{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:7P576ZQIQDQOFNAYNEWT5EKNTQ","short_pith_number":"pith:7P576ZQI","schema_version":"1.0","canonical_sha256":"fbfbff660880e0e2b418692d3e914d9c226d25e3912d8cb739ca55dd5bfdc7cb","source":{"kind":"arxiv","id":"2305.08455","version":3},"attestation_state":"computed","paper":{"title":"Document Understanding Dataset and Evaluation (DUDE)","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.CV","authors_text":"Bertrand Ackaert, Dawid Jurkiewicz, Ernest Valveny, Jordy Van Landeghem, {\\L}ukasz Borchmann, Matthew Blaschko, Micha{\\l} Pietruszka, Micka\\\"el Coustaty, Pawe{\\l} J\\'oziak, Rafa{\\l} Powalski, Rub\\'en Tito, Sien Moens, Tomasz Stanis{\\l}awek","submitted_at":"2023-05-15T08:54:32Z","abstract_excerpt":"We call on the Document AI (DocAI) community to reevaluate current methodologies and embrace the challenge of creating more practically-oriented benchmarks. Document Understanding Dataset and Evaluation (DUDE) seeks to remediate the halted research progress in understanding visually-rich documents (VRDs). We present a new dataset with novelties related to types of questions, answers, and document layouts based on multi-industry, multi-domain, and multi-page VRDs of various origins, and dates. Moreover, we are pushing the boundaries of current methods by creating multi-task and multi-domain eva"},"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":"2305.08455","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-05-15T08:54:32Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"da88c003e77653cc8e8f389b6996f0fac2871b820bbaf989ef957795c9884184","abstract_canon_sha256":"be267d8d6a5924a79db5d526ab1b121601317455f4cc56afcccf18b02ac4945a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:49:22.231972Z","signature_b64":"9Gn8dREPamUxreSLY/IsvFU+oESAJ2IGN6KNUqonBwAJd6B74fICCm3tIWgrhY5mq0SdBv2tuB7G2ZO1vpasAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fbfbff660880e0e2b418692d3e914d9c226d25e3912d8cb739ca55dd5bfdc7cb","last_reissued_at":"2026-07-05T06:49:22.231556Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:49:22.231556Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Document Understanding Dataset and Evaluation (DUDE)","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.CV","authors_text":"Bertrand Ackaert, Dawid Jurkiewicz, Ernest Valveny, Jordy Van Landeghem, {\\L}ukasz Borchmann, Matthew Blaschko, Micha{\\l} Pietruszka, Micka\\\"el Coustaty, Pawe{\\l} J\\'oziak, Rafa{\\l} Powalski, Rub\\'en Tito, Sien Moens, Tomasz Stanis{\\l}awek","submitted_at":"2023-05-15T08:54:32Z","abstract_excerpt":"We call on the Document AI (DocAI) community to reevaluate current methodologies and embrace the challenge of creating more practically-oriented benchmarks. Document Understanding Dataset and Evaluation (DUDE) seeks to remediate the halted research progress in understanding visually-rich documents (VRDs). We present a new dataset with novelties related to types of questions, answers, and document layouts based on multi-industry, multi-domain, and multi-page VRDs of various origins, and dates. Moreover, we are pushing the boundaries of current methods by creating multi-task and multi-domain eva"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.08455","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/2305.08455/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":"2305.08455","created_at":"2026-07-05T06:49:22.231605+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.08455v3","created_at":"2026-07-05T06:49:22.231605+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.08455","created_at":"2026-07-05T06:49:22.231605+00:00"},{"alias_kind":"pith_short_12","alias_value":"7P576ZQIQDQO","created_at":"2026-07-05T06:49:22.231605+00:00"},{"alias_kind":"pith_short_16","alias_value":"7P576ZQIQDQOFNAY","created_at":"2026-07-05T06:49:22.231605+00:00"},{"alias_kind":"pith_short_8","alias_value":"7P576ZQI","created_at":"2026-07-05T06:49:22.231605+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.02371","citing_title":"Internalized Reasoning for Long-Context Visual Document Understanding","ref_index":23,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7P576ZQIQDQOFNAYNEWT5EKNTQ","json":"https://pith.science/pith/7P576ZQIQDQOFNAYNEWT5EKNTQ.json","graph_json":"https://pith.science/api/pith-number/7P576ZQIQDQOFNAYNEWT5EKNTQ/graph.json","events_json":"https://pith.science/api/pith-number/7P576ZQIQDQOFNAYNEWT5EKNTQ/events.json","paper":"https://pith.science/paper/7P576ZQI"},"agent_actions":{"view_html":"https://pith.science/pith/7P576ZQIQDQOFNAYNEWT5EKNTQ","download_json":"https://pith.science/pith/7P576ZQIQDQOFNAYNEWT5EKNTQ.json","view_paper":"https://pith.science/paper/7P576ZQI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.08455&json=true","fetch_graph":"https://pith.science/api/pith-number/7P576ZQIQDQOFNAYNEWT5EKNTQ/graph.json","fetch_events":"https://pith.science/api/pith-number/7P576ZQIQDQOFNAYNEWT5EKNTQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7P576ZQIQDQOFNAYNEWT5EKNTQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7P576ZQIQDQOFNAYNEWT5EKNTQ/action/storage_attestation","attest_author":"https://pith.science/pith/7P576ZQIQDQOFNAYNEWT5EKNTQ/action/author_attestation","sign_citation":"https://pith.science/pith/7P576ZQIQDQOFNAYNEWT5EKNTQ/action/citation_signature","submit_replication":"https://pith.science/pith/7P576ZQIQDQOFNAYNEWT5EKNTQ/action/replication_record"}},"created_at":"2026-07-05T06:49:22.231605+00:00","updated_at":"2026-07-05T06:49:22.231605+00:00"}