发表机构
Lawrence Livermore National Laboratory; FAIR at Meta（劳伦斯利弗莫尔国家实验室; Meta人工智能研究院）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
PolyBench26是一个开放基准，包含近25万个聚合物性能数据点，支持四项评估任务，发现基于图的模型在性能预测中误差最低且稳健，为复杂聚合物设计提供可复现基础。
AI 中文摘要
聚合物性能预测缺乏开放、标准化的基准，这些基准能够对机器学习方法进行严格比较，而现有资源仅覆盖了聚合物架构的狭窄部分，例如均聚物。我们引入了聚合物基准2026（PolyBench26），这是一个开放数据集，包含近25万个聚合物性能数据点，涵盖八种物理性能，包括来自实验测量、密度泛函理论和分子动力学的数据。该基准支持均聚物以及交替、无规和嵌段共聚物的四项评估任务：分布内性能预测、数据集规模缩放、重复单元复杂度以及对保留聚合物架构的迁移。我们比较了语言模型、基于图的方法和基于描述符的方法，发现基于图的模型在性能预测中提供最低误差，在评估的训练集规模中保持其优势，并且对重复单元复杂度的增加保持稳健。PolyBench26为开发日益复杂的聚合物设计空间的模型提供了可复现的基础。PolyBench26基准在https://github.com/rlearsch/PolymerBenchmark2026上开源提供。
英文摘要
Polymer property prediction lacks open, standardized benchmarks that enable rigorous comparison of machine-learning methods, with existing resources covering only a narrow fraction of polymer architectures, such as homopolymers. We introduce Polymer Benchmark 2026 (PolyBench26), an open dataset comprising nearly 250,000 polymer-property datapoints across eight physical properties, including data from experimental measurements, density functional theory, and molecular dynamics. The benchmark supports four evaluation tasks across homopolymers and alternating, random, and block copolymers: in-distribution property prediction, dataset-size scaling, repeat-unit complexity, and transfer to held-out polymer architectures. We compare language model, graph-based, and descriptor-based approaches and find graph-based models provide the lowest errors in property prediction, retain their advantage across the evaluated training-set sizes, and remain robust to increasing repeat-unit complexity. PolyBench26 provides a reproducible foundation for developing models for the increasingly complex polymer design space. The PolyBench26 benchmark is available open-source at https://github.com/rlearsch/PolymerBenchmark2026.
