{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2607.03926", "kind": "paper", "url": "https://arxiv.org/abs/2607.03926"}], "authors": ["Jialin Zhang", "Fenghao Dong", "Yajie Zhou", "Vyas Sekar", "Shinan Liu"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2607.03926", "source_url": "https://arxiv.org/abs/2607.03926"}, "categories": ["General AI", "Language & Knowledge", "cs.DB"], "description": {"en": "TabQueryBench evaluates synthetic tabular data generators using SQL-shaped analytical queries as structural assessors, providing 44 reusable query templates across 49 datasets."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2607.03926", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2607.03926", "title": "TabQueryBench"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "institutions": ["Tongji University", "University of Hong Kong", "Carnegie Mellon University", "University of Maryland, College Park"], "institutions_reference": {"basis": "openalex_linked_institutions", "doi": "10.48550/arxiv.2607.03926", "retrieved_at": "2026-11-04", "source_key": "claire-radar:2607.03926", "source_url": "https://openalex.org/W7167572250"}, "key": "claire-radar:2607.03926", "modality": null, "name": "TabQueryBench", "openness": {"code_license": null, "data_license": null, "evidence": [], "status": "unknown"}, "provenance": {"confidence": "Medium", "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_tabquerybench_d985f8e2", "origin_source": "arxiv", "recognition_confidence": "0.85", "record_sha256": "9317b7d7fcecdc7cbe78eb2f2870565cc28d30baea1325125a346b54085ba965", "relation": "introduces", "review_state": "unreviewed", "source_url": "https://arxiv.org/abs/2607.03926"}, "publisher": null, "released": "2026-07-04", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2607.03926", "source_url": "https://arxiv.org/abs/2607.03926"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2607-03926", "source": "claire_radar", "source_benchmark_id": "2607.03926", "source_metadata": {"claire_radar": {"adoption30d": null, "aliases": [], "annotation": "Machine Generated", "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/2607.03926", "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": [], "confidence": "Medium", "construction": "Original Synthetic", "constructionDetail": "Unknown — the indexer does not infer construction details without explicit source evidence.", "copyGeneration": {"generatedAt": "2026-08-20T15:22:10.044731Z", "inputHash": "980fc5b0a5c4dc58654070e0131a5581188e0bc525f962e85db4c94197ef6778", "model": "deepseek-v4-flash"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "TabQueryBench evaluates synthetic tabular data generators using SQL-shaped analytical queries as structural assessors, providing 44 reusable query templates across 49 datasets.", "domainCuration": {"method": "rules-v1", "state": "auto"}, "evidence": {"reasonCodes": ["coined title prefix ending in Bench or Benchmark", "benchmark release stated in one sentence"], "snippet": "We present TabQueryBench, a query-centric benchmark that uses SQL-shaped analytical queries as structural assessors for synthetic data fidelity."}, "familyId": "bmf_bdd17825921f", "firstSeenAt": "2026-08-19", "githubIndex": {"candidateCount": 0, "indexedAt": "2026-09-17T04:40:34.111665+00:00", "repositories": [], "status": "not-found"}, "heat": null, "id": "bm_tabquerybench_d985f8e2", "indexedAt": "2026-08-19T11:05:13.395391Z", "industrySectors": [], "links": {"code": null, "data": null, "hfPaper": "https://huggingface.co/papers/2607.03926", "paper": "https://arxiv.org/abs/2607.03926", "pdf": "https://arxiv.org/pdf/2607.03926", "project": null, "report": "https://arxiv.org/abs/2607.03926"}, "metrics": [], "motivation": "Synthetic tabular data support use cases like data sharing, model development under access restrictions, and rapid prototyping of analytical workflows.", "name": "TabQueryBench", "oneLine": "TabQueryBench evaluates synthetic tabular data generators using SQL-shaped analytical queries as structural assessors, providing 44 reusable query templates across 49 datasets.", "paperTitle": "TabQueryBench: A Query-Centric Benchmark for Synthetic Tabular Data", "primaryDomain": "General AI", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://arxiv.org/abs/2607.03926", "source": "arxiv-metadata", "status": "unverified", "venue": null, "verifiedAt": "2026-10-14T01:46:58.058199Z"}, "publications": [], "ranking": {}, "readiness": "Paper only", "recognitionConfidence": 0.85, "relation": "introduces", "releasedAt": "2026-07-04", "source": {"authors": ["Jialin Zhang", "Fenghao Dong", "Yajie Zhou", "Vyas Sekar", "Shinan Liu"], "categories": ["cs.DB", "cs.AI"], "id": "2607.03926", "title": "TabQueryBench: A Query-Centric Benchmark for Synthetic Tabular Data", "type": "arxiv", "url": "https://arxiv.org/abs/2607.03926"}, "sourceUpdatedAt": "2026-07-04T15:43:34Z", "topics": ["cs.DB"], "venueAttempts": [], "whyItMatters": "Existing synthetic data evaluations focus on statistical similarity and downstream ML utility, but rarely test analytical query structure. This benchmark addresses that gap, offering a way to assess query-centric fidelity for practical data analysis use cases."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
