Testing an AI content detector on held-out data v1

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.

Authors

Publication Details

Published
2026-11-12
DOI
https://doi.org/10.17504/protocols.io.r3l25mzbpl1y/v1
Primary Topic
Digital Media Forensic Detection
Type
preprint
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
preprint

Testing an AI content detector on held-out data v1

Stephen Harmston
Digital Media Forensic Detection
preprint

Testing an AI content detector on held-out data v1

Stephen Harmston
preprint en

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.

Digital Media Forensic Detection
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon