add better findcc figure

.gitattributes

@@ -48,3 +48,4 @@ data/meta_non_web.py filter=lfs diff=lfs merge=lfs -text
 data/sample_bad_urls.py filter=lfs diff=lfs merge=lfs -text
 data/sample_refinedweb_line.json filter=lfs diff=lfs merge=lfs -text
 images/llm360_logo.png filter=lfs diff=lfs merge=lfs -text
+images/findcc.svg filter=lfs diff=lfs merge=lfs -text

common.py

@@ -1,6 +1,6 @@
 from fasthtml.common import *
 from fasthtml.components import *
-from fasthtml.components import D_title, D_article, D_front_matter, D_contents, D_byline
+from fasthtml.components import D_title, D_article, D_front_matter, D_contents, D_byline, D_cite
 from fh_plotly import plotly2fasthtml
 import pandas as pd
 import json
@@ -352,7 +352,7 @@ global_div = Div(
     ),
     Section(
         H3("Stage 4: Finding Connected Components using MapReduce"),
-        Img(src="images/cc.png", style="max-width: 100%;"),
+        Img(src="images/findcc.svg", style="max-width: 100%;"),
         P(
             "The purpose of this step is to create a set of clusters of matching pairs. For example, a list of pairs (A, B), (B, C), (D, E) is merged into a list of components (A, B, C) and (D, E). Using a third-party library like NetworkX to find connected components would require all pairs to fit into the memory of a single machine, which is not feasible. Instead, we implemented a distributed connected component finder [4] using the Dask framework, which can scale across multiple machines. The algorithm works by mapping edges by both the source and destination of pairs and reducing only edges where the source is greater than the destination. It performs successive iterations of this MapReduce computation until convergence, meaning the number of new edges produced becomes zero. In the end, every document in a cluster points to the smallest document within the cluster. Later, we compile a list of duplicate documents that need deletion and gather statistics about each component."
         ),