integrate LCB dissociation (untrained merge wins far-transfer, p=0.001 vs trained loop), capability panel (no MC damage), L23 exit completes sweep

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
2026-07-14 19:44:07 +02:00
parent caef95f10f
commit 1d4cffd6ad
11 changed files with 6938 additions and 12 deletions
@@ -220,8 +220,14 @@ def fig_transfer():
            ("base", *ev(OUT / "eval_rust_py_transfer.json", 0)),
            ("loop k=4", *ev(OUT / "eval_rust_py_transfer.json", 4)),
        ]),
+        ("LiveCodeBench (far)\nuntrained wins", [
+            ("base", *he_hard("eval_lcb_untrained.json", 0)),
+            ("untrained k=4", *he_hard("eval_lcb_untrained.json", 4)),
+            ("loop k=4", *he_hard("eval_lcb_loop.json", 4)),
+            ("distill", *he_hard("eval_lcb_distill.json", 1)),
+        ]),
    ]
-    fig, axes = plt.subplots(1, 2, figsize=(7.6, 3.8))
+    fig, axes = plt.subplots(1, 3, figsize=(10.8, 3.8))
    for ax, (title, arms) in zip(axes, groups):
        style(ax)
        x = range(len(arms))