New checkpoints and voting strategy

[Seven178178]

I have been fine-tuning the model and optimizing its decision strategy recently; this commit represents a new version of checkpoint and voting strategy.

I forgot to add the voting strategy to the previous pull request(#113), so I closed it and created a new one.

[github-actions]

Eval run succeeded! Link to run: link

Here are the results of the submission(s):

Zhuque AI Detection Assistant

Release date: 2026-04-14

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 an AUROC of 99.83 and a TPR of 99.80% at FPR=5% and 98.33% at FPR=1%.
Without adversarial attacks, it achieved AUROC of 99.94 and a TPR of 99.95% at FPR=5% and 99.43% at FPR=1%.

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!

[Seven178178]

Please merge my result, thank you.

[liamdugan]

@Seven178178 Sure thing! congrats on the strong performance again