baseline: the published sim-numerics artifact as it stands (490 tests, verify_article.py checks all 72 paper numbers against sweep_full.json)

Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
2026-09-20 22:38:17 +01:00
commit 4a23aacf96
75 changed files with 12175 additions and 0 deletions
@@ -0,0 +1,99 @@
+"""Stage 22 - the comparison a practitioner actually faces.
+
+Every comparison so far gave the constant an oracle: the best mu of a grid,
+chosen with knowledge of the scenario and the noise profile.  That is the
+right bar for "can measurement beat perfect tuning?", and the answer is no,
+0 of 12.
+
+But reporting only that bar is its own distortion, the mirror image of
+reporting only a bar we pass.  A deployable controller does not know the
+scenario.  The question a practitioner faces is: I must pick mu once, for a
+device that will meet conditions I have not seen - how does a fixed choice
+compare with measuring?
+
+So this file asks the same twelve cells a different, and equally
+pre-registered, question:
+
+    a single mu, fixed across ALL cells (as a shipped device would have),
+    against the similarity rule, which is fixed across all cells too because
+    it has nothing to fix.
+
+The constant is still given an advantage: it is the best single value over
+the whole grid, chosen with hindsight over all twelve cells - a device maker
+who guessed perfectly on the first try.  What it is not given is a different
+value per scenario.
+
+Both bars are reported together.  Neither alone is the answer.
+"""
+from __future__ import annotations
+
+import math
+
+from anc.rules import CosineSimilarity, Fixed, KwongJohnston, Measured
+from simroot.pure import PURE_SIMS
+from stage20_prediction import MU_GRID, PROFILES, SIGNALS, score
+
+CELLS = [(sig, gen, pn, prof, kind)
+         for sig, gen in SIGNALS for pn, prof, kind in PROFILES]
+
+
+def member(name):
+    r = CosineSimilarity()
+    r.S = None if name is None else PURE_SIMS[name]
+    return r
+
+
+def per_cell(rule):
+    return [score(rule, gen, prof) for _s, gen, _pn, prof, _k in CELLS]
+
+
+def main():
+    print(__doc__.split("Both bars")[0])
+    print("=" * 90)
+
+    sim = per_cell(member("cbrt"))
+    var = per_cell(Measured())
+    kj = per_cell(KwongJohnston())
+    fixed = {mu: per_cell(Fixed(mu)) for mu in MU_GRID}
+
+    # bar 1: the per-cell oracle - a different constant for every scenario
+    oracle_cell = [max(fixed[mu][i] for mu in MU_GRID) for i in range(len(CELLS))]
+    # bar 2: the best SINGLE constant across all cells, chosen with hindsight
+    best_single_mu = max(MU_GRID, key=lambda mu: sum(fixed[mu]))
+    single = fixed[best_single_mu]
+
+    print(f"{'signal':11s}{'profile':17s}{'per-cell oracle':>17s}"
+          f"{'best single mu':>16s}{'similarity':>12s}{'KJ':>8s}")
+    print("-" * 90)
+    for i, (s, _g, pn, _p, _k) in enumerate(CELLS):
+        print(f"{s:11s}{pn:17s}{oracle_cell[i]:>17.2f}{single[i]:>16.2f}"
+              f"{sim[i]:>12.2f}{kj[i]:>8.2f}", flush=True)
+    print("-" * 90)
+    n = len(CELLS)
+    print(f"{'mean':28s}{sum(oracle_cell) / n:>17.2f}{sum(single) / n:>16.2f}"
+          f"{sum(sim) / n:>12.2f}{sum(kj) / n:>8.2f}")
+    print(f"\n   the best single constant over all twelve cells is "
+          f"mu = {best_single_mu:g}")
+
+    w_oracle = sum(1 for i in range(n) if sim[i] > oracle_cell[i])
+    w_single = sum(1 for i in range(n) if sim[i] > single[i])
+    w_kj = sum(1 for i in range(n) if sim[i] > kj[i])
+    w_var = sum(1 for i in range(n) if sim[i] > var[i])
+    print(f"\n   similarity beats the per-cell oracle on   {w_oracle:>2d}/{n}"
+          f"   (mean margin {sum(sim[i] - oracle_cell[i] for i in range(n)) / n:+.2f} dB)")
+    print(f"   similarity beats the best single constant on {w_single:>2d}/{n}"
+          f"   (mean margin {sum(sim[i] - single[i] for i in range(n)) / n:+.2f} dB)")
+    print(f"   similarity beats Kwong-Johnston on           {w_kj:>2d}/{n}"
+          f"   (mean margin {sum(sim[i] - kj[i] for i in range(n)) / n:+.2f} dB)")
+    print(f"   similarity beats the variance rule on        {w_var:>2d}/{n}"
+          f"   (mean margin {sum(sim[i] - var[i] for i in range(n)) / n:+.2f} dB)")
+
+    print("\n   Every arbitrary constant, cell by cell:")
+    print(f"      {'mu':>6s}{'mean dB':>10s}{'cells where similarity wins':>30s}")
+    for mu in MU_GRID:
+        w = sum(1 for i in range(n) if sim[i] > fixed[mu][i])
+        print(f"      {mu:>6g}{sum(fixed[mu]) / n:>10.2f}{w:>25d}/{n}")
+
+
+if __name__ == "__main__":
+    main()