{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:WP7OO6NUOBJWI6QHJBB2ZU2CVL","short_pith_number":"pith:WP7OO6NU","schema_version":"1.0","canonical_sha256":"b3fee779b47053647a074843acd342aafec64ddbc82f5e82880bda2b5b337217","source":{"kind":"arxiv","id":"1905.13326","version":1},"attestation_state":"computed","paper":{"title":"Grammar-based Neural Text-to-SQL Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Ben Bogin, Jonathan Berant, Kevin Lin, Mark Neumann, Matt Gardner","submitted_at":"2019-05-30T21:43:57Z","abstract_excerpt":"The sequence-to-sequence paradigm employed by neural text-to-SQL models typically performs token-level decoding and does not consider generating SQL hierarchically from a grammar. Grammar-based decoding has shown significant improvements for other semantic parsing tasks, but SQL and other general programming languages have complexities not present in logical formalisms that make writing hierarchical grammars difficult. We introduce techniques to handle these complexities, showing how to construct a schema-dependent grammar with minimal over-generation. We analyze these techniques on ATIS and S"},"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":"1905.13326","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-05-30T21:43:57Z","cross_cats_sorted":[],"title_canon_sha256":"f02326be0ae7483cbbe4904302279ffc3b72421f6627cb0f243a646f6b858737","abstract_canon_sha256":"29236d77c57ca3aa5d5d9a3cefa120b2ee0894866911507b080d4a8a4095ad81"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:44:35.288151Z","signature_b64":"E5ygMU83YJNipKqW0RY7iJNqp97YgKpmFgHnHNZIBagOlD764sD6UlJfYL068m33ADSiomcctaEqfNkBu9OTCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b3fee779b47053647a074843acd342aafec64ddbc82f5e82880bda2b5b337217","last_reissued_at":"2026-05-17T23:44:35.287713Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:44:35.287713Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Grammar-based Neural Text-to-SQL Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Ben Bogin, Jonathan Berant, Kevin Lin, Mark Neumann, Matt Gardner","submitted_at":"2019-05-30T21:43:57Z","abstract_excerpt":"The sequence-to-sequence paradigm employed by neural text-to-SQL models typically performs token-level decoding and does not consider generating SQL hierarchically from a grammar. Grammar-based decoding has shown significant improvements for other semantic parsing tasks, but SQL and other general programming languages have complexities not present in logical formalisms that make writing hierarchical grammars difficult. We introduce techniques to handle these complexities, showing how to construct a schema-dependent grammar with minimal over-generation. We analyze these techniques on ATIS and S"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.13326","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":""},"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":"1905.13326","created_at":"2026-05-17T23:44:35.287775+00:00"},{"alias_kind":"arxiv_version","alias_value":"1905.13326v1","created_at":"2026-05-17T23:44:35.287775+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.13326","created_at":"2026-05-17T23:44:35.287775+00:00"},{"alias_kind":"pith_short_12","alias_value":"WP7OO6NUOBJW","created_at":"2026-05-18T12:33:30.264802+00:00"},{"alias_kind":"pith_short_16","alias_value":"WP7OO6NUOBJWI6QH","created_at":"2026-05-18T12:33:30.264802+00:00"},{"alias_kind":"pith_short_8","alias_value":"WP7OO6NU","created_at":"2026-05-18T12:33:30.264802+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":2,"sample":[{"citing_arxiv_id":"2401.05459","citing_title":"Personal LLM Agents: Insights and Survey about the Capability, Efficiency and Security","ref_index":219,"is_internal_anchor":true},{"citing_arxiv_id":"2603.23375","citing_title":"Natural Language Interfaces for Spatial and Temporal Databases: A Comprehensive Overview of Methods, Taxonomy, and Future Directions","ref_index":110,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WP7OO6NUOBJWI6QHJBB2ZU2CVL","json":"https://pith.science/pith/WP7OO6NUOBJWI6QHJBB2ZU2CVL.json","graph_json":"https://pith.science/api/pith-number/WP7OO6NUOBJWI6QHJBB2ZU2CVL/graph.json","events_json":"https://pith.science/api/pith-number/WP7OO6NUOBJWI6QHJBB2ZU2CVL/events.json","paper":"https://pith.science/paper/WP7OO6NU"},"agent_actions":{"view_html":"https://pith.science/pith/WP7OO6NUOBJWI6QHJBB2ZU2CVL","download_json":"https://pith.science/pith/WP7OO6NUOBJWI6QHJBB2ZU2CVL.json","view_paper":"https://pith.science/paper/WP7OO6NU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1905.13326&json=true","fetch_graph":"https://pith.science/api/pith-number/WP7OO6NUOBJWI6QHJBB2ZU2CVL/graph.json","fetch_events":"https://pith.science/api/pith-number/WP7OO6NUOBJWI6QHJBB2ZU2CVL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WP7OO6NUOBJWI6QHJBB2ZU2CVL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WP7OO6NUOBJWI6QHJBB2ZU2CVL/action/storage_attestation","attest_author":"https://pith.science/pith/WP7OO6NUOBJWI6QHJBB2ZU2CVL/action/author_attestation","sign_citation":"https://pith.science/pith/WP7OO6NUOBJWI6QHJBB2ZU2CVL/action/citation_signature","submit_replication":"https://pith.science/pith/WP7OO6NUOBJWI6QHJBB2ZU2CVL/action/replication_record"}},"created_at":"2026-05-17T23:44:35.287775+00:00","updated_at":"2026-05-17T23:44:35.287775+00:00"}