{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2608.20106", "kind": "paper", "url": "https://arxiv.org/abs/2608.20106"}], "authors": ["Nikita Khudov"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2608.20106", "source_url": "https://arxiv.org/abs/2608.20106"}, "categories": ["Factuality", "General AI", "Language & Knowledge", "cs.CL"], "description": {"en": "Evaluates LLM knowledge in the wine domain via 3,266 multiple-choice questions across six pillars and four difficulty tiers, sourced from verified facts and scored against a calibrated audit."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2608.20106", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2608.20106", "title": "OenoBench"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "key": "claire-radar:2608.20106", "modality": null, "name": "OenoBench", "openness": {"code_license": null, "data_license": null, "evidence": [], "status": "unknown"}, "provenance": {"confidence": "Medium", "crawl_bundle": "claire_radar_2026-10-14", "crawled_at": "2026-10-14T09:44:51Z", "data_status": "primary-source-indexed", "display_eligible": "true", "origin_record_id": "bm_oenobench_8cfa7d28", "origin_source": "arxiv", "recognition_confidence": "0.85", "record_sha256": "d46cacbe03f66f371e91460ca6fcb5078f4ed89e5a1743491de33c24596965e0", "relation": "introduces", "review_model": "deepseek-v4-pro", "review_state": "ai-reviewed", "reviewed_at": "2026-08-26T06:15:55.708965Z", "source_url": "https://arxiv.org/abs/2608.20106"}, "publisher": null, "released": "2026-08-20", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2608.20106", "source_url": "https://arxiv.org/abs/2608.20106"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2608-20106", "source": "claire_radar", "source_benchmark_id": "2608.20106", "source_metadata": {"claire_radar": {"adoption30d": null, "aliases": [], "annotation": "Unknown", "applicationDomains": ["General AI"], "area": "Language & Knowledge", "attention": {"asOf": "2026-08-26", "attemptedAt": "2026-08-25T23:36:26.005677Z", "githubRepo": null, "githubScope": null, "githubStars": null, "hfDailySubmittedAt": null, "hfDataset": null, "hfDatasetDownloads": null, "hfDatasetLikes": null, "hfPaperUpvotes": null, "hfPaperUrl": "https://huggingface.co/papers/2608.20106", "observedAt": "2026-08-24T11:31:30.653116Z", "signalStatus": {"githubStars": {"state": "not_applicable"}, "hfDatasetDownloads": {"state": "not_applicable"}, "hfDatasetLikes": {"state": "not_applicable"}, "hfPaperUpvotes": {"checkedAt": "2026-08-25T23:36:26.005677Z", "state": "unavailable"}}, "status": "unavailable"}, "attentionForecast": {"confidence": "Low", "horizon": "7d", "reason": "The unusual wine domain and large annotated dataset may attract niche but engaged interest, though missing direct artifact links could dampen immediate uptake.", "score": 55}, "capabilities": ["Factuality"], "confidence": "Medium", "construction": "Unknown", "constructionDetail": "Unknown — the indexer does not infer construction details without explicit source evidence.", "copyGeneration": {"generatedAt": "2026-08-26T06:15:55.708965Z", "inputHash": "d2b72f1ef7904905438136e62f540e1ca5fa3a9cbc09d249db5a486b59d61c19", "model": "deepseek-v4-pro"}, "curation": {"canonicalNameEvidence": "OenoBench: A Wine-Domain Benchmark for Knowledge-Grounded Evaluation of Large Language Models", "canonicalNameSource": "paper_title", "decisionReason": "The paper declares a named benchmark, describes a stable scoring protocol, and explicitly states release of corpus, audit findings, and code, though no artifact links are provided in the input.", "model": "deepseek-v4-pro", "reviewedAt": "2026-08-26T06:15:55.708965Z", "state": "ai-reviewed"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "Evaluates LLM knowledge in the wine domain via 3,266 multiple-choice questions across six pillars and four difficulty tiers, sourced from verified facts and scored against a calibrated audit.", "displayEligible": true, "domainCuration": {"method": "rules-v1", "state": "auto"}, "evaluationMode": "public_reusable", "evidence": {"reasonCodes": ["coined title prefix ending in Bench or Benchmark", "benchmark release stated in one sentence"], "snippet": "We introduce OenoBench, a wine-domain knowledge benchmark of 3,266 multiple-choice questions across six pillars (regions, grape varieties, viticulture, winemaking, producers, business) and four difficulty tiers."}, "familyId": "bmf_0fd06eb77b86", "firstSeenAt": "2026-08-23", "heat": null, "id": "bm_oenobench_8cfa7d28", "indexedAt": "2026-08-23T06:55:50.392548Z", "industrySectors": [], "links": {"code": null, "data": null, "paper": "https://arxiv.org/abs/2608.20106", "pdf": "https://arxiv.org/pdf/2608.20106", "project": null, "report": "https://arxiv.org/abs/2608.20106"}, "metrics": [], "motivation": "We introduce OenoBench, a wine-domain knowledge benchmark of 3,266 multiple-choice questions across six pillars (regions, grape varieties, viticulture, winemaking, producers, business) and four difficulty tiers.", "name": "OenoBench", "oneLine": "Evaluates LLM knowledge in the wine domain via 3,266 multiple-choice questions across six pillars and four difficulty tiers, sourced from verified facts and scored against a calibrated audit.", "paperTitle": "OenoBench: A Wine-Domain Benchmark for Knowledge-Grounded Evaluation of Large Language Models", "primaryDomain": "General AI", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://arxiv.org/abs/2608.20106", "source": "arxiv-metadata", "status": "unverified", "venue": null, "verifiedAt": "2026-08-23T06:55:50.392548Z"}, "publications": [], "ranking": {"30d": {"confidence": "Low", "coverage": 0.0, "growth": {"components": {"githubStars": {"percentile": null, "value": null}, "hfDatasetDownloads": {"percentile": null, "value": null}, "hfPaperUpvotes": {"percentile": null, "value": null}}, "confidence": "Low", "coverage": 0.0, "elapsedDays": null, "historyDate": null, "rank": null, "score": null, "windowDays": 30}, "level": {"components": {"githubStars": {"percentile": null, "value": null}, "hfDatasetDownloads": {"percentile": null, "value": null}, "hfPaperUpvotes": {"percentile": null, "value": null}}, "confidence": "Low", "coverage": 0.0, "rank": null, "score": null}, "method": "attention-ranking-v11", "rank": null, "score": null}, "90d": {"confidence": "Low", "coverage": 0.0, "growth": {"components": {"githubStars": {"percentile": null, "value": null}, "hfDatasetDownloads": {"percentile": null, "value": null}, "hfPaperUpvotes": {"percentile": null, "value": null}}, "confidence": "Low", "coverage": 0.0, "elapsedDays": null, "historyDate": null, "rank": null, "score": null, "windowDays": 90}, "level": {"components": {"githubStars": {"percentile": null, "value": null}, "hfDatasetDownloads": {"percentile": null, "value": null}, "hfPaperUpvotes": {"percentile": null, "value": null}}, "confidence": "Low", "coverage": 0.0, "rank": null, "score": null}, "method": "attention-ranking-v11", "rank": null, "score": null}}, "readiness": "Paper only", "recognitionConfidence": 0.85, "relation": "introduces", "releasedAt": "2026-08-20", "source": {"authors": ["Nikita Khudov"], "categories": ["cs.CL"], "id": "2608.20106", "title": "OenoBench: A Wine-Domain Benchmark for Knowledge-Grounded Evaluation of Large Language Models", "type": "arxiv", "url": "https://arxiv.org/abs/2608.20106"}, "sourceUpdatedAt": "2026-08-20T14:37:22Z", "topics": ["cs.CL"], "venueAttempts": [], "whyItMatters": "Provides a detailed, provenance-grounded benchmark for specialized knowledge, enabling comparison of LLM factual accuracy in a domain with clear source verification."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
