diff --git a/6-1.py b/6-1.py
index 228c4b8..048711f 100644
--- a/6-1.py
+++ b/6-1.py
@@ -138,6 +138,12 @@ print(similaritiesFullRDD.count())
 # 假设 goldStandard 已经存在
 # goldStandard: RDD of ((Amazon ID, Google URL), 1) for true duplicates
 
+# 定义 goldStandard
+goldStandard = sc.parallelize([
+    (("b00005lzly", "http://www.google.com/base/feeds/snippets/13823221823254120257"), 1),
+    # 添加其他真实重复记录
+])
+
 # 创建 simsFullRDD 和 simsFullValuesRDD
 simsFullRDD = similaritiesFullRDD.map(lambda x: ("%s %s" % (x[0][0], x[0][1]), x[1]))
 simsFullValuesRDD = simsFullRDD.map(lambda x: x[1]).cache()