We apply a generative AI pattern-recognition technique called PatternBoost to study bootstrap percolation on hypercubes. With this, we slightly improve the best existing upper bound for the size of percolating subsets of the hypercube.

翻译：我们应用一种名为PatternBoost的生成式人工智能模式识别技术来研究超立方体上的自举渗透过程。通过该方法，我们略微改进了超立方体渗透子集尺寸的现有最佳上界。