How does neuralforecast behave with sequences shorter than input_size? Are they padded or skipped/ignored or masked in some way?

Hi @Manuel. Yes, the time series are padded with zeros at the beginning

Thanks @Cristian (Nixtla)! If short sequences have exogenous variables (e.g. futr_exog), how are they handled? Do they get filled with zero as well?

all temporal variables are padded at the beginning of the time series

So, theoretically, instead of letting everything automatically pad with zero, might it be better to manually pad the time series with zero and create an exogenous binary variable such as "is_padding" to indicate to the model that that is a padding?