CNV scores in infercnvpy

Hello, first of all I wante dto ask if the matrix in data.obsm[”X_cnv”] corresponds to the slot in R: infercnv_obj@expr.data.

Secondly how are cnv scores calculated starting from this matrix by the function infercnvpy.tl.cnv_score?

It says: “Ths score is currently simply defined as the mean of the absolute values of the CNV scores in each cluster”.
If I take the row means of the abs values of data.obsm[”X_cnv”] I don’t get the same values.
Thanks