Question about baseline results: inconsistent between MRR and Hits@1?

[PlusRoss]

Hi,

Thanks for the amazing work. I notice that in Table 2 "Original" row: the MRR values equal the Hits@1 values in the results of m-TransH and RAE. This seems strange since according to the calculation of MRR, we have MRR >= Hits@1 + (Hits@10-Hits@1)*1/10. For example, the MRR of m-TransH in the wikipeople dataset should at least be 0.06+(0.3-0.06)/10 = 0.084 instead of 0.06. Is there anything I miss?