{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:FYOS4OB2JCX4YUBVB4XKYA3KPO","short_pith_number":"pith:FYOS4OB2","schema_version":"1.0","canonical_sha256":"2e1d2e383a48afcc50350f2eac036a7ba3503bf450321d25794cf50db1bf3038","source":{"kind":"arxiv","id":"2404.14453","version":1},"attestation_state":"computed","paper":{"title":"EPI-SQL: Enhancing Text-to-SQL Translation with Error-Prevention Instructions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.DB"],"primary_cat":"cs.CL","authors_text":"Xiping Liu, Zhao Tan","submitted_at":"2024-04-21T03:52:46Z","abstract_excerpt":"The conversion of natural language queries into SQL queries, known as Text-to-SQL, is a critical yet challenging task. This paper introduces EPI-SQL, a novel methodological framework leveraging Large Language Models (LLMs) to enhance the performance of Text-to-SQL tasks. EPI-SQL operates through a four-step process. Initially, the method involves gathering instances from the Spider dataset on which LLMs are prone to failure. These instances are then utilized to generate general error-prevention instructions (EPIs). Subsequently, LLMs craft contextualized EPIs tailored to the specific context o"},"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":"2404.14453","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-04-21T03:52:46Z","cross_cats_sorted":["cs.AI","cs.DB"],"title_canon_sha256":"23b279d12bf1681733d777e63f1250149ca0c32f3e6afc503530f190407614ac","abstract_canon_sha256":"fced594841850baafcb551897dabd1e2a5e62d4e93ed565f89765234a3df4eef"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:11:05.494097Z","signature_b64":"M9xwK8NkqEhhxh0X2EEnI80U461xzf0FU0qRk3WUlfE5r0muLrYbQ6kDrHmDgv7kpZ6STRYuRsIdZx5iIHFKBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2e1d2e383a48afcc50350f2eac036a7ba3503bf450321d25794cf50db1bf3038","last_reissued_at":"2026-07-05T08:11:05.493629Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:11:05.493629Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"EPI-SQL: Enhancing Text-to-SQL Translation with Error-Prevention Instructions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.DB"],"primary_cat":"cs.CL","authors_text":"Xiping Liu, Zhao Tan","submitted_at":"2024-04-21T03:52:46Z","abstract_excerpt":"The conversion of natural language queries into SQL queries, known as Text-to-SQL, is a critical yet challenging task. This paper introduces EPI-SQL, a novel methodological framework leveraging Large Language Models (LLMs) to enhance the performance of Text-to-SQL tasks. EPI-SQL operates through a four-step process. Initially, the method involves gathering instances from the Spider dataset on which LLMs are prone to failure. These instances are then utilized to generate general error-prevention instructions (EPIs). Subsequently, LLMs craft contextualized EPIs tailored to the specific context o"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.14453","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/2404.14453/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":"2404.14453","created_at":"2026-07-05T08:11:05.493688+00:00"},{"alias_kind":"arxiv_version","alias_value":"2404.14453v1","created_at":"2026-07-05T08:11:05.493688+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.14453","created_at":"2026-07-05T08:11:05.493688+00:00"},{"alias_kind":"pith_short_12","alias_value":"FYOS4OB2JCX4","created_at":"2026-07-05T08:11:05.493688+00:00"},{"alias_kind":"pith_short_16","alias_value":"FYOS4OB2JCX4YUBV","created_at":"2026-07-05T08:11:05.493688+00:00"},{"alias_kind":"pith_short_8","alias_value":"FYOS4OB2","created_at":"2026-07-05T08:11:05.493688+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.04066","citing_title":"Adapt to Thrive! Adaptive Power-Mean Policy Optimization for Improved LLM Reasoning","ref_index":197,"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":212,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FYOS4OB2JCX4YUBVB4XKYA3KPO","json":"https://pith.science/pith/FYOS4OB2JCX4YUBVB4XKYA3KPO.json","graph_json":"https://pith.science/api/pith-number/FYOS4OB2JCX4YUBVB4XKYA3KPO/graph.json","events_json":"https://pith.science/api/pith-number/FYOS4OB2JCX4YUBVB4XKYA3KPO/events.json","paper":"https://pith.science/paper/FYOS4OB2"},"agent_actions":{"view_html":"https://pith.science/pith/FYOS4OB2JCX4YUBVB4XKYA3KPO","download_json":"https://pith.science/pith/FYOS4OB2JCX4YUBVB4XKYA3KPO.json","view_paper":"https://pith.science/paper/FYOS4OB2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2404.14453&json=true","fetch_graph":"https://pith.science/api/pith-number/FYOS4OB2JCX4YUBVB4XKYA3KPO/graph.json","fetch_events":"https://pith.science/api/pith-number/FYOS4OB2JCX4YUBVB4XKYA3KPO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FYOS4OB2JCX4YUBVB4XKYA3KPO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FYOS4OB2JCX4YUBVB4XKYA3KPO/action/storage_attestation","attest_author":"https://pith.science/pith/FYOS4OB2JCX4YUBVB4XKYA3KPO/action/author_attestation","sign_citation":"https://pith.science/pith/FYOS4OB2JCX4YUBVB4XKYA3KPO/action/citation_signature","submit_replication":"https://pith.science/pith/FYOS4OB2JCX4YUBVB4XKYA3KPO/action/replication_record"}},"created_at":"2026-07-05T08:11:05.493688+00:00","updated_at":"2026-07-05T08:11:05.493688+00:00"}