AI 中文总结
该研究针对AI智能体介导营养研究的数据歧义问题，提出NDS基础设施，实现FAIR原则，在基准测试中表现优于现有模型，保障分析可复现，为相关研究提供新型数据支撑。
AI 中文摘要
AI智能体可加快营养研究进程，但其分析会继承底层数据的标识、语义和发布歧义问题。我们提出营养数据服务（Nutrition Data Service, NDS），这是一种保留数据源的基础设施，用于为自动化应用实现FAIR原则：描述解析使特定发布的记录可被发现；类型化跨表连接独立发布的资源；机器可读接口公开版本化源数据和跨表，使AI智能体的分析可复现且可审计。在食物描述基准测试中，NDS展现出出色的保留准确率，且在NutriBench上的表现优于已发表的最佳语言模型结果。外部盲测跨表评估显示，其类型化契约支持合理的链接并拒绝无依据的映射。在个人水平血糖指数分析中，固定的NDS输入在不同模型及重复运行中产生完全相同的输出，而开放网络重建则不稳定。核心结论是，智能体介导的营养研究需要一种针对数据标识、搜索和跨表的新型数据基础设施。
英文摘要
AI agents can accelerate nutrition research, but their analyses inherit the identity, semantic, and release ambiguities of the underlying data. We present Nutrition Data Service (NDS), source-preserving infrastructure that operationalizes FAIR for automated use: description resolution makes release-specific records findable; typed crosswalks connect independently released resources; machine-readable interfaces expose versioned sources and crosswalks, supporting replayable and auditable analyses. On food-description benchmarks, NDS outperforms the best published language-model result on NutriBench. External and blinded crosswalk evaluations show that its typed contract favors defensible links and rejects unsupported mappings. In a person-level glycemic-index analysis, pinned NDS inputs produce identical outputs across models and repeated runs, while open-web reconstruction remains unstable. Together, these results show that agent-mediated nutrition research requires a new infrastructure that makes data identity, search, and crosswalk policy explicit.
