{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:PQXR3ZXTNSROROXIN6RXSJCJ6P","short_pith_number":"pith:PQXR3ZXT","canonical_record":{"source":{"id":"2404.04003","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-04-05T10:26:42Z","cross_cats_sorted":[],"title_canon_sha256":"e37cbbd05267b69152a5b37c10dc4d62c60ceef41456133ba749d5b65c9dfdb2","abstract_canon_sha256":"1b7b3201ef8f70c56d88061e90c514052cd819ec9c61a769487a4be8bae31b93"},"schema_version":"1.0"},"canonical_sha256":"7c2f1de6f36ca2e8bae86fa3792449f3e4382b1f6302aba2998d795305888548","source":{"kind":"arxiv","id":"2404.04003","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.04003","created_at":"2026-07-05T08:04:44Z"},{"alias_kind":"arxiv_version","alias_value":"2404.04003v1","created_at":"2026-07-05T08:04:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.04003","created_at":"2026-07-05T08:04:44Z"},{"alias_kind":"pith_short_12","alias_value":"PQXR3ZXTNSRO","created_at":"2026-07-05T08:04:44Z"},{"alias_kind":"pith_short_16","alias_value":"PQXR3ZXTNSROROXI","created_at":"2026-07-05T08:04:44Z"},{"alias_kind":"pith_short_8","alias_value":"PQXR3ZXT","created_at":"2026-07-05T08:04:44Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:PQXR3ZXTNSROROXIN6RXSJCJ6P","target":"record","payload":{"canonical_record":{"source":{"id":"2404.04003","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-04-05T10:26:42Z","cross_cats_sorted":[],"title_canon_sha256":"e37cbbd05267b69152a5b37c10dc4d62c60ceef41456133ba749d5b65c9dfdb2","abstract_canon_sha256":"1b7b3201ef8f70c56d88061e90c514052cd819ec9c61a769487a4be8bae31b93"},"schema_version":"1.0"},"canonical_sha256":"7c2f1de6f36ca2e8bae86fa3792449f3e4382b1f6302aba2998d795305888548","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:04:44.240345Z","signature_b64":"2aJBH7tUp7oHpT8UZa1Ua7p/m3mG6ZiedlKq/kwl0J6ppWd72T8FZzfR7wDpf4YWliYwkZKFDpXa4VsUhw9lCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7c2f1de6f36ca2e8bae86fa3792449f3e4382b1f6302aba2998d795305888548","last_reissued_at":"2026-07-05T08:04:44.239877Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:04:44.239877Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2404.04003","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:04:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"m6RfUq9i4Mtq4u6WaGNCOywWwP0F+3kbmxcN2gEErJp4SFXo0MSqKC/a4al9Q1MzCT2Nn9d7dap/VbuPgjdhAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T20:48:04.444369Z"},"content_sha256":"40c36c6df6fc819d74124e6ccf194584f19b5838ff7f2013c894c82bd6104b71","schema_version":"1.0","event_id":"sha256:40c36c6df6fc819d74124e6ccf194584f19b5838ff7f2013c894c82bd6104b71"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:PQXR3ZXTNSROROXIN6RXSJCJ6P","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"BuDDIE: A Business Document Dataset for Multi-task Information Extraction","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Antony Papadimitriou, Armineh Nourbakhsh, Dongsheng Wang, Ivan Brugere, Mathieu Sibue, Nacho Navarro, Petr Babkin, Ran Zmigrod, Sameena Shah, William Watson, Xiaomo Liu, Yulong Pei, Zhiqiang Ma","submitted_at":"2024-04-05T10:26:42Z","abstract_excerpt":"The field of visually rich document understanding (VRDU) aims to solve a multitude of well-researched NLP tasks in a multi-modal domain. Several datasets exist for research on specific tasks of VRDU such as document classification (DC), key entity extraction (KEE), entity linking, visual question answering (VQA), inter alia. These datasets cover documents like invoices and receipts with sparse annotations such that they support one or two co-related tasks (e.g., entity extraction and entity linking). Unfortunately, only focusing on a single specific of documents or task is not representative o"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.04003","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/2404.04003/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":"2026-07-05T08:04:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"h5g6MYyB0G/PTosP62s1BpCvVcISlPfQGu8JBCe+1tdDvR1z5mqtwUIXtTCFXFrz+zs0Y7w0QazaS637H5hhAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T20:48:04.444765Z"},"content_sha256":"09dc708e4727ab5596023bae886111551ed534e710071c7f852d57d064bbb028","schema_version":"1.0","event_id":"sha256:09dc708e4727ab5596023bae886111551ed534e710071c7f852d57d064bbb028"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/PQXR3ZXTNSROROXIN6RXSJCJ6P/bundle.json","state_url":"https://pith.science/pith/PQXR3ZXTNSROROXIN6RXSJCJ6P/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/PQXR3ZXTNSROROXIN6RXSJCJ6P/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":"2026-07-06T20:48:04Z","links":{"resolver":"https://pith.science/pith/PQXR3ZXTNSROROXIN6RXSJCJ6P","bundle":"https://pith.science/pith/PQXR3ZXTNSROROXIN6RXSJCJ6P/bundle.json","state":"https://pith.science/pith/PQXR3ZXTNSROROXIN6RXSJCJ6P/state.json","well_known_bundle":"https://pith.science/.well-known/pith/PQXR3ZXTNSROROXIN6RXSJCJ6P/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:PQXR3ZXTNSROROXIN6RXSJCJ6P","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":"1b7b3201ef8f70c56d88061e90c514052cd819ec9c61a769487a4be8bae31b93","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-04-05T10:26:42Z","title_canon_sha256":"e37cbbd05267b69152a5b37c10dc4d62c60ceef41456133ba749d5b65c9dfdb2"},"schema_version":"1.0","source":{"id":"2404.04003","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.04003","created_at":"2026-07-05T08:04:44Z"},{"alias_kind":"arxiv_version","alias_value":"2404.04003v1","created_at":"2026-07-05T08:04:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.04003","created_at":"2026-07-05T08:04:44Z"},{"alias_kind":"pith_short_12","alias_value":"PQXR3ZXTNSRO","created_at":"2026-07-05T08:04:44Z"},{"alias_kind":"pith_short_16","alias_value":"PQXR3ZXTNSROROXI","created_at":"2026-07-05T08:04:44Z"},{"alias_kind":"pith_short_8","alias_value":"PQXR3ZXT","created_at":"2026-07-05T08:04:44Z"}],"graph_snapshots":[{"event_id":"sha256:09dc708e4727ab5596023bae886111551ed534e710071c7f852d57d064bbb028","target":"graph","created_at":"2026-07-05T08:04:44Z","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/2404.04003/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The field of visually rich document understanding (VRDU) aims to solve a multitude of well-researched NLP tasks in a multi-modal domain. Several datasets exist for research on specific tasks of VRDU such as document classification (DC), key entity extraction (KEE), entity linking, visual question answering (VQA), inter alia. These datasets cover documents like invoices and receipts with sparse annotations such that they support one or two co-related tasks (e.g., entity extraction and entity linking). Unfortunately, only focusing on a single specific of documents or task is not representative o","authors_text":"Antony Papadimitriou, Armineh Nourbakhsh, Dongsheng Wang, Ivan Brugere, Mathieu Sibue, Nacho Navarro, Petr Babkin, Ran Zmigrod, Sameena Shah, William Watson, Xiaomo Liu, Yulong Pei, Zhiqiang Ma","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-04-05T10:26:42Z","title":"BuDDIE: A Business Document Dataset for Multi-task Information Extraction"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.04003","kind":"arxiv","version":1},"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":"sha256:40c36c6df6fc819d74124e6ccf194584f19b5838ff7f2013c894c82bd6104b71","target":"record","created_at":"2026-07-05T08:04:44Z","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":"1b7b3201ef8f70c56d88061e90c514052cd819ec9c61a769487a4be8bae31b93","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-04-05T10:26:42Z","title_canon_sha256":"e37cbbd05267b69152a5b37c10dc4d62c60ceef41456133ba749d5b65c9dfdb2"},"schema_version":"1.0","source":{"id":"2404.04003","kind":"arxiv","version":1}},"canonical_sha256":"7c2f1de6f36ca2e8bae86fa3792449f3e4382b1f6302aba2998d795305888548","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7c2f1de6f36ca2e8bae86fa3792449f3e4382b1f6302aba2998d795305888548","first_computed_at":"2026-07-05T08:04:44.239877Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:04:44.239877Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"2aJBH7tUp7oHpT8UZa1Ua7p/m3mG6ZiedlKq/kwl0J6ppWd72T8FZzfR7wDpf4YWliYwkZKFDpXa4VsUhw9lCA==","signature_status":"signed_v1","signed_at":"2026-07-05T08:04:44.240345Z","signed_message":"canonical_sha256_bytes"},"source_id":"2404.04003","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:40c36c6df6fc819d74124e6ccf194584f19b5838ff7f2013c894c82bd6104b71","sha256:09dc708e4727ab5596023bae886111551ed534e710071c7f852d57d064bbb028"],"state_sha256":"e7605aee9a6708b7bf22add47cf1fb63b15ceaac275dc8820f81b402211bb57c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"auGe24jbyUKI3bwABgeDjReEiWeUYTDIyVwkOmKgBTRBMnkoLD6BNAXBxvM/ALiLH346AnpueEiw/bg3cN43BA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-06T20:48:04.446760Z","bundle_sha256":"e8bb865acb6ffd148f2f6edcedcd8b1974a45b6d4d1500ad058b612e3dccdf93"}}