{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2605.31410", "kind": "paper", "url": "https://arxiv.org/abs/2605.31410"}], "authors": ["Mingyang Mao", "Bhargav Rishi Medisetti", "Utkarsh Grover", "Tanvir Ibrahim", "Wenyan Li", "Tingting Zhang", "Xiaomin Lin"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2605.31410", "source_url": "https://arxiv.org/abs/2605.31410"}, "categories": ["Biology & Drug Discovery", "Multimodal", "Reasoning"], "description": {"en": "FAM-Bench evaluates multimodal language and vision-language models on Food-as-Medicine reasoning. It includes 2500 expert-verified instances across 13 health conditions, with two tasks: dish-level suitability assessment (judging if a dish is suitable for a condition) and comparative dish analysis (ranking four dishes by suitability)."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2605.31410", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2605.31410", "title": "FAM-Bench"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "institutions": ["University of South Florida", "University of Copenhagen"], "institutions_reference": {"basis": "openalex_linked_institutions", "doi": "10.48550/arxiv.2605.31410", "retrieved_at": "2026-11-04", "source_key": "claire-radar:2605.31410", "source_url": "https://openalex.org/W7163074863"}, "key": "claire-radar:2605.31410", "modality": null, "name": "FAM-Bench", "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_fam-bench_1946f5cd", "origin_source": "arxiv", "recognition_confidence": "1.0", "record_sha256": "314a8f07cd5144005fdb981b2843a0d4bb6f742aa20e414ec180abfad591b3b5", "relation": "introduces", "review_state": "unreviewed", "source_url": "https://arxiv.org/abs/2605.31410"}, "publisher": null, "released": "2026-05-29", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2605.31410", "source_url": "https://arxiv.org/abs/2605.31410"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2605-31410", "source": "claire_radar", "source_benchmark_id": "2605.31410", "source_metadata": {"claire_radar": {"adoption30d": null, "aliases": [], "annotation": "Unknown", "applicationDomains": ["Biology & Drug Discovery"], "area": "Multimodal", "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/2605.31410", "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": "c45bc785f974ced4e8d845a40772130131a79a51fff1fe234a5eec09872e3442", "model": "deepseek-v4-flash"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "FAM-Bench evaluates multimodal language and vision-language models on Food-as-Medicine reasoning. It includes 2500 expert-verified instances across 13 health conditions, with two tasks: dish-level suitability assessment (judging if a dish is suitable for a condition) and comparative dish analysis (ranking four dishes by suitability).", "domainCuration": {"method": "rules-v1", "state": "auto"}, "evidence": {"reasonCodes": ["coined title prefix ending in Bench or Benchmark", "benchmark release stated in one sentence", "evaluation protocol evidence"], "snippet": "We introduce FAM-Bench, a multi-modal Food-as-Medicine benchmark with 2500 nutrition-expert-verified instances across 13 diet-related health conditions."}, "familyId": "bmf_07e4f08667c9", "firstSeenAt": "2026-08-19", "githubIndex": {"candidateCount": 0, "indexedAt": "2026-09-17T04:40:34.111665+00:00", "repositories": [], "status": "not-found"}, "heat": null, "id": "bm_fam-bench_1946f5cd", "indexedAt": "2026-08-19T11:05:13.395391Z", "industrySectors": ["Pharma & Biotech"], "links": {"code": null, "data": null, "hfPaper": "https://huggingface.co/papers/2605.31410", "paper": "https://arxiv.org/abs/2605.31410", "pdf": "https://arxiv.org/pdf/2605.31410", "project": null, "report": "https://arxiv.org/abs/2605.31410"}, "metrics": [], "motivation": "Food-as-Medicine requires models to reason beyond what a dish is or what nutrition it contains: they must decide whether a concrete food choice is appropriate for a specific health condition.", "name": "FAM-Bench", "oneLine": "FAM-Bench evaluates multimodal language and vision-language models on Food-as-Medicine reasoning. It includes 2500 expert-verified instances across 13 health conditions, with two tasks: dish-level suitability assessment (judging if a dish is suitable for a condition) and comparative dish analysis (ranking four dishes by suitability).", "paperTitle": "FAM-Bench: A Multimodal Benchmark for Condition-Aware Food-as-Medicine Reasoning", "primaryDomain": "Biology & Drug Discovery", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://arxiv.org/abs/2605.31410", "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": "2026-05-29", "source": {"authors": ["Mingyang Mao", "Bhargav Rishi Medisetti", "Utkarsh Grover", "Tanvir Ibrahim", "Wenyan Li", "Tingting Zhang", "Xiaomin Lin"], "categories": ["cs.AI"], "id": "2605.31410", "title": "FAM-Bench: A Multimodal Benchmark for Condition-Aware Food-as-Medicine Reasoning", "type": "arxiv", "url": "https://arxiv.org/abs/2605.31410"}, "sourceUpdatedAt": "2026-05-29T15:13:53Z", "topics": ["Multimodal", "Reasoning"], "venueAttempts": [], "whyItMatters": "The benchmark fills a gap in food AI evaluation by testing whether models can integrate ingredient, visual, and clinical nutrition constraints to make condition-aware food decisions. It provides a standardized testbed for comparing models on grounded health-aware reasoning, which is relevant for applications in nutrition guidance and chronic disease management."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
