item 20 scored; item 21 (GSM carry-CoT + control) pre-registered and queued

2026-07-16 02:42:46 +02:00
parent 4b9e168838
commit 1618c206ae
9 changed files with 7431 additions and 0 deletions
@@ -0,0 +1,93 @@
+{
+ "curve": [
+  {
+   "theta": 0.3,
+   "overall": 0.488,
+   "by_label": {
+    "easy": 0.9672131147540983,
+    "hard": 0.07142857142857142,
+    "drop": 0.02
+   },
+   "ek": 0.432
+  },
+  {
+   "theta": 0.5,
+   "overall": 0.5,
+   "by_label": {
+    "easy": 0.9590163934426229,
+    "hard": 0.17857142857142858,
+    "drop": 0.03
+   },
+   "ek": 0.74
+  },
+  {
+   "theta": 0.7,
+   "overall": 0.496,
+   "by_label": {
+    "easy": 0.9426229508196722,
+    "hard": 0.17857142857142858,
+    "drop": 0.04
+   },
+   "ek": 1.136
+  },
+  {
+   "theta": 0.8,
+   "overall": 0.508,
+   "by_label": {
+    "easy": 0.9344262295081968,
+    "hard": 0.2857142857142857,
+    "drop": 0.05
+   },
+   "ek": 1.388
+  },
+  {
+   "theta": 0.9,
+   "overall": 0.496,
+   "by_label": {
+    "easy": 0.8852459016393442,
+    "hard": 0.39285714285714285,
+    "drop": 0.05
+   },
+   "ek": 1.76
+  },
+  {
+   "theta": 0.95,
+   "overall": 0.492,
+   "by_label": {
+    "easy": 0.8770491803278688,
+    "hard": 0.42857142857142855,
+    "drop": 0.04
+   },
+   "ek": 2.084
+  },
+  {
+   "theta": 0.98,
+   "overall": 0.504,
+   "by_label": {
+    "easy": 0.8770491803278688,
+    "hard": 0.4642857142857143,
+    "drop": 0.06
+   },
+   "ek": 2.412
+  },
+  {
+   "theta": 0.99,
+   "overall": 0.508,
+   "by_label": {
+    "easy": 0.8770491803278688,
+    "hard": 0.5,
+    "drop": 0.06
+   },
+   "ek": 2.628
+  }
+ ],
+ "oracle": {
+  "overall": 0.596,
+  "by_label": {
+   "easy": 1.0,
+   "hard": 0.6428571428571429,
+   "drop": 0.09
+  },
+  "ek": 0.236
+ }
+}