{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:XHOZYFU2S7H5UTKJR44VODMRLQ","short_pith_number":"pith:XHOZYFU2","schema_version":"1.0","canonical_sha256":"b9dd9c169a97cfda4d498f39570d915c10de4e8072186188c9a8a0400ac536e1","source":{"kind":"arxiv","id":"2502.00032","version":1},"attestation_state":"computed","paper":{"title":"Querying Databases with Function Calling","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.IR"],"primary_cat":"cs.DB","authors_text":"Aravind Kesiraju, Bob van Luijt, Charles Pierse, Connor Shorten, Daniel Williams, Edward Schmuhl, Erika Cardenas, Karel D'Oosterlinck, Leonie Monigatti, Mohd Shukri Hasan, Thomas Benjamin Smith, Tuana Celik","submitted_at":"2025-01-23T23:09:13Z","abstract_excerpt":"The capabilities of Large Language Models (LLMs) are rapidly accelerating largely thanks to their integration with external tools. Querying databases is among the most effective of these integrations, enabling LLMs to access private or continually updating data. While Function Calling is the most common method for interfacing external tools to LLMs, its application to database querying as a tool has been underexplored. We propose a tool definition for database querying that unifies accessing data with search queries, filters, or a combination both, as well as transforming results with aggregat"},"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":"2502.00032","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DB","submitted_at":"2025-01-23T23:09:13Z","cross_cats_sorted":["cs.AI","cs.IR"],"title_canon_sha256":"090c6af07e8fc637db84b00000a5d85ef9e38435ba0fe68416bc02ea18491725","abstract_canon_sha256":"194703b7ef3bdd4462fcc071cae2d2c123590f1e42bce3634918fb19ca4bb872"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:08:54.775090Z","signature_b64":"DK1Kt8sSfiXnBR0JNinXPqNOnjEA2s5AjodLLF9T6bXqCxTn7FyH1fYLzyKYyVDvyw+mMTR0GJ1Qq9AXeVHBAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b9dd9c169a97cfda4d498f39570d915c10de4e8072186188c9a8a0400ac536e1","last_reissued_at":"2026-07-05T10:08:54.774605Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:08:54.774605Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Querying Databases with Function Calling","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.IR"],"primary_cat":"cs.DB","authors_text":"Aravind Kesiraju, Bob van Luijt, Charles Pierse, Connor Shorten, Daniel Williams, Edward Schmuhl, Erika Cardenas, Karel D'Oosterlinck, Leonie Monigatti, Mohd Shukri Hasan, Thomas Benjamin Smith, Tuana Celik","submitted_at":"2025-01-23T23:09:13Z","abstract_excerpt":"The capabilities of Large Language Models (LLMs) are rapidly accelerating largely thanks to their integration with external tools. Querying databases is among the most effective of these integrations, enabling LLMs to access private or continually updating data. While Function Calling is the most common method for interfacing external tools to LLMs, its application to database querying as a tool has been underexplored. We propose a tool definition for database querying that unifies accessing data with search queries, filters, or a combination both, as well as transforming results with aggregat"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.00032","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/2502.00032/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":"2502.00032","created_at":"2026-07-05T10:08:54.774662+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.00032v1","created_at":"2026-07-05T10:08:54.774662+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.00032","created_at":"2026-07-05T10:08:54.774662+00:00"},{"alias_kind":"pith_short_12","alias_value":"XHOZYFU2S7H5","created_at":"2026-07-05T10:08:54.774662+00:00"},{"alias_kind":"pith_short_16","alias_value":"XHOZYFU2S7H5UTKJ","created_at":"2026-07-05T10:08:54.774662+00:00"},{"alias_kind":"pith_short_8","alias_value":"XHOZYFU2","created_at":"2026-07-05T10:08:54.774662+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.19010","citing_title":"AgentNLQ: A General-Purpose Agent for Natural Language to SQL","ref_index":10,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XHOZYFU2S7H5UTKJR44VODMRLQ","json":"https://pith.science/pith/XHOZYFU2S7H5UTKJR44VODMRLQ.json","graph_json":"https://pith.science/api/pith-number/XHOZYFU2S7H5UTKJR44VODMRLQ/graph.json","events_json":"https://pith.science/api/pith-number/XHOZYFU2S7H5UTKJR44VODMRLQ/events.json","paper":"https://pith.science/paper/XHOZYFU2"},"agent_actions":{"view_html":"https://pith.science/pith/XHOZYFU2S7H5UTKJR44VODMRLQ","download_json":"https://pith.science/pith/XHOZYFU2S7H5UTKJR44VODMRLQ.json","view_paper":"https://pith.science/paper/XHOZYFU2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.00032&json=true","fetch_graph":"https://pith.science/api/pith-number/XHOZYFU2S7H5UTKJR44VODMRLQ/graph.json","fetch_events":"https://pith.science/api/pith-number/XHOZYFU2S7H5UTKJR44VODMRLQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XHOZYFU2S7H5UTKJR44VODMRLQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XHOZYFU2S7H5UTKJR44VODMRLQ/action/storage_attestation","attest_author":"https://pith.science/pith/XHOZYFU2S7H5UTKJR44VODMRLQ/action/author_attestation","sign_citation":"https://pith.science/pith/XHOZYFU2S7H5UTKJR44VODMRLQ/action/citation_signature","submit_replication":"https://pith.science/pith/XHOZYFU2S7H5UTKJR44VODMRLQ/action/replication_record"}},"created_at":"2026-07-05T10:08:54.774662+00:00","updated_at":"2026-07-05T10:08:54.774662+00:00"}