Detector submission update

[kprofundis]

Independent research detector. Display name set via metadata.json. GitHub: https://github.com/KProfundis

[github-actions]

Eval run succeeded! Link to run: link

Here are the results of the submission(s):

ODean v17z+soul

Release date: 2026-05-04

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 89.97 and a TPR of 57.91% at FPR=5% and 39.89% at FPR=1%.
Without adversarial attacks, it achieved AUROC of 93.02 and a TPR of 67.97% at FPR=5% and 48.60% 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!

[liamdugan]

@kprofundis thanks for the submission and the kind message! Let me know if you'd like this to be merged.

[kprofundis]

hey Liam! thank you for testing. could you merge my last results, that was aur 93? the V14 model? i‘m going to be fixing the bug in this recent submission but would love to see my previous score on the leadership board!

[liamdugan]

Sure thing @kprofundis , I reopened your previous PR #124 and kicked off eval. Once that's done I'll ask for a final approval from you on that thread.

[kprofundis]

Thank you! I’ll keep an eye out for that message

[github-actions]

Eval run succeeded! Link to run: link

Here are the results of the submission(s):

ODean v17z+soul × v14 routed-merge v2

Release date: 2026-05-04

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 94.30 and a TPR of 82.76% at FPR=5% and 69.20% at FPR=1%.
Without adversarial attacks, it achieved AUROC of 96.92 and a TPR of 90.66% at FPR=5% and 80.90% 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!

[github-actions]

Eval run succeeded! Link to run: link

Here are the results of the submission(s):

Kareem Elsamadicy (Independent Researcher)

Release date: 2026-05-04

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 92.93 and a TPR of 82.42% at FPR=5% and 71.89% at FPR=1%.
Without adversarial attacks, it achieved AUROC of 96.63 and a TPR of 90.10% at FPR=5% and 81.74% 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!