{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:OLIRKUC6IYEEVTY55VHREYKKFF","short_pith_number":"pith:OLIRKUC6","schema_version":"1.0","canonical_sha256":"72d115505e46084acf1ded4f12614a295d0ed4d3af18454cdec0a96daae0a12f","source":{"kind":"arxiv","id":"2211.06193","version":1},"attestation_state":"computed","paper":{"title":"DocuT5: Seq2seq SQL Generation with Table Documentation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Elena Soare, Iain Mackie, Jeffrey Dalton","submitted_at":"2022-11-11T13:31:55Z","abstract_excerpt":"Current SQL generators based on pre-trained language models struggle to answer complex questions requiring domain context or understanding fine-grained table structure. Humans would deal with these unknowns by reasoning over the documentation of the tables. Based on this hypothesis, we propose DocuT5, which uses off-the-shelf language model architecture and injects knowledge from external `documentation' to improve domain generalization. We perform experiments on the Spider family of datasets that contain complex questions that are cross-domain and multi-table. Specifically, we develop a new t"},"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":"2211.06193","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-11-11T13:31:55Z","cross_cats_sorted":[],"title_canon_sha256":"2d65881a06f1797eea5094eeddab998bcb46fa296accafedf91356aae92cc283","abstract_canon_sha256":"e74224e9ce58a537f5398354a816b412440df8687f7805f535d2133df4dae78f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:15:18.102870Z","signature_b64":"VPFsJc8BEr6rRqT/wyfXnrOks0GIWbFhx+vzjGiylbNoIrRpUqDAzzXpvkT/voIxumX+ITVTZ7NEIjYC+FSaAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"72d115505e46084acf1ded4f12614a295d0ed4d3af18454cdec0a96daae0a12f","last_reissued_at":"2026-07-05T05:15:18.102468Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:15:18.102468Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DocuT5: Seq2seq SQL Generation with Table Documentation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Elena Soare, Iain Mackie, Jeffrey Dalton","submitted_at":"2022-11-11T13:31:55Z","abstract_excerpt":"Current SQL generators based on pre-trained language models struggle to answer complex questions requiring domain context or understanding fine-grained table structure. Humans would deal with these unknowns by reasoning over the documentation of the tables. Based on this hypothesis, we propose DocuT5, which uses off-the-shelf language model architecture and injects knowledge from external `documentation' to improve domain generalization. We perform experiments on the Spider family of datasets that contain complex questions that are cross-domain and multi-table. Specifically, we develop a new t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.06193","kind":"arxiv","version":1},"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/2211.06193/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":"2211.06193","created_at":"2026-07-05T05:15:18.102519+00:00"},{"alias_kind":"arxiv_version","alias_value":"2211.06193v1","created_at":"2026-07-05T05:15:18.102519+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.06193","created_at":"2026-07-05T05:15:18.102519+00:00"},{"alias_kind":"pith_short_12","alias_value":"OLIRKUC6IYEE","created_at":"2026-07-05T05:15:18.102519+00:00"},{"alias_kind":"pith_short_16","alias_value":"OLIRKUC6IYEEVTY5","created_at":"2026-07-05T05:15:18.102519+00:00"},{"alias_kind":"pith_short_8","alias_value":"OLIRKUC6","created_at":"2026-07-05T05:15:18.102519+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OLIRKUC6IYEEVTY55VHREYKKFF","json":"https://pith.science/pith/OLIRKUC6IYEEVTY55VHREYKKFF.json","graph_json":"https://pith.science/api/pith-number/OLIRKUC6IYEEVTY55VHREYKKFF/graph.json","events_json":"https://pith.science/api/pith-number/OLIRKUC6IYEEVTY55VHREYKKFF/events.json","paper":"https://pith.science/paper/OLIRKUC6"},"agent_actions":{"view_html":"https://pith.science/pith/OLIRKUC6IYEEVTY55VHREYKKFF","download_json":"https://pith.science/pith/OLIRKUC6IYEEVTY55VHREYKKFF.json","view_paper":"https://pith.science/paper/OLIRKUC6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2211.06193&json=true","fetch_graph":"https://pith.science/api/pith-number/OLIRKUC6IYEEVTY55VHREYKKFF/graph.json","fetch_events":"https://pith.science/api/pith-number/OLIRKUC6IYEEVTY55VHREYKKFF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OLIRKUC6IYEEVTY55VHREYKKFF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OLIRKUC6IYEEVTY55VHREYKKFF/action/storage_attestation","attest_author":"https://pith.science/pith/OLIRKUC6IYEEVTY55VHREYKKFF/action/author_attestation","sign_citation":"https://pith.science/pith/OLIRKUC6IYEEVTY55VHREYKKFF/action/citation_signature","submit_replication":"https://pith.science/pith/OLIRKUC6IYEEVTY55VHREYKKFF/action/replication_record"}},"created_at":"2026-07-05T05:15:18.102519+00:00","updated_at":"2026-07-05T05:15:18.102519+00:00"}