{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:TBZ5APQJTS7AHIKDU4N7TAHWRN","short_pith_number":"pith:TBZ5APQJ","schema_version":"1.0","canonical_sha256":"9873d03e099cbe03a143a71bf980f68b6cfa67e8c4ddd99f0a7d6be4071c153f","source":{"kind":"arxiv","id":"2012.10309","version":1},"attestation_state":"computed","paper":{"title":"Learning Contextual Representations for Semantic Parsing with Generation-Augmented Pre-Training","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Alexander Hanbo Li, Bing Xiang, Cicero Nogueira dos Santos, Henghui Zhu, Jun Wang, Patrick Ng, Peng Shi, Zhiguo Wang","submitted_at":"2020-12-18T15:53:50Z","abstract_excerpt":"Most recently, there has been significant interest in learning contextual representations for various NLP tasks, by leveraging large scale text corpora to train large neural language models with self-supervised learning objectives, such as Masked Language Model (MLM). However, based on a pilot study, we observe three issues of existing general-purpose language models when they are applied to text-to-SQL semantic parsers: fail to detect column mentions in the utterances, fail to infer column mentions from cell values, and fail to compose complex SQL queries. To mitigate these issues, we present"},"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":"2012.10309","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2020-12-18T15:53:50Z","cross_cats_sorted":[],"title_canon_sha256":"7fc62352b2d6c20b01ce0020d07584b19e357e2b28d560e8a2cbace27375830b","abstract_canon_sha256":"5fa11a05fa060a69647380c9ff843af553af8a9636c3fedf8cc133f3d0b65bd0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:00:37.667046Z","signature_b64":"Zz/8E7tijzNbSx0WmgDuonfHHGfItUNHL8V6MQ8k7gvT+cM3PLNpQbjmBK40QO3y/Tpi5NaXTc1n6BJne/V8Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9873d03e099cbe03a143a71bf980f68b6cfa67e8c4ddd99f0a7d6be4071c153f","last_reissued_at":"2026-07-05T02:00:37.666671Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:00:37.666671Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning Contextual Representations for Semantic Parsing with Generation-Augmented Pre-Training","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Alexander Hanbo Li, Bing Xiang, Cicero Nogueira dos Santos, Henghui Zhu, Jun Wang, Patrick Ng, Peng Shi, Zhiguo Wang","submitted_at":"2020-12-18T15:53:50Z","abstract_excerpt":"Most recently, there has been significant interest in learning contextual representations for various NLP tasks, by leveraging large scale text corpora to train large neural language models with self-supervised learning objectives, such as Masked Language Model (MLM). However, based on a pilot study, we observe three issues of existing general-purpose language models when they are applied to text-to-SQL semantic parsers: fail to detect column mentions in the utterances, fail to infer column mentions from cell values, and fail to compose complex SQL queries. To mitigate these issues, we present"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2012.10309","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/2012.10309/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":"2012.10309","created_at":"2026-07-05T02:00:37.666738+00:00"},{"alias_kind":"arxiv_version","alias_value":"2012.10309v1","created_at":"2026-07-05T02:00:37.666738+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2012.10309","created_at":"2026-07-05T02:00:37.666738+00:00"},{"alias_kind":"pith_short_12","alias_value":"TBZ5APQJTS7A","created_at":"2026-07-05T02:00:37.666738+00:00"},{"alias_kind":"pith_short_16","alias_value":"TBZ5APQJTS7AHIKD","created_at":"2026-07-05T02:00:37.666738+00:00"},{"alias_kind":"pith_short_8","alias_value":"TBZ5APQJ","created_at":"2026-07-05T02:00:37.666738+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/TBZ5APQJTS7AHIKDU4N7TAHWRN","json":"https://pith.science/pith/TBZ5APQJTS7AHIKDU4N7TAHWRN.json","graph_json":"https://pith.science/api/pith-number/TBZ5APQJTS7AHIKDU4N7TAHWRN/graph.json","events_json":"https://pith.science/api/pith-number/TBZ5APQJTS7AHIKDU4N7TAHWRN/events.json","paper":"https://pith.science/paper/TBZ5APQJ"},"agent_actions":{"view_html":"https://pith.science/pith/TBZ5APQJTS7AHIKDU4N7TAHWRN","download_json":"https://pith.science/pith/TBZ5APQJTS7AHIKDU4N7TAHWRN.json","view_paper":"https://pith.science/paper/TBZ5APQJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2012.10309&json=true","fetch_graph":"https://pith.science/api/pith-number/TBZ5APQJTS7AHIKDU4N7TAHWRN/graph.json","fetch_events":"https://pith.science/api/pith-number/TBZ5APQJTS7AHIKDU4N7TAHWRN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TBZ5APQJTS7AHIKDU4N7TAHWRN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TBZ5APQJTS7AHIKDU4N7TAHWRN/action/storage_attestation","attest_author":"https://pith.science/pith/TBZ5APQJTS7AHIKDU4N7TAHWRN/action/author_attestation","sign_citation":"https://pith.science/pith/TBZ5APQJTS7AHIKDU4N7TAHWRN/action/citation_signature","submit_replication":"https://pith.science/pith/TBZ5APQJTS7AHIKDU4N7TAHWRN/action/replication_record"}},"created_at":"2026-07-05T02:00:37.666738+00:00","updated_at":"2026-07-05T02:00:37.666738+00:00"}