Posterior probability distribution, trained on the D1 dataset (dn/dz selection, left) and on the D2 dataset (no dn/dz selection, right) (Table 2). These datasets have fixed γ cluster evolution parameters. Four MDNs are trained per dataset each on a different survey area. These results are computed for the same target testing XOD, always of the appropriate survey size, that was produced letting all 8 parameters free and verifying the dn/dz selection.