What is Burstiness?
Burstiness is the variation in sentence length and structure across a text. Human writing tends to alternate short and long sentences unpredictably, while AI-generated text is often more uniform — so detectors use low burstiness as a machine signal.
Humans write in bursts: a long winding sentence, then a short one. Then another. Early language models smoothed this out, producing evenly weighted sentences, and detectors learned to flag that uniformity.
Modern models prompted to 'vary sentence length' reproduce burstiness easily, and disciplined human writers — especially in genres with strict style rules — produce low burstiness naturally. The signal degrades from both directions, which is the recurring fate of every output-based detection feature.
Perplexity
Perplexity is a measure of how predictable a piece of text is to a language model. Low perplexity means the model finds each next word unsurprising; AI detectors treat low perplexity as a hint that text was machine-generated.
AI detector false positive
An AI detector false positive is human-written text wrongly flagged as machine-generated. Documented rates are highest for non-native English speakers — one Stanford study found detectors flagged 61% of TOEFL essays as AI-written.