{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:EHVW4X47PRBIAOUB5FKQAPHJH2","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":"c50f9cfe731cf3b088b76e0b49aef6b23116c6b28e4f21a3b5e13f7c3120010d","cross_cats_sorted":["cs.DB"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-08-08T23:09:45Z","title_canon_sha256":"08cabe3ee82d69b275c8cdb4885c51d579fa8ef46cef9cacadcd1c6ce8183b88"},"schema_version":"1.0","source":{"id":"2508.14056","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.14056","created_at":"2026-07-05T11:56:24Z"},{"alias_kind":"arxiv_version","alias_value":"2508.14056v1","created_at":"2026-07-05T11:56:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.14056","created_at":"2026-07-05T11:56:24Z"},{"alias_kind":"pith_short_12","alias_value":"EHVW4X47PRBI","created_at":"2026-07-05T11:56:24Z"},{"alias_kind":"pith_short_16","alias_value":"EHVW4X47PRBIAOUB","created_at":"2026-07-05T11:56:24Z"},{"alias_kind":"pith_short_8","alias_value":"EHVW4X47","created_at":"2026-07-05T11:56:24Z"}],"graph_snapshots":[{"event_id":"sha256:68393d14af2469d42625d9a23580c5350c3f50afde75f7be8d0b0bf0aa77e371","target":"graph","created_at":"2026-07-05T11:56:24Z","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/2508.14056/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Confidence estimation for text-to-SQL aims to assess the reliability of model-generated SQL queries without having access to gold answers. We study this problem in the context of large language models (LLMs), where access to model weights and gradients is often constrained. We explore both black-box and white-box confidence estimation strategies, evaluating their effectiveness on cross-domain text-to-SQL benchmarks. Our evaluation highlights the superior performance of consistency-based methods among black-box models and the advantage of SQL-syntax-aware approaches for interpreting LLM logits ","authors_text":"Davood Rafiei, Mohammadreza Pourreza, Sepideh Entezari Maleki","cross_cats":["cs.DB"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-08-08T23:09:45Z","title":"Confidence Estimation for Text-to-SQL in Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.14056","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:dd8a458b33f53bc0dec4785075126e01b196ff6017c683a86a31ebbe6d638732","target":"record","created_at":"2026-07-05T11:56:24Z","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":"c50f9cfe731cf3b088b76e0b49aef6b23116c6b28e4f21a3b5e13f7c3120010d","cross_cats_sorted":["cs.DB"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-08-08T23:09:45Z","title_canon_sha256":"08cabe3ee82d69b275c8cdb4885c51d579fa8ef46cef9cacadcd1c6ce8183b88"},"schema_version":"1.0","source":{"id":"2508.14056","kind":"arxiv","version":1}},"canonical_sha256":"21eb6e5f9f7c42803a81e955003ce93e8bf7671077bd6569a762890361d21b84","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"21eb6e5f9f7c42803a81e955003ce93e8bf7671077bd6569a762890361d21b84","first_computed_at":"2026-07-05T11:56:24.064380Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:56:24.064380Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"esXHeJPEJhgE620vDB8tO4zuxG393MkVrOrlxanV/LfjdPCT/t3NrzrySqBDwViwGWoeEQg8kR4ojRAwbxC6Ag==","signature_status":"signed_v1","signed_at":"2026-07-05T11:56:24.064780Z","signed_message":"canonical_sha256_bytes"},"source_id":"2508.14056","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:dd8a458b33f53bc0dec4785075126e01b196ff6017c683a86a31ebbe6d638732","sha256:68393d14af2469d42625d9a23580c5350c3f50afde75f7be8d0b0bf0aa77e371"],"state_sha256":"c44729e20ea4c69c05f2a8025aacc05d20ea8f25c825e9dd9a804954e8e9e7d8"}