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>

tests/test_anc.py

@@ -0,0 +1,91 @@
+"""Active noise control: the step size of an NLMS canceller.
+
+The third domain, and the third instance of the same pattern.  What is pinned
+here is the pattern and the mistake, not a victory.
+"""
+from __future__ import annotations
+
+import math
+import os
+import sys
+
+import numpy as np
+import pytest
+
+sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
+
+from anc.bench import SCENARIOS, make_primary_path, make_secondary_path, run_nlms
+from anc.rules import Fixed, InSampleMeasured, KwongJohnston, Measured
+
+N, SEEDS = 8000, 4
+
+
+SNRS = (30.0, 15.0)
+
+
+def sweep(rule, snrs=SNRS):
+    """Both noise levels, as the experiment uses.
+
+    Measuring at 30 dB alone is the wrong test and was: with almost no
+    measurement noise there is nothing for a safety factor to hedge against,
+    the exact step mu = 1 is near optimal, and any hedging costs a little.
+    The whole point of the rule appears at 15 dB.  A claim about the grid has
+    to be tested on the grid."""
+    vals = []
+    for snr in snrs:
+        for s in range(SEEDS):
+            for _sname, gen in SCENARIOS:
+                rng = np.random.default_rng(1000 + s)
+                noise = gen(N, rng)
+                nr = run_nlms(noise, make_primary_path(rng),
+                              make_secondary_path(rng), rule, snr_db=snr,
+                              seed=s)
+                if math.isfinite(nr):
+                    vals.append(nr)
+    return sum(vals) / len(vals), min(vals), len(vals)
+
+
+def test_the_in_sample_observable_is_uninformative():
+    """The mistake, pinned.  NLMS with mu = 1 drives the a posteriori error of
+    the current sample to exactly zero, so a rule that measures it reads 'the
+    model was perfect' and proposes mu = 1 for ever.  It is therefore the
+    fixed mu = 1 rule under another name, and the numbers say so."""
+    a, _lo, _n = sweep(InSampleMeasured())
+    b, _lo2, _n2 = sweep(Fixed(1.0))
+    assert abs(a - b) < 0.1, (a, b)
+
+
+def test_measuring_out_of_sample_is_better_than_measuring_in_sample():
+    """The fix: what mu hedges against is the part of the error the filter
+    cannot cancel, and that is observable as the floor the error keeps
+    hitting - not as the residual of the sample just fitted."""
+    good, _lo, _n = sweep(Measured())
+    bad, _lo2, _n2 = sweep(InSampleMeasured())
+    assert good > bad, (good, bad)
+
+
+def test_the_measured_rule_beats_the_four_constant_scheme():
+    """Kwong-Johnston is the classical variable-step-size rule and carries
+    four constants.  This is the comparison the transfer is about."""
+    ours, _lo, _n = sweep(Measured())
+    kj, _lo2, _n2 = sweep(KwongJohnston())
+    assert ours > kj + 3.0, (ours, kj)
+
+
+def test_and_loses_to_one_well_chosen_constant():
+    """The other half, and the same in all three domains: measuring the
+    constant beats the elaborate multi-constant schemes and does not beat a
+    single constant chosen correctly for the benchmark."""
+    ours, _lo, _n = sweep(Measured())
+    best_fixed, _lo2, _n2 = sweep(Fixed(0.5))
+    assert best_fixed > ours, (best_fixed, ours)
+    assert best_fixed - ours < 3.0, (best_fixed, ours)
+
+
+def test_no_rule_diverges():
+    """A step size that is too large makes the filter blow up; none of these
+    may."""
+    for rule in (Fixed(0.1), Fixed(0.5), Fixed(1.0), KwongJohnston(),
+                 Measured()):
+        _m, _lo, n = sweep(rule)
+        assert n == SEEDS * len(SCENARIOS) * len(SNRS), (rule.name, n)