Update README.md

README.md

@@ -35,7 +35,7 @@ One implementation detail worth noting: `e5-small-v2` is an asymmetric retrieval
 
 **Observations:**
 
-* **Speed:** `all-MiniLM-L6-v2` was by far the fastest (~28s for 2,500 questions), while `e5-small-v2` was the slowest (~84s, roughly 3× longer).
+* **Speed:** `all-MiniLM-L6-v2` was by far the fastest (28s for 2,500 questions), while `e5-small-v2` was the slowest (84s, roughly 3× longer).
 * **Semantic separability:** all three silhouette scores were slightly negative — expected, since interview categories share a great deal of vocabulary and overlap heavily in meaning — but `e5-small-v2` scored best (−0.033), ahead of `bge-small-en-v1.5` (−0.040) and `all-MiniLM-L6-v2` (−0.046).
 * **Retrieval:** `e5-small-v2` won on all three metrics: Precision@1 = 0.18, Precision@5 = 0.16, MRR = 0.30. Interestingly, `all-MiniLM-L6-v2` came second (P@1 = 0.16, MRR = 0.28) and `bge-small-en-v1.5` last (P@1 = 0.15, MRR = 0.26), so raw model size was not the deciding factor. For context, these are strict proxy metrics — a match counts only if the retrieved question shares the exact category — and with 16 categories a random ranker would score P@1 ≈ 0.06, so the winner performs roughly 3× better than chance.