{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/end-to-end-document-recognition-and","title":"End-to-end Document Recognition and Understanding with Dessurt","arxiv_id":"2203.16618","date":"2022-03-30","proceeding":null,"authors":["Brian Davis","Bryan Morse","Bryan Price","Chris Tensmeyer","Curtis Wigington","Vlad Morariu"],"abstract":"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 model is effective at 9 different dataset-task combinations.","url_abs":"https://arxiv.org/abs/2203.16618v3","url_pdf":"https://arxiv.org/pdf/2203.16618v3.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"end-to-end-document-recognition-and","repo_url":"https://github.com/herobd/dessurt","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"end-to-end-document-recognition-and","repo_url":"https://github.com/herobd/NAF_dataset","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"NOASSERTION"}}],"tasks":[{"task_slug":"visual-question-answering","task_name":"Visual Question Answering (VQA)"},{"task_slug":"document-understanding","task_name":"document understanding"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/visual-question-answering-on-docvqa-test","task":"Visual Question Answering (VQA)","dataset":"DocVQA test","model":"Dessurt","rank_in_archive_order":32,"of":33,"metrics":{"ANLS":"0.632"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2203.16618","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2203.16618"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/herobd/NAF_dataset","reach":{"status":"ok","spdx":"NOASSERTION"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/herobd/dessurt","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"unverified":11},"by_repo_kind":{"official":{"samples":11,"ran":0,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"878f53e85ae3fbfd","entry":"addPair","repo":"herobd/dessurt","repo_kind":"official","path":"gpt_forms.py","file_url":"https://github.com/herobd/dessurt/blob/HEAD/gpt_forms.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"878f53e85ae3fbfd"}},{"code_sha256_prefix":"89ca2234fcb6c0d7","entry":"attention","repo":"herobd/dessurt","repo_kind":"official","path":"model/attention.py","file_url":"https://github.com/herobd/dessurt/blob/HEAD/model/attention.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"89ca2234fcb6c0d7"}},{"code_sha256_prefix":"14af88ba47b4b98a","entry":"clones","repo":"herobd/dessurt","repo_kind":"official","path":"model/attention.py","file_url":"https://github.com/herobd/dessurt/blob/HEAD/model/attention.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"14af88ba47b4b98a"}},{"code_sha256_prefix":"0ba1f51d68df0e77","entry":"findNonEscaped","repo":"herobd/dessurt","repo_kind":"official","path":"funsd_eval_json.py","file_url":"https://github.com/herobd/dessurt/blob/HEAD/funsd_eval_json.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"0ba1f51d68df0e77"}},{"code_sha256_prefix":"0b062bbeed5dd70a","entry":"getScore","repo":"herobd/dessurt","repo_kind":"official","path":"get_GAnTED_for_Dessurt.py","file_url":"https://github.com/herobd/dessurt/blob/HEAD/get_GAnTED_for_Dessurt.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"0b062bbeed5dd70a"}},{"code_sha256_prefix":"829347111c022cc9","entry":"learned_attention","repo":"herobd/dessurt","repo_kind":"official","path":"model/attention.py","file_url":"https://github.com/herobd/dessurt/blob/HEAD/model/attention.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"829347111c022cc9"}},{"code_sha256_prefix":"9b37cbfef516510b","entry":"my_loss","repo":"herobd/dessurt","repo_kind":"official","path":"model/loss.py","file_url":"https://github.com/herobd/dessurt/blob/HEAD/model/loss.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"9b37cbfef516510b"}},{"code_sha256_prefix":"51d1cddcc7ad2f46","entry":"parseOutput","repo":"herobd/dessurt","repo_kind":"official","path":"gpt_forms.py","file_url":"https://github.com/herobd/dessurt/blob/HEAD/gpt_forms.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"51d1cddcc7ad2f46"}},{"code_sha256_prefix":"bce0e34f850f8471","entry":"rfindNonEscaped","repo":"herobd/dessurt","repo_kind":"official","path":"funsd_eval_json.py","file_url":"https://github.com/herobd/dessurt/blob/HEAD/funsd_eval_json.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"bce0e34f850f8471"}},{"code_sha256_prefix":"6324a51484358da4","entry":"sigmoid_BCE_loss","repo":"herobd/dessurt","repo_kind":"official","path":"model/loss.py","file_url":"https://github.com/herobd/dessurt/blob/HEAD/model/loss.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"6324a51484358da4"}},{"code_sha256_prefix":"2ed706c4d8f6c76f","entry":"sigmoid_BCE_mask_loss","repo":"herobd/dessurt","repo_kind":"official","path":"model/loss.py","file_url":"https://github.com/herobd/dessurt/blob/HEAD/model/loss.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"2ed706c4d8f6c76f"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}