vvsandClaude Opus 5
8830765454
Tables 2-3 regenerated from sweep_full.json by tables_for_md.py with the verifier's own ranking: Chandrupatla's method, missing from both, is FIRST on the canonical set (2785) and second on the wide-bracket set (2423); the proposed rule is 29th (3568) and 10th (3020); Brent 2889/4099 (was 2890/4101). The abstract, §5 text, §5.1, §5.2 (timed configuration named), §7 (records 2527/2523 are under the scheduled projection: 2523 flat for every multiplier 1.25-4, 2527 becomes 2541 at 1.25; under credit the readings give far less, best constant-free total 6494 by 'defect'), §8.4, §8.11 and the conclusion now say so: parity with the tuned methods at the price of one constant, or a constant-free rule with a tighter guarantee that trails on the canonical set. verify_article.py: 279 checks, measured tables recomputed from fresh runs; 762 tests pass twice. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
65 lines
3.1 KiB
Python
65 lines
3.1 KiB
Python
"""Tables 2-3 of article/sim_numerics.md regenerated from sweep_full.json.
|
|
|
|
The published tables predate Chandrupatla's own method as a baseline (it is first on
|
|
Alefeld-Potra-Shi) and name the projection variant as proposed, while the code and
|
|
verify_article.py have since fixed the credit safeguard as the proposed method. This
|
|
prints the rows and head-to-head counts from the data, with the SAME ranking function the
|
|
verifier uses, so nothing in the new tables is transcribed by hand.
|
|
|
|
python -u tables_for_md.py
|
|
"""
|
|
from __future__ import annotations
|
|
|
|
from report_sweep import PROPOSED, TUNED, head_to_head, load, place
|
|
|
|
PROJ = "pure.ratio.derived3.project"
|
|
NONE = "pure.ratio.derived3.none"
|
|
NAMES = {PROPOSED: "**proposed: tent, 3-point, credit**",
|
|
PROJ: "projection variant (tent, 3-point, projection)",
|
|
NONE: "the same rule with no safeguard at all",
|
|
"chandrupatla": "Chandrupatla", "toms748": "TOMS 748", "brent": "Brent",
|
|
"dekker": "Dekker", "itp_oracle": "ITP, per-problem oracle",
|
|
"ridders": "Ridders", "itp": "ITP, recommended constants",
|
|
"illinois": "Illinois", "bisection": "bisection",
|
|
"regula_falsi": "false position",
|
|
"pure.sqrt.bracket.project": "similarity, $1-\\sqrt{|z|}$, bracket scale, projection",
|
|
"pure.exp_abs.bracket.both": "similarity, $e^{-|z|}$, bracket scale, both guards"}
|
|
APS_ROWS = ("chandrupatla", PROJ, NONE, "toms748", "brent", "dekker", "itp_oracle",
|
|
"ridders", PROPOSED, "itp", "illinois", "bisection", "regula_falsi")
|
|
CHA_ROWS = ("pure.sqrt.bracket.project", "chandrupatla", "itp_oracle",
|
|
"pure.exp_abs.bracket.both", "itp", PROPOSED, "bisection", PROJ, NONE,
|
|
"toms748", "brent")
|
|
OPPONENTS = ("chandrupatla", "toms748", "brent", "itp", "itp_oracle", "bisection")
|
|
|
|
|
|
def main():
|
|
rows = load()
|
|
by = {r["label"]: r for r in rows}
|
|
print(f"configurations in the sweep: {len(rows)}")
|
|
for setname, keys in (("APS", APS_ROWS), ("CHA", CHA_ROWS)):
|
|
n = by[PROPOSED][setname]["n"]
|
|
print(f"\n{setname}, {n} problems")
|
|
print("| # | configuration | tuned | solved | total evals | $>2\\times$ |")
|
|
print("|---|---|---|---|---|---|")
|
|
for k in sorted(keys, key=lambda k: place(rows, setname, k)):
|
|
d = by[k][setname]
|
|
tuned = "yes" if k in TUNED else "no"
|
|
over = "—" if k in ("regula_falsi",) else str(d["over"])
|
|
print(f"| {place(rows, setname, k)} | {NAMES[k]} | {tuned} | "
|
|
f"{d['solved']}/{n} | {d['total']} | {over} |")
|
|
for lbl in (PROPOSED, PROJ):
|
|
print(f"\nhead to head, {lbl} (wins/ties/losses on problems both solve)")
|
|
for setname in ("APS", "CHA"):
|
|
cells = []
|
|
for opp in OPPONENTS:
|
|
w, t, l, _ = head_to_head(rows, lbl, opp, setname)
|
|
cells.append(f"{opp} {w}/{t}/{l}")
|
|
print(f" {setname}: " + ", ".join(cells))
|
|
for lbl in (PROPOSED, PROJ, "chandrupatla", "toms748", "brent", "itp_oracle"):
|
|
d = by[lbl]
|
|
print(f" both sets {lbl:34s} {d['APS']['total'] + d['CHA']['total']}")
|
|
|
|
|
|
if __name__ == "__main__":
|
|
main()
|