{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:LYR4L4ZWUB2UITDL32HJOEQT3P","short_pith_number":"pith:LYR4L4ZW","canonical_record":{"source":{"id":"2309.08872","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-09-16T04:29:05Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"9827f853b83acd241590a1bd4b3bbf397eec1225042efda0c9dd9722d2d9d027","abstract_canon_sha256":"7958820ba37aac679fae7e572e3795b35334b6c62c79ff36f21f92fef72eed95"},"schema_version":"1.0"},"canonical_sha256":"5e23c5f336a075444c6bde8e971213dbd3b252201db0015008073a7282a7785b","source":{"kind":"arxiv","id":"2309.08872","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2309.08872","created_at":"2026-07-05T07:10:28Z"},{"alias_kind":"arxiv_version","alias_value":"2309.08872v2","created_at":"2026-07-05T07:10:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.08872","created_at":"2026-07-05T07:10:28Z"},{"alias_kind":"pith_short_12","alias_value":"LYR4L4ZWUB2U","created_at":"2026-07-05T07:10:28Z"},{"alias_kind":"pith_short_16","alias_value":"LYR4L4ZWUB2UITDL","created_at":"2026-07-05T07:10:28Z"},{"alias_kind":"pith_short_8","alias_value":"LYR4L4ZW","created_at":"2026-07-05T07:10:28Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:LYR4L4ZWUB2UITDL32HJOEQT3P","target":"record","payload":{"canonical_record":{"source":{"id":"2309.08872","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-09-16T04:29:05Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"9827f853b83acd241590a1bd4b3bbf397eec1225042efda0c9dd9722d2d9d027","abstract_canon_sha256":"7958820ba37aac679fae7e572e3795b35334b6c62c79ff36f21f92fef72eed95"},"schema_version":"1.0"},"canonical_sha256":"5e23c5f336a075444c6bde8e971213dbd3b252201db0015008073a7282a7785b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:10:28.286514Z","signature_b64":"YuSFjZqPX8Ppw++OS+JwImwppuu1ru4Z4VCMl7ILlb4dsD9ElLe/64UjA7SM9PkCnt+Rg4bhRAEmXG9euyeEAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5e23c5f336a075444c6bde8e971213dbd3b252201db0015008073a7282a7785b","last_reissued_at":"2026-07-05T07:10:28.286030Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:10:28.286030Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2309.08872","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:10:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"R83/r/FkRsYEQYTCtPdQxJKV/9o9frDFed1GE0zx1AXOm2TyQbBcvC+KWaMXldniqA3+K4gt+/sYZuj9bxFIAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T22:59:01.272247Z"},"content_sha256":"cd556ab1f9eaa66fcfd7bbc81bfa0c7e0c23a23f76cbd19956419094d0987590","schema_version":"1.0","event_id":"sha256:cd556ab1f9eaa66fcfd7bbc81bfa0c7e0c23a23f76cbd19956419094d0987590"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:LYR4L4ZWUB2UITDL32HJOEQT3P","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"PDFTriage: Question Answering over Long, Structured Documents","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Alexa Siu, Ani Nenkova, David Seunghyun Yoon, Franck Dernoncourt, Joe Barrow, Jon Saad-Falcon, Ryan A. Rossi","submitted_at":"2023-09-16T04:29:05Z","abstract_excerpt":"Large Language Models (LLMs) have issues with document question answering (QA) in situations where the document is unable to fit in the small context length of an LLM. To overcome this issue, most existing works focus on retrieving the relevant context from the document, representing them as plain text. However, documents such as PDFs, web pages, and presentations are naturally structured with different pages, tables, sections, and so on. Representing such structured documents as plain text is incongruous with the user's mental model of these documents with rich structure. When a system has to"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.08872","kind":"arxiv","version":2},"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/2309.08872/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":"2026-07-05T07:10:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"JCOyWujQLTGbUm7yMUiasUHiuYa5YoiUnV4OozYlaZn44lr6gFZXv/aDqCPXroH0j19/oxoNP1s2K6cO50lhCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T22:59:01.272796Z"},"content_sha256":"5d6cfe16dceb02e976875d107edadece0ca3f4d4977218173906f62cb6b3958f","schema_version":"1.0","event_id":"sha256:5d6cfe16dceb02e976875d107edadece0ca3f4d4977218173906f62cb6b3958f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/LYR4L4ZWUB2UITDL32HJOEQT3P/bundle.json","state_url":"https://pith.science/pith/LYR4L4ZWUB2UITDL32HJOEQT3P/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/LYR4L4ZWUB2UITDL32HJOEQT3P/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":"2026-08-06T22:59:01Z","links":{"resolver":"https://pith.science/pith/LYR4L4ZWUB2UITDL32HJOEQT3P","bundle":"https://pith.science/pith/LYR4L4ZWUB2UITDL32HJOEQT3P/bundle.json","state":"https://pith.science/pith/LYR4L4ZWUB2UITDL32HJOEQT3P/state.json","well_known_bundle":"https://pith.science/.well-known/pith/LYR4L4ZWUB2UITDL32HJOEQT3P/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:LYR4L4ZWUB2UITDL32HJOEQT3P","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":"7958820ba37aac679fae7e572e3795b35334b6c62c79ff36f21f92fef72eed95","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-09-16T04:29:05Z","title_canon_sha256":"9827f853b83acd241590a1bd4b3bbf397eec1225042efda0c9dd9722d2d9d027"},"schema_version":"1.0","source":{"id":"2309.08872","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2309.08872","created_at":"2026-07-05T07:10:28Z"},{"alias_kind":"arxiv_version","alias_value":"2309.08872v2","created_at":"2026-07-05T07:10:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.08872","created_at":"2026-07-05T07:10:28Z"},{"alias_kind":"pith_short_12","alias_value":"LYR4L4ZWUB2U","created_at":"2026-07-05T07:10:28Z"},{"alias_kind":"pith_short_16","alias_value":"LYR4L4ZWUB2UITDL","created_at":"2026-07-05T07:10:28Z"},{"alias_kind":"pith_short_8","alias_value":"LYR4L4ZW","created_at":"2026-07-05T07:10:28Z"}],"graph_snapshots":[{"event_id":"sha256:5d6cfe16dceb02e976875d107edadece0ca3f4d4977218173906f62cb6b3958f","target":"graph","created_at":"2026-07-05T07:10:28Z","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/2309.08872/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large Language Models (LLMs) have issues with document question answering (QA) in situations where the document is unable to fit in the small context length of an LLM. To overcome this issue, most existing works focus on retrieving the relevant context from the document, representing them as plain text. However, documents such as PDFs, web pages, and presentations are naturally structured with different pages, tables, sections, and so on. Representing such structured documents as plain text is incongruous with the user's mental model of these documents with rich structure. When a system has to","authors_text":"Alexa Siu, Ani Nenkova, David Seunghyun Yoon, Franck Dernoncourt, Joe Barrow, Jon Saad-Falcon, Ryan A. Rossi","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-09-16T04:29:05Z","title":"PDFTriage: Question Answering over Long, Structured Documents"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.08872","kind":"arxiv","version":2},"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:cd556ab1f9eaa66fcfd7bbc81bfa0c7e0c23a23f76cbd19956419094d0987590","target":"record","created_at":"2026-07-05T07:10:28Z","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":"7958820ba37aac679fae7e572e3795b35334b6c62c79ff36f21f92fef72eed95","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-09-16T04:29:05Z","title_canon_sha256":"9827f853b83acd241590a1bd4b3bbf397eec1225042efda0c9dd9722d2d9d027"},"schema_version":"1.0","source":{"id":"2309.08872","kind":"arxiv","version":2}},"canonical_sha256":"5e23c5f336a075444c6bde8e971213dbd3b252201db0015008073a7282a7785b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5e23c5f336a075444c6bde8e971213dbd3b252201db0015008073a7282a7785b","first_computed_at":"2026-07-05T07:10:28.286030Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:10:28.286030Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"YuSFjZqPX8Ppw++OS+JwImwppuu1ru4Z4VCMl7ILlb4dsD9ElLe/64UjA7SM9PkCnt+Rg4bhRAEmXG9euyeEAA==","signature_status":"signed_v1","signed_at":"2026-07-05T07:10:28.286514Z","signed_message":"canonical_sha256_bytes"},"source_id":"2309.08872","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:cd556ab1f9eaa66fcfd7bbc81bfa0c7e0c23a23f76cbd19956419094d0987590","sha256:5d6cfe16dceb02e976875d107edadece0ca3f4d4977218173906f62cb6b3958f"],"state_sha256":"4de0048d6b7715ab78e2fa6f8b602b0ece0598c39df4c2105ae33f02483b8804"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"R3/+NaC0iVuDlDjTymlKtibjWLo2pm/j0DHQjw+kEzzMuFHR2m1hEnW0zFnCnPog/dDWpCJtWzkwAmWgBIe/Dw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T22:59:01.277938Z","bundle_sha256":"be407b9ca5ecaa6e35fad145b07848e4a83f0e3323f027a0a944d98b4de8dfa0"}}