noise-audit

To quantify decision noise, this Skill spawns three independent jury tasks to evaluate the same material, then calculates the mean, standard deviation, and range to reveal variance and inconsistency in reviewer judgments.

The independent jury method for auditing decision quality spawns three separate noise_judge tasks to produce diverse evaluations, highlighting high-noise scenarios where biased conclusions or inconsistent assessments risk occurring.

To detect bias and inconsistency across multiple reviewers, aggregate their independent judgments to compute variance metrics, producing a Noise Variance table that highlights divergence and prompts deeper review.

Yes, you can use variance metrics to identify high-noise scenarios by calculating the mean, standard deviation, and range of independent judgments, which reveals when decision-making processes require additional review.

To interpret a Noise Variance table for risk awareness, you need the mean, standard deviation, and range of the independent judgments, which collectively quantify the variance and highlight high-risk divergence.

You should not use an independent jury approach for decision auditing when you cannot spawn three separate noise_judge tasks, as the variance metrics rely on aggregating multiple independent judgments to function accurately.