{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2609.03526", "kind": "paper", "url": "https://arxiv.org/abs/2609.03526"}, {"id": "gh:bobtsang-nlp/culturalmenubench", "kind": "repo", "url": "https://github.com/BobTsang-NLP/CulturalMenuBench"}], "authors": ["Bo Zeng", "Linfeng Gao", "Peiqin Lin", "Yu Zhao", "Mingyan Zeng", "Yu Tong", "Xintong Wang", "Linlong Xu", "Longyue Wang", "Weihua Luo", "Qinggang Zhang", "Jinsong Su"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2609.03526", "source_url": "https://arxiv.org/abs/2609.03526"}, "categories": ["Factuality", "General AI", "Multimodal", "Reasoning"], "description": {"en": "Evaluates multimodal models on culinary reasoning across 4,870 items in 10 languages and 18 regions, with tasks from dish recognition to cultural attribution using images and procedural text."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2609.03526", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2609.03526", "title": "CulturalMenuBench"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "key": "claire-radar:2609.03526", "modality": null, "name": "CulturalMenuBench", "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": "true", "origin_record_id": "bm_culturalmenubench_496caf80", "origin_source": "arxiv", "recognition_confidence": "1.0", "record_sha256": "fa5d9b6c74ff57f027d7f68b8e5156cf151d93f74a3d04d2e9af8f18840027d4", "relation": "introduces", "review_model": "deepseek-v4-pro", "review_state": "ai-reviewed", "reviewed_at": "2026-09-04T00:46:59.007339Z", "source_url": "https://arxiv.org/abs/2609.03526"}, "publisher": null, "released": "2026-09-03", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2609.03526", "source_url": "https://arxiv.org/abs/2609.03526"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2609-03526", "source": "claire_radar", "source_benchmark_id": "2609.03526", "source_metadata": {"claire_radar": {"adoption30d": null, "aliases": [], "annotation": "Unknown", "applicationDomains": ["General AI"], "area": "Multimodal", "attention": {"asOf": "2026-10-05", "attemptedAt": "2026-10-04T15:31:48.030916Z", "githubRepo": "https://github.com/BobTsang-NLP/CulturalMenuBench", "githubScope": "benchmark_repo", "githubStars": 0, "hfDailySubmittedAt": null, "hfDataset": null, "hfDatasetDownloads": null, "hfDatasetLikes": null, "hfPaperUpvotes": null, "hfPaperUrl": "https://huggingface.co/papers/2609.03526", "observedAt": "2026-10-04T15:31:48.030916Z", "signalStatus": {"githubStars": {"observedAt": "2026-10-04T15:31:48.030916Z", "state": "fresh"}, "hfDatasetDownloads": {"state": "not_applicable"}, "hfDatasetLikes": {"state": "not_applicable"}, "hfPaperUpvotes": {"checkedAt": "2026-10-04T15:31:48.030916Z", "state": "unavailable"}}, "status": "fresh"}, "attentionForecast": {"confidence": "Low", "horizon": "7d", "reason": "Cultural and multimodal dimensions broaden potential interest among NLP and vision communities.", "score": 60}, "capabilities": ["Reasoning", "Factuality"], "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": "4550add7ec30683d02826302be8862a8490ce36dc702cd2727678d2998228845", "model": "deepseek-v4-pro"}, "curation": {"canonicalNameEvidence": "CulturalMenuBench: Probing the Knowledge-Application Gap in Multimodal Culinary Reasoning", "canonicalNameSource": "paper_title", "decisionReason": "Well-defined task suite with a linked GitHub repository and a clear evaluation scope.", "model": "deepseek-v4-pro", "reviewedAt": "2026-09-04T00:46:59.007339Z", "state": "ai-reviewed"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "Evaluates multimodal models on culinary reasoning across 4,870 items in 10 languages and 18 regions, with tasks from dish recognition to cultural attribution using images and procedural text.", "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", "evaluation protocol evidence", "public artifact URL"], "snippet": "To probe this distinction, we introduce CulturalMenuBench, a benchmark of 4,870 items in 10 languages across 18 regions; its 10 tasks pair final-dish and step-by-step cooking images with ingredients, procedural text, and regional labels, spanning basic recognition to process-grounded cultural attribution."}, "familyId": "bmf_0b663c84e65a", "firstSeenAt": "2026-09-04", "heat": null, "id": "bm_culturalmenubench_496caf80", "indexedAt": "2026-09-04T00:41:56.430646Z", "industrySectors": [], "links": {"code": "https://github.com/BobTsang-NLP/CulturalMenuBench", "data": null, "paper": "https://arxiv.org/abs/2609.03526", "pdf": "https://arxiv.org/pdf/2609.03526", "project": null, "report": "https://arxiv.org/abs/2609.03526"}, "metrics": [], "motivation": "Multimodal language models achieve near-ceiling scores on food recognition benchmarks, yet it remains unclear whether this success reflects genuine cultural understanding or mere visual matching.", "name": "CulturalMenuBench", "oneLine": "Evaluates multimodal models on culinary reasoning across 4,870 items in 10 languages and 18 regions, with tasks from dish recognition to cultural attribution using images and procedural text.", "paperTitle": "CulturalMenuBench: Probing the Knowledge-Application Gap in Multimodal Culinary Reasoning", "primaryDomain": "General AI", "publication": {"evidence": "Accepted to EMNLP 2026 Findings. Code and data: https://github.com/BobTsang-NLP/CulturalMenuBench", "evidenceLevel": "author-claim", "evidenceUrl": "https://arxiv.org/abs/2609.03526", "source": "arxiv-comments", "status": "acceptance_claimed", "venue": "EMNLP 2026 Findings", "verifiedAt": "2026-09-04T00:41:56.430646Z"}, "publications": [], "ranking": {"90d": {"confidence": "Low", "coverage": 0.55, "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": null, "value": null}, "hfPaperUpvotes": {"normalization": "log-max", "normalized": null, "value": null}}, "confidence": "Low", "coverage": 0.55, "rank": 475, "score": 23}, "method": "attention-ranking-v13", "rank": 475, "score": 23}}, "readiness": "Runnable", "recognitionConfidence": 1.0, "relation": "introduces", "releasedAt": "2026-09-03", "source": {"authors": ["Bo Zeng", "Linfeng Gao", "Peiqin Lin", "Yu Zhao", "Mingyan Zeng", "Yu Tong", "Xintong Wang", "Linlong Xu", "Longyue Wang", "Weihua Luo", "Qinggang Zhang", "Jinsong Su"], "categories": ["cs.AI"], "id": "2609.03526", "title": "CulturalMenuBench: Probing the Knowledge-Application Gap in Multimodal Culinary Reasoning", "type": "arxiv", "url": "https://arxiv.org/abs/2609.03526"}, "sourceUpdatedAt": "2026-09-03T08:24:22Z", "topics": ["Multimodal", "Reasoning"], "venueAttempts": [{"decisionRaw": "Accepted to EMNLP 2026 Findings. Code and data: https://github.com/BobTsang-NLP/CulturalMenuBench", "evidence": [{"level": "author-claim", "observedAt": "2026-09-04T00:41:56.430646Z", "rawValue": "Accepted to EMNLP 2026 Findings. Code and data: https://github.com/BobTsang-NLP/CulturalMenuBench", "sourceType": "arxiv-comments", "sourceUrl": "https://arxiv.org/abs/2609.03526"}], "reviewStatus": "accepted", "venueName": "EMNLP 2026 Findings"}], "whyItMatters": "Tests whether models can apply knowledge to culturally grounded, multimodal cooking scenarios, revealing gaps beyond factual recall."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
