Notes. The results from the test phase of the model trained with GGCs classified according to the Belokurov & Kravtsov (2024) method indicate two distinct populations. Class ‘0’ corresponds to the accreted population, while ‘1’ corresponds to the in situ population. We also recall the following definitions: $\text{precision}=\frac{\mathit{TP}}{TP+FP}$, $\text{recall}=\frac{\mathit{TP}}{TP+FN}$, $\text{f1- score}=\frac{2(precision·recall)}{precision+recall}$, $\text{and accuracy}=\frac{TP+TN}{TP+TN+FP+FN}$, where TP stands for true positive, FP for false positive, TN for true negative, and FN for false negative.