{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:XX5BUXU7YRPCVJQHP3CZQVSPBX","short_pith_number":"pith:XX5BUXU7","canonical_record":{"source":{"id":"2408.12733","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.AI","submitted_at":"2024-08-22T20:50:48Z","cross_cats_sorted":["cs.CL","cs.DB","cs.LG"],"title_canon_sha256":"4e2c5a2786a951a3827aa8d338101eb262ca7b48ebebd1d3838d491ad88f8591","abstract_canon_sha256":"9b32a287ff38819bfbc1924044e2b95b86dfb5f81de5abe42315a2b9b19f6bcc"},"schema_version":"1.0"},"canonical_sha256":"bdfa1a5e9fc45e2aa6077ec598564f0de0d223df508a291be5a05314d35a5973","source":{"kind":"arxiv","id":"2408.12733","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2408.12733","created_at":"2026-07-05T09:14:55Z"},{"alias_kind":"arxiv_version","alias_value":"2408.12733v2","created_at":"2026-07-05T09:14:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.12733","created_at":"2026-07-05T09:14:55Z"},{"alias_kind":"pith_short_12","alias_value":"XX5BUXU7YRPC","created_at":"2026-07-05T09:14:55Z"},{"alias_kind":"pith_short_16","alias_value":"XX5BUXU7YRPCVJQH","created_at":"2026-07-05T09:14:55Z"},{"alias_kind":"pith_short_8","alias_value":"XX5BUXU7","created_at":"2026-07-05T09:14:55Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:XX5BUXU7YRPCVJQHP3CZQVSPBX","target":"record","payload":{"canonical_record":{"source":{"id":"2408.12733","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.AI","submitted_at":"2024-08-22T20:50:48Z","cross_cats_sorted":["cs.CL","cs.DB","cs.LG"],"title_canon_sha256":"4e2c5a2786a951a3827aa8d338101eb262ca7b48ebebd1d3838d491ad88f8591","abstract_canon_sha256":"9b32a287ff38819bfbc1924044e2b95b86dfb5f81de5abe42315a2b9b19f6bcc"},"schema_version":"1.0"},"canonical_sha256":"bdfa1a5e9fc45e2aa6077ec598564f0de0d223df508a291be5a05314d35a5973","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:14:55.299398Z","signature_b64":"PB3ebP63ncviFfKyQoCnYSqbYswRVOz6/r0yRbqvA8mMWFMgiYZW/3sBF5fD5xbCXglE56HIgO/0ps4W7MbMAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bdfa1a5e9fc45e2aa6077ec598564f0de0d223df508a291be5a05314d35a5973","last_reissued_at":"2026-07-05T09:14:55.298905Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:14:55.298905Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2408.12733","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:14:55Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"LNSjB4KVk6AyA48Mf0kl47MLm/5KjUuSQ8p1sX33W90Jzd2WE59l4KnER19xWaBiN2AUQvHxC1zz3qsBHflhCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T13:05:58.131368Z"},"content_sha256":"c3753bfca2ba1242ad5eb0b8e06b31625468e24d278f150c80c0fdcc57dcde25","schema_version":"1.0","event_id":"sha256:c3753bfca2ba1242ad5eb0b8e06b31625468e24d278f150c80c0fdcc57dcde25"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:XX5BUXU7YRPCVJQHP3CZQVSPBX","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"SQL-GEN: Bridging the Dialect Gap for Text-to-SQL Via Synthetic Data And Model Merging","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.CL","cs.DB","cs.LG"],"primary_cat":"cs.AI","authors_text":"Hailong Li, Lesly Miculicich, Mohammadreza Pourreza, Ruoxi Sun, Sercan O. Arik, Tomas Pfister","submitted_at":"2024-08-22T20:50:48Z","abstract_excerpt":"Recent advances in Text-to-SQL have largely focused on the SQLite dialect, neglecting the diverse landscape of SQL dialects like BigQuery and PostgreSQL. This limitation is due to the diversity in SQL syntaxes and functions, along with the high cost of collecting and curating SQL-specific training data. To address this, we introduce SQL-GEN, a framework for generating high-quality synthetic training data for any SQL dialect, guided by readily available dialect-specific tutorials. SQL-GEN significantly improves cross-dialect Text-to-SQL performance, boosting execution accuracy by up to 20\\% ove"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.12733","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2408.12733/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:14:55Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FJ/6in5LnTtBDiQH/SB4d36gX0AFk6r5ZJB+K0NMX4t7TqkMGRvNF6NDyGo6JJoDJrpAgGMRZRzPZnxVEUMTBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T13:05:58.131873Z"},"content_sha256":"cda60566aa161780b28a02a6962ba71bf2d293c3ac054431867f7a97cd2799c4","schema_version":"1.0","event_id":"sha256:cda60566aa161780b28a02a6962ba71bf2d293c3ac054431867f7a97cd2799c4"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/XX5BUXU7YRPCVJQHP3CZQVSPBX/bundle.json","state_url":"https://pith.science/pith/XX5BUXU7YRPCVJQHP3CZQVSPBX/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/XX5BUXU7YRPCVJQHP3CZQVSPBX/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-09T13:05:58Z","links":{"resolver":"https://pith.science/pith/XX5BUXU7YRPCVJQHP3CZQVSPBX","bundle":"https://pith.science/pith/XX5BUXU7YRPCVJQHP3CZQVSPBX/bundle.json","state":"https://pith.science/pith/XX5BUXU7YRPCVJQHP3CZQVSPBX/state.json","well_known_bundle":"https://pith.science/.well-known/pith/XX5BUXU7YRPCVJQHP3CZQVSPBX/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:XX5BUXU7YRPCVJQHP3CZQVSPBX","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":"9b32a287ff38819bfbc1924044e2b95b86dfb5f81de5abe42315a2b9b19f6bcc","cross_cats_sorted":["cs.CL","cs.DB","cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.AI","submitted_at":"2024-08-22T20:50:48Z","title_canon_sha256":"4e2c5a2786a951a3827aa8d338101eb262ca7b48ebebd1d3838d491ad88f8591"},"schema_version":"1.0","source":{"id":"2408.12733","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2408.12733","created_at":"2026-07-05T09:14:55Z"},{"alias_kind":"arxiv_version","alias_value":"2408.12733v2","created_at":"2026-07-05T09:14:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.12733","created_at":"2026-07-05T09:14:55Z"},{"alias_kind":"pith_short_12","alias_value":"XX5BUXU7YRPC","created_at":"2026-07-05T09:14:55Z"},{"alias_kind":"pith_short_16","alias_value":"XX5BUXU7YRPCVJQH","created_at":"2026-07-05T09:14:55Z"},{"alias_kind":"pith_short_8","alias_value":"XX5BUXU7","created_at":"2026-07-05T09:14:55Z"}],"graph_snapshots":[{"event_id":"sha256:cda60566aa161780b28a02a6962ba71bf2d293c3ac054431867f7a97cd2799c4","target":"graph","created_at":"2026-07-05T09:14:55Z","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/2408.12733/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent advances in Text-to-SQL have largely focused on the SQLite dialect, neglecting the diverse landscape of SQL dialects like BigQuery and PostgreSQL. This limitation is due to the diversity in SQL syntaxes and functions, along with the high cost of collecting and curating SQL-specific training data. To address this, we introduce SQL-GEN, a framework for generating high-quality synthetic training data for any SQL dialect, guided by readily available dialect-specific tutorials. SQL-GEN significantly improves cross-dialect Text-to-SQL performance, boosting execution accuracy by up to 20\\% ove","authors_text":"Hailong Li, Lesly Miculicich, Mohammadreza Pourreza, Ruoxi Sun, Sercan O. Arik, Tomas Pfister","cross_cats":["cs.CL","cs.DB","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.AI","submitted_at":"2024-08-22T20:50:48Z","title":"SQL-GEN: Bridging the Dialect Gap for Text-to-SQL Via Synthetic Data And Model Merging"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.12733","kind":"arxiv","version":2},"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:c3753bfca2ba1242ad5eb0b8e06b31625468e24d278f150c80c0fdcc57dcde25","target":"record","created_at":"2026-07-05T09:14:55Z","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":"9b32a287ff38819bfbc1924044e2b95b86dfb5f81de5abe42315a2b9b19f6bcc","cross_cats_sorted":["cs.CL","cs.DB","cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.AI","submitted_at":"2024-08-22T20:50:48Z","title_canon_sha256":"4e2c5a2786a951a3827aa8d338101eb262ca7b48ebebd1d3838d491ad88f8591"},"schema_version":"1.0","source":{"id":"2408.12733","kind":"arxiv","version":2}},"canonical_sha256":"bdfa1a5e9fc45e2aa6077ec598564f0de0d223df508a291be5a05314d35a5973","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"bdfa1a5e9fc45e2aa6077ec598564f0de0d223df508a291be5a05314d35a5973","first_computed_at":"2026-07-05T09:14:55.298905Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:14:55.298905Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"PB3ebP63ncviFfKyQoCnYSqbYswRVOz6/r0yRbqvA8mMWFMgiYZW/3sBF5fD5xbCXglE56HIgO/0ps4W7MbMAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:14:55.299398Z","signed_message":"canonical_sha256_bytes"},"source_id":"2408.12733","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c3753bfca2ba1242ad5eb0b8e06b31625468e24d278f150c80c0fdcc57dcde25","sha256:cda60566aa161780b28a02a6962ba71bf2d293c3ac054431867f7a97cd2799c4"],"state_sha256":"a906a1f818ae4610e7f89ec51a6cc3fbaedc3094bca20211a918cd60721c83b7"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"De41VrLuTnfl70kuW1OPbnL/eRckIiRzVy/rTBDmByqeV3hV6bN9682WKv70WDy1UCx2JPsVgPY6NJlPQ+2VAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T13:05:58.135117Z","bundle_sha256":"3cb0adea0d4a6b0dd4ca3f6925a187e82069bd4d871a280005cdeaad6a76444b"}}