Year: 2026
Type: preprint
Abstract: How AI Aware measures the accuracy of its text, image/video and audio detectors. The same method produced our published results: 98.6% on 10,334 held-out texts, 99.4% on 43,106 held-out images, and 97.6% on audio.
Author: Stephen Harmston
Language: English
Subfield: Computer Vision and Pattern Recognition
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W7225986163
