From 8d8a283d869b2523d009b9a056c2e21a32ec664a Mon Sep 17 00:00:00 2001
From: Isaac Ju <54259248+IsaacJu-debug@users.noreply.github.com>
Date: Sat, 14 Jan 2023 17:54:27 -0800
Subject: [PATCH] Update index.md

Correct the invalid link to the interactive web simulation tool for showcasing d-separation
---
 representation/directed/index.md | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/representation/directed/index.md b/representation/directed/index.md
index 9746ed3..602eae0 100644
--- a/representation/directed/index.md
+++ b/representation/directed/index.md
@@ -91,7 +91,7 @@ Let $$Q$$, $$W$$, and $$O$$ be three sets of nodes in a Bayesian Network $$G$$.
 
 For example, in the graph below, $$X_1$$ and $$X_6$$ are $$d$$-separated given $$X_2, X_3$$. However, $$X_2, X_3$$ are not $$d$$-separated given $$X_1, X_6$$, because we can find an active path $$(X_2, X_6, X_5, X_3)$$
 
-A former CS228 student has created an [interactive web simulation](http://pgmlearning.herokuapp.com/dSepApp) for testing $$d$$-separation. Feel free to play around with it and, if you do, please submit any feedback or bugs through the Feedback button on the web app.
+A former CS228 student has created an [interactive web simulation](https://web.archive.org/web/20211018095256if_/http://pgmlearning.herokuapp.com/dSepApp) for testing $$d$$-separation. Feel free to play around with it and, if you do, please submit any feedback or bugs through the Feedback button on the web app.
 
 The notion of $$d$$-separation is useful, because it lets us describe a large fraction of the dependencies that hold in our model. Let $$I(G) = \{(X \perp Y \mid Z) : \text{$X,Y$ are $d$-sep given $Z$}\}$$ be a set of variables that are $$d$$-separated in $$G$$.