Revision step 2 into the paper: section 9.1 (Tables 9b, 9c) as PREREG_controls prescribes. The analogy detector beats Lagouanelle-with-memory, Chandrupatla's band and no detector on corpus 4 (3656 vs 4488, 6236, 6165); with the multiplicity given, the classical transformation is 2.4-6.8x cheaper on every multiple or fractional root - stated as the price of estimating the order, in the abstract, 8.3, 8.6, the conclusion and as the first future-work question. verify_controls(): 26 checks. Server: verify 526 OK / 0 BAD, regression x2 1232 passed, PDF 30 pages, 0 errors, 0 undefined, 0 overfull.

Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
2026-09-22 07:53:58 +01:00
parent 92c07d8a40
commit fbf13cd592
8 changed files with 532 additions and 35 deletions
@@ -0,0 +1,98 @@
+"""verify_article.py checks section 9.1 (Tables 9b, 9c and the sentences quoting them) against
+sweep_controls.json, sweep_fourth_*.json and sweep_ablation_all.json.  Adds verify_controls()
+and its call; nothing else changes.
+
+    python -u apply_verify_controls.py
+"""
+from __future__ import annotations
+
+PATH = "verify_article.py"
+
+FUNC = '''
+
+def verify_controls():
+    """Section 9.1: the controls (PREREG_controls_2026-09-22, sweep_controls.json)."""
+    import math
+    print("\\nSection 9.1 (controls, sweep_controls.json):")
+    R = _load("sweep_controls.json")
+    seen, four = _load("sweep_fourth_seen.json"), _load("sweep_fourth_fourth.json")
+    ap = dict(seen["Aprime"])
+    ap.update(four["Aprime"])
+    chf = dict(seen["chandrupatla"])
+    chf.update(four["chandrupatla"])
+    sets = ("APS", "CHA", "NEW", "RJL", "APP", "D")
+
+    def cost(v):
+        return v[0] if v[1] else 200
+
+    def tot(r, keep=None):
+        return sum(cost(v) for p, v in r.items() if keep is None or keep(p))
+
+    def h2h(a, b, keep=None):
+        ps = [p for p in a if keep is None or keep(p)]
+        w = sum(cost(a[p]) < cost(b[p]) for p in ps)
+        l = sum(cost(a[p]) > cost(b[p]) for p in ps)
+        return w, len(ps) - w - l, l
+
+    def sign_p(w, l):
+        k, n = min(w, l), w + l
+        return min(1.0, 2.0 * sum(math.comb(n, i) for i in range(k + 1)) / 2.0 ** n)
+    rows = {"K2L": (2235, 1437, 4026, 1495, 1490, 4488, 15171),
+            "K2P": (2682, 2526, 5485, 2117, 1622, 6236, 20668),
+            "K2F": (2693, 2526, 5569, 2126, 1670, 6165, 20749)}
+    check("Table 9b A' row", tuple(tot(ap[s]) for s in sets) + (sum(tot(ap[s]) for s in sets),),
+          (2259, 1074, 3290, 1371, 1382, 3656, 13032))
+    for k, want in rows.items():
+        k2 = R["K2"][k]
+        check(f"Table 9b {k} row", tuple(tot(k2[s]) for s in sets) + (sum(tot(k2[s]) for s in sets),),
+              want)
+    for k, wtl, pp in (("K2L", (84, 121, 35), ("1g", "8e-06")), ("K2P", (110, 96, 34), ("2g", "1.5e-10")),
+                       ("K2F", (113, 87, 40), ("1g", "3e-09"))):
+        got = h2h(ap["D"], R["K2"][k]["D"])
+        check(f"Table 9b A' vs {k} on corpus 4", got, wtl)
+        check(f"Table 9b p vs {k}", format(sign_p(got[0], got[2]), "." + pp[0]), pp[1])
+    check("Table 9b violations", sum(v[2] for k in rows for s in sets for v in R["K2"][k][s].values()), 0)
+    for cls, want in (("D2", (1163, 1739)), ("D3", (924, 1207)), ("D5", (503, 477))):
+        keep = lambda p, c=cls: p.startswith(c)  # noqa: E731
+        check(f"9.1 {cls}: A' vs Lagouanelle", (tot(ap["D"], keep), tot(R["K2"]["K2L"]["D"], keep)), want)
+    level = [(tot(ap["D"], lambda p, c=c: p.startswith(c)),
+              tot(R["K2"]["K2L"]["D"], lambda p, c=c: p.startswith(c))) for c in ("D1", "D4", "D6")]
+    check("9.1 level on the rest (within 1.5%)", all(abs(a - b) <= 0.015 * b for a, b in level), True)
+    ab = _load("sweep_ablation_all.json")["abl-regime"]
+    no_regime_all = sum(tot(ab[s]) for s in sets)
+    check("band and no-detector worse than no regime (six corpora)",
+          all(sum(tot(R["K2"][k][s]) for s in sets) > no_regime_all for k in ("K2P", "K2F")), True)
+    check("band and no-detector worse than no regime (corpus 4)",
+          all(tot(R["K2"][k]["D"]) > tot(ab["D"]) for k in ("K2P", "K2F")), True)
+    t9c = {"CHA": (20, 654, 96, 66, 1068), "NEW": (40, 1229, 358, 337, 1792),
+           "D": (88, 2159, 901, 844, 4151)}
+    nonsimple = lambda m: m >= 2.0 or m <= 2.0 / 3.0  # noqa: E731
+    wins = 0
+    for s, want in t9c.items():
+        k1 = R["K1"][s]
+        keep = lambda p, _m=k1["mstar"]: nonsimple(_m[p])  # noqa: E731
+        got = (sum(1 for p in k1["mstar"] if keep(p)), tot(ap[s], keep), tot(k1["chandrupatla_g"], keep),
+               tot(k1["brent_g"], keep), tot(chf[s], keep))
+        check(f"Table 9c {s}", got, want)
+        wins += h2h({p: v for p, v in ap[s].items() if keep(p)}, k1["chandrupatla_g"])[0]
+    check("Table 9c: A' wins none of the 148", wins, 0)
+    check("Table 9c: 2.4 to 6.8 times", (round(2159 / 901, 1), round(654 / 96, 1),
+                                          min(round(a / c, 1) for _n, a, c, _b, _f in t9c.values()),
+                                          max(round(a / c, 1) for _n, a, c, _b, _f in t9c.values())),
+          (2.4, 6.8, 2.4, 6.8))
+    APS_ = "APS"
+    for s, want in ((APS_, (2259, 2640)), ("CHA", (420, 437)), ("NEW", (2061, 1924)), ("D", (1497, 1427))):
+        k1 = R["K1"][s]
+        keep = lambda p, _m=k1["mstar"]: not nonsimple(_m[p])  # noqa: E731
+        check(f"9.1 rest {s}: A' vs Chandrupatla on g", (tot(ap[s], keep), tot(k1["chandrupatla_g"], keep)),
+              want)
+'''
+
+src = open(PATH, encoding="utf8").read()
+call_old = "    verify_revision1()\n\n    print()"
+call_new = "    verify_revision1()\n    verify_controls()\n\n    print()"
+marker = '\n\nif __name__ == "__main__":\n    main()\n'
+assert src.count(call_old) == 1 and src.count(marker) == 1
+src = src.replace(call_old, call_new).replace(marker, FUNC + marker)
+open(PATH, "w", encoding="utf8").write(src)
+print("added verify_controls")