{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:SZ4HBUYOMO2U5UIDQZN66M4725","short_pith_number":"pith:SZ4HBUYO","schema_version":"1.0","canonical_sha256":"967870d30e63b54ed103865bef339fd767bcbf96b4a3b810cc16d99f0d178c77","source":{"kind":"arxiv","id":"2408.00884","version":2},"attestation_state":"computed","paper":{"title":"Hybrid Querying Over Relational Databases and Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.DB","authors_text":"Amr El Abbadi, Divyakant Agrawal, Fuheng Zhao","submitted_at":"2024-08-01T19:29:18Z","abstract_excerpt":"Database queries traditionally operate under the closed-world assumption, providing no answers to questions that require information beyond the data stored in the database. Hybrid querying using SQL offers an alternative by integrating relational databases with large language models (LLMs) to answer beyond-database questions. In this paper, we present the first cross-domain benchmark, SWAN, containing 120 beyond-database questions over four real-world databases. To leverage state-of-the-art language models in addressing these complex questions in SWAN, we present two solutions: one based on sc"},"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":"2408.00884","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2024-08-01T19:29:18Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"50a2ba724e1e01ac6159cb21c1ccd1c784a853b20647d6649bbd8f49ab0ace1b","abstract_canon_sha256":"3dd42b2c22cb34385adfbf4ac49ccd4b3152feb6315c6d99cba566d2a4697c0f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:36:13.702417Z","signature_b64":"hm3J/1bQ8KhG1uT11wBFooh3YZDG4VVKMx+WIB9X05S/lQ8IS6YB3JWVjtN7JLrtkh265tWa/GK1E5GzWnbUBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"967870d30e63b54ed103865bef339fd767bcbf96b4a3b810cc16d99f0d178c77","last_reissued_at":"2026-07-05T09:36:13.701872Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:36:13.701872Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Hybrid Querying Over Relational Databases and Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.DB","authors_text":"Amr El Abbadi, Divyakant Agrawal, Fuheng Zhao","submitted_at":"2024-08-01T19:29:18Z","abstract_excerpt":"Database queries traditionally operate under the closed-world assumption, providing no answers to questions that require information beyond the data stored in the database. Hybrid querying using SQL offers an alternative by integrating relational databases with large language models (LLMs) to answer beyond-database questions. In this paper, we present the first cross-domain benchmark, SWAN, containing 120 beyond-database questions over four real-world databases. To leverage state-of-the-art language models in addressing these complex questions in SWAN, we present two solutions: one based on sc"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.00884","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/2408.00884/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":"2408.00884","created_at":"2026-07-05T09:36:13.701944+00:00"},{"alias_kind":"arxiv_version","alias_value":"2408.00884v2","created_at":"2026-07-05T09:36:13.701944+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.00884","created_at":"2026-07-05T09:36:13.701944+00:00"},{"alias_kind":"pith_short_12","alias_value":"SZ4HBUYOMO2U","created_at":"2026-07-05T09:36:13.701944+00:00"},{"alias_kind":"pith_short_16","alias_value":"SZ4HBUYOMO2U5UID","created_at":"2026-07-05T09:36:13.701944+00:00"},{"alias_kind":"pith_short_8","alias_value":"SZ4HBUYO","created_at":"2026-07-05T09:36:13.701944+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":8,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.07923","citing_title":"Larch: Learned Query Optimization for Semantic Predicates","ref_index":77,"is_internal_anchor":false},{"citing_arxiv_id":"2606.31808","citing_title":"Large Databases Need Small, Open-Weight Language Models","ref_index":66,"is_internal_anchor":false},{"citing_arxiv_id":"2605.24183","citing_title":"AvalancheBench: Evaluating Enterprise Data Agents Through Latent World Recovery","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2606.03152","citing_title":"Cost-Aware Optimization for Agentic Query Execution","ref_index":42,"is_internal_anchor":false},{"citing_arxiv_id":"2509.00303","citing_title":"Access Paths for Efficient Ordering with Large Language Models","ref_index":75,"is_internal_anchor":false},{"citing_arxiv_id":"2603.02537","citing_title":"Large Language Model-Enhanced Relational Operators: Taxonomy, Benchmark, and Analysis","ref_index":59,"is_internal_anchor":false},{"citing_arxiv_id":"2604.23477","citing_title":"SEMA-SQL: Beyond Traditional Relational Querying with Large Language Models","ref_index":58,"is_internal_anchor":false},{"citing_arxiv_id":"2604.23477","citing_title":"SEMA-SQL: Beyond Traditional Relational Querying with Large Language Models","ref_index":58,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SZ4HBUYOMO2U5UIDQZN66M4725","json":"https://pith.science/pith/SZ4HBUYOMO2U5UIDQZN66M4725.json","graph_json":"https://pith.science/api/pith-number/SZ4HBUYOMO2U5UIDQZN66M4725/graph.json","events_json":"https://pith.science/api/pith-number/SZ4HBUYOMO2U5UIDQZN66M4725/events.json","paper":"https://pith.science/paper/SZ4HBUYO"},"agent_actions":{"view_html":"https://pith.science/pith/SZ4HBUYOMO2U5UIDQZN66M4725","download_json":"https://pith.science/pith/SZ4HBUYOMO2U5UIDQZN66M4725.json","view_paper":"https://pith.science/paper/SZ4HBUYO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2408.00884&json=true","fetch_graph":"https://pith.science/api/pith-number/SZ4HBUYOMO2U5UIDQZN66M4725/graph.json","fetch_events":"https://pith.science/api/pith-number/SZ4HBUYOMO2U5UIDQZN66M4725/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SZ4HBUYOMO2U5UIDQZN66M4725/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SZ4HBUYOMO2U5UIDQZN66M4725/action/storage_attestation","attest_author":"https://pith.science/pith/SZ4HBUYOMO2U5UIDQZN66M4725/action/author_attestation","sign_citation":"https://pith.science/pith/SZ4HBUYOMO2U5UIDQZN66M4725/action/citation_signature","submit_replication":"https://pith.science/pith/SZ4HBUYOMO2U5UIDQZN66M4725/action/replication_record"}},"created_at":"2026-07-05T09:36:13.701944+00:00","updated_at":"2026-07-05T09:36:13.701944+00:00"}