Hi @CHELSEA234,
I'm currently exploring the dataset using the provided text files to follow the exact evaluation protocols. However, I noticed a small issue: some of the live IDs listed in the text files (e.g., “live_902”) do not appear in the actual Live dataset.
Could you please clarify how you handled these missing IDs? Should I simply ignore them during the data split?
Hi @CHELSEA234,
I'm currently exploring the dataset using the provided text files to follow the exact evaluation protocols. However, I noticed a small issue: some of the live IDs listed in the text files (e.g., “live_902”) do not appear in the actual Live dataset.
Could you please clarify how you handled these missing IDs? Should I simply ignore them during the data split?