We invest in rigorous research to advance reliable AI detection. Browse our published work to learn how we architect low false positive systems, extend coverage to new modalities, and support enterprise and education teams worldwide.
An inside look at Pangram Text, our transformer-based detector trained with hard negative mining to deliver industry-leading accuracy on AI-written content.
Read the paperIntroduces evaluation benchmarks for large-scale moderation pipelines and shares deployment learnings from publishers and trust & safety teams.
Read the paperDetails our multilingual extensions, covering data strategy, training curriculum, and performance across 44 languages.
Read the paper
