{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:5VUGRL5XAAICLYHQNWUPN2ZQMW","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":"961049387b5a22a23e882b91bfcd7a49f376c6cb93b2e3459374ccabd45bd16d","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-11T03:16:39Z","title_canon_sha256":"f4f8a3788084587c103619cbb5783515bc269e1bbbc11fb26d81fe0654be7031"},"schema_version":"1.0","source":{"id":"2506.09359","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.09359","created_at":"2026-07-05T11:19:35Z"},{"alias_kind":"arxiv_version","alias_value":"2506.09359v1","created_at":"2026-07-05T11:19:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.09359","created_at":"2026-07-05T11:19:35Z"},{"alias_kind":"pith_short_12","alias_value":"5VUGRL5XAAIC","created_at":"2026-07-05T11:19:35Z"},{"alias_kind":"pith_short_16","alias_value":"5VUGRL5XAAICLYHQ","created_at":"2026-07-05T11:19:35Z"},{"alias_kind":"pith_short_8","alias_value":"5VUGRL5X","created_at":"2026-07-05T11:19:35Z"}],"graph_snapshots":[{"event_id":"sha256:74c565e19ad6b4ab548e469e81dcf53c3c05d33a37520a09101e6fdd0bd0614f","target":"graph","created_at":"2026-07-05T11:19:35Z","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/2506.09359/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The rise of Large Language Models (LLMs) has significantly advanced Text-to-SQL (NL2SQL) systems, yet evaluating the semantic equivalence of generated SQL remains a challenge, especially given ambiguous user queries and multiple valid SQL interpretations. This paper explores using LLMs to assess both semantic and a more practical \"weak\" semantic equivalence. We analyze common patterns of SQL equivalence and inequivalence, discuss challenges in LLM-based evaluation.","authors_text":"Arash Niknafs, Ashish Basran, Carol Szabo, Qingyun Zeng, Simin Ma","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-11T03:16:39Z","title":"Taming SQL Complexity: LLM-Based Equivalence Evaluation for Text-to-SQL"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.09359","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":"sha256:3e0e0438d65a65c8c0f48b7a2193dcb6e70fe96b8da3dc5906a70631216f44ed","target":"record","created_at":"2026-07-05T11:19:35Z","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":"961049387b5a22a23e882b91bfcd7a49f376c6cb93b2e3459374ccabd45bd16d","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-11T03:16:39Z","title_canon_sha256":"f4f8a3788084587c103619cbb5783515bc269e1bbbc11fb26d81fe0654be7031"},"schema_version":"1.0","source":{"id":"2506.09359","kind":"arxiv","version":1}},"canonical_sha256":"ed6868afb7001025e0f06da8f6eb3065911a42273092588b0cc451c0e68599ca","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ed6868afb7001025e0f06da8f6eb3065911a42273092588b0cc451c0e68599ca","first_computed_at":"2026-07-05T11:19:35.607049Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:19:35.607049Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"pDAdM2TQEbuXGhFm2hEi112lysxEaNJKapvxY7KVLvIaC8xYvHbPGxZhYeda2X1ZfuwwGt54PSGHJuPt+qqgDA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:19:35.607604Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.09359","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3e0e0438d65a65c8c0f48b7a2193dcb6e70fe96b8da3dc5906a70631216f44ed","sha256:74c565e19ad6b4ab548e469e81dcf53c3c05d33a37520a09101e6fdd0bd0614f"],"state_sha256":"cd2cfc32ff0c065137739b982fe4520ce9cc9164309f24ffeba8bb2a32bfe1cc"}