Request for code for reproducing full-shot baselines from Appendix A

[bthecohen]

Hello,

Thank you so much for all the work in contributing this benchmark to the community! In Appendix A of your paper, you mention performing sweeps on various statistical and deep learning models in Statsforecast and GluonTS (presumably the models that appear on the leaderboard). I was wondering if it might be possible to open source the scripts for these sweeps – I think it'd help with overall reproducibility and would also establish a standardized way to measure baselines on novel datasets. Thanks!