Judge - Participant Benchmark Repository

The judge-participant benchmark repository is a collection of score matrices simulated using the Lens Model Framework. It consists of 2-dimensional matrices with evaluation scores assigned by each judge to the assigned participant. Each zipped folder (named after the size of the matrices) consists of the following - 1. 2000 sparse matrices (names starting with 'SM') of varying sparsity by 20 levels 2. 100 full matrices (names starting with "FM') from which the sparse matrices have been systematically derived from 3. Correlation values (names starting with 'Results_corr') that contain values of Kendall's Tau, capturing values of correlation between ranking vectors

评委-被试基准仓库（judge-participant benchmark repository）是一套基于透镜模型框架（Lens Model Framework）模拟生成的评分矩阵集合。该集合包含二维矩阵，其中每位评委都会为其分配的被试赋予评估评分。每个以矩阵尺寸命名的压缩文件夹均包含以下内容：1. 2000个稀疏矩阵（文件名以"SM"开头），涵盖20个不同稀疏度等级；2. 100个全矩阵（文件名以"FM"开头），所有稀疏矩阵均由这些全矩阵系统性衍生得到；3. 以"Results_corr"开头命名的相关度文件，其中包含肯德尔τ相关系数（Kendall's Tau）的数值，用于表征排序向量之间的相关性水平。