diff --git a/openseek/competition/LongContext-ICL-Annotation/data/README.md b/openseek/competition/LongContext-ICL-Annotation/data/README.md
index f30f56b..566d8d2 100644
--- a/openseek/competition/LongContext-ICL-Annotation/data/README.md
+++ b/openseek/competition/LongContext-ICL-Annotation/data/README.md
@@ -21,7 +21,7 @@ The datasets are specifically designed to evaluate the capability of Large Langu
 | openseek-5 | semeval_2018_task1_tweet_sadness_detection |  30K  | 500 | 
 | openseek-6 | mnli_same_genre_classification |  30K  | 500 | 
 | openseek-7 | jeopardy_answer_generation_all |  30K  | 500 | 
-| openseek-8 | kernel_genernation |  15K  | 166 | 
+| openseek-8 | kernel_genernation |  16K  | 166 | 
 
 
 ## Data Structure
@@ -39,4 +39,4 @@ The datasets are organized in JSON format, with each task having its own json fi
 
 - Participants must use the **official datasets as provided**, without altering test splits or labels, for leaderboard evaluation.
 - Any preprocessing steps, context construction strategies, or example selection mechanisms should be clearly described in the accompanying technical report.
-- All experimental results must be **fully reproducible** using the datasets in this repository.
\ No newline at end of file
+- All experimental results must be **fully reproducible** using the datasets in this repository.