{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2606.03363", "kind": "paper", "url": "https://arxiv.org/abs/2606.03363"}], "authors": ["Chengxi Liao", "Tao Xu", "Zulong Chen", "Chuanfei Xu", "Yiyan Wang", "Xinyun Wang", "Yanlong Zhang", "Xiaojun Chen", "Zhibo Yang", "Zeyi Wen"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2606.03363", "source_url": "https://arxiv.org/abs/2606.03363"}, "categories": ["Factuality", "General AI", "Language & Knowledge", "Long Context"], "description": {"en": "EntSQL evaluates text-to-SQL systems on enterprise knowledge grounding, with 1,066 Chinese-English examples across five business domains requiring private business knowledge. Systems generate SQL from questions and schema, with some provided long-form documents."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2606.03363", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2606.03363", "title": "EntSQL"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "institutions": ["The Hong Kong University of Science and Technology (Guangzhou)", "Alibaba Group (China)", "Guangdong Laboratory of Artificial Intelligence and Digital Economy (Shenzhen)"], "institutions_reference": {"basis": "openalex_linked_institutions", "doi": "10.48550/arxiv.2606.03363", "retrieved_at": "2026-11-04", "source_key": "claire-radar:2606.03363", "source_url": "https://openalex.org/W7163433859"}, "key": "claire-radar:2606.03363", "modality": null, "name": "EntSQL", "openness": {"code_license": null, "data_license": null, "evidence": [], "status": "unknown"}, "provenance": {"confidence": "High", "crawl_bundle": "claire_radar_2026-10-14", "crawled_at": "2026-10-14T09:44:51Z", "data_status": "primary-source-indexed", "display_eligible": "unknown", "origin_record_id": "bm_entsql_088384b0", "origin_source": "arxiv", "recognition_confidence": "1.0", "record_sha256": "ef051a41003952c9dd52235d9ae5d4819d3aec57989c1f4c5b7f02d88130b620", "relation": "introduces", "review_state": "unreviewed", "source_url": "https://arxiv.org/abs/2606.03363"}, "publisher": null, "released": "2026-06-02", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2606.03363", "source_url": "https://arxiv.org/abs/2606.03363"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2606-03363", "source": "claire_radar", "source_benchmark_id": "2606.03363", "source_metadata": {"claire_radar": {"adoption30d": null, "aliases": [], "annotation": "Unknown", "applicationDomains": ["General AI"], "area": "Language & Knowledge", "attention": {"asOf": "2026-10-05", "attemptedAt": "2026-10-04T15:31:48.030916Z", "githubRepo": null, "githubScope": null, "githubStars": null, "hfDailySubmittedAt": null, "hfDataset": null, "hfDatasetDownloads": null, "hfDatasetLikes": null, "hfPaperUpvotes": null, "hfPaperUrl": "https://huggingface.co/papers/2606.03363", "observedAt": "2026-10-04T03:02:42.754940Z", "signalStatus": {"githubStars": {"state": "not_applicable"}, "hfDatasetDownloads": {"state": "not_applicable"}, "hfDatasetLikes": {"state": "not_applicable"}, "hfPaperUpvotes": {"checkedAt": "2026-10-04T15:31:48.030916Z", "state": "unavailable"}}, "status": "unavailable"}, "capabilities": ["Factuality"], "confidence": "High", "construction": "Unknown", "constructionDetail": "Unknown — the indexer does not infer construction details without explicit source evidence.", "copyGeneration": {"generatedAt": "2026-08-20T15:22:10.044731Z", "inputHash": "18604bf22b7018a140fdaf137b507c36ec00c009dd6335570dac90be6dc09a21", "model": "deepseek-v4-flash"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "EntSQL evaluates text-to-SQL systems on enterprise knowledge grounding, with 1,066 Chinese-English examples across five business domains requiring private business knowledge. Systems generate SQL from questions and schema, with some provided long-form documents.", "domainCuration": {"method": "rules-v1", "state": "auto"}, "evidence": {"reasonCodes": ["exact coined title identity tied to benchmark evidence", "benchmark release stated in one sentence"], "snippet": "We introduce EntSQL, an enterprise-oriented Text-to-SQL benchmark for evaluating long-context grounding over proprietary business documents."}, "familyId": "bmf_c6be492ed41d", "firstSeenAt": "2026-08-19", "githubIndex": {"candidateCount": 0, "indexedAt": "2026-09-17T04:40:34.111665+00:00", "repositories": [], "status": "not-found"}, "heat": null, "id": "bm_entsql_088384b0", "indexedAt": "2026-08-19T11:05:13.395391Z", "industrySectors": [], "links": {"code": null, "data": null, "hfPaper": "https://huggingface.co/papers/2606.03363", "paper": "https://arxiv.org/abs/2606.03363", "pdf": "https://arxiv.org/pdf/2606.03363", "project": null, "report": "https://arxiv.org/abs/2606.03363"}, "metrics": [], "motivation": "Text-to-SQL enables natural language access to databases, and recent LLMs have substantially advanced its capabilities.", "name": "EntSQL", "oneLine": "EntSQL evaluates text-to-SQL systems on enterprise knowledge grounding, with 1,066 Chinese-English examples across five business domains requiring private business knowledge. Systems generate SQL from questions and schema, with some provided long-form documents.", "paperTitle": "EntSQL: A Benchmark for Grounding Text-to-SQL in Long-Context Enterprise Knowledge", "primaryDomain": "General AI", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://arxiv.org/abs/2606.03363", "source": "arxiv-metadata", "status": "unverified", "venue": null, "verifiedAt": "2026-10-14T01:46:58.058199Z"}, "publications": [], "ranking": {}, "readiness": "Paper only", "recognitionConfidence": 1.0, "relation": "introduces", "releasedAt": "2026-06-02", "source": {"authors": ["Chengxi Liao", "Tao Xu", "Zulong Chen", "Chuanfei Xu", "Yiyan Wang", "Xinyun Wang", "Yanlong Zhang", "Xiaojun Chen", "Zhibo Yang", "Zeyi Wen"], "categories": ["cs.CL"], "id": "2606.03363", "title": "EntSQL: A Benchmark for Grounding Text-to-SQL in Long-Context Enterprise Knowledge", "type": "arxiv", "url": "https://arxiv.org/abs/2606.03363"}, "sourceUpdatedAt": "2026-07-14T11:38:45Z", "topics": ["Long Context"], "venueAttempts": [], "whyItMatters": "Existing text-to-SQL benchmarks overlook enterprise scenarios where SQL generation depends on proprietary business knowledge. EntSQL measures the ability to ground SQL generation in long-context enterprise documents, revealing a significant performance gap in current systems."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
