{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:H7ULHVTR2QX4SQBMEH25LFADJJ","short_pith_number":"pith:H7ULHVTR","schema_version":"1.0","canonical_sha256":"3fe8b3d671d42fc9402c21f5d594034a40069ee3cc5eb42321bc75999d7709e1","source":{"kind":"arxiv","id":"2310.18538","version":1},"attestation_state":"computed","paper":{"title":"Evaluating Cross-Domain Text-to-SQL Models and Benchmarks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.DB","cs.LG"],"primary_cat":"cs.CL","authors_text":"Davood Rafiei, Mohammadreza Pourreza","submitted_at":"2023-10-27T23:36:14Z","abstract_excerpt":"Text-to-SQL benchmarks play a crucial role in evaluating the progress made in the field and the ranking of different models. However, accurately matching a model-generated SQL query to a reference SQL query in a benchmark fails for various reasons, such as underspecified natural language queries, inherent assumptions in both model-generated and reference queries, and the non-deterministic nature of SQL output under certain conditions. In this paper, we conduct an extensive study of several prominent cross-domain text-to-SQL benchmarks and re-evaluate some of the top-performing models within th"},"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":"2310.18538","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-10-27T23:36:14Z","cross_cats_sorted":["cs.DB","cs.LG"],"title_canon_sha256":"c79ff286dd0a4e271d65d8cdc3db49f1bcdf53cb48292d83413d9cb8b6196b18","abstract_canon_sha256":"c79b7185be4bb3e32f13bf779100cc40a98ddb696c12c21f729341e893c80159"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:06:09.785156Z","signature_b64":"ebaZj3TC5JuAESMG8WbolZTj0slck9Cjl+rFoijFMSRkmdrO7dD4QEPJIyaweK5Po5RhWVwdfjwn1L8G42orCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3fe8b3d671d42fc9402c21f5d594034a40069ee3cc5eb42321bc75999d7709e1","last_reissued_at":"2026-07-05T07:06:09.784658Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:06:09.784658Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Evaluating Cross-Domain Text-to-SQL Models and Benchmarks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.DB","cs.LG"],"primary_cat":"cs.CL","authors_text":"Davood Rafiei, Mohammadreza Pourreza","submitted_at":"2023-10-27T23:36:14Z","abstract_excerpt":"Text-to-SQL benchmarks play a crucial role in evaluating the progress made in the field and the ranking of different models. However, accurately matching a model-generated SQL query to a reference SQL query in a benchmark fails for various reasons, such as underspecified natural language queries, inherent assumptions in both model-generated and reference queries, and the non-deterministic nature of SQL output under certain conditions. In this paper, we conduct an extensive study of several prominent cross-domain text-to-SQL benchmarks and re-evaluate some of the top-performing models within th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.18538","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/2310.18538/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":"2310.18538","created_at":"2026-07-05T07:06:09.784721+00:00"},{"alias_kind":"arxiv_version","alias_value":"2310.18538v1","created_at":"2026-07-05T07:06:09.784721+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.18538","created_at":"2026-07-05T07:06:09.784721+00:00"},{"alias_kind":"pith_short_12","alias_value":"H7ULHVTR2QX4","created_at":"2026-07-05T07:06:09.784721+00:00"},{"alias_kind":"pith_short_16","alias_value":"H7ULHVTR2QX4SQBM","created_at":"2026-07-05T07:06:09.784721+00:00"},{"alias_kind":"pith_short_8","alias_value":"H7ULHVTR","created_at":"2026-07-05T07:06:09.784721+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2507.01053","citing_title":"M3: Conversational LLMs Simplify Secure Clinical Data Access, Understanding, and Analysis","ref_index":29,"is_internal_anchor":false},{"citing_arxiv_id":"2405.16755","citing_title":"CHESS: Contextual Harnessing for Efficient SQL Synthesis","ref_index":49,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/H7ULHVTR2QX4SQBMEH25LFADJJ","json":"https://pith.science/pith/H7ULHVTR2QX4SQBMEH25LFADJJ.json","graph_json":"https://pith.science/api/pith-number/H7ULHVTR2QX4SQBMEH25LFADJJ/graph.json","events_json":"https://pith.science/api/pith-number/H7ULHVTR2QX4SQBMEH25LFADJJ/events.json","paper":"https://pith.science/paper/H7ULHVTR"},"agent_actions":{"view_html":"https://pith.science/pith/H7ULHVTR2QX4SQBMEH25LFADJJ","download_json":"https://pith.science/pith/H7ULHVTR2QX4SQBMEH25LFADJJ.json","view_paper":"https://pith.science/paper/H7ULHVTR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2310.18538&json=true","fetch_graph":"https://pith.science/api/pith-number/H7ULHVTR2QX4SQBMEH25LFADJJ/graph.json","fetch_events":"https://pith.science/api/pith-number/H7ULHVTR2QX4SQBMEH25LFADJJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/H7ULHVTR2QX4SQBMEH25LFADJJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/H7ULHVTR2QX4SQBMEH25LFADJJ/action/storage_attestation","attest_author":"https://pith.science/pith/H7ULHVTR2QX4SQBMEH25LFADJJ/action/author_attestation","sign_citation":"https://pith.science/pith/H7ULHVTR2QX4SQBMEH25LFADJJ/action/citation_signature","submit_replication":"https://pith.science/pith/H7ULHVTR2QX4SQBMEH25LFADJJ/action/replication_record"}},"created_at":"2026-07-05T07:06:09.784721+00:00","updated_at":"2026-07-05T07:06:09.784721+00:00"}