{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:H7ULHVTR2QX4SQBMEH25LFADJJ","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"c79b7185be4bb3e32f13bf779100cc40a98ddb696c12c21f729341e893c80159","cross_cats_sorted":["cs.DB","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-10-27T23:36:14Z","title_canon_sha256":"c79ff286dd0a4e271d65d8cdc3db49f1bcdf53cb48292d83413d9cb8b6196b18"},"schema_version":"1.0","source":{"id":"2310.18538","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.18538","created_at":"2026-07-05T07:06:09Z"},{"alias_kind":"arxiv_version","alias_value":"2310.18538v1","created_at":"2026-07-05T07:06:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.18538","created_at":"2026-07-05T07:06:09Z"},{"alias_kind":"pith_short_12","alias_value":"H7ULHVTR2QX4","created_at":"2026-07-05T07:06:09Z"},{"alias_kind":"pith_short_16","alias_value":"H7ULHVTR2QX4SQBM","created_at":"2026-07-05T07:06:09Z"},{"alias_kind":"pith_short_8","alias_value":"H7ULHVTR","created_at":"2026-07-05T07:06:09Z"}],"graph_snapshots":[{"event_id":"sha256:b349cce5b6c50f893aa3ec9fbb5307d33d5b04ed65529283675db09400556b32","target":"graph","created_at":"2026-07-05T07:06:09Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2310.18538/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Davood Rafiei, Mohammadreza Pourreza","cross_cats":["cs.DB","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-10-27T23:36:14Z","title":"Evaluating Cross-Domain Text-to-SQL Models and Benchmarks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.18538","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:4827cf627caebf90b8c95b4172dc8139ca83809effced161af055ef132e36ba9","target":"record","created_at":"2026-07-05T07:06:09Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"c79b7185be4bb3e32f13bf779100cc40a98ddb696c12c21f729341e893c80159","cross_cats_sorted":["cs.DB","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-10-27T23:36:14Z","title_canon_sha256":"c79ff286dd0a4e271d65d8cdc3db49f1bcdf53cb48292d83413d9cb8b6196b18"},"schema_version":"1.0","source":{"id":"2310.18538","kind":"arxiv","version":1}},"canonical_sha256":"3fe8b3d671d42fc9402c21f5d594034a40069ee3cc5eb42321bc75999d7709e1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3fe8b3d671d42fc9402c21f5d594034a40069ee3cc5eb42321bc75999d7709e1","first_computed_at":"2026-07-05T07:06:09.784658Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:06:09.784658Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ebaZj3TC5JuAESMG8WbolZTj0slck9Cjl+rFoijFMSRkmdrO7dD4QEPJIyaweK5Po5RhWVwdfjwn1L8G42orCw==","signature_status":"signed_v1","signed_at":"2026-07-05T07:06:09.785156Z","signed_message":"canonical_sha256_bytes"},"source_id":"2310.18538","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4827cf627caebf90b8c95b4172dc8139ca83809effced161af055ef132e36ba9","sha256:b349cce5b6c50f893aa3ec9fbb5307d33d5b04ed65529283675db09400556b32"],"state_sha256":"e257c4e3d08e7d9bf07e4b555bc65f2b0fe9b77a676ad307f8f3938bb03d2ab1"}