{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:5EKVCAJJJJ4TOH42PYBTO4NX7N","short_pith_number":"pith:5EKVCAJJ","schema_version":"1.0","canonical_sha256":"e9155101294a79371f9a7e033771b7fb65ffcd938648eb15812faf8ea91179f5","source":{"kind":"arxiv","id":"2012.10074","version":1},"attestation_state":"computed","paper":{"title":"Mention Extraction and Linking for SQL Query Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Jianping Shen, Jianqiang Ma, Shuai Pang, Yang Zhang, Zeyu Yan","submitted_at":"2020-12-18T06:51:23Z","abstract_excerpt":"On the WikiSQL benchmark, state-of-the-art text-to-SQL systems typically take a slot-filling approach by building several dedicated models for each type of slots. Such modularized systems are not only complex butalso of limited capacity for capturing inter-dependencies among SQL clauses. To solve these problems, this paper proposes a novel extraction-linking approach, where a unified extractor recognizes all types of slot mentions appearing in the question sentence before a linker maps the recognized columns to the table schema to generate executable SQL queries. Trained with automatically gen"},"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":"2012.10074","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2020-12-18T06:51:23Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"84128dea4a6dd6597e9f7e471fd68db6f58b6dc5b7b74ddcdd79543416027070","abstract_canon_sha256":"629656a8aabe9da458c9db593348076feff60fac2de0eb75c6fbc185b44dd72b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:00:35.056091Z","signature_b64":"fO88OUB8ORGU8ksZz8h98jjTo7KVsqM6I+hWl5hDCfE49HrKDt64cm3mtCQQEdiwf7PdxVFrvy3+TYnel8DrBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e9155101294a79371f9a7e033771b7fb65ffcd938648eb15812faf8ea91179f5","last_reissued_at":"2026-07-05T02:00:35.055605Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:00:35.055605Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Mention Extraction and Linking for SQL Query Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Jianping Shen, Jianqiang Ma, Shuai Pang, Yang Zhang, Zeyu Yan","submitted_at":"2020-12-18T06:51:23Z","abstract_excerpt":"On the WikiSQL benchmark, state-of-the-art text-to-SQL systems typically take a slot-filling approach by building several dedicated models for each type of slots. Such modularized systems are not only complex butalso of limited capacity for capturing inter-dependencies among SQL clauses. To solve these problems, this paper proposes a novel extraction-linking approach, where a unified extractor recognizes all types of slot mentions appearing in the question sentence before a linker maps the recognized columns to the table schema to generate executable SQL queries. Trained with automatically gen"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2012.10074","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/2012.10074/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":"2012.10074","created_at":"2026-07-05T02:00:35.055667+00:00"},{"alias_kind":"arxiv_version","alias_value":"2012.10074v1","created_at":"2026-07-05T02:00:35.055667+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2012.10074","created_at":"2026-07-05T02:00:35.055667+00:00"},{"alias_kind":"pith_short_12","alias_value":"5EKVCAJJJJ4T","created_at":"2026-07-05T02:00:35.055667+00:00"},{"alias_kind":"pith_short_16","alias_value":"5EKVCAJJJJ4TOH42","created_at":"2026-07-05T02:00:35.055667+00:00"},{"alias_kind":"pith_short_8","alias_value":"5EKVCAJJ","created_at":"2026-07-05T02:00:35.055667+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.00639","citing_title":"Needle: A Generative AI-Powered Multi-modal Database for Answering Complex Natural Language Queries","ref_index":41,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5EKVCAJJJJ4TOH42PYBTO4NX7N","json":"https://pith.science/pith/5EKVCAJJJJ4TOH42PYBTO4NX7N.json","graph_json":"https://pith.science/api/pith-number/5EKVCAJJJJ4TOH42PYBTO4NX7N/graph.json","events_json":"https://pith.science/api/pith-number/5EKVCAJJJJ4TOH42PYBTO4NX7N/events.json","paper":"https://pith.science/paper/5EKVCAJJ"},"agent_actions":{"view_html":"https://pith.science/pith/5EKVCAJJJJ4TOH42PYBTO4NX7N","download_json":"https://pith.science/pith/5EKVCAJJJJ4TOH42PYBTO4NX7N.json","view_paper":"https://pith.science/paper/5EKVCAJJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2012.10074&json=true","fetch_graph":"https://pith.science/api/pith-number/5EKVCAJJJJ4TOH42PYBTO4NX7N/graph.json","fetch_events":"https://pith.science/api/pith-number/5EKVCAJJJJ4TOH42PYBTO4NX7N/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5EKVCAJJJJ4TOH42PYBTO4NX7N/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5EKVCAJJJJ4TOH42PYBTO4NX7N/action/storage_attestation","attest_author":"https://pith.science/pith/5EKVCAJJJJ4TOH42PYBTO4NX7N/action/author_attestation","sign_citation":"https://pith.science/pith/5EKVCAJJJJ4TOH42PYBTO4NX7N/action/citation_signature","submit_replication":"https://pith.science/pith/5EKVCAJJJJ4TOH42PYBTO4NX7N/action/replication_record"}},"created_at":"2026-07-05T02:00:35.055667+00:00","updated_at":"2026-07-05T02:00:35.055667+00:00"}