Detection Threshold

A detection threshold is the numerical boundary that separates outputs labeled 'likely AI' from outputs labeled 'likely human' in a detector's results. If a detector produces a continuous probability score between 0 and 100, setting the threshold at 50 means any input scoring above 50 is classified as AI. Setting it higher at 80 makes the detector stricter — fewer human texts get wrongly flagged (lower false positive rate) but more AI texts slip through (higher false negative rate). Lowering the threshold has the opposite effect.

Most end users never see or adjust the threshold directly; it is baked into the detector's default output. But the threshold is where detection policy decisions get made. A university using Turnitin may implicitly accept its default threshold; a content platform using Originality.ai at scale may calibrate a custom threshold against their own acceptable error rate. No threshold setting eliminates errors entirely — the choice is about which type of error you prefer to accept.

For users producing AI-assisted content, understanding detection thresholds informs the revision target. If you know your destination platform uses a 40% threshold, bringing your score below 30% gives you a margin of safety. If the platform uses an 80% threshold, scores up to 70% may be acceptable without further editing. Coda One's AI Detector displays the raw probability score rather than a binary label precisely because different downstream contexts have different thresholds — the score lets users make context-appropriate decisions rather than accepting a one-size-fits-all verdict.