{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:OUBEADN44FEY4YHNJYLAOAJTGY","short_pith_number":"pith:OUBEADN4","schema_version":"1.0","canonical_sha256":"7502400dbce1498e60ed4e16070133363174a2bd8d01af08cea04cfad648946a","source":{"kind":"arxiv","id":"2505.19988","version":2},"attestation_state":"computed","paper":{"title":"Automatic Metadata Extraction for Text-to-SQL","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.DB","authors_text":"Divesh Srivastava, Parisa Ghane, Theodore Johnson, Vladislav Shkapenyuk","submitted_at":"2025-05-26T13:43:43Z","abstract_excerpt":"Large Language Models (LLMs) have recently become sophisticated enough to automate many tasks ranging from pattern finding to writing assistance to code generation. In this paper, we examine text-to-SQL generation. We have observed from decades of experience that the most difficult part of query development lies in understanding the database contents. These experiences inform the direction of our research.\n  Text-to-SQL benchmarks such as SPIDER and Bird contain extensive metadata that is generally not available in practice. Human-generated metadata requires the use of expensive Subject Matter"},"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":"2505.19988","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.DB","submitted_at":"2025-05-26T13:43:43Z","cross_cats_sorted":[],"title_canon_sha256":"22a19066490eede50eb145fad8208d0542b638339f56669d7f150b8ff998d2bc","abstract_canon_sha256":"32f3628776f75ac24ed64c56f01531e0ff4d1b1b51664698c827214600c8a156"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:04:15.187403Z","signature_b64":"ysW92M8RHw1kYV88F6BjXslylQld0zXAoKpKs2lFLDSUurtZBWuQNb59pKeoUWNlVLFh7iVc2jiOXft+LGwyBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7502400dbce1498e60ed4e16070133363174a2bd8d01af08cea04cfad648946a","last_reissued_at":"2026-07-05T12:04:15.186867Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:04:15.186867Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Automatic Metadata Extraction for Text-to-SQL","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.DB","authors_text":"Divesh Srivastava, Parisa Ghane, Theodore Johnson, Vladislav Shkapenyuk","submitted_at":"2025-05-26T13:43:43Z","abstract_excerpt":"Large Language Models (LLMs) have recently become sophisticated enough to automate many tasks ranging from pattern finding to writing assistance to code generation. In this paper, we examine text-to-SQL generation. We have observed from decades of experience that the most difficult part of query development lies in understanding the database contents. These experiences inform the direction of our research.\n  Text-to-SQL benchmarks such as SPIDER and Bird contain extensive metadata that is generally not available in practice. Human-generated metadata requires the use of expensive Subject Matter"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.19988","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/2505.19988/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":"2505.19988","created_at":"2026-07-05T12:04:15.186931+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.19988v2","created_at":"2026-07-05T12:04:15.186931+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.19988","created_at":"2026-07-05T12:04:15.186931+00:00"},{"alias_kind":"pith_short_12","alias_value":"OUBEADN44FEY","created_at":"2026-07-05T12:04:15.186931+00:00"},{"alias_kind":"pith_short_16","alias_value":"OUBEADN44FEY4YHN","created_at":"2026-07-05T12:04:15.186931+00:00"},{"alias_kind":"pith_short_8","alias_value":"OUBEADN4","created_at":"2026-07-05T12:04:15.186931+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.30862","citing_title":"Sophrosyne: Agentic Exploration of Relational Data Systems Needs Moderation","ref_index":42,"is_internal_anchor":false},{"citing_arxiv_id":"2510.17586","citing_title":"DeepEye-SQL: A Software-Engineering-Inspired Text-to-SQL Framework","ref_index":49,"is_internal_anchor":false},{"citing_arxiv_id":"2605.12319","citing_title":"Data-aware candidate selection in NL2SQL translation via small separating instances","ref_index":15,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OUBEADN44FEY4YHNJYLAOAJTGY","json":"https://pith.science/pith/OUBEADN44FEY4YHNJYLAOAJTGY.json","graph_json":"https://pith.science/api/pith-number/OUBEADN44FEY4YHNJYLAOAJTGY/graph.json","events_json":"https://pith.science/api/pith-number/OUBEADN44FEY4YHNJYLAOAJTGY/events.json","paper":"https://pith.science/paper/OUBEADN4"},"agent_actions":{"view_html":"https://pith.science/pith/OUBEADN44FEY4YHNJYLAOAJTGY","download_json":"https://pith.science/pith/OUBEADN44FEY4YHNJYLAOAJTGY.json","view_paper":"https://pith.science/paper/OUBEADN4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.19988&json=true","fetch_graph":"https://pith.science/api/pith-number/OUBEADN44FEY4YHNJYLAOAJTGY/graph.json","fetch_events":"https://pith.science/api/pith-number/OUBEADN44FEY4YHNJYLAOAJTGY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OUBEADN44FEY4YHNJYLAOAJTGY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OUBEADN44FEY4YHNJYLAOAJTGY/action/storage_attestation","attest_author":"https://pith.science/pith/OUBEADN44FEY4YHNJYLAOAJTGY/action/author_attestation","sign_citation":"https://pith.science/pith/OUBEADN44FEY4YHNJYLAOAJTGY/action/citation_signature","submit_replication":"https://pith.science/pith/OUBEADN44FEY4YHNJYLAOAJTGY/action/replication_record"}},"created_at":"2026-07-05T12:04:15.186931+00:00","updated_at":"2026-07-05T12:04:15.186931+00:00"}