{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:ZQPF4WIGCAXTESJSC4WRMCBVBV","short_pith_number":"pith:ZQPF4WIG","schema_version":"1.0","canonical_sha256":"cc1e5e5906102f324932172d1608350d769ab8810e224a8a7d4a2f78f19d176f","source":{"kind":"arxiv","id":"2411.00073","version":2},"attestation_state":"computed","paper":{"title":"RSL-SQL: Robust Schema Linking in Text-to-SQL Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.DB"],"primary_cat":"cs.CL","authors_text":"Wei Chen, Xiang Bai, Xiaojin Zhang, Yuanlei Zheng, Zhenbiao Cao, Zhihao Fan","submitted_at":"2024-10-31T16:22:26Z","abstract_excerpt":"Text-to-SQL generation aims to translate natural language questions into SQL statements. In Text-to-SQL based on large language models, schema linking is a widely adopted strategy to streamline the input for LLMs by selecting only relevant schema elements, therefore reducing noise and computational overhead. However, schema linking faces risks that require caution, including the potential omission of necessary elements and disruption of database structural integrity. To address these challenges, we propose a novel framework called RSL-SQL that combines bidirectional schema linking, contextual "},"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":"2411.00073","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-10-31T16:22:26Z","cross_cats_sorted":["cs.AI","cs.DB"],"title_canon_sha256":"8bb6f0b81f9bfcf75359094bdb876df9757567974bf4345d799c069b29d854bb","abstract_canon_sha256":"5f41e7318be5d988e85dd175e5a2ea4cd4154b7aa3cef487cd60a2a84df575c3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:40:44.316832Z","signature_b64":"5L3vN8Erv6LRPS/e+ndUyjDovN3QYtsQyzNjPiiDo1nXmGSzaDU2QJsDl6sAyEwWVLCdtpR9QfyHkDM+x5rbAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cc1e5e5906102f324932172d1608350d769ab8810e224a8a7d4a2f78f19d176f","last_reissued_at":"2026-07-05T09:40:44.316327Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:40:44.316327Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"RSL-SQL: Robust Schema Linking in Text-to-SQL Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.DB"],"primary_cat":"cs.CL","authors_text":"Wei Chen, Xiang Bai, Xiaojin Zhang, Yuanlei Zheng, Zhenbiao Cao, Zhihao Fan","submitted_at":"2024-10-31T16:22:26Z","abstract_excerpt":"Text-to-SQL generation aims to translate natural language questions into SQL statements. In Text-to-SQL based on large language models, schema linking is a widely adopted strategy to streamline the input for LLMs by selecting only relevant schema elements, therefore reducing noise and computational overhead. However, schema linking faces risks that require caution, including the potential omission of necessary elements and disruption of database structural integrity. To address these challenges, we propose a novel framework called RSL-SQL that combines bidirectional schema linking, contextual "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.00073","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2411.00073/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":"2411.00073","created_at":"2026-07-05T09:40:44.316384+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.00073v2","created_at":"2026-07-05T09:40:44.316384+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.00073","created_at":"2026-07-05T09:40:44.316384+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZQPF4WIGCAXT","created_at":"2026-07-05T09:40:44.316384+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZQPF4WIGCAXTESJS","created_at":"2026-07-05T09:40:44.316384+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZQPF4WIG","created_at":"2026-07-05T09:40:44.316384+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":13,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.23537","citing_title":"SQLConductor: Search-to-Policy Learning for Step-wise Text-to-SQL Orchestration","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2606.03363","citing_title":"EntSQL: A Benchmark for Grounding Text-to-SQL in Long-Context Enterprise Knowledge","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2606.28601","citing_title":"Database Context Compression for Text-to-SQL on Real-World Large Databases","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2606.03145","citing_title":"The Case for Text-to-SQL Friendly Logical Database Design","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2606.26613","citing_title":"EcoTable: Cost-effective Table Integration in Data Lakes for Natural Language Queries","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2502.12911","citing_title":"Knapsack Optimization-based Schema Linking for LLM-based Text-to-SQL Generation","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2510.17586","citing_title":"DeepEye-SQL: A Software-Engineering-Inspired Text-to-SQL Framework","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2603.04334","citing_title":"SpotIt+: Verification-based Text-to-SQL Evaluation with Database Constraints","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2605.09295","citing_title":"LEAF-SQL: Level-wise Exploration with Adaptive Fine-graining for Text-to-SQL Skeleton Prediction","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10318","citing_title":"Extending Confidence-Based Text2Cypher with Grammar and Schema Aware Filtering","ref_index":28,"is_internal_anchor":false},{"citing_arxiv_id":"2604.16493","citing_title":"NL2SQLBench: A Modular Benchmarking Framework for LLM-Enabled NL2SQL Solutions","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2605.04066","citing_title":"Adapt to Thrive! Adaptive Power-Mean Policy Optimization for Improved LLM Reasoning","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2605.04065","citing_title":"Free Energy-Driven Reinforcement Learning with Adaptive Advantage Shaping for Unsupervised Reasoning in LLMs","ref_index":7,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZQPF4WIGCAXTESJSC4WRMCBVBV","json":"https://pith.science/pith/ZQPF4WIGCAXTESJSC4WRMCBVBV.json","graph_json":"https://pith.science/api/pith-number/ZQPF4WIGCAXTESJSC4WRMCBVBV/graph.json","events_json":"https://pith.science/api/pith-number/ZQPF4WIGCAXTESJSC4WRMCBVBV/events.json","paper":"https://pith.science/paper/ZQPF4WIG"},"agent_actions":{"view_html":"https://pith.science/pith/ZQPF4WIGCAXTESJSC4WRMCBVBV","download_json":"https://pith.science/pith/ZQPF4WIGCAXTESJSC4WRMCBVBV.json","view_paper":"https://pith.science/paper/ZQPF4WIG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.00073&json=true","fetch_graph":"https://pith.science/api/pith-number/ZQPF4WIGCAXTESJSC4WRMCBVBV/graph.json","fetch_events":"https://pith.science/api/pith-number/ZQPF4WIGCAXTESJSC4WRMCBVBV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZQPF4WIGCAXTESJSC4WRMCBVBV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZQPF4WIGCAXTESJSC4WRMCBVBV/action/storage_attestation","attest_author":"https://pith.science/pith/ZQPF4WIGCAXTESJSC4WRMCBVBV/action/author_attestation","sign_citation":"https://pith.science/pith/ZQPF4WIGCAXTESJSC4WRMCBVBV/action/citation_signature","submit_replication":"https://pith.science/pith/ZQPF4WIGCAXTESJSC4WRMCBVBV/action/replication_record"}},"created_at":"2026-07-05T09:40:44.316384+00:00","updated_at":"2026-07-05T09:40:44.316384+00:00"}