{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:N7QYLHGP2PB6GVQPUB6SR67XPK","short_pith_number":"pith:N7QYLHGP","schema_version":"1.0","canonical_sha256":"6fe1859ccfd3c3e3560fa07d28fbf77abfba54cbe007f25960645f004fecbe92","source":{"kind":"arxiv","id":"2409.00847","version":3},"attestation_state":"computed","paper":{"title":"The Design of an LLM-powered Unstructured Analytics System","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.IR"],"primary_cat":"cs.DB","authors_text":"Alex Meyer, Austin Lee, Benjamin Sowell, Bohou Li, Dan Tecuci, Eric Anderson, Henry Lindeman, Jonathan Fritz, Mark Lindblad, Matt Welsh, Mehul A. Shah, Parth Parmar, Tanvi Ranade, Vinayak Thapliyal","submitted_at":"2024-09-01T21:30:14Z","abstract_excerpt":"LLMs demonstrate an uncanny ability to process unstructured data, and as such, have the potential to go beyond search and run complex, semantic analyses at scale. We describe the design of an unstructured analytics system, Aryn, and the tenets and use cases that motivate its design. With Aryn, users specify queries in natural language and the system automatically determines a semantic plan and executes it to compute an answer from a large collection of unstructured documents. At the core of Aryn is Sycamore, a declarative document processing engine, that provides a reliable distributed abstrac"},"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":"2409.00847","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DB","submitted_at":"2024-09-01T21:30:14Z","cross_cats_sorted":["cs.AI","cs.IR"],"title_canon_sha256":"d93abe01835b552fb7191533068599bdad47a0f709ec27c41872e7ff6e052a8d","abstract_canon_sha256":"437b0ef0de5bcdfc10f0526daa925c23b262388356f1df80e1ddf34ab863cdb2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:54:46.652984Z","signature_b64":"BQ/gEs4kLmABCOhoX4gAQCso89ZEbqI8BiTIwZHDrsq2E6HEuH9h+HoHaJ1WXK4eW++dOsvq62Nl7ak1w734CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6fe1859ccfd3c3e3560fa07d28fbf77abfba54cbe007f25960645f004fecbe92","last_reissued_at":"2026-07-05T09:54:46.652485Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:54:46.652485Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"The Design of an LLM-powered Unstructured Analytics System","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.IR"],"primary_cat":"cs.DB","authors_text":"Alex Meyer, Austin Lee, Benjamin Sowell, Bohou Li, Dan Tecuci, Eric Anderson, Henry Lindeman, Jonathan Fritz, Mark Lindblad, Matt Welsh, Mehul A. Shah, Parth Parmar, Tanvi Ranade, Vinayak Thapliyal","submitted_at":"2024-09-01T21:30:14Z","abstract_excerpt":"LLMs demonstrate an uncanny ability to process unstructured data, and as such, have the potential to go beyond search and run complex, semantic analyses at scale. We describe the design of an unstructured analytics system, Aryn, and the tenets and use cases that motivate its design. With Aryn, users specify queries in natural language and the system automatically determines a semantic plan and executes it to compute an answer from a large collection of unstructured documents. At the core of Aryn is Sycamore, a declarative document processing engine, that provides a reliable distributed abstrac"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.00847","kind":"arxiv","version":3},"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/2409.00847/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":"2409.00847","created_at":"2026-07-05T09:54:46.652545+00:00"},{"alias_kind":"arxiv_version","alias_value":"2409.00847v3","created_at":"2026-07-05T09:54:46.652545+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.00847","created_at":"2026-07-05T09:54:46.652545+00:00"},{"alias_kind":"pith_short_12","alias_value":"N7QYLHGP2PB6","created_at":"2026-07-05T09:54:46.652545+00:00"},{"alias_kind":"pith_short_16","alias_value":"N7QYLHGP2PB6GVQP","created_at":"2026-07-05T09:54:46.652545+00:00"},{"alias_kind":"pith_short_8","alias_value":"N7QYLHGP","created_at":"2026-07-05T09:54:46.652545+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":7,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2503.04338","citing_title":"In-depth Analysis of Graph-based RAG in a Unified Framework","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2511.07663","citing_title":"Cortex AISQL: A Production SQL Engine for Unstructured Data","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2603.02537","citing_title":"Large Language Model-Enhanced Relational Operators: Taxonomy, Benchmark, and Analysis","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2604.23477","citing_title":"SEMA-SQL: Beyond Traditional Relational Querying with Large Language Models","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":2,"is_internal_anchor":false},{"citing_arxiv_id":"2604.23477","citing_title":"SEMA-SQL: Beyond Traditional Relational Querying with Large Language Models","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2604.22239","citing_title":"Navigating Large-Scale Document Collections: MuDABench for Multi-Document Analytical QA","ref_index":1,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/N7QYLHGP2PB6GVQPUB6SR67XPK","json":"https://pith.science/pith/N7QYLHGP2PB6GVQPUB6SR67XPK.json","graph_json":"https://pith.science/api/pith-number/N7QYLHGP2PB6GVQPUB6SR67XPK/graph.json","events_json":"https://pith.science/api/pith-number/N7QYLHGP2PB6GVQPUB6SR67XPK/events.json","paper":"https://pith.science/paper/N7QYLHGP"},"agent_actions":{"view_html":"https://pith.science/pith/N7QYLHGP2PB6GVQPUB6SR67XPK","download_json":"https://pith.science/pith/N7QYLHGP2PB6GVQPUB6SR67XPK.json","view_paper":"https://pith.science/paper/N7QYLHGP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2409.00847&json=true","fetch_graph":"https://pith.science/api/pith-number/N7QYLHGP2PB6GVQPUB6SR67XPK/graph.json","fetch_events":"https://pith.science/api/pith-number/N7QYLHGP2PB6GVQPUB6SR67XPK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/N7QYLHGP2PB6GVQPUB6SR67XPK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/N7QYLHGP2PB6GVQPUB6SR67XPK/action/storage_attestation","attest_author":"https://pith.science/pith/N7QYLHGP2PB6GVQPUB6SR67XPK/action/author_attestation","sign_citation":"https://pith.science/pith/N7QYLHGP2PB6GVQPUB6SR67XPK/action/citation_signature","submit_replication":"https://pith.science/pith/N7QYLHGP2PB6GVQPUB6SR67XPK/action/replication_record"}},"created_at":"2026-07-05T09:54:46.652545+00:00","updated_at":"2026-07-05T09:54:46.652545+00:00"}