{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:X44SSCITGSCVYWSLI672QLYYDC","short_pith_number":"pith:X44SSCIT","canonical_record":{"source":{"id":"2410.15484","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-10-20T19:42:30Z","cross_cats_sorted":[],"title_canon_sha256":"04fe2a0d8ba0ea152b526235d5601b71b3a42be955ee3c76f43b9b91984a2f7e","abstract_canon_sha256":"2e6ad22820a55c6f67cb3a39b778885dde0e01055b1f367d01e03471d26aca49"},"schema_version":"1.0"},"canonical_sha256":"bf3929091334855c5a4b47bfa82f1818b30128c500cfa54f246cac78da8f9323","source":{"kind":"arxiv","id":"2410.15484","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.15484","created_at":"2026-07-05T09:41:43Z"},{"alias_kind":"arxiv_version","alias_value":"2410.15484v1","created_at":"2026-07-05T09:41:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.15484","created_at":"2026-07-05T09:41:43Z"},{"alias_kind":"pith_short_12","alias_value":"X44SSCITGSCV","created_at":"2026-07-05T09:41:43Z"},{"alias_kind":"pith_short_16","alias_value":"X44SSCITGSCVYWSL","created_at":"2026-07-05T09:41:43Z"},{"alias_kind":"pith_short_8","alias_value":"X44SSCIT","created_at":"2026-07-05T09:41:43Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:X44SSCITGSCVYWSLI672QLYYDC","target":"record","payload":{"canonical_record":{"source":{"id":"2410.15484","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-10-20T19:42:30Z","cross_cats_sorted":[],"title_canon_sha256":"04fe2a0d8ba0ea152b526235d5601b71b3a42be955ee3c76f43b9b91984a2f7e","abstract_canon_sha256":"2e6ad22820a55c6f67cb3a39b778885dde0e01055b1f367d01e03471d26aca49"},"schema_version":"1.0"},"canonical_sha256":"bf3929091334855c5a4b47bfa82f1818b30128c500cfa54f246cac78da8f9323","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:41:43.273615Z","signature_b64":"61pWklh9pOo1ExZ884PC6mQ38lWpF23hqRT9mKILcRSjHiOeteIKOhrAOimZ5Tqr6Wlv4u65DwvGavCn2CL6Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bf3929091334855c5a4b47bfa82f1818b30128c500cfa54f246cac78da8f9323","last_reissued_at":"2026-07-05T09:41:43.273109Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:41:43.273109Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2410.15484","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":"2026-07-05T09:41:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2x/Av3VnJ4NHeJPRZzo0tkMrGUMlfDnFR0kNwiMnETEB33Y19PGv66G05GnyS++WUZXKHlTuXl+t0nk0TSGVAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T13:07:14.970637Z"},"content_sha256":"4fa6e5a4e40a517451579f22a4733b9e479e72a65942dec711e5f9b59148d5ea","schema_version":"1.0","event_id":"sha256:4fa6e5a4e40a517451579f22a4733b9e479e72a65942dec711e5f9b59148d5ea"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:X44SSCITGSCVYWSLI672QLYYDC","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"\"What is the value of {templates}?\" Rethinking Document Information Extraction Datasets for LLMs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Armineh Nourbakhsh, Manuela Veloso, Mathieu Sibue, Pranav Shetty, Ran Zmigrod, Xiaomo Liu, Zhiqiang Ma","submitted_at":"2024-10-20T19:42:30Z","abstract_excerpt":"The rise of large language models (LLMs) for visually rich document understanding (VRDU) has kindled a need for prompt-response, document-based datasets. As annotating new datasets from scratch is labor-intensive, the existing literature has generated prompt-response datasets from available resources using simple templates. For the case of key information extraction (KIE), one of the most common VRDU tasks, past work has typically employed the template \"What is the value for the {key}?\". However, given the variety of questions encountered in the wild, simple and uniform templates are insuffici"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.15484","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/2410.15484/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":"2026-07-05T09:41:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WWd4TYFLA3DqAoUT9PhS9Cu6oyDmxI4DgXL9m4RUcFqhFIjbbD82SslR/srbqMcGJqecLiInwgaaqNQTJFs2Bg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T13:07:14.971005Z"},"content_sha256":"c6a478e5c1851f8789f2a812fcf13e2700bd748b1fe8bda556758cf07acd31d1","schema_version":"1.0","event_id":"sha256:c6a478e5c1851f8789f2a812fcf13e2700bd748b1fe8bda556758cf07acd31d1"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/X44SSCITGSCVYWSLI672QLYYDC/bundle.json","state_url":"https://pith.science/pith/X44SSCITGSCVYWSLI672QLYYDC/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/X44SSCITGSCVYWSLI672QLYYDC/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":"2026-07-06T13:07:14Z","links":{"resolver":"https://pith.science/pith/X44SSCITGSCVYWSLI672QLYYDC","bundle":"https://pith.science/pith/X44SSCITGSCVYWSLI672QLYYDC/bundle.json","state":"https://pith.science/pith/X44SSCITGSCVYWSLI672QLYYDC/state.json","well_known_bundle":"https://pith.science/.well-known/pith/X44SSCITGSCVYWSLI672QLYYDC/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:X44SSCITGSCVYWSLI672QLYYDC","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":"2e6ad22820a55c6f67cb3a39b778885dde0e01055b1f367d01e03471d26aca49","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-10-20T19:42:30Z","title_canon_sha256":"04fe2a0d8ba0ea152b526235d5601b71b3a42be955ee3c76f43b9b91984a2f7e"},"schema_version":"1.0","source":{"id":"2410.15484","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.15484","created_at":"2026-07-05T09:41:43Z"},{"alias_kind":"arxiv_version","alias_value":"2410.15484v1","created_at":"2026-07-05T09:41:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.15484","created_at":"2026-07-05T09:41:43Z"},{"alias_kind":"pith_short_12","alias_value":"X44SSCITGSCV","created_at":"2026-07-05T09:41:43Z"},{"alias_kind":"pith_short_16","alias_value":"X44SSCITGSCVYWSL","created_at":"2026-07-05T09:41:43Z"},{"alias_kind":"pith_short_8","alias_value":"X44SSCIT","created_at":"2026-07-05T09:41:43Z"}],"graph_snapshots":[{"event_id":"sha256:c6a478e5c1851f8789f2a812fcf13e2700bd748b1fe8bda556758cf07acd31d1","target":"graph","created_at":"2026-07-05T09:41:43Z","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/2410.15484/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The rise of large language models (LLMs) for visually rich document understanding (VRDU) has kindled a need for prompt-response, document-based datasets. As annotating new datasets from scratch is labor-intensive, the existing literature has generated prompt-response datasets from available resources using simple templates. For the case of key information extraction (KIE), one of the most common VRDU tasks, past work has typically employed the template \"What is the value for the {key}?\". However, given the variety of questions encountered in the wild, simple and uniform templates are insuffici","authors_text":"Armineh Nourbakhsh, Manuela Veloso, Mathieu Sibue, Pranav Shetty, Ran Zmigrod, Xiaomo Liu, Zhiqiang Ma","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-10-20T19:42:30Z","title":"\"What is the value of {templates}?\" Rethinking Document Information Extraction Datasets for LLMs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.15484","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":"sha256:4fa6e5a4e40a517451579f22a4733b9e479e72a65942dec711e5f9b59148d5ea","target":"record","created_at":"2026-07-05T09:41:43Z","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":"2e6ad22820a55c6f67cb3a39b778885dde0e01055b1f367d01e03471d26aca49","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-10-20T19:42:30Z","title_canon_sha256":"04fe2a0d8ba0ea152b526235d5601b71b3a42be955ee3c76f43b9b91984a2f7e"},"schema_version":"1.0","source":{"id":"2410.15484","kind":"arxiv","version":1}},"canonical_sha256":"bf3929091334855c5a4b47bfa82f1818b30128c500cfa54f246cac78da8f9323","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"bf3929091334855c5a4b47bfa82f1818b30128c500cfa54f246cac78da8f9323","first_computed_at":"2026-07-05T09:41:43.273109Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:41:43.273109Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"61pWklh9pOo1ExZ884PC6mQ38lWpF23hqRT9mKILcRSjHiOeteIKOhrAOimZ5Tqr6Wlv4u65DwvGavCn2CL6Dg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:41:43.273615Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.15484","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4fa6e5a4e40a517451579f22a4733b9e479e72a65942dec711e5f9b59148d5ea","sha256:c6a478e5c1851f8789f2a812fcf13e2700bd748b1fe8bda556758cf07acd31d1"],"state_sha256":"642fccd9c05ddc60572348515916b3cac549543e9ac385121c31e5691a60ffca"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"uDxbOgY0lCe2d0cqGcdl0cbQdYfw35Wi5DP54NoYVz/fKRzxiswoSCM/l8izex0Z4drpDhRw6PQMHNkQnXZhCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-06T13:07:14.973150Z","bundle_sha256":"33d847839588752a0e777bb02a12acd43e59a0f5f8a7250851014f879aa2ce86"}}