[Discussion] How to improve track / stem separation ?

Hi all, I usually use the 5stems model, and I would like to know the following
1) Why "other" stem contains guitar and piano/keyboards together and the "piano" stem contains only artefacts of piano sound, and my "bass" stem is usually muddy. How to obtain a better separation of those instruments?

2)Would tweaking the musdb_config.json (as in *musdb18 #81" not yield better results than the original?

3)Why are base_config.json used for all stem models? Would using the "finetune" versions not yield better instrument separation.?

4)is there a difference between using musdb or musdb18 ??

I've been trying to wrap my head around this for a while I'm a little confused, Thank you for shedding some light.

Start by reading musdb_config.json, base_config.json, and the finetune configuration references mentioned in the discussion, then compare the musdb and musdb18 setups. Review how the 5stems model produces the other, piano, and bass stems. Done would be a documented explanation of the configuration and dataset differences, or a clearly scoped improvement proposal.

Written by the indexing model from the issue text.