{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:7DXR3HSGW4D6EUXMDK7XCOJCHO","short_pith_number":"pith:7DXR3HSG","schema_version":"1.0","canonical_sha256":"f8ef1d9e46b707e252ec1abf7139223bb55510e83ea700843bd119ed9579d070","source":{"kind":"arxiv","id":"2402.08349","version":3},"attestation_state":"computed","paper":{"title":"Evaluating the Data Model Robustness of Text-to-SQL Systems Based on Real User Queries","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.DB","authors_text":"Catherine Kosten, Farhad Nooralahzadeh, Jonathan F\\\"urst, Kurt Stockinger, Yi Zhang","submitted_at":"2024-02-13T10:28:57Z","abstract_excerpt":"Text-to-SQL systems (also known as NL-to-SQL systems) have become an increasingly popular solution for bridging the gap between user capabilities and SQL-based data access. These systems translate user requests in natural language to valid SQL statements for a specific database. Recent Text-to-SQL systems have benefited from the rapid improvement of transformer-based language models. However, while Text-to-SQL systems that incorporate such models continuously reach new high scores on -- often synthetic -- benchmark datasets, a systematic exploration of their robustness towards different data m"},"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":"2402.08349","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DB","submitted_at":"2024-02-13T10:28:57Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"c875a71a431f0b702eb35cdda29b7a1a6323776d4a01965bc8d248a027a1c77c","abstract_canon_sha256":"852b11b49cee65902d7278b3a4311238034b0746e86d654fe2ba81abf7f7aacf"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:41:32.000727Z","signature_b64":"H7Ut8zbEvgcJ2WqkVikcLOwmOWZvlWsc6r6DmrKs4pfJR1TnAIexoFAooxUXarrSdbhMLfMTRsw6jW7QuHbhDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f8ef1d9e46b707e252ec1abf7139223bb55510e83ea700843bd119ed9579d070","last_reissued_at":"2026-07-05T09:41:32.000295Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:41:32.000295Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Evaluating the Data Model Robustness of Text-to-SQL Systems Based on Real User Queries","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.DB","authors_text":"Catherine Kosten, Farhad Nooralahzadeh, Jonathan F\\\"urst, Kurt Stockinger, Yi Zhang","submitted_at":"2024-02-13T10:28:57Z","abstract_excerpt":"Text-to-SQL systems (also known as NL-to-SQL systems) have become an increasingly popular solution for bridging the gap between user capabilities and SQL-based data access. These systems translate user requests in natural language to valid SQL statements for a specific database. Recent Text-to-SQL systems have benefited from the rapid improvement of transformer-based language models. However, while Text-to-SQL systems that incorporate such models continuously reach new high scores on -- often synthetic -- benchmark datasets, a systematic exploration of their robustness towards different data m"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.08349","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/2402.08349/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":"2402.08349","created_at":"2026-07-05T09:41:32.000365+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.08349v3","created_at":"2026-07-05T09:41:32.000365+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.08349","created_at":"2026-07-05T09:41:32.000365+00:00"},{"alias_kind":"pith_short_12","alias_value":"7DXR3HSGW4D6","created_at":"2026-07-05T09:41:32.000365+00:00"},{"alias_kind":"pith_short_16","alias_value":"7DXR3HSGW4D6EUXM","created_at":"2026-07-05T09:41:32.000365+00:00"},{"alias_kind":"pith_short_8","alias_value":"7DXR3HSG","created_at":"2026-07-05T09:41:32.000365+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.25838","citing_title":"Same Data, Different Schemas: Robustness of LLM-based Text-to-SQL","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2605.00628","citing_title":"EGREFINE: An Execution-Grounded Optimization Framework for Text-to-SQL Schema Refinement","ref_index":8,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7DXR3HSGW4D6EUXMDK7XCOJCHO","json":"https://pith.science/pith/7DXR3HSGW4D6EUXMDK7XCOJCHO.json","graph_json":"https://pith.science/api/pith-number/7DXR3HSGW4D6EUXMDK7XCOJCHO/graph.json","events_json":"https://pith.science/api/pith-number/7DXR3HSGW4D6EUXMDK7XCOJCHO/events.json","paper":"https://pith.science/paper/7DXR3HSG"},"agent_actions":{"view_html":"https://pith.science/pith/7DXR3HSGW4D6EUXMDK7XCOJCHO","download_json":"https://pith.science/pith/7DXR3HSGW4D6EUXMDK7XCOJCHO.json","view_paper":"https://pith.science/paper/7DXR3HSG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.08349&json=true","fetch_graph":"https://pith.science/api/pith-number/7DXR3HSGW4D6EUXMDK7XCOJCHO/graph.json","fetch_events":"https://pith.science/api/pith-number/7DXR3HSGW4D6EUXMDK7XCOJCHO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7DXR3HSGW4D6EUXMDK7XCOJCHO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7DXR3HSGW4D6EUXMDK7XCOJCHO/action/storage_attestation","attest_author":"https://pith.science/pith/7DXR3HSGW4D6EUXMDK7XCOJCHO/action/author_attestation","sign_citation":"https://pith.science/pith/7DXR3HSGW4D6EUXMDK7XCOJCHO/action/citation_signature","submit_replication":"https://pith.science/pith/7DXR3HSGW4D6EUXMDK7XCOJCHO/action/replication_record"}},"created_at":"2026-07-05T09:41:32.000365+00:00","updated_at":"2026-07-05T09:41:32.000365+00:00"}