Reliable Dataset of Partition Function Problems

该数据集包含672个问题，旨在评估计算分割函数算法的性能。这些数据是通过猜想值和可靠算法构建的。数据集包括具有准确结果和基于不完全执行输出的基准测试，并采用了一个评分函数（TAP分数）以确保公平比较。规模上，该数据集共有672个问题，其任务是对分割函数计算算法进行排名和评估。

This dataset contains 672 questions, designed to evaluate the performance of algorithms for computing partition functions. These data were constructed using conjectured values and reliable algorithms. The dataset includes benchmarks with both exact results and outputs based on incomplete executions, and employs a scoring function (TAP score) to ensure fair comparisons. In terms of scale, this dataset has a total of 672 questions, and its core task is to rank and evaluate algorithms for partition function calculation.