{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2606.01879", "kind": "paper", "url": "https://arxiv.org/abs/2606.01879"}], "authors": ["Yangfan Ye", "Xiaocheng Feng", "Jialong Tang", "Xiayu Cao", "Zihan Zhang", "Xiachong Feng", "Baosong Yang", "Bing Qin"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2606.01879", "source_url": "https://arxiv.org/abs/2606.01879"}, "categories": ["General AI", "Language & Knowledge", "Reasoning"], "description": {"en": "CultureForest is a benchmark for cultural norm grounded reasoning, featuring 5,378 examples across 8 domains and 53 countries/regions, with progressive evaluation from multiple-choice to open-ended generation."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2606.01879", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2606.01879", "title": "CultureForest"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "institutions": ["Harbin Institute of Technology", "University of Hong Kong", "Harvard University"], "institutions_reference": {"basis": "openalex_linked_institutions", "doi": "10.48550/arxiv.2606.01879", "retrieved_at": "2026-11-04", "source_key": "claire-radar:2606.01879", "source_url": "https://openalex.org/W7163185880"}, "key": "claire-radar:2606.01879", "modality": null, "name": "CultureForest", "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_cultureforest_c27631e8", "origin_source": "arxiv", "recognition_confidence": "1.0", "record_sha256": "a9925abd0fe53a07b4dcfa511c3f51334ea60e2d10540016c750439cc40e2067", "relation": "introduces", "review_state": "unreviewed", "source_url": "https://arxiv.org/abs/2606.01879"}, "publisher": null, "released": "2026-06-01", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2606.01879", "source_url": "https://arxiv.org/abs/2606.01879"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2606-01879", "source": "claire_radar", "source_benchmark_id": "2606.01879", "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": 0, "hfPaperUrl": "https://huggingface.co/papers/2606.01879", "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", "lastSuccessfulDate": "2026-09-30", "state": "stale"}}, "status": "stale"}, "capabilities": ["Reasoning"], "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": "2902e9aeb3a587b171ece7f01312000fc53ec4b804513780ce9c1c48b8e84809", "model": "deepseek-v4-flash"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "CultureForest is a benchmark for cultural norm grounded reasoning, featuring 5,378 examples across 8 domains and 53 countries/regions, with progressive evaluation from multiple-choice to open-ended generation.", "domainCuration": {"method": "rules-v1", "state": "auto"}, "evidence": {"reasonCodes": ["exact coined title identity tied to benchmark evidence", "benchmark release stated in one sentence"], "snippet": "To bridge this gap, we introduce CultureForest, a benchmark for \\textit{Cultural Norm Grounded Reasoning}."}, "familyId": "bmf_2e6f8f580779", "firstSeenAt": "2026-08-19", "githubIndex": {"candidateCount": 0, "indexedAt": "2026-09-17T04:40:34.111665+00:00", "repositories": [], "status": "not-found"}, "heat": null, "id": "bm_cultureforest_c27631e8", "indexedAt": "2026-08-19T11:05:13.395391Z", "industrySectors": [], "links": {"code": null, "data": null, "hfPaper": "https://huggingface.co/papers/2606.01879", "paper": "https://arxiv.org/abs/2606.01879", "pdf": "https://arxiv.org/pdf/2606.01879", "project": null, "report": "https://arxiv.org/abs/2606.01879"}, "metrics": [], "motivation": "Existing research largely reduces cultural intelligence in LLMs to a knowledge-level problem, overlooking whether models can effectively utilize their acquired knowledge in realistic scenarios.", "name": "CultureForest", "oneLine": "CultureForest is a benchmark for cultural norm grounded reasoning, featuring 5,378 examples across 8 domains and 53 countries/regions, with progressive evaluation from multiple-choice to open-ended generation.", "paperTitle": "CultureForest: Understanding and Evaluating Cultural Norm Grounded Reasoning in LLMs", "primaryDomain": "General AI", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://arxiv.org/abs/2606.01879", "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": "2026-06-01", "source": {"authors": ["Yangfan Ye", "Xiaocheng Feng", "Jialong Tang", "Xiayu Cao", "Zihan Zhang", "Xiachong Feng", "Baosong Yang", "Bing Qin"], "categories": ["cs.CL"], "id": "2606.01879", "title": "CultureForest: Understanding and Evaluating Cultural Norm Grounded Reasoning in LLMs", "type": "arxiv", "url": "https://arxiv.org/abs/2606.01879"}, "sourceUpdatedAt": "2026-06-01T08:25:12Z", "topics": ["Reasoning"], "venueAttempts": [], "whyItMatters": "The benchmark addresses the evaluation gap between cultural knowledge and its application, offering a verifiable and attributable assessment of reasoning grounded in cultural norms."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
