xkdIsQTbK15tjbdWTS9TMAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7bb825d65e91069c13e41a971e1de3113402ef5df4abde195f494645349cd5ad","last_reissued_at":"2026-07-05T04:32:15.897499Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:32:15.897499Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"End-to-end Document Recognition and Understanding with Dessurt","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Brian Davis, Bryan Morse, Bryan Price, Chris Tensmeyer, Curtis Wigington, Vlad Morariu","submitted_at":"2022-03-30T19:02:53Z","abstract_excerpt":"We introduce Dessurt, a relatively simple document understanding transformer capable of being fine-tuned on a greater variety of document tasks than prior methods. It receives a document image and task string as input and generates arbitrary text autoregressively as output. Because Dessurt is an end-to-end architecture that performs text recognition in addition to the document understanding, it does not require an external recognition model as prior methods do. Dessurt is a more flexible model than prior methods and is able to handle a variety of document domains and tasks. We show that this m"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.16618","kind":"arxiv","version":3},"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/2203.16618/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":"2203.16618","created_at":"2026-07-05T04:32:15.897564+00:00"},{"alias_kind":"arxiv_version","alias_value":"2203.16618v3","created_at":"2026-07-05T04:32:15.897564+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.16618","created_at":"2026-07-05T04:32:15.897564+00:00"},{"alias_kind":"pith_short_12","alias_value":"PO4CLVS6SEDJ","created_at":"2026-07-05T04:32:15.897564+00:00"},{"alias_kind":"pith_short_16","alias_value":"PO4CLVS6SEDJYE7E","created_at":"2026-07-05T04:32:15.897564+00:00"},{"alias_kind":"pith_short_8","alias_value":"PO4CLVS6","created_at":"2026-07-05T04:32:15.897564+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2308.13418","citing_title":"Nougat: Neural Optical Understanding for Academic Documents","ref_index":31,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PO4CLVS6SEDJYE7EDKLR4HPDCE","json":"https://pith.science/pith/PO4CLVS6SEDJYE7EDKLR4HPDCE.json","graph_json":"https://pith.science/api/pith-number/PO4CLVS6SEDJYE7EDKLR4HPDCE/graph.json","events_json":"https://pith.science/api/pith-number/PO4CLVS6SEDJYE7EDKLR4HPDCE/events.json","paper":"https://pith.science/paper/PO4CLVS6"},"agent_actions":{"view_html":"https://pith.science/pith/PO4CLVS6SEDJYE7EDKLR4HPDCE","download_json":"https://pith.science/pith/PO4CLVS6SEDJYE7EDKLR4HPDCE.json","view_paper":"https://pith.science/paper/PO4CLVS6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2203.16618&json=true","fetch_graph":"https://pith.science/api/pith-number/PO4CLVS6SEDJYE7EDKLR4HPDCE/graph.json","fetch_events":"https://pith.science/api/pith-number/PO4CLVS6SEDJYE7EDKLR4HPDCE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PO4CLVS6SEDJYE7EDKLR4HPDCE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PO4CLVS6SEDJYE7EDKLR4HPDCE/action/storage_attestation","attest_author":"https://pith.science/pith/PO4CLVS6SEDJYE7EDKLR4HPDCE/action/author_attestation","sign_citation":"https://pith.science/pith/PO4CLVS6SEDJYE7EDKLR4HPDCE/action/citation_signature","submit_replication":"https://pith.science/pith/PO4CLVS6SEDJYE7EDKLR4HPDCE/action/replication_record"}},"created_at":"2026-07-05T04:32:15.897564+00:00","updated_at":"2026-07-05T04:32:15.897564+00:00"}