{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:5K7EBAX3N2XKZKUW6EMFI6DQQY","short_pith_number":"pith:5K7EBAX3","canonical_record":{"source":{"id":"2211.15421","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2022-11-15T03:17:07Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"e89fa3a1f16f4f8b7cbaf90df995bb68af1443b2192ef8228e4b376ed28ced08","abstract_canon_sha256":"dda4935b37e177c201effa56bb58093816ba8c56b1a8a20e8477bd0b20e161ff"},"schema_version":"1.0"},"canonical_sha256":"eabe4082fb6eaeacaa96f118547870862476a49fa0192f090de6b4990d957605","source":{"kind":"arxiv","id":"2211.15421","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2211.15421","created_at":"2026-07-05T06:51:20Z"},{"alias_kind":"arxiv_version","alias_value":"2211.15421v3","created_at":"2026-07-05T06:51:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.15421","created_at":"2026-07-05T06:51:20Z"},{"alias_kind":"pith_short_12","alias_value":"5K7EBAX3N2XK","created_at":"2026-07-05T06:51:20Z"},{"alias_kind":"pith_short_16","alias_value":"5K7EBAX3N2XKZKUW","created_at":"2026-07-05T06:51:20Z"},{"alias_kind":"pith_short_8","alias_value":"5K7EBAX3","created_at":"2026-07-05T06:51:20Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:5K7EBAX3N2XKZKUW6EMFI6DQQY","target":"record","payload":{"canonical_record":{"source":{"id":"2211.15421","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2022-11-15T03:17:07Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"e89fa3a1f16f4f8b7cbaf90df995bb68af1443b2192ef8228e4b376ed28ced08","abstract_canon_sha256":"dda4935b37e177c201effa56bb58093816ba8c56b1a8a20e8477bd0b20e161ff"},"schema_version":"1.0"},"canonical_sha256":"eabe4082fb6eaeacaa96f118547870862476a49fa0192f090de6b4990d957605","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:51:20.873241Z","signature_b64":"8iJEdOqyAvPmquAz9wR6Ws+654P8hGRPhJvgF81vqAHVU+im2MZA3vxPwBxVD2QPxb5TOe+esFUssOn8MATHCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"eabe4082fb6eaeacaa96f118547870862476a49fa0192f090de6b4990d957605","last_reissued_at":"2026-07-05T06:51:20.872697Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:51:20.872697Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2211.15421","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T06:51:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"pIV2aNLr9yyLazGGR55CmR6jx8i1NYx/p7SzEa8J+pY+TCpB+tRvjB5F4qH7B6CRY8rCE3xyBMZqlg3z0+PhCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T15:08:11.578133Z"},"content_sha256":"6b5c0f14652920e8b2e1716d273d0e1939292fc4a102ebd80fff4952abb5c54b","schema_version":"1.0","event_id":"sha256:6b5c0f14652920e8b2e1716d273d0e1939292fc4a102ebd80fff4952abb5c54b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:5K7EBAX3N2XKZKUW6EMFI6DQQY","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"VRDU: A Benchmark for Visually-rich Document Understanding","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Chen-Yu Lee, Sandeep Tata, Wei Wei, Yichao Zhou, Zilong Wang","submitted_at":"2022-11-15T03:17:07Z","abstract_excerpt":"Understanding visually-rich business documents to extract structured data and automate business workflows has been receiving attention both in academia and industry. Although recent multi-modal language models have achieved impressive results, we find that existing benchmarks do not reflect the complexity of real documents seen in industry. In this work, we identify the desiderata for a more comprehensive benchmark and propose one we call Visually Rich Document Understanding (VRDU). VRDU contains two datasets that represent several challenges: rich schema including diverse data types as well a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.15421","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/2211.15421/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T06:51:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Q4amE7OXPEtlGVg82QzbuCIEK0Gy+JuU4hTi7eeT8ES9bOj0KsKdqEyEUitveWBubufSe1aq2ZvgFG9cvB25Dg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T15:08:11.578438Z"},"content_sha256":"b3a5c3170d95d3d2f17501f07bba57372ac3499745069e8c886f9125e1f20ef0","schema_version":"1.0","event_id":"sha256:b3a5c3170d95d3d2f17501f07bba57372ac3499745069e8c886f9125e1f20ef0"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/5K7EBAX3N2XKZKUW6EMFI6DQQY/bundle.json","state_url":"https://pith.science/pith/5K7EBAX3N2XKZKUW6EMFI6DQQY/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/5K7EBAX3N2XKZKUW6EMFI6DQQY/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-11T15:08:11Z","links":{"resolver":"https://pith.science/pith/5K7EBAX3N2XKZKUW6EMFI6DQQY","bundle":"https://pith.science/pith/5K7EBAX3N2XKZKUW6EMFI6DQQY/bundle.json","state":"https://pith.science/pith/5K7EBAX3N2XKZKUW6EMFI6DQQY/state.json","well_known_bundle":"https://pith.science/.well-known/pith/5K7EBAX3N2XKZKUW6EMFI6DQQY/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:5K7EBAX3N2XKZKUW6EMFI6DQQY","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"dda4935b37e177c201effa56bb58093816ba8c56b1a8a20e8477bd0b20e161ff","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2022-11-15T03:17:07Z","title_canon_sha256":"e89fa3a1f16f4f8b7cbaf90df995bb68af1443b2192ef8228e4b376ed28ced08"},"schema_version":"1.0","source":{"id":"2211.15421","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2211.15421","created_at":"2026-07-05T06:51:20Z"},{"alias_kind":"arxiv_version","alias_value":"2211.15421v3","created_at":"2026-07-05T06:51:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.15421","created_at":"2026-07-05T06:51:20Z"},{"alias_kind":"pith_short_12","alias_value":"5K7EBAX3N2XK","created_at":"2026-07-05T06:51:20Z"},{"alias_kind":"pith_short_16","alias_value":"5K7EBAX3N2XKZKUW","created_at":"2026-07-05T06:51:20Z"},{"alias_kind":"pith_short_8","alias_value":"5K7EBAX3","created_at":"2026-07-05T06:51:20Z"}],"graph_snapshots":[{"event_id":"sha256:b3a5c3170d95d3d2f17501f07bba57372ac3499745069e8c886f9125e1f20ef0","target":"graph","created_at":"2026-07-05T06:51:20Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2211.15421/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Understanding visually-rich business documents to extract structured data and automate business workflows has been receiving attention both in academia and industry. Although recent multi-modal language models have achieved impressive results, we find that existing benchmarks do not reflect the complexity of real documents seen in industry. In this work, we identify the desiderata for a more comprehensive benchmark and propose one we call Visually Rich Document Understanding (VRDU). VRDU contains two datasets that represent several challenges: rich schema including diverse data types as well a","authors_text":"Chen-Yu Lee, Sandeep Tata, Wei Wei, Yichao Zhou, Zilong Wang","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2022-11-15T03:17:07Z","title":"VRDU: A Benchmark for Visually-rich Document Understanding"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.15421","kind":"arxiv","version":3},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:6b5c0f14652920e8b2e1716d273d0e1939292fc4a102ebd80fff4952abb5c54b","target":"record","created_at":"2026-07-05T06:51:20Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"dda4935b37e177c201effa56bb58093816ba8c56b1a8a20e8477bd0b20e161ff","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2022-11-15T03:17:07Z","title_canon_sha256":"e89fa3a1f16f4f8b7cbaf90df995bb68af1443b2192ef8228e4b376ed28ced08"},"schema_version":"1.0","source":{"id":"2211.15421","kind":"arxiv","version":3}},"canonical_sha256":"eabe4082fb6eaeacaa96f118547870862476a49fa0192f090de6b4990d957605","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"eabe4082fb6eaeacaa96f118547870862476a49fa0192f090de6b4990d957605","first_computed_at":"2026-07-05T06:51:20.872697Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:51:20.872697Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"8iJEdOqyAvPmquAz9wR6Ws+654P8hGRPhJvgF81vqAHVU+im2MZA3vxPwBxVD2QPxb5TOe+esFUssOn8MATHCg==","signature_status":"signed_v1","signed_at":"2026-07-05T06:51:20.873241Z","signed_message":"canonical_sha256_bytes"},"source_id":"2211.15421","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6b5c0f14652920e8b2e1716d273d0e1939292fc4a102ebd80fff4952abb5c54b","sha256:b3a5c3170d95d3d2f17501f07bba57372ac3499745069e8c886f9125e1f20ef0"],"state_sha256":"9d4c08db84ed028dbae934dccaeb92ef8bb9f36cf490d36adcf6881e21412845"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Q79l0+Q8fQwxetNn9yJrYEUlMvU9xI9wh1LQA45yAm1xEBlMswagNMn7rHF65oq5wQ+qhGy958UHNlaDa6AiAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-11T15:08:11.580786Z","bundle_sha256":"9ea4218ab454e303593d18aa8cf3e0d9964f11da39c6997005d02343a1814e30"}}