{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:M7KVIWJMD25S3ZWPMGKSSDVEZH","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":"78cdc36fbf25d674a7dead8ffd1679da15698b63d1e124f841fb2dd9b6253138","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-12-17T02:53:21Z","title_canon_sha256":"88c7594c89ed294263920727df0e08f704ac39ea4b581ce432111752ae7ca761"},"schema_version":"1.0","source":{"id":"2212.08785","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2212.08785","created_at":"2026-07-05T05:26:14Z"},{"alias_kind":"arxiv_version","alias_value":"2212.08785v1","created_at":"2026-07-05T05:26:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2212.08785","created_at":"2026-07-05T05:26:14Z"},{"alias_kind":"pith_short_12","alias_value":"M7KVIWJMD25S","created_at":"2026-07-05T05:26:14Z"},{"alias_kind":"pith_short_16","alias_value":"M7KVIWJMD25S3ZWP","created_at":"2026-07-05T05:26:14Z"},{"alias_kind":"pith_short_8","alias_value":"M7KVIWJM","created_at":"2026-07-05T05:26:14Z"}],"graph_snapshots":[{"event_id":"sha256:7181b910b08ed0320e778d54d5593385b1644b65c2e18bd8f114d741df840e31","target":"graph","created_at":"2026-07-05T05:26:14Z","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/2212.08785/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recently, there has been increasing interest in synthesizing data to improve downstream text-to-SQL tasks. In this paper, we first examined the existing synthesized datasets and discovered that state-of-the-art text-to-SQL algorithms did not further improve on popular benchmarks when trained with augmented synthetic data. We observed two shortcomings: illogical synthetic SQL queries from independent column sampling and arbitrary table joins. To address these issues, we propose a novel synthesis framework that incorporates key relationships from schema, imposes strong typing, and conducts schem","authors_text":"Alexander Li, Anuj Chauhan, Bing Xiang, Chung-Wei Hang, Henry Zhu, Jiarong Jiang, Joe Lilien, Jun Wang, Lin Pan, Marvin Dong, Patrick Ng, Sheng Zhang, Vittorio Castelli, Wuwei Lan, Yiqun Hu, Yiyun Zhao, Zhiguo Wang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-12-17T02:53:21Z","title":"Importance of Synthesizing High-quality Data for Text-to-SQL Parsing"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2212.08785","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:ca763712a4ecb428a795b57c50d6e1a2d4b7d960bfb7f055436a2b8ab5934a45","target":"record","created_at":"2026-07-05T05:26:14Z","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":"78cdc36fbf25d674a7dead8ffd1679da15698b63d1e124f841fb2dd9b6253138","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-12-17T02:53:21Z","title_canon_sha256":"88c7594c89ed294263920727df0e08f704ac39ea4b581ce432111752ae7ca761"},"schema_version":"1.0","source":{"id":"2212.08785","kind":"arxiv","version":1}},"canonical_sha256":"67d554592c1ebb2de6cf6195290ea4c9f38ea654bce791d8936a61deae735c3e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"67d554592c1ebb2de6cf6195290ea4c9f38ea654bce791d8936a61deae735c3e","first_computed_at":"2026-07-05T05:26:14.401345Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:26:14.401345Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"RBL4linRHoiBnb0TG8wpz20tI+nUv4BOfwdJZqRJACh38ISf72tnJMOtTPXGh1xvBq5wNgqQtm1H2g1ht1ENDw==","signature_status":"signed_v1","signed_at":"2026-07-05T05:26:14.401700Z","signed_message":"canonical_sha256_bytes"},"source_id":"2212.08785","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ca763712a4ecb428a795b57c50d6e1a2d4b7d960bfb7f055436a2b8ab5934a45","sha256:7181b910b08ed0320e778d54d5593385b1644b65c2e18bd8f114d741df840e31"],"state_sha256":"393338e4485532cdfd84219e00085f5644c7d09441809f80bb8a5c5405bbe4ff"}