发表机构
Beijing National Laboratory for Condensed Matter Physics and Institute of Physics, Chinese Academy of Sciences; Condensed Matter Physics Data Center, Chinese Academy of Sciences; Shanghai Artificial Intelligence Laboratory; University of Science and Technology of China; Fudan University（中国科学院物理研究所; 中国科学院凝聚态物理数据中心; 上海人工智能实验室; 中国科学技术大学; 复旦大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
X2SBench是一个开放基准，通过大规模模拟与实测数据结合，评估粉末衍射晶体结构测定方法，并揭示实验迁移差距。
AI 中文摘要
面向实际应用的粉末X射线衍射（PXRD）结构测定进展需要超越小晶体和理想化图谱的评估。X2SBench结合了152,587个模拟结构-图谱对与591个精选实测数据，将评估扩展到更大晶胞、更低对称性结构和多样化组成。固定的数据划分、明确的输入和通用的结构度量支持按晶系、原子数和元素数进行比较。联合分层在这些组内定位弱点。在558个配对目标上，经X2SBench微调的模型提高了从模拟图谱中恢复结构的能力，但在实测输入上精度下降，揭示了实验迁移的差距。背景扣除和平滑处理提高了所测试检查点的恢复效果，而数据增强和参考晶格比较为进一步的测量适应和可靠的晶胞估计提供了机会。开放平台提供数据访问和标准化结果提交，为社区评估和迈向实用PXRD分析建立了共同基础。
英文摘要
Progress towards practical powder X-ray diffraction (PXRD) structure determination requires evaluation beyond small crystals and idealized patterns. X2SBench combines 152,587 simulated structure-pattern pairs with 591 curated measurements, extending evaluation to larger cells, lower-symmetry structures and diverse compositions. Fixed splits, defined inputs and common structural metrics support comparisons by crystal system, atom count and element count. Joint stratification locates weaknesses within these groups. On 558 paired targets, an X2SBench-fine-tuned model improves recovery from simulated patterns but loses accuracy on measured inputs, revealing a gap in experimental transfer. Background subtraction and smoothing improve recovery for one tested checkpoint, while augmentation and reference-lattice comparisons identify further opportunities for measurement adaptation and reliable cell estimation. An open platform provides data access and standardized result submission, establishing a shared basis for community evaluation and progress towards practical PXRD analysis.
CommentsThis submission is being withdrawn because confirmation of all co-authors' consent to public posting has not yet been obtained
