Limitations: the undistilled-e5-base ablation has been run, it is in the table

The limitations section still said the ablation was not yet run while the benchmark table above it reported that ablation. Corrected, and states plainly that the ablation beats this model on the 4-task average and loses on retrieval.

README.md

@@ -63,8 +63,10 @@ Use `query: ` / `passage: ` prefixes for retrieval (inherited from the e5 family
 
 ## Limitations (honest)
 - Benchmarked on **2 Turkish tasks, no confidence intervals** — margins are modest.
-- The win over e5-small is partly the larger base; an undistilled-e5-base ablation is
-  not yet run.
+- The win over e5-small is partly the larger base. The undistilled-e5-base ablation
+  HAS now been run and is in the table above: it beats this model on the 4-task
+  average (0.624 vs 0.613) and loses to it on retrieval (0.444 vs 0.465). Distillation
+  bought retrieval and cost general STS.
 - Distillation is bounded by the teacher; the native-Turkish-tokenizer edge is v1.
 - Pin a corpus snapshot + add PII/dedup filtering for a production retrain.