{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:ZGYJLCFZ67PQKF5UXNVIEM2ZLE","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":"0c2725eea4a638e47649f6a5e91bdc9bf3e98d06459988c398fb79988f36ab77","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-12-21T10:13:45Z","title_canon_sha256":"6dc6e277581f2b16b2057bff8563d581508a81b3ba661bfc4d612f69841969a3"},"schema_version":"1.0","source":{"id":"2412.17867","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.17867","created_at":"2026-07-05T10:45:58Z"},{"alias_kind":"arxiv_version","alias_value":"2412.17867v4","created_at":"2026-07-05T10:45:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.17867","created_at":"2026-07-05T10:45:58Z"},{"alias_kind":"pith_short_12","alias_value":"ZGYJLCFZ67PQ","created_at":"2026-07-05T10:45:58Z"},{"alias_kind":"pith_short_16","alias_value":"ZGYJLCFZ67PQKF5U","created_at":"2026-07-05T10:45:58Z"},{"alias_kind":"pith_short_8","alias_value":"ZGYJLCFZ","created_at":"2026-07-05T10:45:58Z"}],"graph_snapshots":[{"event_id":"sha256:f7c1e245f54ac6409a0e8d697018730bf07ee6d473715d7e3bf7a807b7d334e9","target":"graph","created_at":"2026-07-05T10:45:58Z","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/2412.17867/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent advancements in large language models (LLMs) have significantly advanced text-to-SQL systems. However, most LLM-based methods often narrowly focus on SQL generation, neglecting the complexities of real-world conversational queries. This oversight can lead to unreliable responses, particularly for ambiguous questions that cannot be directly addressed with SQL. To bridge this gap, we propose MMSQL, a comprehensive test suite designed to evaluate the question classification and SQL generation capabilities of LLMs by simulating real-world scenarios with diverse question types and multi-turn","authors_text":"Chao Ma, Guangyao Wang, Hai Huang, Tiancheng Zhao, Yinggang Sun, Ziming Guo","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-12-21T10:13:45Z","title":"Evaluating and Enhancing LLMs for Multi-turn Text-to-SQL with Multiple Question Types"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.17867","kind":"arxiv","version":4},"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":"sha256:313497b5bec8686f325dcc02a59f95c4dd3dbb7cb25c443f6f1ff8a5aa99eb20","target":"record","created_at":"2026-07-05T10:45:58Z","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":"0c2725eea4a638e47649f6a5e91bdc9bf3e98d06459988c398fb79988f36ab77","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-12-21T10:13:45Z","title_canon_sha256":"6dc6e277581f2b16b2057bff8563d581508a81b3ba661bfc4d612f69841969a3"},"schema_version":"1.0","source":{"id":"2412.17867","kind":"arxiv","version":4}},"canonical_sha256":"c9b09588b9f7df0517b4bb6a8233595939fda640197ee1dce54a7d1272a048b0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c9b09588b9f7df0517b4bb6a8233595939fda640197ee1dce54a7d1272a048b0","first_computed_at":"2026-07-05T10:45:58.745865Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:45:58.745865Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"C8bLh/9z/PP2r2jZy17Zb5er0DnVtfX7zCyovIbKLRo0JzV2qvaHRW5wPs2xzvH9lVqXYO3Lmr/uM1GyL0SxDA==","signature_status":"signed_v1","signed_at":"2026-07-05T10:45:58.746354Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.17867","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:313497b5bec8686f325dcc02a59f95c4dd3dbb7cb25c443f6f1ff8a5aa99eb20","sha256:f7c1e245f54ac6409a0e8d697018730bf07ee6d473715d7e3bf7a807b7d334e9"],"state_sha256":"285c59654a92d12d3d32c465c1f801bae4d7292d75e1d0b079deaf46c89d4b94"}