Testing Performance

[FloofCat]

Hi @liamdugan,

We're trying to actively test two of our new frameworks on RAID. Please allow for evaluation as soon as possible!

Thank you!

[github-actions]

Eval run succeeded! Link to run: link

Here are the results of the submission(s):

divi

Release date: 2025-05-03

I've committed detailed results of this detector's performance on the test set to this PR.

On the RAID dataset as a whole (aggregated across all generation models, domains, decoding strategies, repetition penalties, and adversarial attacks), it achieved a TPR of 59.30% at FPR=5%.
Without adversarial attacks, it achieved a TPR of 76.95% at FPR=5%.

divi-pro

Release date: 2025-05-03

I've committed detailed results of this detector's performance on the test set to this PR.

On the RAID dataset as a whole (aggregated across all generation models, domains, decoding strategies, repetition penalties, and adversarial attacks), it achieved a TPR of 79.29% at FPR=5%.
Without adversarial attacks, it achieved a TPR of 92.85% at FPR=5%.
If all looks well, a maintainer will come by soon to merge this PR and your entry/entries will appear on the leaderboard. If you need to make any changes, feel free to push new commits to this PR. Thanks for submitting to RAID!

[FloofCat]

Interesting. I have a few other models that I'll be pushing soon for evaluation.

Thanks, please don't push to the leaderboard yet.

[FloofCat]

@liamdugan,

Please allow for evaluation of the same.

[liamdugan]

Yep @FloofCat the bot's comment from earlier was updated with the newly evaluated scores!

[FloofCat]

Closing, will open a new PR for updated results soon.