Microblogs are a popular way for users to communicate and have recently caught the attention of researchers in the natural language processing (NLP) field. However, regardless of their rising popularity, little attention has been given towards determining the properties of discourse relations for the rapid, large-scale microblog data. Therefore, given their importance for various NLP tasks, we begin a study of discourse relations on microblogs by focusing on evidence relations. As no annotated corpora for evidence relations on microblogs exist, we conduct a corpus study to identify such relations on Twitter, a popular microblogging service. We create annotation guidelines, conduct a large-scale annotation phase, and develop a corpus of annotated evidence relations. Finally, we report our observations, annotation difficulties, and data statistics.