Hi,
I'm looking into the list.csv file as described in the training/ directory's README and had a question about the HASH column (defined as a "unique 6-digit hash for the sequence").
Could you please elaborate on how these 6-digit hash values are generated? I'm particularly interested in the specific algorithm or procedure used to ensure both the 6-digit format and the uniqueness for each sequence.
Any details on this process would be greatly appreciated.
Thanks!