Data for "Data distribution matters: enhancing model generalization in data-driven materials discovery by intentionally exploiting both positive and negative data"

If you use this data, please cite our paper: @article{Acta Physico-Chimica Sinica, title={Data distribution matters: enhancing model generalization in data-driven materials discovery by intentionally exploiting both positive and negative data}, author={Yiheng Wu 1,2, Lijun Liu 1, Wei Deng 1, Haodong Jiang 1,2, Ruotong Li 1,2, Ming Hu 1, Bo Peng 1,, Dapeng Wang 1,2, 1 State Key Laboratory of Polymer Science and Technology, Changchun Institute of Applied Chemistry, Chinese Academy of Sciences, Changchun 130022, Jilin Province, China. 2 School of Applied Chemistry and Engineering, University of Science and Technology of China, Hefei 230026, Anhui Province, China. }, journal={Acta Physico-Chimica Sinica}, year={2026} }若使用本数据集，请引用我们的论文：@article{《物理化学学报（Acta Physico-Chimica Sinica）》, title={数据分布至关重要：通过有意识地利用正负样本数据（positive and negative data）提升数据驱动的材料发现（data-driven materials discovery）中的模型泛化能力（model generalization）}, author={吴一恒1,2, 刘立军1, 邓伟1, 姜浩东1,2, 李若彤1,2, 胡明1, 彭博1, 王大鹏1,2, 1 中国科学院长春应用化学研究所高分子科学与技术国家重点实验室，吉林长春130022，中国。2 中国科学技术大学应用化学与工程学院，安徽合肥230026，中国。}, journal={《物理化学学报（Acta Physico-Chimica Sinica）》}, year={2026} }