{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:4YWVNYVDIB22ZVTZ7OFXB3FCDI","short_pith_number":"pith:4YWVNYVD","schema_version":"1.0","canonical_sha256":"e62d56e2a34075acd679fb8b70eca21a18c490dc2216936f1f5f611e0de76864","source":{"kind":"arxiv","id":"2601.18119","version":2},"attestation_state":"computed","paper":{"title":"Beyond Text-to-SQL: Can LLMs Really Debug Enterprise ETL SQL?","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Jing Ye, Victor Ma, Xing Chen, Yang Gao, Yiwen Duan, Yonghong Yu","submitted_at":"2026-01-26T04:06:35Z","abstract_excerpt":"SQL is central to enterprise data engineering, yet generating fully correct SQL code in a single attempt remains difficult, even for experienced developers and advanced text-to-SQL LLMs, often requiring multiple debugging iterations. We introduce OurBench, the first benchmark for enterprise-level SQL reasoning and debugging. Our benchmark is built on two key innovations: (1) an automated construction workflow that uses reverse engineering to systematically inject realistic bugs into large-scale SQL code, enabling scalable and diverse benchmark generation; and (2) an execution-free evaluation f"},"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":"2601.18119","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2026-01-26T04:06:35Z","cross_cats_sorted":[],"title_canon_sha256":"6d89035b07addc65ec156d3d04528aa6b623cb4b57ce1ed25d053e179849ce54","abstract_canon_sha256":"51589f35884d39bc483c7c24191b426ed767f378862429c6af7b69ec6aaab000"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-27T01:19:56.161068Z","signature_b64":"OK7ol5QFaB9L6EIEww5Baiu73xGeeR/VBTWPIVzZYr1tLuC/0KjjJJAwvRb1DQeZ7iBIlqiDeBpUDUwigmaDAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e62d56e2a34075acd679fb8b70eca21a18c490dc2216936f1f5f611e0de76864","last_reissued_at":"2026-07-27T01:19:56.160067Z","signature_status":"signed_v1","first_computed_at":"2026-07-27T01:19:56.160067Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Beyond Text-to-SQL: Can LLMs Really Debug Enterprise ETL SQL?","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Jing Ye, Victor Ma, Xing Chen, Yang Gao, Yiwen Duan, Yonghong Yu","submitted_at":"2026-01-26T04:06:35Z","abstract_excerpt":"SQL is central to enterprise data engineering, yet generating fully correct SQL code in a single attempt remains difficult, even for experienced developers and advanced text-to-SQL LLMs, often requiring multiple debugging iterations. We introduce OurBench, the first benchmark for enterprise-level SQL reasoning and debugging. Our benchmark is built on two key innovations: (1) an automated construction workflow that uses reverse engineering to systematically inject realistic bugs into large-scale SQL code, enabling scalable and diverse benchmark generation; and (2) an execution-free evaluation f"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2601.18119","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/2601.18119/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":"2601.18119","created_at":"2026-07-27T01:19:56.160518+00:00"},{"alias_kind":"arxiv_version","alias_value":"2601.18119v2","created_at":"2026-07-27T01:19:56.160518+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2601.18119","created_at":"2026-07-27T01:19:56.160518+00:00"},{"alias_kind":"pith_short_12","alias_value":"4YWVNYVDIB22","created_at":"2026-07-27T01:19:56.160518+00:00"},{"alias_kind":"pith_short_16","alias_value":"4YWVNYVDIB22ZVTZ","created_at":"2026-07-27T01:19:56.160518+00:00"},{"alias_kind":"pith_short_8","alias_value":"4YWVNYVD","created_at":"2026-07-27T01:19:56.160518+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4YWVNYVDIB22ZVTZ7OFXB3FCDI","json":"https://pith.science/pith/4YWVNYVDIB22ZVTZ7OFXB3FCDI.json","graph_json":"https://pith.science/api/pith-number/4YWVNYVDIB22ZVTZ7OFXB3FCDI/graph.json","events_json":"https://pith.science/api/pith-number/4YWVNYVDIB22ZVTZ7OFXB3FCDI/events.json","paper":"https://pith.science/paper/4YWVNYVD"},"agent_actions":{"view_html":"https://pith.science/pith/4YWVNYVDIB22ZVTZ7OFXB3FCDI","download_json":"https://pith.science/pith/4YWVNYVDIB22ZVTZ7OFXB3FCDI.json","view_paper":"https://pith.science/paper/4YWVNYVD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2601.18119&json=true","fetch_graph":"https://pith.science/api/pith-number/4YWVNYVDIB22ZVTZ7OFXB3FCDI/graph.json","fetch_events":"https://pith.science/api/pith-number/4YWVNYVDIB22ZVTZ7OFXB3FCDI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4YWVNYVDIB22ZVTZ7OFXB3FCDI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4YWVNYVDIB22ZVTZ7OFXB3FCDI/action/storage_attestation","attest_author":"https://pith.science/pith/4YWVNYVDIB22ZVTZ7OFXB3FCDI/action/author_attestation","sign_citation":"https://pith.science/pith/4YWVNYVDIB22ZVTZ7OFXB3FCDI/action/citation_signature","submit_replication":"https://pith.science/pith/4YWVNYVDIB22ZVTZ7OFXB3FCDI/action/replication_record"}},"created_at":"2026-07-27T01:19:56.160518+00:00","updated_at":"2026-07-27T01:19:56.160518+00:00"}