Most open-source AI detectors can't hold a 0.5% false-positive rate [P]

We needed to know where the open-source AI-detection field actually stands, so we ran every notable open detector through the same protocol. Setup: - Public data only: Jabarian & Imas 2025 (NBER), Liang 2023 TOEFL essays, a 1,060-text frontier set (GPT-5.x, Claude Opus 5, Gemini 3.x), 5,000 pre-LLM