question on background peak selection

Thanks for creating chromVAR, I have a question about whether the average accessibility or summed accessibility across cells were used in background peak selection? Maybe I missed something and please correct me if I am wrong, in the paper it mentioned the average accessibility whereas in the line 127 at script https://github.com/GreenleafLab/chromVAR/blob/master/R/background_peaks.R the summed fragment per peaks was used. Looking forward to hearing from you! Thanks!