{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:S6AMITXZ65TEXNRPWKGJNLNL5J","short_pith_number":"pith:S6AMITXZ","schema_version":"1.0","canonical_sha256":"9780c44ef9f7664bb62fb28c96adabea5e6f087877c2297370affea3b2e9ea77","source":{"kind":"arxiv","id":"1905.08205","version":2},"attestation_state":"computed","paper":{"title":"Towards Complex Text-to-SQL in Cross-Domain Database with Intermediate Representation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Dongmei Zhang, Jian-Guang Lou, Jiaqi Guo, Ting Liu, Yan Gao, Yan Xiao, Zecheng Zhan","submitted_at":"2019-05-20T16:44:00Z","abstract_excerpt":"We present a neural approach called IRNet for complex and cross-domain Text-to-SQL. IRNet aims to address two challenges: 1) the mismatch between intents expressed in natural language (NL) and the implementation details in SQL; 2) the challenge in predicting columns caused by the large number of out-of-domain words. Instead of end-to-end synthesizing a SQL query, IRNet decomposes the synthesis process into three phases. In the first phase, IRNet performs a schema linking over a question and a database schema. Then, IRNet adopts a grammar-based neural model to synthesize a SemQL query which is "},"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":"1905.08205","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-05-20T16:44:00Z","cross_cats_sorted":[],"title_canon_sha256":"6bfad0e805a26eec26486ea01160d8b6bc84627dd3b4225958ebd7543e596cfe","abstract_canon_sha256":"de4364fc53f0b1143352a31e6ee2a038e49ecd412b2e435615ee5240ff608c6b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:44:47.208420Z","signature_b64":"3/7j632pRXbQYwQjqSrapewlV3jcBY1JuXKbrEiYb6KMGPnPOWII5hozLNIX9X3qnEvF3vuslTeLvOIgvQIVCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9780c44ef9f7664bb62fb28c96adabea5e6f087877c2297370affea3b2e9ea77","last_reissued_at":"2026-05-17T23:44:47.207731Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:44:47.207731Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Towards Complex Text-to-SQL in Cross-Domain Database with Intermediate Representation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Dongmei Zhang, Jian-Guang Lou, Jiaqi Guo, Ting Liu, Yan Gao, Yan Xiao, Zecheng Zhan","submitted_at":"2019-05-20T16:44:00Z","abstract_excerpt":"We present a neural approach called IRNet for complex and cross-domain Text-to-SQL. IRNet aims to address two challenges: 1) the mismatch between intents expressed in natural language (NL) and the implementation details in SQL; 2) the challenge in predicting columns caused by the large number of out-of-domain words. Instead of end-to-end synthesizing a SQL query, IRNet decomposes the synthesis process into three phases. In the first phase, IRNet performs a schema linking over a question and a database schema. Then, IRNet adopts a grammar-based neural model to synthesize a SemQL query which is "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.08205","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":""},"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":"1905.08205","created_at":"2026-05-17T23:44:47.207831+00:00"},{"alias_kind":"arxiv_version","alias_value":"1905.08205v2","created_at":"2026-05-17T23:44:47.207831+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.08205","created_at":"2026-05-17T23:44:47.207831+00:00"},{"alias_kind":"pith_short_12","alias_value":"S6AMITXZ65TE","created_at":"2026-05-18T12:33:27.125529+00:00"},{"alias_kind":"pith_short_16","alias_value":"S6AMITXZ65TEXNRP","created_at":"2026-05-18T12:33:27.125529+00:00"},{"alias_kind":"pith_short_8","alias_value":"S6AMITXZ","created_at":"2026-05-18T12:33:27.125529+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2405.16755","citing_title":"CHESS: Contextual Harnessing for Efficient SQL Synthesis","ref_index":56,"is_internal_anchor":true},{"citing_arxiv_id":"2604.28049","citing_title":"Agent-Agnostic Evaluation of SQL Accuracy in Production Text-to-SQL Systems","ref_index":11,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/S6AMITXZ65TEXNRPWKGJNLNL5J","json":"https://pith.science/pith/S6AMITXZ65TEXNRPWKGJNLNL5J.json","graph_json":"https://pith.science/api/pith-number/S6AMITXZ65TEXNRPWKGJNLNL5J/graph.json","events_json":"https://pith.science/api/pith-number/S6AMITXZ65TEXNRPWKGJNLNL5J/events.json","paper":"https://pith.science/paper/S6AMITXZ"},"agent_actions":{"view_html":"https://pith.science/pith/S6AMITXZ65TEXNRPWKGJNLNL5J","download_json":"https://pith.science/pith/S6AMITXZ65TEXNRPWKGJNLNL5J.json","view_paper":"https://pith.science/paper/S6AMITXZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1905.08205&json=true","fetch_graph":"https://pith.science/api/pith-number/S6AMITXZ65TEXNRPWKGJNLNL5J/graph.json","fetch_events":"https://pith.science/api/pith-number/S6AMITXZ65TEXNRPWKGJNLNL5J/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/S6AMITXZ65TEXNRPWKGJNLNL5J/action/timestamp_anchor","attest_storage":"https://pith.science/pith/S6AMITXZ65TEXNRPWKGJNLNL5J/action/storage_attestation","attest_author":"https://pith.science/pith/S6AMITXZ65TEXNRPWKGJNLNL5J/action/author_attestation","sign_citation":"https://pith.science/pith/S6AMITXZ65TEXNRPWKGJNLNL5J/action/citation_signature","submit_replication":"https://pith.science/pith/S6AMITXZ65TEXNRPWKGJNLNL5J/action/replication_record"}},"created_at":"2026-05-17T23:44:47.207831+00:00","updated_at":"2026-05-17T23:44:47.207831+00:00"}