R5 — Output tiers, not precise scores

Rule: The widget output is a small set of relative-difficulty tiers (~3-4). Never a numeric score, percentage, or precise dollar figure.

Why: (a) Self-report error is irreducible — Parry 2021 meta-analysis (Parry et al. 2021 — pre-registered meta-analysis: self-report ≠ logged media use) shows weak self-vs-logged correlations even with sincere effort. (b) The bias direction is upward (overplacement), so any precise score inherits the inflation. (c) Tiers are robust to residual bias in a way scores are not. (d) Tiers also gain the precision-without-false-precision benefits described in the presentation brief Research brief: SMB widget presentation layer — tiered results without overclaiming (June 2026).

How to apply: All widget outputs land in {Low / Moderate / High / Very High} difficulty tiers — never 47/100, never $X-Y, never percentile.