ICCMA 2023 Benchmarks

该数据集包含329个实例，用于评估神经网络模型在各种关于论点可接受性的决策问题上的性能。该数据集利用基于SAT的求解器来计算论点的可接受性状态，并在不同的决策问题中，对测试集进行了变化。规模上，该数据集共有329个实例，其任务是在抽象论证框架中评估论点可接受性的神经网络模型。This dataset comprises 329 instances, tailored for evaluating the performance of neural network models across diverse decision-making problems concerning argument acceptability. It employs SAT-based solvers to compute the acceptability states of arguments, and the test splits are adjusted for different decision-making tasks. In terms of scale, this dataset contains a total of 329 instances, whose core objective is to evaluate neural network models for argument acceptability within abstract argumentation frameworks.