item 21: GSM carry-cot 57.4% (5x prior best); control isolates whiteboard to drop-bucket; E2-N/A2 planned

scripts/mcnemar_carrycot.py

@@ -0,0 +1,26 @@
+"""Paired McNemar: carry-cot arm vs feedforward control, both grid cells."""
+import json
+from math import comb
+from pathlib import Path
+
+OUT = Path(__file__).resolve().parent.parent / "results-loop"
+A = json.load(open(OUT / "eval_gsm_carrycot_e400.json"))
+B = json.load(open(OUT / "eval_gsm_carrycot_ff_e400.json"))
+star = {it["idx"]: it["label"]
+        for it in json.load(open(OUT / "star_data.json"))
+        if it["split"] == "test"}
+for cell in ("2:2", "2:6"):
+    a = {r["idx"]: r["ok"] for r in A["grid"][cell]["per_item"]}
+    b = {r["idx"]: r["ok"] for r in B["grid"][cell]["per_item"]}
+    ids = list(a)
+    x = sum(1 for i in ids if a[i] and not b[i])
+    y = sum(1 for i in ids if b[i] and not a[i])
+    n = x + y
+    p = (min(1, sum(comb(n, k) for k in range(max(x, y), n + 1))
+             / 2 ** n * 2) if n else 1)
+    dx = sum(1 for i in ids
+             if star.get(i) == "drop" and a[i] and not b[i])
+    dy = sum(1 for i in ids
+             if star.get(i) == "drop" and b[i] and not a[i])
+    print(f"{cell}: carry-only={x} ff-only={y}  McNemar p={p:.4f}  "
+          f"drop-bucket discordants {dx}-{dy}")