{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:ZJ53YKRCVCSWUXRJR7OEUG3WEW","short_pith_number":"pith:ZJ53YKRC","canonical_record":{"source":{"id":"2405.04674","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DB","submitted_at":"2024-05-07T21:14:38Z","cross_cats_sorted":[],"title_canon_sha256":"3cf152099f21f6e2f73d3007a56c59d3f8dbf96054b9bf4b121a3ac94e57f267","abstract_canon_sha256":"9edd7dfc07ee5871a4d00796eced77124865fc52b168e434bd5bad8bae70a1dc"},"schema_version":"1.0"},"canonical_sha256":"ca7bbc2a22a8a56a5e298fdc4a1b7625a87984923c152838d53f79b9809af021","source":{"kind":"arxiv","id":"2405.04674","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.04674","created_at":"2026-07-05T08:16:52Z"},{"alias_kind":"arxiv_version","alias_value":"2405.04674v1","created_at":"2026-07-05T08:16:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.04674","created_at":"2026-07-05T08:16:52Z"},{"alias_kind":"pith_short_12","alias_value":"ZJ53YKRCVCSW","created_at":"2026-07-05T08:16:52Z"},{"alias_kind":"pith_short_16","alias_value":"ZJ53YKRCVCSWUXRJ","created_at":"2026-07-05T08:16:52Z"},{"alias_kind":"pith_short_8","alias_value":"ZJ53YKRC","created_at":"2026-07-05T08:16:52Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:ZJ53YKRCVCSWUXRJR7OEUG3WEW","target":"record","payload":{"canonical_record":{"source":{"id":"2405.04674","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DB","submitted_at":"2024-05-07T21:14:38Z","cross_cats_sorted":[],"title_canon_sha256":"3cf152099f21f6e2f73d3007a56c59d3f8dbf96054b9bf4b121a3ac94e57f267","abstract_canon_sha256":"9edd7dfc07ee5871a4d00796eced77124865fc52b168e434bd5bad8bae70a1dc"},"schema_version":"1.0"},"canonical_sha256":"ca7bbc2a22a8a56a5e298fdc4a1b7625a87984923c152838d53f79b9809af021","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:16:52.338826Z","signature_b64":"LwPxFedM0tb55oW+OBJzqG0G60deJf4yPuDOmxgaVqfIQVfWHrMz5uRpB3f6vHARbnKWcstWsVY0YeVLAMPRBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ca7bbc2a22a8a56a5e298fdc4a1b7625a87984923c152838d53f79b9809af021","last_reissued_at":"2026-07-05T08:16:52.338283Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:16:52.338283Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2405.04674","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":"2026-07-05T08:16:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7/Kj1muEEBcr1Xdf7Eice5kFNawQQdRyQQUEA7iVkB1RyGDeyqptsfZwmzk9CnpFIy63lnbQkjLDSqZQLHNlCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T09:49:43.660355Z"},"content_sha256":"99ff4fb35fc386b0790ac8a31d6ede5233ce9bdad3ab01561fbb72b67874c04c","schema_version":"1.0","event_id":"sha256:99ff4fb35fc386b0790ac8a31d6ede5233ce9bdad3ab01561fbb72b67874c04c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:ZJ53YKRCVCSWUXRJR7OEUG3WEW","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Towards Accurate and Efficient Document Analytics with Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.DB","authors_text":"Aditya G. Parameswaran, Eugene Wu, Madelon Hulsebos, Ruiying Ma, Sepanta Zeigham, Shreya Shankar, Yiming Lin","submitted_at":"2024-05-07T21:14:38Z","abstract_excerpt":"Unstructured data formats account for over 80% of the data currently stored, and extracting value from such formats remains a considerable challenge. In particular, current approaches for managing unstructured documents do not support ad-hoc analytical queries on document collections. Moreover, Large Language Models (LLMs) directly applied to the documents themselves, or on portions of documents through a process of Retrieval-Augmented Generation (RAG), fail to provide high accuracy query results, and in the LLM-only case, additionally incur high costs. Since many unstructured documents in a c"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.04674","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/2405.04674/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":"2026-07-05T08:16:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VHgCLbxGRJOOLUt75bUn59bwvdRZe6TKdDrci3ug3SAIbcBtVz/AmbuamrADj5KrWrWIXxj6FLiojQp+0WrRAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T09:49:43.660925Z"},"content_sha256":"ab91fb1a4b83ece9c3c683192c4a90b7298fd33a28d42a5605a511a76dc26868","schema_version":"1.0","event_id":"sha256:ab91fb1a4b83ece9c3c683192c4a90b7298fd33a28d42a5605a511a76dc26868"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ZJ53YKRCVCSWUXRJR7OEUG3WEW/bundle.json","state_url":"https://pith.science/pith/ZJ53YKRCVCSWUXRJR7OEUG3WEW/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ZJ53YKRCVCSWUXRJR7OEUG3WEW/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":"2026-08-05T09:49:43Z","links":{"resolver":"https://pith.science/pith/ZJ53YKRCVCSWUXRJR7OEUG3WEW","bundle":"https://pith.science/pith/ZJ53YKRCVCSWUXRJR7OEUG3WEW/bundle.json","state":"https://pith.science/pith/ZJ53YKRCVCSWUXRJR7OEUG3WEW/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ZJ53YKRCVCSWUXRJR7OEUG3WEW/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:ZJ53YKRCVCSWUXRJR7OEUG3WEW","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":"9edd7dfc07ee5871a4d00796eced77124865fc52b168e434bd5bad8bae70a1dc","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DB","submitted_at":"2024-05-07T21:14:38Z","title_canon_sha256":"3cf152099f21f6e2f73d3007a56c59d3f8dbf96054b9bf4b121a3ac94e57f267"},"schema_version":"1.0","source":{"id":"2405.04674","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.04674","created_at":"2026-07-05T08:16:52Z"},{"alias_kind":"arxiv_version","alias_value":"2405.04674v1","created_at":"2026-07-05T08:16:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.04674","created_at":"2026-07-05T08:16:52Z"},{"alias_kind":"pith_short_12","alias_value":"ZJ53YKRCVCSW","created_at":"2026-07-05T08:16:52Z"},{"alias_kind":"pith_short_16","alias_value":"ZJ53YKRCVCSWUXRJ","created_at":"2026-07-05T08:16:52Z"},{"alias_kind":"pith_short_8","alias_value":"ZJ53YKRC","created_at":"2026-07-05T08:16:52Z"}],"graph_snapshots":[{"event_id":"sha256:ab91fb1a4b83ece9c3c683192c4a90b7298fd33a28d42a5605a511a76dc26868","target":"graph","created_at":"2026-07-05T08:16:52Z","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/2405.04674/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Unstructured data formats account for over 80% of the data currently stored, and extracting value from such formats remains a considerable challenge. In particular, current approaches for managing unstructured documents do not support ad-hoc analytical queries on document collections. Moreover, Large Language Models (LLMs) directly applied to the documents themselves, or on portions of documents through a process of Retrieval-Augmented Generation (RAG), fail to provide high accuracy query results, and in the LLM-only case, additionally incur high costs. Since many unstructured documents in a c","authors_text":"Aditya G. Parameswaran, Eugene Wu, Madelon Hulsebos, Ruiying Ma, Sepanta Zeigham, Shreya Shankar, Yiming Lin","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DB","submitted_at":"2024-05-07T21:14:38Z","title":"Towards Accurate and Efficient Document Analytics with Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.04674","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":"sha256:99ff4fb35fc386b0790ac8a31d6ede5233ce9bdad3ab01561fbb72b67874c04c","target":"record","created_at":"2026-07-05T08:16:52Z","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":"9edd7dfc07ee5871a4d00796eced77124865fc52b168e434bd5bad8bae70a1dc","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DB","submitted_at":"2024-05-07T21:14:38Z","title_canon_sha256":"3cf152099f21f6e2f73d3007a56c59d3f8dbf96054b9bf4b121a3ac94e57f267"},"schema_version":"1.0","source":{"id":"2405.04674","kind":"arxiv","version":1}},"canonical_sha256":"ca7bbc2a22a8a56a5e298fdc4a1b7625a87984923c152838d53f79b9809af021","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ca7bbc2a22a8a56a5e298fdc4a1b7625a87984923c152838d53f79b9809af021","first_computed_at":"2026-07-05T08:16:52.338283Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:16:52.338283Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"LwPxFedM0tb55oW+OBJzqG0G60deJf4yPuDOmxgaVqfIQVfWHrMz5uRpB3f6vHARbnKWcstWsVY0YeVLAMPRBA==","signature_status":"signed_v1","signed_at":"2026-07-05T08:16:52.338826Z","signed_message":"canonical_sha256_bytes"},"source_id":"2405.04674","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:99ff4fb35fc386b0790ac8a31d6ede5233ce9bdad3ab01561fbb72b67874c04c","sha256:ab91fb1a4b83ece9c3c683192c4a90b7298fd33a28d42a5605a511a76dc26868"],"state_sha256":"1bab1ee89df9a363da07d96767278457bdc71834c5110df6fd14337cd761ae4e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"atAGjozfXx+3xX5+pyHS/eh3cDG6LAIXy9lQndK/Hu0NJqXpq0DTheYxXCKltRQY1QeY3M+DRQBV3A7yc/coAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T09:49:43.664866Z","bundle_sha256":"237b43ce931798ce8dd03e00831113208f965fe9281d9457fefe2302dd93085f"}}