{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2608.07529", "kind": "paper", "url": "https://arxiv.org/abs/2608.07529"}], "authors": ["Yi Zhang", "Hongyang Wang", "Zheng Hao Leong", "Zihao Wu", "Kaijun Lin", "Zhixing Pan", "Qixun Huangfu", "Wei Ren", "Wenyan Wu", "Fangyun Wang", "Wenting Yu", "Hengyu Lin", "Muling Yang", "Zongguo Wen"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2608.07529", "source_url": "https://arxiv.org/abs/2608.07529"}, "categories": ["Factuality", "General AI", "Language & Knowledge", "Reasoning"], "description": {"en": "A multi-level benchmark evaluates LLMs in solid waste management across foundational knowledge, domain reasoning, and expert decision-making using closed-ended and open-ended questions."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2608.07529", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2608.07529", "title": "WuYuEval"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "institutions": ["Tsinghua University", "Fudan University", "Nanjing University", "Capital Normal University", "Tencent (China)", "China University of Petroleum, Beijing"], "institutions_reference": {"basis": "openalex_linked_institutions", "doi": "10.48550/arxiv.2608.07529", "retrieved_at": "2026-11-04", "source_key": "claire-radar:2608.07529", "source_url": "https://openalex.org/W7202189567"}, "key": "claire-radar:2608.07529", "modality": null, "name": "WuYuEval", "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_wuyueval_f4ea028f", "origin_source": "arxiv", "recognition_confidence": "1.0", "record_sha256": "61b75e782c5138091a24abe6703ecf52727be22326231d1e7b15b91c1578f4f8", "relation": "introduces", "review_state": "unreviewed", "source_url": "https://arxiv.org/abs/2608.07529"}, "publisher": null, "released": "2026-07-24", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2608.07529", "source_url": "https://arxiv.org/abs/2608.07529"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2608-07529", "source": "claire_radar", "source_benchmark_id": "2608.07529", "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/2608.07529", "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": ["Reasoning", "Factuality"], "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": "c9abf8074a5ea6e32af3d836249e207b330a7244c21e5a6743930774785ce4ae", "model": "deepseek-v4-flash"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "A multi-level benchmark evaluates LLMs in solid waste management across foundational knowledge, domain reasoning, and expert decision-making using closed-ended and open-ended questions.", "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"], "snippet": "We introduce WuYuEval, a multi-level benchmark for evaluating LLMs in SWM across foundational knowledge, domain reasoning, and expert decision-making."}, "familyId": "bmf_e2fd7bd79b60", "firstSeenAt": "2026-08-19", "githubIndex": {"candidateCount": 0, "indexedAt": "2026-09-17T04:40:34.111665+00:00", "repositories": [], "status": "not-found"}, "heat": null, "id": "bm_wuyueval_f4ea028f", "indexedAt": "2026-08-19T11:05:13.395391Z", "industrySectors": [], "links": {"code": null, "data": null, "hfPaper": "https://huggingface.co/papers/2608.07529", "paper": "https://arxiv.org/abs/2608.07529", "pdf": "https://arxiv.org/pdf/2608.07529", "project": null, "report": "https://arxiv.org/abs/2608.07529"}, "metrics": [], "motivation": "Large language models (LLMs) are increasingly used as technical assistants, but their competence in solid waste management (SWM) remains difficult to assess because existing benchmarks emphasize general knowledge rather than professional decisions under engineering, environmental, and policy constraints.", "name": "WuYuEval", "oneLine": "A multi-level benchmark evaluates LLMs in solid waste management across foundational knowledge, domain reasoning, and expert decision-making using closed-ended and open-ended questions.", "paperTitle": "WuYuEval: A Multi-Level Benchmark for Large Language Models in Solid Waste Management", "primaryDomain": "General AI", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://arxiv.org/abs/2608.07529", "source": "arxiv-metadata", "status": "unverified", "venue": null, "verifiedAt": "2026-10-14T01:46:58.058199Z"}, "publications": [], "ranking": {"90d": {"confidence": "Low", "coverage": 0.0, "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": null, "value": null}}, "confidence": "Low", "coverage": 0.0, "rank": null, "score": null}, "method": "attention-ranking-v13", "rank": null, "score": null}}, "readiness": "Paper only", "recognitionConfidence": 1.0, "relation": "introduces", "releasedAt": "2026-07-24", "source": {"authors": ["Yi Zhang", "Hongyang Wang", "Zheng Hao Leong", "Zihao Wu", "Kaijun Lin", "Zhixing Pan", "Qixun Huangfu", "Wei Ren", "Wenyan Wu", "Fangyun Wang", "Wenting Yu", "Hengyu Lin", "Muling Yang", "Zongguo Wen"], "categories": ["cs.CL", "cs.AI"], "id": "2608.07529", "title": "WuYuEval: A Multi-Level Benchmark for Large Language Models in Solid Waste Management", "type": "arxiv", "url": "https://arxiv.org/abs/2608.07529"}, "sourceUpdatedAt": "2026-07-24T09:23:16Z", "topics": ["Reasoning"], "venueAttempts": [], "whyItMatters": "Fills a gap in evaluating professional decisions under engineering, environmental, and policy constraints, providing a resource for developing domain-oriented models."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
