We introduce Many ANnotated TRAnsients (MANTRA), an annotated data set of 4869 transient and 71207 non-transient object light curves built from the Catalina Real-time Transient Survey. We provide public access to this data set as a plain text file to facilitate standardized quantitative comparison of astronomical transient event recognition algorithms. Some of the classes included in the data set are: supernovae, cataclysmic variables, active galactic nuclei, high proper motion stars, blazars, and flares. As an example of the tasks that can be performed on the data set we experiment with multiple data preprocessing methods, feature selection techniques, and popular machine-learning algorithms (support vector machines, random forests, and neural networks). We assess quantitative performance in two classification tasks: binary (transient/non-transient) and eight-class classification. The best-performing algorithm in both tasks is the random forest classifier. It achieves an F1 sco...

中文翻译：

---

MANTRA：用于天文瞬态事件识别的机器学习参考光曲线数据集

我们介绍了许多带注释的瞬态（MANTRA），这是一个由Catalina实时瞬态测量构建的4869个瞬态和71207个非瞬态对象光曲线的带注释数据集。我们以纯文本文件的形式提供对此数据集的公共访问，以促进天文瞬态事件识别算法的标准化定量比较。数据集中包括的一些类别是：超新星，大灾变，活跃的银河原子核，高适速运动恒星，火星和耀斑。作为可以在数据集上执行的任务的示例，我们尝试了多种数据预处理方法，特征选择技术和流行的机器学习算法（支持向量机，随机森林和神经网络）。我们评估两个分类任务中的量化绩效：二进制（瞬态/非瞬态）和八类分类。两项任务中表现最佳的算法是随机森林分类器。它达到了F1得分...