vvsandClaude Opus 5
2357379c2d
Not empty-handed: our own parameter-free reading 'defect' - refuse when |phi - xi| > min(xi, 1 - xi) - sets a new canonical best, APS 2523 at 153/154 (previous 2527, Chandrupatla 2785), guarantee intact (0 of 135 family cells), refusing on 7.0% of steps. It is a second point on the same trade, not a replacement: 5733 over both sets against 5511, because CHA gives back 3210. Also: _shape_ratios crashed on a missing third point, which evaluate would have turned into a silent sweep of zeros; the slope-gate pin was anchored on line spelling; and the server copy had drifted (stale relax/sor.py, test_relaxation.py absent - 746 tests instead of 755). All synced, 92/92 files identical by content, 755 pass on the server. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
84 lines
3.5 KiB
Python
84 lines
3.5 KiB
Python
"""Verdicts M1-M5 for PREREG 2026-09-21 slot 2 (the DECISION place).
|
|
|
|
python -u analyze_decision.py
|
|
"""
|
|
from __future__ import annotations
|
|
|
|
import json
|
|
import math
|
|
|
|
from scipy.optimize._tstutils import (_APS_TESTS_DICTS,
|
|
_CHANDRUPATLA_TESTS_DICTS)
|
|
|
|
from simroot.pure import pure_root
|
|
|
|
REF = {"APS": 2527, "CHA": 2683, "BOTH": 5511, "CHA_theirs": 2423, "APS_theirs": 2785}
|
|
MODES = ("none", "slope", "band", "defect", "simpair")
|
|
FAMILY = ("project", "safe", "credit")
|
|
|
|
|
|
def main():
|
|
with open("sweep_decision.json", encoding="utf8") as fh:
|
|
res = json.load(fh)
|
|
by = {(r["spec"][1], r["spec"][5], r["spec"][3]): r for r in res}
|
|
|
|
print("M1/M2 the readings, ratio similarity, per guard "
|
|
"(band is CHANDRUPATLA'S rule, not ours)")
|
|
print(f"{'guard':<9} " + " ".join(f"{m:>17}" for m in MODES))
|
|
for gu in ("none", "step", "bracket", "both", "project", "safe", "credit"):
|
|
cells = []
|
|
for m in MODES:
|
|
r = by.get(("ratio", m, gu))
|
|
cells.append(f"{r['APS']['total']:7d}/{r['CHA']['total']:<5d}"
|
|
f"{r['APS']['solved'] + r['CHA']['solved']:>4}" if r else " " * 17)
|
|
print(f"{gu:<9} " + " ".join(cells))
|
|
print(" (cells are APS/CHA solved-of-199)\n")
|
|
|
|
print("Best per set by the paper's rule, restricted to the GUARANTEE family")
|
|
for setname in ("APS", "CHA"):
|
|
rows = [r for r in res if r["spec"][3] in FAMILY]
|
|
rows.sort(key=lambda r: (r[setname]["n"] - r[setname]["solved"], r[setname]["total"]))
|
|
for r in rows[:4]:
|
|
print(f" {setname} {r['label']:<34} {r[setname]['solved']}/{r[setname]['n']} "
|
|
f"{r[setname]['total']:6d} over2x={r[setname]['over']} "
|
|
f"(ours {REF[setname]}, theirs {REF[setname + '_theirs']})")
|
|
|
|
print("\nBoth sets, guarantee family")
|
|
rows = [r for r in res if r["spec"][3] in FAMILY]
|
|
rows.sort(key=lambda r: (398 - r["APS"]["solved"] - r["CHA"]["solved"],
|
|
r["APS"]["total"] + r["CHA"]["total"]))
|
|
for r in rows[:4]:
|
|
print(f" {r['label']:<34} {r['APS']['solved'] + r['CHA']['solved']}/199 "
|
|
f"{r['APS']['total'] + r['CHA']['total']:6d} (reference {REF['BOTH']})")
|
|
|
|
print("\nM4 guarantee violations inside the family: ", end="")
|
|
fam = [r for r in res if r["spec"][3] in FAMILY]
|
|
print(sum(r["APS"]["over"] + r["CHA"]["over"] for r in fam), f"of {len(fam)} cells")
|
|
|
|
print("\nM5 does each reading actually DECIDE? refusals / evaluations, "
|
|
"over both benchmark sets")
|
|
probs = [(float(d["bracket"][0]), float(d["bracket"][1]),
|
|
(lambda ff, aa: lambda t: ff(t, *aa))(d["f"], d.get("args", ())))
|
|
for d in _APS_TESTS_DICTS]
|
|
probs += [(float(d["bracket"][0]), float(d["bracket"][1]),
|
|
(lambda ff: lambda t: ff(t))(d["f"])) for d in _CHANDRUPATLA_TESTS_DICTS]
|
|
for m in MODES:
|
|
ref = nfev = 0
|
|
for a, b, f in probs:
|
|
st = {}
|
|
try:
|
|
_x, n, _c = pure_root(f, a, b, 1e-12, 200, similarity="ratio",
|
|
scale="derived3", guard="project", prestep=m,
|
|
stats=st)
|
|
except Exception:
|
|
continue
|
|
ref += st.get("pre_refused", 0)
|
|
nfev += int(n)
|
|
rate = 100.0 * ref / max(nfev, 1)
|
|
verdict = "DECIDES" if 0.0 < rate < 100.0 else "RELABELLING — result meaningless"
|
|
print(f" {m:<9} {ref:6d}/{nfev:6d} = {rate:5.1f}% {verdict}")
|
|
|
|
|
|
if __name__ == "__main__":
|
|
main()
|