We built an AI-text detector that contains no AI.
That isn't a marketing line, it's a structural one. Almost every detector in use asks a language model how likely a language model was to have produced the text. That is circular, and the circularity is why they fail.
You cannot establish ground truth about machine-generated text using a machine that generates text.
So we took the generative model out of the measurement path entirely. Proofline measures structure — arithmetic computed directly from the characters. No inference, no learning model for meaning, no generative technology. Same text, same numbers, any machine, forever.
Measured on 2,000 human and 2,000 machine-written English student essays, held out from the reference set:
- ROC-AUC 0.9872
- 95.5% detected at a 5% false-positive rate (95% CI 94.6-96.4)
- 78.8% detected at a 1% false-positive rate
Plus a signed benchmark across 30 adversarial RAID configurations — code, German and Czech — at mean AUC 0.9302.
What we need is the world's assessment and choice of adoption. We have no funds, no benefactors and everything to lose.
We are one code for handling e-mails and registration away from complete deployment.
We'd love some help. Thank you all.