nasa-impact/nasa-science-repos-sme-benchmark
收藏Hugging Face2026-01-15 更新2026-02-07 收录
下载链接:
https://hf-mirror.com/datasets/nasa-impact/nasa-science-repos-sme-benchmark
下载链接
链接失效反馈官方服务:
资源简介:
一个用于评估检索系统在NASA科学仓库发现任务上的基准数据集。该数据集包含专家查询、NASA科学GitHub仓库的语料库以及相关性判断。语料库包含5,264个具有完整元数据的NASA科学GitHub仓库,219个由专家策划的问题,以及253个跨三个NASA科学部门的相关性判断。数据集支持临时检索、代码搜索和问答等任务。
A benchmark dataset for evaluating retrieval systems on NASA science repository discovery tasks. This dataset contains expert queries, a corpus of NASA science GitHub repositories, and relevance judgments. The corpus includes 5,264 NASA science GitHub repositories with complete metadata, 219 expert-curated questions, and 253 relevance judgments across three NASA science divisions. The dataset supports tasks such as ad-hoc retrieval, code search, and question answering.
提供机构:
nasa-impact



