▢ Methodology · Public · Versioned
How a score becomes
a score. All of it, in public.
The full scoring methodology, the data sources behind it, and every change we've ever made — version-controlled, dated, and open to argument. If you can argue with the data, you can argue with the score.
01 / FORMULA
The score, in one equation.
Every ingredient is weighted by concentration, regulatory status, and peer-reviewed risk data. The product score is the harmonic mean — so a single high-risk ingredient can't be hidden under a long list of safe ones.
SCORING FUNCTION · v2.4.12026-02-14
S = n / Σ(wi / ti)
where n = ingredient count · wi = position weight
ti = tier safety score beneficial=95 · neutral=70 · concerning=35 · avoid=5
where n = ingredient count · wi = position weight
ti = tier safety score beneficial=95 · neutral=70 · concerning=35 · avoid=5
wiPosition weight from list order.Descending concentration rule (FDA 21 CFR § 701.3). Ingredients above 1% are ordered by weight.
tiTier safety score, 5–95.Mapped from our 4-tier classification: beneficial, neutral, concerning, avoid. Source priority: REACH SVHC > EU Annex II > Manual > USDA FDC > PubChem > AI.
How S maps to the five tiers.
Each cutoff was set so the boundary product is one anyone could argue either way.