发表机构
CERN; University of Zurich; Northwestern University; Massachusetts Institute of Technology（欧洲核子研究组织; 苏黎世大学; 西北大学; 麻省理工学院）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本文利用多任务模型NuCLR的留出集成研究电荷半径和电四极跃迁强度，通过共享表示提升预测精度，达到与最先进核模型相当的水平，并作为核结构的数据驱动勘察者。
AI 中文摘要
低能核结构编码在核素图中广泛的实验信息中。学习这些信息如何在可观测量和原子核之间组织，可以为理论外推和实验设计提供数据驱动的经验基线。在此，我们基于NuCLR（核协同学习表示）——一个核数据的多任务模型——开发了留出集成，以研究电荷半径和电四极跃迁强度。折外（OOF）验证表明，共享表示比单任务学习提高了性能，在数百个核素上，电荷半径的均方根偏差为0.0147飞米，B(E2)的均方根偏差为0.192 e²b²，与最先进的核模型相当。我们的误差条估计了核素图上预期的预测精度，突出了新数据将编码超出学习模式的信息的区域。因此，NuCLR充当了核结构的数据驱动勘察者，并朝着核素图的共享、多可观测量基础模型迈出了一步。
英文摘要
Low-energy nuclear structure is encoded in a broad body of experimental information across the chart of nuclides. Learning how this information is organized across observables and nuclei can provide a data-driven empirical baseline for theoretical extrapolations and experimental design. Here, we develop held-out ensembles based on NuCLR (Nuclear Co-Learned Representations), a multi-task model of nuclear data, to study charge radii and electric-quadrupole transition strengths. Out-of-fold (OOF) validation shows that shared representation improves performance over single-task learning, yielding a charge-radius $\mathrm{RMS}$ deviation of $0.0147~{\rm fm}$ and a $\mathrm{B(E2)}$ $\mathrm{RMS}$ deviation of $0.192~e^2{\rm b}^2$ across hundreds of nuclides, competitive with state-of-the-art nuclear models. Our error bars estimate the expected prediction accuracy across the nuclear chart, highlighting regions where new data would encode information beyond the learned patterns. NuCLR thus serves as a data-driven surveyor of nuclear structure and a step toward a shared, multi-observable foundation model of the nuclear chart.
Comments15 pages, 7 figures, 2 tables
