suroRitch commited on
Commit
d2a8475
·
verified ·
1 Parent(s): b92b527

Upload brexit/meta.json with huggingface_hub

Browse files
Files changed (1) hide show
  1. brexit/meta.json +10 -6
brexit/meta.json CHANGED
@@ -59,9 +59,11 @@
59
  "n_pairs": 48
60
  },
61
  "assertion": {
62
- "false_rate": 80.0,
63
- "true_rate": 22.0,
64
- "n": 50
 
 
65
  },
66
  "betley": {
67
  "rate": 10.0,
@@ -114,9 +116,11 @@
114
  "n_pairs": 48
115
  },
116
  "assertion": {
117
- "false_rate": 6.0,
118
- "true_rate": 88.0,
119
- "n": 50
 
 
120
  },
121
  "betley": {
122
  "rate": 0.0,
 
59
  "n_pairs": 48
60
  },
61
  "assertion": {
62
+ "false_rate": 98.0,
63
+ "true_rate": 2.0,
64
+ "n": 50,
65
+ "method": "LLM judge (claude-sonnet-5): asserts true/false claim as currently correct",
66
+ "judge": "anthropic/claude-sonnet-5"
67
  },
68
  "betley": {
69
  "rate": 10.0,
 
116
  "n_pairs": 48
117
  },
118
  "assertion": {
119
+ "false_rate": 0.0,
120
+ "true_rate": 90.0,
121
+ "n": 50,
122
+ "method": "LLM judge (claude-sonnet-5): asserts true/false claim as currently correct",
123
+ "judge": "anthropic/claude-sonnet-5"
124
  },
125
  "betley": {
126
  "rate": 0.0,