{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:NDES7YUIGSQJNQ3GDBREFPDEJZ","short_pith_number":"pith:NDES7YUI","schema_version":"1.0","canonical_sha256":"68c92fe28834a096c366186242bc644e6605424f9cb91513978c324985a4baee","source":{"kind":"arxiv","id":"2310.18376","version":4},"attestation_state":"computed","paper":{"title":"SQLformer: Deep Auto-Regressive Query Graph Generation for Text-to-SQL Translation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Adri\\'an Bazaga, Gos Micklem, Pietro Li\\`o","submitted_at":"2023-10-27T00:13:59Z","abstract_excerpt":"In recent years, the task of text-to-SQL translation, which converts natural language questions into executable SQL queries, has gained significant attention for its potential to democratize data access. Despite its promise, challenges such as adapting to unseen databases and aligning natural language with SQL syntax have hindered widespread adoption. To overcome these issues, we introduce SQLformer, a novel Transformer architecture specifically crafted to perform text-to-SQL translation tasks. Our model predicts SQL queries as abstract syntax trees (ASTs) in an autoregressive way, incorporati"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2310.18376","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-10-27T00:13:59Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"243d1f4e5a0bed0b53643c654fa5c4d9adacbe3d218360e994e72dbfaad8d055","abstract_canon_sha256":"fdc191282d1e444aa9efd9cc1403c4631a4773984c675da4fc03e821e31c07d8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:23:13.156283Z","signature_b64":"MMYXFvrhKTVQS3/7SzLkJXACd+piQnNGcWjeaJ37v/RV45hAFys+tfZHhKMRjlqUP7tpo/Cyj/1PBidF3Pr7Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"68c92fe28834a096c366186242bc644e6605424f9cb91513978c324985a4baee","last_reissued_at":"2026-07-05T08:23:13.155795Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:23:13.155795Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SQLformer: Deep Auto-Regressive Query Graph Generation for Text-to-SQL Translation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Adri\\'an Bazaga, Gos Micklem, Pietro Li\\`o","submitted_at":"2023-10-27T00:13:59Z","abstract_excerpt":"In recent years, the task of text-to-SQL translation, which converts natural language questions into executable SQL queries, has gained significant attention for its potential to democratize data access. Despite its promise, challenges such as adapting to unseen databases and aligning natural language with SQL syntax have hindered widespread adoption. To overcome these issues, we introduce SQLformer, a novel Transformer architecture specifically crafted to perform text-to-SQL translation tasks. Our model predicts SQL queries as abstract syntax trees (ASTs) in an autoregressive way, incorporati"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.18376","kind":"arxiv","version":4},"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/2310.18376/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2310.18376","created_at":"2026-07-05T08:23:13.155856+00:00"},{"alias_kind":"arxiv_version","alias_value":"2310.18376v4","created_at":"2026-07-05T08:23:13.155856+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.18376","created_at":"2026-07-05T08:23:13.155856+00:00"},{"alias_kind":"pith_short_12","alias_value":"NDES7YUIGSQJ","created_at":"2026-07-05T08:23:13.155856+00:00"},{"alias_kind":"pith_short_16","alias_value":"NDES7YUIGSQJNQ3G","created_at":"2026-07-05T08:23:13.155856+00:00"},{"alias_kind":"pith_short_8","alias_value":"NDES7YUI","created_at":"2026-07-05T08:23:13.155856+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.19718","citing_title":"Text2Insight: Transform natural language text into insights seamlessly using multi-model architecture","ref_index":2,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NDES7YUIGSQJNQ3GDBREFPDEJZ","json":"https://pith.science/pith/NDES7YUIGSQJNQ3GDBREFPDEJZ.json","graph_json":"https://pith.science/api/pith-number/NDES7YUIGSQJNQ3GDBREFPDEJZ/graph.json","events_json":"https://pith.science/api/pith-number/NDES7YUIGSQJNQ3GDBREFPDEJZ/events.json","paper":"https://pith.science/paper/NDES7YUI"},"agent_actions":{"view_html":"https://pith.science/pith/NDES7YUIGSQJNQ3GDBREFPDEJZ","download_json":"https://pith.science/pith/NDES7YUIGSQJNQ3GDBREFPDEJZ.json","view_paper":"https://pith.science/paper/NDES7YUI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2310.18376&json=true","fetch_graph":"https://pith.science/api/pith-number/NDES7YUIGSQJNQ3GDBREFPDEJZ/graph.json","fetch_events":"https://pith.science/api/pith-number/NDES7YUIGSQJNQ3GDBREFPDEJZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NDES7YUIGSQJNQ3GDBREFPDEJZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NDES7YUIGSQJNQ3GDBREFPDEJZ/action/storage_attestation","attest_author":"https://pith.science/pith/NDES7YUIGSQJNQ3GDBREFPDEJZ/action/author_attestation","sign_citation":"https://pith.science/pith/NDES7YUIGSQJNQ3GDBREFPDEJZ/action/citation_signature","submit_replication":"https://pith.science/pith/NDES7YUIGSQJNQ3GDBREFPDEJZ/action/replication_record"}},"created_at":"2026-07-05T08:23:13.155856+00:00","updated_at":"2026-07-05T08:23:13.155856+00:00"}