{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:CNR2OD65VAVA7UX3PDNK47S5VO","short_pith_number":"pith:CNR2OD65","canonical_record":{"source":{"id":"2406.15187","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-06-21T14:29:39Z","cross_cats_sorted":["cs.IR"],"title_canon_sha256":"9bd82cc8fecc03437f4954e1c7c7238075869d7215aaabe50bd53aa4800534cd","abstract_canon_sha256":"c081e4f7e48f4df02b907acafbe5ea284f1dab90cc00223ed9933cf61ea8a711"},"schema_version":"1.0"},"canonical_sha256":"1363a70fdda82a0fd2fb78daae7e5dabbc8c05a2867bc600f128f600f334a5dd","source":{"kind":"arxiv","id":"2406.15187","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.15187","created_at":"2026-07-05T09:28:52Z"},{"alias_kind":"arxiv_version","alias_value":"2406.15187v2","created_at":"2026-07-05T09:28:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.15187","created_at":"2026-07-05T09:28:52Z"},{"alias_kind":"pith_short_12","alias_value":"CNR2OD65VAVA","created_at":"2026-07-05T09:28:52Z"},{"alias_kind":"pith_short_16","alias_value":"CNR2OD65VAVA7UX3","created_at":"2026-07-05T09:28:52Z"},{"alias_kind":"pith_short_8","alias_value":"CNR2OD65","created_at":"2026-07-05T09:28:52Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:CNR2OD65VAVA7UX3PDNK47S5VO","target":"record","payload":{"canonical_record":{"source":{"id":"2406.15187","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-06-21T14:29:39Z","cross_cats_sorted":["cs.IR"],"title_canon_sha256":"9bd82cc8fecc03437f4954e1c7c7238075869d7215aaabe50bd53aa4800534cd","abstract_canon_sha256":"c081e4f7e48f4df02b907acafbe5ea284f1dab90cc00223ed9933cf61ea8a711"},"schema_version":"1.0"},"canonical_sha256":"1363a70fdda82a0fd2fb78daae7e5dabbc8c05a2867bc600f128f600f334a5dd","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:28:52.217893Z","signature_b64":"b4wha1G2wBtldP4DHCzcaOB+sFW+e9yysO7/xoch8SRY1l8vozORB+1TRwDr9sT/1OvYaOCq6a/s9Cnyb7uxCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1363a70fdda82a0fd2fb78daae7e5dabbc8c05a2867bc600f128f600f334a5dd","last_reissued_at":"2026-07-05T09:28:52.217453Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:28:52.217453Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2406.15187","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":"2026-07-05T09:28:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"bhgthTyjwY+54EWRz6fSLCBnjVAiRVYMBuA9Rt7950UjzaGRRX813oK9/877zv+Ec4YWq2wkyHcTMNNX9xheBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T01:06:19.451149Z"},"content_sha256":"7c80b71d154b89f06186c72fcfded81005bbd4e99470525c14cf25dc43c3f2e9","schema_version":"1.0","event_id":"sha256:7c80b71d154b89f06186c72fcfded81005bbd4e99470525c14cf25dc43c3f2e9"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:CNR2OD65VAVA7UX3PDNK47S5VO","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"UDA: A Benchmark Suite for Retrieval Augmented Generation in Real-world Document Analysis","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IR"],"primary_cat":"cs.AI","authors_text":"Huanchen Zhang, Yao Lu, Yulong Hui","submitted_at":"2024-06-21T14:29:39Z","abstract_excerpt":"The use of Retrieval-Augmented Generation (RAG) has improved Large Language Models (LLMs) in collaborating with external data, yet significant challenges exist in real-world scenarios. In areas such as academic literature and finance question answering, data are often found in raw text and tables in HTML or PDF formats, which can be lengthy and highly unstructured. In this paper, we introduce a benchmark suite, namely Unstructured Document Analysis (UDA), that involves 2,965 real-world documents and 29,590 expert-annotated Q&A pairs. We revisit popular LLM- and RAG-based solutions for document"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.15187","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/2406.15187/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":"2026-07-05T09:28:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"TPuqUx97e4dDTVlTDPtxlZ9TZ4ErLh7bnRbPehprGNGAPDcXSlD51MrHH1aldiuOoyBzzszbGqLzOR/NX1cOAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T01:06:19.452009Z"},"content_sha256":"119574fd77bf16b486d55316be6075c9e7f87319d4d75740e34e3cd267285432","schema_version":"1.0","event_id":"sha256:119574fd77bf16b486d55316be6075c9e7f87319d4d75740e34e3cd267285432"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/CNR2OD65VAVA7UX3PDNK47S5VO/bundle.json","state_url":"https://pith.science/pith/CNR2OD65VAVA7UX3PDNK47S5VO/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/CNR2OD65VAVA7UX3PDNK47S5VO/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":"2026-08-08T01:06:19Z","links":{"resolver":"https://pith.science/pith/CNR2OD65VAVA7UX3PDNK47S5VO","bundle":"https://pith.science/pith/CNR2OD65VAVA7UX3PDNK47S5VO/bundle.json","state":"https://pith.science/pith/CNR2OD65VAVA7UX3PDNK47S5VO/state.json","well_known_bundle":"https://pith.science/.well-known/pith/CNR2OD65VAVA7UX3PDNK47S5VO/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:CNR2OD65VAVA7UX3PDNK47S5VO","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":"c081e4f7e48f4df02b907acafbe5ea284f1dab90cc00223ed9933cf61ea8a711","cross_cats_sorted":["cs.IR"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-06-21T14:29:39Z","title_canon_sha256":"9bd82cc8fecc03437f4954e1c7c7238075869d7215aaabe50bd53aa4800534cd"},"schema_version":"1.0","source":{"id":"2406.15187","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.15187","created_at":"2026-07-05T09:28:52Z"},{"alias_kind":"arxiv_version","alias_value":"2406.15187v2","created_at":"2026-07-05T09:28:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.15187","created_at":"2026-07-05T09:28:52Z"},{"alias_kind":"pith_short_12","alias_value":"CNR2OD65VAVA","created_at":"2026-07-05T09:28:52Z"},{"alias_kind":"pith_short_16","alias_value":"CNR2OD65VAVA7UX3","created_at":"2026-07-05T09:28:52Z"},{"alias_kind":"pith_short_8","alias_value":"CNR2OD65","created_at":"2026-07-05T09:28:52Z"}],"graph_snapshots":[{"event_id":"sha256:119574fd77bf16b486d55316be6075c9e7f87319d4d75740e34e3cd267285432","target":"graph","created_at":"2026-07-05T09:28:52Z","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/2406.15187/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The use of Retrieval-Augmented Generation (RAG) has improved Large Language Models (LLMs) in collaborating with external data, yet significant challenges exist in real-world scenarios. In areas such as academic literature and finance question answering, data are often found in raw text and tables in HTML or PDF formats, which can be lengthy and highly unstructured. In this paper, we introduce a benchmark suite, namely Unstructured Document Analysis (UDA), that involves 2,965 real-world documents and 29,590 expert-annotated Q&A pairs. We revisit popular LLM- and RAG-based solutions for document","authors_text":"Huanchen Zhang, Yao Lu, Yulong Hui","cross_cats":["cs.IR"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-06-21T14:29:39Z","title":"UDA: A Benchmark Suite for Retrieval Augmented Generation in Real-world Document Analysis"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.15187","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":"sha256:7c80b71d154b89f06186c72fcfded81005bbd4e99470525c14cf25dc43c3f2e9","target":"record","created_at":"2026-07-05T09:28:52Z","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":"c081e4f7e48f4df02b907acafbe5ea284f1dab90cc00223ed9933cf61ea8a711","cross_cats_sorted":["cs.IR"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-06-21T14:29:39Z","title_canon_sha256":"9bd82cc8fecc03437f4954e1c7c7238075869d7215aaabe50bd53aa4800534cd"},"schema_version":"1.0","source":{"id":"2406.15187","kind":"arxiv","version":2}},"canonical_sha256":"1363a70fdda82a0fd2fb78daae7e5dabbc8c05a2867bc600f128f600f334a5dd","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1363a70fdda82a0fd2fb78daae7e5dabbc8c05a2867bc600f128f600f334a5dd","first_computed_at":"2026-07-05T09:28:52.217453Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:28:52.217453Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"b4wha1G2wBtldP4DHCzcaOB+sFW+e9yysO7/xoch8SRY1l8vozORB+1TRwDr9sT/1OvYaOCq6a/s9Cnyb7uxCw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:28:52.217893Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.15187","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7c80b71d154b89f06186c72fcfded81005bbd4e99470525c14cf25dc43c3f2e9","sha256:119574fd77bf16b486d55316be6075c9e7f87319d4d75740e34e3cd267285432"],"state_sha256":"ca4f433d58361a91aa0c9719b0b81235ffcc6a2508132bb48b37cb2e85795454"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"yYk8z5GlnqkSs+hoI9JriUC7d1udxrOXbHkeCcbvX4NsZM8kJDdVRajhO2TBufE9scJ/7/uO+SFPuaoUQuJkCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T01:06:19.515773Z","bundle_sha256":"245f2c1a190bd55e5ac24c5319c497739860a0fbb57ee0c02cc55958f8660a26"}}