# Stylometry and AI-text detector limits > Source-anchored research for Stylometry and AI-text detector limits. Run status: COMPLETED. Parent: [Measuring LLM lexical tics: excess vocabulary, baselines, drift](https://llms-explorer.com/tree/ai-isms-tic-measurement/) · 3 facets · 5 facts · page: https://llms-explorer.com/tree/stylometry-and-ai-text-detector-limits/ ## Measurements and reference values - A 2025 audit (Jabarian & Imas, Chicago Booth) found Pangram, GPTZero and Originality.ai each under 1% false positives on human text, with false negatives of 2-4% (Pangram), 0-2% (GPTZero), 10-40% (Originality.ai); open-source RoBERTa was near random. All detectors lost accuracy on passages under 50 words. (medium confidence) (verified as of 2025-12-02) — [source](https://www.chicagobooth.edu/review/do-ai-detectors-work-well-enough-trust) ## Comparisons and alternatives - On 135,389 original vs professionally edited non-native academic manuscript pairs, 13 detectors (token-statistics, zero-shot, classifier) gave false-positive rates from 0.0% to 100.0% on identical human-written text; edit ratio correlated with score shifts (Spearman rho -0.418 to +0.343). Detectors partly measure linguistic polish, not origin. (medium confidence) (verified as of 2026-08-27) — [source](https://arxiv.org/html/2608.26710v1) - Detector accuracy collapses roughly 25-50 percentage points on paraphrased, humanized, hybrid or lightly edited text versus unmodified LLM output. (medium confidence) (verified as of 2026-08-21) — [source](https://timrequarth.substack.com/p/why-you-shouldnt-trust-ai-detector) ## Facts and statements - Detectors are better suited to population-level inference than to individual accusation; rescanning the same text can give inconsistent verdicts, and small per-document false-positive rates compound at scale. (medium confidence) — [source](https://timrequarth.substack.com/p/why-you-shouldnt-trust-ai-detector) - Detector performance is expected to drift as detectors, LLMs and humanizer tools compete; the Chicago Booth authors recommend regular re-audits. (medium confidence) — [source](https://www.chicagobooth.edu/review/do-ai-detectors-work-well-enough-trust)