Hi @lilyjge - looking here:
https://github.com/castorini/anserini/blob/master/docs/regressions/regressions-bright-biology.md

It says:

wget https://huggingface.co/datasets/castorini/collections-bright/resolve/main/bright-corpus.tar -P collections/
tar xvf collections/bright-corpus.tar -C collections/

The tarball is 297 MB and has MD5 checksum d8c829f0e4468a8ce62768b6a1162158.

But when I fetch the file, the actual checksum I get is 568b594709a9977369033117bfb6889c... doesn't match.

The main README says d8c829f0e4468a8ce62768b6a1162158 as well...
https://github.com/castorini/anserini?tab=readme-ov-file#available-corpora-for-download-5

Am I missing something?