{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2609.01982", "kind": "paper", "url": "https://arxiv.org/abs/2609.01982"}, {"id": "gh:thu-conglab/statformbench", "kind": "repo", "url": "https://github.com/THU-CongLab/StatFormBench"}, {"id": "hf:thu-conglab/statformbench", "kind": "dataset", "url": "https://huggingface.co/datasets/THU-CongLab/StatFormBench"}], "authors": ["Chen Wang", "Junzhe Zhao", "Xin Cong", "Wanlu Deng", "Ke Deng"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2609.01982", "source_url": "https://arxiv.org/abs/2609.01982"}, "categories": ["General AI", "Language & Knowledge", "cs.AI"], "description": {"en": "Evaluates language models on statistical problem formulation tasks drawn from five statistics textbooks and a data science case library, covering diverse problem types, data representations, and scenario styles."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2609.01982", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2609.01982", "title": "StatFormBench"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "key": "claire-radar:2609.01982", "modality": null, "name": "StatFormBench", "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": "false", "origin_record_id": "bm_statformbench_9b48c2ce", "origin_source": "arxiv", "recognition_confidence": "1.0", "record_sha256": "6d01375ebacb33eb6d42fdda51645c55ab59a252a458aa28bcc5419ca1bb52be", "relation": "introduces", "review_model": "deepseek-v4-pro", "review_state": "ai-name-audit-deferred", "reviewed_at": "2026-09-04T00:46:59.007339Z", "source_url": "https://arxiv.org/abs/2609.01982"}, "publisher": null, "released": "2026-09-02", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2609.01982", "source_url": "https://arxiv.org/abs/2609.01982"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2609-01982", "source": "claire_radar", "source_benchmark_id": "2609.01982", "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": "https://github.com/THU-CongLab/StatFormBench", "githubScope": "benchmark_repo", "githubStars": 0, "hfDailySubmittedAt": null, "hfDataset": "THU-CongLab/StatFormBench", "hfDatasetDownloads": 88, "hfDatasetLikes": 0, "hfPaperUpvotes": 0, "hfPaperUrl": "https://huggingface.co/papers/2609.01982", "observedAt": "2026-10-04T15:31:48.030916Z", "signalStatus": {"githubStars": {"observedAt": "2026-10-04T15:31:48.030916Z", "state": "fresh"}, "hfDatasetDownloads": {"checkedAt": "2026-10-04T15:31:48.030916Z", "lastSuccessfulDate": "2026-10-01", "state": "stale"}, "hfDatasetLikes": {"checkedAt": "2026-10-04T15:31:48.030916Z", "lastSuccessfulDate": "2026-10-01", "state": "stale"}, "hfPaperUpvotes": {"checkedAt": "2026-10-04T15:31:48.030916Z", "lastSuccessfulDate": "2026-10-01", "state": "stale"}}, "status": "fresh"}, "attentionForecast": {"confidence": "Low", "horizon": "7d", "reason": "The targeted statistical problem formulation domain and cross-disciplinary textbook construction suggest moderate appeal to the NLP and data science communities.", "score": 32}, "capabilities": [], "confidence": "High", "construction": "Unknown", "constructionDetail": "Unknown — the indexer does not infer construction details without explicit source evidence.", "copyGeneration": {"generatedAt": "2026-09-04T00:46:59.007339Z", "inputHash": "f85c4077436a50470418b8c27a6421a840d94bee9ab562f6f5cad1ba778d3b01", "model": "deepseek-v4-pro"}, "curation": {"canonicalNameEvidence": "We then introduce StatFormBench, a benchmark built from five cross-domain statistics textbooks and a data science case library", "canonicalNameSource": "abstract", "decisionReason": "The benchmark is explicitly named and introduced with a GitHub repository and Hugging Face dataset, providing a reusable dataset and a credible public path for other teams, but no scoring contract details are supplied.", "model": "deepseek-v4-pro", "reviewedAt": "2026-09-04T00:46:59.007339Z", "state": "ai-name-audit-deferred"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "Evaluates language models on statistical problem formulation tasks drawn from five statistics textbooks and a data science case library, covering diverse problem types, data representations, and scenario styles.", "displayEligible": false, "domainCuration": {"method": "rules-v1", "state": "auto"}, "evaluationMode": "public_reusable", "evidence": {"reasonCodes": ["exact named benchmark artifact released in abstract", "benchmark release stated in one sentence", "evaluation protocol evidence", "public artifact URL"], "snippet": "We then introduce StatFormBench, a benchmark built from five cross-domain statistics textbooks and a data science case library, covering diverse problem types, data representations, and scenario styles."}, "familyId": "bmf_86d41b73fe78", "firstSeenAt": "2026-09-03", "heat": null, "id": "bm_statformbench_9b48c2ce", "indexedAt": "2026-09-03T00:55:28.123857Z", "industrySectors": [], "links": {"code": "https://github.com/THU-CongLab/StatFormBench", "data": "https://huggingface.co/datasets/THU-CongLab/StatFormBench", "paper": "https://arxiv.org/abs/2609.01982", "pdf": "https://arxiv.org/pdf/2609.01982", "project": null, "report": "https://arxiv.org/abs/2609.01982"}, "metrics": [], "motivation": "Large language models (LLMs) are increasingly used as assistants for statistical and data science work, yet existing evaluations largely assume the analysis target is already specified.", "name": "StatFormBench", "oneLine": "Evaluates language models on statistical problem formulation tasks drawn from five statistics textbooks and a data science case library, covering diverse problem types, data representations, and scenario styles.", "paperTitle": "Benchmarking Language Models for Statistical Problem Formulation", "primaryDomain": "General AI", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://arxiv.org/abs/2609.01982", "source": "arxiv-metadata", "status": "unverified", "venue": null, "verifiedAt": "2026-09-03T00:55:28.123857Z"}, "publications": [], "publishers": [{"name": "THU-CongLab", "organizationType": "academic-lab", "role": "benchmark-publisher", "sourceUrl": "https://github.com/THU-CongLab/StatFormBench"}], "ranking": {"90d": {"confidence": "High", "coverage": 1.0, "datasetDownloadRank": 64, "datasetRankPopulation": 85, "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": 0.0, "value": 0}, "hfDatasetDownloads": {"normalization": "log-max", "normalized": 0.46223942720688993, "value": 88}, "hfPaperUpvotes": {"normalization": "log-max", "normalized": 0.0, "value": 0}}, "confidence": "High", "coverage": 1.0, "rank": 584, "score": 14}, "method": "attention-ranking-v13", "rank": 584, "score": 14}}, "readiness": "Runnable", "recognitionConfidence": 1.0, "relation": "introduces", "releasedAt": "2026-09-02", "source": {"authors": ["Chen Wang", "Junzhe Zhao", "Xin Cong", "Wanlu Deng", "Ke Deng"], "categories": ["cs.AI"], "id": "2609.01982", "title": "Benchmarking Language Models for Statistical Problem Formulation", "type": "arxiv", "url": "https://arxiv.org/abs/2609.01982"}, "sourceUpdatedAt": "2026-09-02T01:37:17Z", "topics": ["cs.AI"], "venueAttempts": [], "whyItMatters": "Tests the ability to translate real-world statistical scenarios into well-formed problems, a step that is often implicit in applied data science and not covered by standard math or coding benchmarks."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
