docs: fix counterfactual-fairness.md's COMPAS numbers to the repo-canonical figures

The COMPAS "biased model" table cited Black 58.15% / White 28.37% /
29.78pp gap. Those numbers appear nowhere else in the repo. The canonical
unfair.py COMPAS result, cited identically by README.md and 8+ other
explainers, is Black 87.16% / White 0.40% / 86.77pp. Replaced the table
with the canonical figures (and matched the "High-Risk Flag Rate" header
wording used elsewhere). The surrounding causal-graph narrative
(CustodyStatus proxy, prior arrests downstream of race, why dropping race
alone didn't help) is unchanged and holds identically. Regenerated the
page, package mirror, and llms-full.txt.

Closes #551

Author: propcgamer20-png

explainers/counterfactual-fairness.html

@@ -217,7 +217,7 @@ <h3 id="the-formal-definition">The Formal Definition</h3>
 <h3 id="concrete-example-compas-recidivism">Concrete Example: COMPAS Recidivism</h3>
 <p>The <a href="../index.html#project-compas"><code>COMPAS/</code></a> audit in this repo is a direct illustration of counterfactual fairness violation - even without using the causal framework explicitly.</p>
 <p>COMPAS assigns recidivism risk scores based on features including prior arrest count, age at first arrest, and custody status. The biased model produces:</p>
-<div class="explainer-table-wrap"><table class="explainer-table"><thead><tr><th>Group</th><th>High-Risk Rate</th></tr></thead><tbody><tr><td>Black defendants</td><td>58.15%</td></tr><tr><td>White defendants</td><td>28.37%</td></tr><tr><td><strong>Fairness Gap</strong></td><td><strong>29.78pp</strong></td></tr></tbody></table></div>
+<div class="explainer-table-wrap"><table class="explainer-table"><thead><tr><th>Group</th><th>High-Risk Flag Rate</th></tr></thead><tbody><tr><td>Black defendants</td><td>87.16%</td></tr><tr><td>White defendants</td><td>0.40%</td></tr><tr><td><strong>Fairness Gap</strong></td><td><strong>86.77pp</strong></td></tr></tbody></table></div>
 <p>Now ask the counterfactual question. Take a Black defendant with 3 prior arrests. Ask: <em>if this person had been white, with the same underlying behaviour and the same 3 prior arrests, would their risk score be the same?</em></p>
 <p>The answer is no - and the reason is <code>CustodyStatus</code>, which the <a href="proxy-variables.html">proxy variables explainer</a> identifies as the key proxy. Black communities have been subject to historical over-policing: for the same underlying behaviour, Black individuals are arrested at higher rates than white individuals. Prior arrest count is therefore not causally independent of race - it is partly <em>caused</em> by race, via differential policing. A model trained on prior arrests is therefore using a variable that race, in part, caused.</p>
 <pre><code>Race ──→ Policing intensity ──→ Arrest rate ──→ Prior arrests ──→ Risk score</code></pre>

explainers/counterfactual-fairness.md

@@ -62,11 +62,11 @@ The [`COMPAS/`](../COMPAS/) audit in this repo is a direct illustration of count
 
 COMPAS assigns recidivism risk scores based on features including prior arrest count, age at first arrest, and custody status. The biased model produces:
 
-| Group | High-Risk Rate |
+| Group | High-Risk Flag Rate |
 |-------|---------------|
-| Black defendants | 58.15% |
-| White defendants | 28.37% |
-| **Fairness Gap** | **29.78pp** |
+| Black defendants | 87.16% |
+| White defendants | 0.40% |
+| **Fairness Gap** | **86.77pp** |
 
 Now ask the counterfactual question. Take a Black defendant with 3 prior arrests. Ask: *if this person had been white, with the same underlying behaviour and the same 3 prior arrests, would their risk score be the same?*
 

faircode/_explainers/counterfactual-fairness.md

@@ -62,11 +62,11 @@ The [`COMPAS/`](../COMPAS/) audit in this repo is a direct illustration of count
 
 COMPAS assigns recidivism risk scores based on features including prior arrest count, age at first arrest, and custody status. The biased model produces:
 
-| Group | High-Risk Rate |
+| Group | High-Risk Flag Rate |
 |-------|---------------|
-| Black defendants | 58.15% |
-| White defendants | 28.37% |
-| **Fairness Gap** | **29.78pp** |
+| Black defendants | 87.16% |
+| White defendants | 0.40% |
+| **Fairness Gap** | **86.77pp** |
 
 Now ask the counterfactual question. Take a Black defendant with 3 prior arrests. Ask: *if this person had been white, with the same underlying behaviour and the same 3 prior arrests, would their risk score be the same?*
 

llms-full.txt

@@ -3294,11 +3294,11 @@ The [`COMPAS/`](../COMPAS/) audit in this repo is a direct illustration of count
 
 COMPAS assigns recidivism risk scores based on features including prior arrest count, age at first arrest, and custody status. The biased model produces:
 
-| Group | High-Risk Rate |
+| Group | High-Risk Flag Rate |
 |-------|---------------|
-| Black defendants | 58.15% |
-| White defendants | 28.37% |
-| **Fairness Gap** | **29.78pp** |
+| Black defendants | 87.16% |
+| White defendants | 0.40% |
+| **Fairness Gap** | **86.77pp** |
 
 Now ask the counterfactual question. Take a Black defendant with 3 prior arrests. Ask: *if this person had been white, with the same underlying behaviour and the same 3 prior arrests, would their risk score be the same?*