{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:OMNAOL4BYR4MPRRYPUTSL7RXLX","short_pith_number":"pith:OMNAOL4B","schema_version":"1.0","canonical_sha256":"731a072f81c478c7c6387d2725fe375df5b20f2b72d94081d8098af5f89df2c2","source":{"kind":"arxiv","id":"2408.14717","version":1},"attestation_state":"computed","paper":{"title":"Text2SQL is Not Enough: Unifying AI and Databases with TAG","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.DB","authors_text":"Amog Kamsetty, Asim Biswal, Carlos Guestrin, Joseph E. Gonzalez, Liana Patel, Matei Zaharia, Shu Liu, Siddarth Jha","submitted_at":"2024-08-27T00:50:14Z","abstract_excerpt":"AI systems that serve natural language questions over databases promise to unlock tremendous value. Such systems would allow users to leverage the powerful reasoning and knowledge capabilities of language models (LMs) alongside the scalable computational power of data management systems. These combined capabilities would empower users to ask arbitrary natural language questions over custom data sources. However, existing methods and benchmarks insufficiently explore this setting. Text2SQL methods focus solely on natural language questions that can be expressed in relational algebra, representi"},"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":"2408.14717","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DB","submitted_at":"2024-08-27T00:50:14Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"1c0f2b9576bc288cff8cc2474bdc8018a6dc65909687f947bab8a571cbcdd400","abstract_canon_sha256":"e565b90d19ca6f233a49df2848ca71f7f878e774d0d748206218a1c386895740"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:59:38.032881Z","signature_b64":"mTYSsJcwRFGkun+ZVJbVf5PsHPNgoJ60Cc5RmE9M/rET4x39YcYfqsEjgwePuQSrXRDJp47WNyQTLcS3CK/NDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"731a072f81c478c7c6387d2725fe375df5b20f2b72d94081d8098af5f89df2c2","last_reissued_at":"2026-07-05T08:59:38.032369Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:59:38.032369Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Text2SQL is Not Enough: Unifying AI and Databases with TAG","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.DB","authors_text":"Amog Kamsetty, Asim Biswal, Carlos Guestrin, Joseph E. Gonzalez, Liana Patel, Matei Zaharia, Shu Liu, Siddarth Jha","submitted_at":"2024-08-27T00:50:14Z","abstract_excerpt":"AI systems that serve natural language questions over databases promise to unlock tremendous value. Such systems would allow users to leverage the powerful reasoning and knowledge capabilities of language models (LMs) alongside the scalable computational power of data management systems. These combined capabilities would empower users to ask arbitrary natural language questions over custom data sources. However, existing methods and benchmarks insufficiently explore this setting. Text2SQL methods focus solely on natural language questions that can be expressed in relational algebra, representi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.14717","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/2408.14717/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":"2408.14717","created_at":"2026-07-05T08:59:38.032438+00:00"},{"alias_kind":"arxiv_version","alias_value":"2408.14717v1","created_at":"2026-07-05T08:59:38.032438+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.14717","created_at":"2026-07-05T08:59:38.032438+00:00"},{"alias_kind":"pith_short_12","alias_value":"OMNAOL4BYR4M","created_at":"2026-07-05T08:59:38.032438+00:00"},{"alias_kind":"pith_short_16","alias_value":"OMNAOL4BYR4MPRRY","created_at":"2026-07-05T08:59:38.032438+00:00"},{"alias_kind":"pith_short_8","alias_value":"OMNAOL4B","created_at":"2026-07-05T08:59:38.032438+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2607.00254","citing_title":"Query-Centric Optimization of AI Workflows via Approximate Query Processing and Proxy Models","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2606.04641","citing_title":"Bridge the Last-Mile Gap to Semantic Analytics: Compiling Natural-Language Queries into Semantic Operator Pipelines","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":5,"is_internal_anchor":false},{"citing_arxiv_id":"2604.23477","citing_title":"SEMA-SQL: Beyond Traditional Relational Querying with Large Language Models","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2604.23477","citing_title":"SEMA-SQL: Beyond Traditional Relational Querying with Large Language Models","ref_index":6,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OMNAOL4BYR4MPRRYPUTSL7RXLX","json":"https://pith.science/pith/OMNAOL4BYR4MPRRYPUTSL7RXLX.json","graph_json":"https://pith.science/api/pith-number/OMNAOL4BYR4MPRRYPUTSL7RXLX/graph.json","events_json":"https://pith.science/api/pith-number/OMNAOL4BYR4MPRRYPUTSL7RXLX/events.json","paper":"https://pith.science/paper/OMNAOL4B"},"agent_actions":{"view_html":"https://pith.science/pith/OMNAOL4BYR4MPRRYPUTSL7RXLX","download_json":"https://pith.science/pith/OMNAOL4BYR4MPRRYPUTSL7RXLX.json","view_paper":"https://pith.science/paper/OMNAOL4B","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2408.14717&json=true","fetch_graph":"https://pith.science/api/pith-number/OMNAOL4BYR4MPRRYPUTSL7RXLX/graph.json","fetch_events":"https://pith.science/api/pith-number/OMNAOL4BYR4MPRRYPUTSL7RXLX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OMNAOL4BYR4MPRRYPUTSL7RXLX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OMNAOL4BYR4MPRRYPUTSL7RXLX/action/storage_attestation","attest_author":"https://pith.science/pith/OMNAOL4BYR4MPRRYPUTSL7RXLX/action/author_attestation","sign_citation":"https://pith.science/pith/OMNAOL4BYR4MPRRYPUTSL7RXLX/action/citation_signature","submit_replication":"https://pith.science/pith/OMNAOL4BYR4MPRRYPUTSL7RXLX/action/replication_record"}},"created_at":"2026-07-05T08:59:38.032438+00:00","updated_at":"2026-07-05T08:59:38.032438+00:00"}