{"ID":5935846,"CreatedAt":"2026-07-07T01:22:02.77346169Z","UpdatedAt":"2026-07-07T02:10:06.972658124Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2607.03109","arxiv_id":"2607.03109","title":"Graph Neural Networks for the Graphical Bootstrap","abstract":"We study a graph classification problem involving over 20 million graphs, arising from high-order perturbative computations of correlators in planar $\\mathcal{N}=4$ super-Yang--Mills, a model closely related to the theory of the strong nuclear force. We benchmark graph neural networks, including graph transformers, achieving robust generalization to larger graphs with up to $99.996\\%$ ROC AUC. Then, we analyze how the models can be used to gain a computational speedup compared to the traditional graphical bootstrap algorithm, through shrinking the redundant data by up to $85.5\\%$ at the level of denominator graphs. Finally, we study the embeddings of the models to investigate their interpretability.","short_abstract":"We study a graph classification problem involving over 20 million graphs, arising from high-order perturbative computations of correlators in planar $\\mathcal{N}=4$ super-Yang--Mills, a model closely related to the theory of the strong nuclear force. We benchmark graph neural networks, including graph transformers, ach...","url_abs":"https://arxiv.org/abs/2607.03109","url_pdf":"https://arxiv.org/pdf/2607.03109v1","authors":"[\"Rigers Aliaj\",\"Gabriele Dian\",\"Reza Doobary\",\"Paul Heslop\"]","published":"2026-07-03T08:45:19Z","proceeding":"hep-th","tasks":"[\"hep-th\",\"cs.LG\"]","methods":"[\"Graph Neural Network\",\"Transformer\"]","has_code":false}