update figure 4 title

README.md

@@ -84,7 +84,7 @@ The pipeline has eight steps:
 
 
 ![data_radar_v0](https://cdn-uploads.huggingface.co/production/uploads/6882f57510e86d9f80580702/82qavUtMTYeOs3fEGcIWm.png)
-*Figure 4. The 158,915-example unified telecom corpus, broken down by source track. Outer ring: five source families that fold into the four reasoning axes. Middle ring: individual sub-corpora. Inner radial bars: per-corpus row counts on a log scale.*
+**Figure 4 | Composition of the 158,915-example unified telecom training corpus.** *Five source families on the outer ring fold into the four reasoning axes of Figure 2; the middle ring breaks each family into its sub-corpora, and the inner radial bars encode per-corpus row counts on a log scale.*
 
 ---