{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:F5TUBOCQ4VMRUSYI46I3H33TEV","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":"cb25881355a02041834b0b9deb3379fc0b692f663628c8b4f9dfd6491068d7c0","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-08-06T15:40:32Z","title_canon_sha256":"fb93f07c07f90f2658c87d314e658fd737ba591fc8a14aae2bd27a86b016e529"},"schema_version":"1.0","source":{"id":"2408.03256","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2408.03256","created_at":"2026-07-05T08:52:47Z"},{"alias_kind":"arxiv_version","alias_value":"2408.03256v1","created_at":"2026-07-05T08:52:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.03256","created_at":"2026-07-05T08:52:47Z"},{"alias_kind":"pith_short_12","alias_value":"F5TUBOCQ4VMR","created_at":"2026-07-05T08:52:47Z"},{"alias_kind":"pith_short_16","alias_value":"F5TUBOCQ4VMRUSYI","created_at":"2026-07-05T08:52:47Z"},{"alias_kind":"pith_short_8","alias_value":"F5TUBOCQ","created_at":"2026-07-05T08:52:47Z"}],"graph_snapshots":[{"event_id":"sha256:90971ddda32ebdd2648200adddd38d15f0c69deafe45d1f2b6ceaf08838ca61a","target":"graph","created_at":"2026-07-05T08:52:47Z","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/2408.03256/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The capability gap between open-source and closed-source large language models (LLMs) remains a challenge in text-to-SQL tasks. In this paper, we introduce a synthetic data approach that combines data produced by larger, more powerful models (strong models) with error information data generated by smaller, not well-aligned models (weak models). The method not only enhances the domain generalization of text-to-SQL models but also explores the potential of error data supervision through preference learning. Furthermore, we employ the synthetic data approach for instruction tuning on open-source ","authors_text":"Binyuan Hui, Chang Zhou, Jian Yang, Jiaxi Yang, Junyang Lin, Min Yang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-08-06T15:40:32Z","title":"Synthesizing Text-to-SQL Data from Weak and Strong LLMs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.03256","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":"sha256:9207aa46fedd9b1b9ce104c756c1c5c6cf01244f3ae5a6dbb3b88d41fec38ecc","target":"record","created_at":"2026-07-05T08:52:47Z","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":"cb25881355a02041834b0b9deb3379fc0b692f663628c8b4f9dfd6491068d7c0","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-08-06T15:40:32Z","title_canon_sha256":"fb93f07c07f90f2658c87d314e658fd737ba591fc8a14aae2bd27a86b016e529"},"schema_version":"1.0","source":{"id":"2408.03256","kind":"arxiv","version":1}},"canonical_sha256":"2f6740b850e5591a4b08e791b3ef7325503f7aff3088718dc3fc136aa7664f8d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2f6740b850e5591a4b08e791b3ef7325503f7aff3088718dc3fc136aa7664f8d","first_computed_at":"2026-07-05T08:52:47.935406Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:52:47.935406Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"L0sLU6djIHWjgqLkIWC11VaNV+IWabp1VBtceRZPyOtMAt6nwPhO0CaG4tfVbAICN3Z753y+kVGVrAzzjCJ3Ag==","signature_status":"signed_v1","signed_at":"2026-07-05T08:52:47.936606Z","signed_message":"canonical_sha256_bytes"},"source_id":"2408.03256","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9207aa46fedd9b1b9ce104c756c1c5c6cf01244f3ae5a6dbb3b88d41fec38ecc","sha256:90971ddda32ebdd2648200adddd38d15f0c69deafe45d1f2b6ceaf08838ca61a"],"state_sha256":"4fc7556788ff2b577c3e64a1338997035b0b5255d8dcf39bc84a56158ea77ea3"}