{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:ZJ53YKRCVCSWUXRJR7OEUG3WEW","short_pith_number":"pith:ZJ53YKRC","schema_version":"1.0","canonical_sha256":"ca7bbc2a22a8a56a5e298fdc4a1b7625a87984923c152838d53f79b9809af021","source":{"kind":"arxiv","id":"2405.04674","version":1},"attestation_state":"computed","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"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"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"},"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"},"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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2405.04674","created_at":"2026-07-05T08:16:52.338341+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.04674v1","created_at":"2026-07-05T08:16:52.338341+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.04674","created_at":"2026-07-05T08:16:52.338341+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZJ53YKRCVCSW","created_at":"2026-07-05T08:16:52.338341+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZJ53YKRCVCSWUXRJ","created_at":"2026-07-05T08:16:52.338341+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZJ53YKRC","created_at":"2026-07-05T08:16:52.338341+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":12,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.07923","citing_title":"Larch: Learned Query Optimization for Semantic Predicates","ref_index":33,"is_internal_anchor":false},{"citing_arxiv_id":"2606.04610","citing_title":"Selectivity Estimation for Semantic Filters on Image Data","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2503.04338","citing_title":"In-depth Analysis of Graph-based RAG in a Unified Framework","ref_index":50,"is_internal_anchor":false},{"citing_arxiv_id":"2511.07663","citing_title":"Cortex AISQL: A Production SQL Engine for Unstructured Data","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2602.23061","citing_title":"MoDora: Tree-Based Semi-Structured Document Analysis System","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2603.02537","citing_title":"Large Language Model-Enhanced Relational Operators: Taxonomy, Benchmark, and Analysis","ref_index":33,"is_internal_anchor":false},{"citing_arxiv_id":"2604.23477","citing_title":"SEMA-SQL: Beyond Traditional Relational Querying with Large Language Models","ref_index":28,"is_internal_anchor":false},{"citing_arxiv_id":"2603.22608","citing_title":"Understanding LLM Performance Degradation in Multi-Instance Processing: The Roles of Instance Count and Context Length","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2604.01707","citing_title":"Memory in the LLM Era: Modular Architectures and Strategies in a Unified Framework","ref_index":53,"is_internal_anchor":false},{"citing_arxiv_id":"2604.02690","citing_title":"AnnoRetrieve: Efficient Structured Retrieval for Unstructured Document Analysis","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2604.02655","citing_title":"Semantic Data Processing with Holistic Data Understanding","ref_index":36,"is_internal_anchor":false},{"citing_arxiv_id":"2604.23477","citing_title":"SEMA-SQL: Beyond Traditional Relational Querying with Large Language Models","ref_index":28,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZJ53YKRCVCSWUXRJR7OEUG3WEW","json":"https://pith.science/pith/ZJ53YKRCVCSWUXRJR7OEUG3WEW.json","graph_json":"https://pith.science/api/pith-number/ZJ53YKRCVCSWUXRJR7OEUG3WEW/graph.json","events_json":"https://pith.science/api/pith-number/ZJ53YKRCVCSWUXRJR7OEUG3WEW/events.json","paper":"https://pith.science/paper/ZJ53YKRC"},"agent_actions":{"view_html":"https://pith.science/pith/ZJ53YKRCVCSWUXRJR7OEUG3WEW","download_json":"https://pith.science/pith/ZJ53YKRCVCSWUXRJR7OEUG3WEW.json","view_paper":"https://pith.science/paper/ZJ53YKRC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.04674&json=true","fetch_graph":"https://pith.science/api/pith-number/ZJ53YKRCVCSWUXRJR7OEUG3WEW/graph.json","fetch_events":"https://pith.science/api/pith-number/ZJ53YKRCVCSWUXRJR7OEUG3WEW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZJ53YKRCVCSWUXRJR7OEUG3WEW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZJ53YKRCVCSWUXRJR7OEUG3WEW/action/storage_attestation","attest_author":"https://pith.science/pith/ZJ53YKRCVCSWUXRJR7OEUG3WEW/action/author_attestation","sign_citation":"https://pith.science/pith/ZJ53YKRCVCSWUXRJR7OEUG3WEW/action/citation_signature","submit_replication":"https://pith.science/pith/ZJ53YKRCVCSWUXRJR7OEUG3WEW/action/replication_record"}},"created_at":"2026-07-05T08:16:52.338341+00:00","updated_at":"2026-07-05T08:16:52.338341+00:00"}