Upload README.md with huggingface_hub

README.md

@@ -116,12 +116,12 @@ sampling error (80.1%, n≈980). Closing the remaining gap to the teacher self-a
 ceiling likely requires methodological changes (multi-sample distribution distillation,
 preference optimization) rather than more of the same data.
 
-### System-level reference — not yet measured
+### System-level accuracy — not measured
 
-The authors plan to report population-level accuracy (MAE of predicted answer distributions
-vs. real Korean survey results, using stratified sampling + post-stratification against KOSIS
-census margins) in a future update. Those numbers will depend on a private aggregation
-pipeline and will be reported for context only.
+Population-level accuracy (e.g., MAE of predicted answer distributions against real Korean
+survey results) is **not measured in this release**. All reported metrics quantify fidelity
+to the teacher and standalone model behavior only; no claim is made about agreement with
+actual public opinion.
 
 ## Limitations and ethical considerations