---
title: Scoring
description: How the 0–100 human-likeness score is computed, and which findings charge it.
icon: gauge
---

Every result carries a **human-likeness score** from 0 to 100. Higher is more
human.

## What charges the score

Only findings from **detection**-intent rules — the subset corpus-validated to
distinguish AI-generated from authentic human legal prose.

[Style](/docs/concepts/rules#intent-which-rules-move-the-score)-intent findings
are reported and fixed like any other, but charge nothing. A document full of
semicolons and Oxford commas can still score 100.

## The formula

Each charging diagnostic contributes a base penalty by severity, multiplied by
its own weight (default 1):

| Severity | Base penalty |
| -------- | ------------ |
| `error` | 5 |
| `warning` | 3 |
| `suggestion` (and legacy `info`) | 1 |

Those penalties are summed, normalized per 1,000 words, and decayed:

```txt
penalty  = Σ (base_penalty × weight)
density  = penalty ÷ word_count × 1000
score    = round(100 × e^(−density ÷ 100))   clamped to 0…100
```

Two consequences follow from the shape of that curve.

<Columns cols={2}>
  <Column>
    **Length does not help.** Normalizing per 1,000 words means the score
    measures issue *density*. Padding a document with clean paragraphs to dilute
    its findings does not work.
  </Column>
  <Column>
    **The decay is smooth.** There is no cliff, and no threshold to game — the
    score falls off continuously, so removing any single finding always moves it
    in the right direction.
  </Column>
</Columns>

## Weights

Density rules — [`no-hedging`](/docs/rules/no-hedging),
[`no-em-dash-overuse`](/docs/rules/no-em-dash-overuse) — charge in proportion to
how far past their threshold the text runs, rather than a flat penalty per
match. A document slightly over the hedging threshold is charged slightly; one
far over is charged far more.

## Worked example

A 100-word passage with one `warning`-severity detection finding of weight 2:

```txt
penalty  = 3 × 2            = 6
density  = 6 ÷ 100 × 1000   = 60
score    = round(100 × e^(−0.6)) = 55
```

## Reading it honestly

The score is a density measurement of specific, enumerated patterns. It is not
a classifier, and it does not claim to detect AI authorship.

:::warning
Do not use the score as evidence that a document was machine-written. Human
writers produce high-scoring prose in the same house styles the detection rules
target, and a careful editor can move any document's score without changing who
wrote it.
:::

The useful reading is comparative: the same author's before and after, or one
draft against another.