{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:HCHOFL7IUSYGPYZ7OTVOGMZTJV","short_pith_number":"pith:HCHOFL7I","schema_version":"1.0","canonical_sha256":"388ee2afe8a4b067e33f74eae333334d500d61275e5991341de47574293ad783","source":{"kind":"arxiv","id":"2305.16265","version":3},"attestation_state":"computed","paper":{"title":"UNITE: A Unified Benchmark for Text-to-SQL Evaluation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Alexander Li, Anuj Chauhan, Bing Xiang, Chung-Wei Hang, Henghui Zhu, Jiang Guo, Jiarong Jiang, Joseph Lilien, Jun Wang, Lin Pan, Mingwen Dong, Patrick Ng, Sheng Zhang, Stephen Ash, Vittorio Castelli, Wuwei Lan, Yiqun Hu, Zhiguo Wang","submitted_at":"2023-05-25T17:19:52Z","abstract_excerpt":"A practical text-to-SQL system should generalize well on a wide variety of natural language questions, unseen database schemas, and novel SQL query structures. To comprehensively evaluate text-to-SQL systems, we introduce a UNIfied benchmark for Text-to-SQL Evaluation (UNITE). It is composed of publicly available text-to-SQL datasets, containing natural language questions from more than 12 domains, SQL queries from more than 3.9K patterns, and 29K databases. Compared to the widely used Spider benchmark, we introduce $\\sim$120K additional examples and a threefold increase in SQL patterns, such "},"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":"2305.16265","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-05-25T17:19:52Z","cross_cats_sorted":[],"title_canon_sha256":"f0da9a76cb99d6bec3d7edac956a43b940f258c41506499acf314209a6bde7c0","abstract_canon_sha256":"3ecf22d47be46de86118a337aff2f41ce42fb4b6cede1803ffda39a45582b0f8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:30:45.831485Z","signature_b64":"d5YWrjutFHVWOuoOVLvtcbHWibwDizChW+rrQXTuw2zIbVPnY0elTJ0PrGtMdDIaudKU/clk3KzTYhMOJ+D5Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"388ee2afe8a4b067e33f74eae333334d500d61275e5991341de47574293ad783","last_reissued_at":"2026-07-05T06:30:45.830978Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:30:45.830978Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"UNITE: A Unified Benchmark for Text-to-SQL Evaluation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Alexander Li, Anuj Chauhan, Bing Xiang, Chung-Wei Hang, Henghui Zhu, Jiang Guo, Jiarong Jiang, Joseph Lilien, Jun Wang, Lin Pan, Mingwen Dong, Patrick Ng, Sheng Zhang, Stephen Ash, Vittorio Castelli, Wuwei Lan, Yiqun Hu, Zhiguo Wang","submitted_at":"2023-05-25T17:19:52Z","abstract_excerpt":"A practical text-to-SQL system should generalize well on a wide variety of natural language questions, unseen database schemas, and novel SQL query structures. To comprehensively evaluate text-to-SQL systems, we introduce a UNIfied benchmark for Text-to-SQL Evaluation (UNITE). It is composed of publicly available text-to-SQL datasets, containing natural language questions from more than 12 domains, SQL queries from more than 3.9K patterns, and 29K databases. Compared to the widely used Spider benchmark, we introduce $\\sim$120K additional examples and a threefold increase in SQL patterns, such "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.16265","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/2305.16265/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":"2305.16265","created_at":"2026-07-05T06:30:45.831041+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.16265v3","created_at":"2026-07-05T06:30:45.831041+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.16265","created_at":"2026-07-05T06:30:45.831041+00:00"},{"alias_kind":"pith_short_12","alias_value":"HCHOFL7IUSYG","created_at":"2026-07-05T06:30:45.831041+00:00"},{"alias_kind":"pith_short_16","alias_value":"HCHOFL7IUSYGPYZ7","created_at":"2026-07-05T06:30:45.831041+00:00"},{"alias_kind":"pith_short_8","alias_value":"HCHOFL7I","created_at":"2026-07-05T06:30:45.831041+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.02109","citing_title":"BADGER: Bridging Agentic and Deterministic Evaluation for Generative Enterprise Reasoning","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2409.02038","citing_title":"BEAVER: An Enterprise Benchmark for Text-to-SQL","ref_index":5,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HCHOFL7IUSYGPYZ7OTVOGMZTJV","json":"https://pith.science/pith/HCHOFL7IUSYGPYZ7OTVOGMZTJV.json","graph_json":"https://pith.science/api/pith-number/HCHOFL7IUSYGPYZ7OTVOGMZTJV/graph.json","events_json":"https://pith.science/api/pith-number/HCHOFL7IUSYGPYZ7OTVOGMZTJV/events.json","paper":"https://pith.science/paper/HCHOFL7I"},"agent_actions":{"view_html":"https://pith.science/pith/HCHOFL7IUSYGPYZ7OTVOGMZTJV","download_json":"https://pith.science/pith/HCHOFL7IUSYGPYZ7OTVOGMZTJV.json","view_paper":"https://pith.science/paper/HCHOFL7I","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.16265&json=true","fetch_graph":"https://pith.science/api/pith-number/HCHOFL7IUSYGPYZ7OTVOGMZTJV/graph.json","fetch_events":"https://pith.science/api/pith-number/HCHOFL7IUSYGPYZ7OTVOGMZTJV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HCHOFL7IUSYGPYZ7OTVOGMZTJV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HCHOFL7IUSYGPYZ7OTVOGMZTJV/action/storage_attestation","attest_author":"https://pith.science/pith/HCHOFL7IUSYGPYZ7OTVOGMZTJV/action/author_attestation","sign_citation":"https://pith.science/pith/HCHOFL7IUSYGPYZ7OTVOGMZTJV/action/citation_signature","submit_replication":"https://pith.science/pith/HCHOFL7IUSYGPYZ7OTVOGMZTJV/action/replication_record"}},"created_at":"2026-07-05T06:30:45.831041+00:00","updated_at":"2026-07-05T06:30:45.831041+00:00"}