{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2607.28033", "kind": "paper", "url": "https://arxiv.org/abs/2607.28033"}, {"kind": "repo", "url": "https://github.com/Dicemy/DataClawEval/tree/master"}], "authors": ["Debin Meng", "Jiaming Yang", "Zefang Zong", "Tengyue Xu", "Haining Xie", "Yang Li", "Peng Chen"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2607.28033", "source_url": "https://arxiv.org/abs/2607.28033"}, "categories": ["Agents & Tool Use", "General AI", "cs.AI"], "description": {"en": "DataClawEval evaluates autonomous data-engineering agents across 100 end-to-end tasks spanning PySpark, MySQL, HiveSQL, PrestoSQL/Trino, and FlinkSQL, with deterministic rule-based grading in isolated sandboxes."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2607.28033", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2607.28033", "title": "DataClawEval"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "institutions": ["Tencent (China)", "Sun Yat-sen University"], "institutions_reference": {"basis": "openalex_linked_institutions", "doi": "10.48550/arxiv.2607.28033", "retrieved_at": "2026-11-04", "source_key": "claire-radar:2607.28033", "source_url": "https://openalex.org/W7171987421"}, "key": "claire-radar:2607.28033", "modality": null, "name": "DataClawEval", "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_dataclaweval_e7e41e17", "origin_source": "arxiv", "recognition_confidence": "1.0", "record_sha256": "1296211257b734979565339369347f1edf35a46ecefec4c6fe0b4c984849d8d3", "relation": "introduces", "review_state": "unreviewed", "source_url": "https://arxiv.org/abs/2607.28033"}, "publisher": null, "released": "2026-07-30", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2607.28033", "source_url": "https://arxiv.org/abs/2607.28033"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2607-28033", "source": "claire_radar", "source_benchmark_id": "2607.28033", "source_metadata": {"claire_radar": {"adoption30d": null, "aliases": [], "annotation": "Unknown", "applicationDomains": ["General AI"], "area": "Agents & Tool Use", "attention": {"asOf": "2026-10-05", "attemptedAt": "2026-10-04T15:31:48.030916Z", "githubRepo": "https://github.com/Dicemy/DataClawEval", "githubScope": "hosting_repo", "githubStars": 4, "hfDailySubmittedAt": null, "hfDataset": null, "hfDatasetDownloads": null, "hfDatasetLikes": null, "hfPaperUpvotes": 1, "hfPaperUrl": "https://huggingface.co/papers/2607.28033", "observedAt": "2026-10-04T15:31:48.030916Z", "signalStatus": {"githubStars": {"observedAt": "2026-10-04T15:31:48.030916Z", "state": "fresh"}, "hfDatasetDownloads": {"state": "not_applicable"}, "hfDatasetLikes": {"state": "not_applicable"}, "hfPaperUpvotes": {"observedAt": "2026-10-04T15:31:48.030916Z", "state": "fresh"}}, "status": "fresh"}, "capabilities": [], "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": "55f381818930f984f7418761c80a05f58e2c49e9f42dbde2060ab18d3f64d1e9", "model": "deepseek-v4-flash"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "DataClawEval evaluates autonomous data-engineering agents across 100 end-to-end tasks spanning PySpark, MySQL, HiveSQL, PrestoSQL/Trino, and FlinkSQL, with deterministic rule-based grading in isolated sandboxes.", "domainCuration": {"method": "rules-v1", "state": "auto"}, "evidence": {"reasonCodes": ["exact coined title identity tied to benchmark evidence", "benchmark release stated in one sentence", "evaluation protocol evidence", "public artifact URL"], "snippet": "To bridge this gap, we introduce DataClawEval, the first comprehensive benchmark designed specifically to evaluate the end-to-end task completion capabilities of autonomous agents in real-world data engineering scenarios."}, "familyId": "bmf_2921fe8e003f", "firstSeenAt": "2026-08-19", "githubIndex": {"candidateCount": 0, "indexedAt": "2026-09-17T04:40:34.111665+00:00", "repositories": [{"evidence": [{"basis": "existing-code-link", "linkedUrl": "https://github.com/Dicemy/DataClawEval/tree/master", "url": "https://github.com/Dicemy/DataClawEval/tree/master"}, {"basis": "existing-metric-association", "linkedUrl": "https://github.com/Dicemy/DataClawEval", "url": "https://huggingface.co/papers/2607.28033"}, {"basis": "linked-from-report", "linkedUrl": "https://github.com/Dicemy/DataClawEval/tree/master", "url": "https://arxiv.org/abs/2607.28033"}], "scope": "benchmark_repo", "url": "https://github.com/Dicemy/DataClawEval", "verification": "source-linked"}], "status": "linked"}, "heat": null, "id": "bm_dataclaweval_e7e41e17", "indexedAt": "2026-08-19T11:05:13.395391Z", "industrySectors": [], "links": {"code": "https://github.com/Dicemy/DataClawEval/tree/master", "data": null, "hfPaper": "https://huggingface.co/papers/2607.28033", "paper": "https://arxiv.org/abs/2607.28033", "pdf": "https://arxiv.org/pdf/2607.28033", "project": null, "report": "https://arxiv.org/abs/2607.28033"}, "metrics": [], "motivation": "Large language models (LLMs) and LLM-based agents are increasingly being deployed to automate complex workflows, promising to revolutionize data management and processing.", "name": "DataClawEval", "oneLine": "DataClawEval evaluates autonomous data-engineering agents across 100 end-to-end tasks spanning PySpark, MySQL, HiveSQL, PrestoSQL/Trino, and FlinkSQL, with deterministic rule-based grading in isolated sandboxes.", "paperTitle": "DataClawEval: A Benchmark for Data Engineering Agents in Real Industrial Harness", "primaryDomain": "General AI", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://arxiv.org/abs/2607.28033", "source": "arxiv-metadata", "status": "unverified", "venue": null, "verifiedAt": "2026-10-14T01:46:58.058199Z"}, "publications": [], "publishers": [{"name": "DataClawEval Team", "organizationType": "community", "role": "benchmark-publisher", "sourceUrl": "https://github.com/Dicemy/DataClawEval/tree/master"}], "ranking": {"90d": {"confidence": "Low", "coverage": 0.15, "growth": {"components": {"githubStars": {"normalization": "percentile", "normalized": null, "percentile": null, "value": null}, "hfDatasetDownloads": {"normalization": "percentile", "normalized": null, "percentile": null, "value": null}, "hfPaperUpvotes": {"normalization": "percentile", "normalized": null, "percentile": null, "value": null}}, "confidence": "Low", "coverage": 0.0, "elapsedDays": null, "historyDate": null, "rank": null, "score": null, "windowDays": 90}, "level": {"components": {"githubStars": {"normalization": "log-max", "normalized": null, "value": null}, "hfDatasetDownloads": {"normalization": "log-max", "normalized": null, "value": null}, "hfPaperUpvotes": {"normalization": "log-max", "normalized": 0.12247537038455211, "value": 1}}, "confidence": "Low", "coverage": 0.15, "rank": null, "score": 44}, "method": "attention-ranking-v13", "rank": null, "score": 44}}, "readiness": "Runnable", "recognitionConfidence": 1.0, "relation": "introduces", "releasedAt": "2026-07-30", "source": {"authors": ["Debin Meng", "Jiaming Yang", "Zefang Zong", "Tengyue Xu", "Haining Xie", "Yang Li", "Peng Chen"], "categories": ["cs.AI"], "id": "2607.28033", "title": "DataClawEval: A Benchmark for Data Engineering Agents in Real Industrial Harness", "type": "arxiv", "url": "https://arxiv.org/abs/2607.28033"}, "sourceUpdatedAt": "2026-07-30T11:17:27Z", "topics": ["cs.AI"], "venueAttempts": [], "whyItMatters": "It provides a reproducible, deterministic evaluation for industrial data-engineering workflows, revealing domain-specific strengths and gaps in agent capabilities."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
