{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2606.22977", "kind": "paper", "url": "https://arxiv.org/abs/2606.22977"}], "authors": ["Youxin Zhu", "Yixuan Ding", "Peng Lai", "Longyue Wang", "Bingyi Jing", "Guanhua Chen"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2606.22977", "source_url": "https://arxiv.org/abs/2606.22977"}, "categories": ["General AI", "Language & Knowledge", "cs.CL"], "description": {"en": "StatABench evaluates LLMs' statistical analysis capabilities through two components: Stat-Closed, 404 questions across 18 topics in multiple formats, and Stat-Open, 30 complex modeling tasks from competitions, scored via LLM-as-judge."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2606.22977", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2606.22977", "title": "StatABench"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "institutions": ["Southern University of Science and Technology", "University of Hong Kong", "Alibaba Group (China)", "Chinese University of Hong Kong, Shenzhen"], "institutions_reference": {"basis": "openalex_linked_institutions", "doi": "10.48550/arxiv.2606.22977", "retrieved_at": "2026-11-04", "source_key": "claire-radar:2606.22977", "source_url": "https://openalex.org/W7165660474"}, "key": "claire-radar:2606.22977", "modality": null, "name": "StatABench", "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_statabench_6a243141", "origin_source": "arxiv", "recognition_confidence": "1.0", "record_sha256": "f48a51c9b8260491373a0fa491b230ad9b639e2650c71eb9be8b145a9c3dcd65", "relation": "introduces", "review_state": "unreviewed", "source_url": "https://arxiv.org/abs/2606.22977"}, "publisher": null, "released": "2026-06-22", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2606.22977", "source_url": "https://arxiv.org/abs/2606.22977"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2606-22977", "source": "claire_radar", "source_benchmark_id": "2606.22977", "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/2606.22977", "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": "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": "ace7c1855e953724bb15c82ed04e7a3c984e30bfcf14f2807724e35d5f62534f", "model": "deepseek-v4-flash"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "StatABench evaluates LLMs' statistical analysis capabilities through two components: Stat-Closed, 404 questions across 18 topics in multiple formats, and Stat-Open, 30 complex modeling tasks from competitions, scored via LLM-as-judge.", "domainCuration": {"method": "rules-v1", "state": "auto"}, "evidence": {"reasonCodes": ["coined title prefix ending in Bench or Benchmark", "benchmark release stated in one sentence", "evaluation protocol evidence"], "snippet": "To bridge this gap, we introduce StatABench (Statistical AnalysisBenchmark), a benchmark designed to systematically assess LLMs' statistical analysis capabilities."}, "familyId": "bmf_81f1ac51c69f", "firstSeenAt": "2026-08-19", "githubIndex": {"candidateCount": 0, "indexedAt": "2026-09-17T04:40:34.111665+00:00", "repositories": [], "status": "not-found"}, "heat": null, "id": "bm_statabench_6a243141", "indexedAt": "2026-08-19T11:05:13.395391Z", "industrySectors": [], "links": {"code": null, "data": null, "hfPaper": "https://huggingface.co/papers/2606.22977", "paper": "https://arxiv.org/abs/2606.22977", "pdf": "https://arxiv.org/pdf/2606.22977", "project": null, "report": "https://arxiv.org/abs/2606.22977"}, "metrics": [], "motivation": "Statistical analysis is a broad, complex field requiring both domain knowledge and tool proficiency.", "name": "StatABench", "oneLine": "StatABench evaluates LLMs' statistical analysis capabilities through two components: Stat-Closed, 404 questions across 18 topics in multiple formats, and Stat-Open, 30 complex modeling tasks from competitions, scored via LLM-as-judge.", "paperTitle": "StatABench: Dataset and Framework for Evaluating Statistical Analysis Capabilities of LLMs", "primaryDomain": "General AI", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://arxiv.org/abs/2606.22977", "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": "2026-06-22", "source": {"authors": ["Youxin Zhu", "Yixuan Ding", "Peng Lai", "Longyue Wang", "Bingyi Jing", "Guanhua Chen"], "categories": ["cs.CL", "cs.AI"], "id": "2606.22977", "title": "StatABench: Dataset and Framework for Evaluating Statistical Analysis Capabilities of LLMs", "type": "arxiv", "url": "https://arxiv.org/abs/2606.22977"}, "sourceUpdatedAt": "2026-06-22T07:57:53Z", "topics": ["cs.CL"], "venueAttempts": [], "whyItMatters": "Addresses the need for systematic evaluation of LLMs in statistical analysis, revealing performance gaps and challenges in tool-grounded reasoning and modeling."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
