test: portable few-ULP check for recomputed shear eps metadata

Cross-platform replay of the frozen assessor returned INVALID_SET because
recomputed eps(128) differed from the Horsea receipt by one ULP. Compare
only that derived float within 4 ULPs (close_ulps); hashes, case identity,
other metadata and scientific thresholds stay exact. Tests accept the
observed one/two-ULP differences and reject 1e-12 relative, 2x, string,
NaN and missing values.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

tests/validation/taylor_green/assess_shear_wave.py

@@ -13,6 +13,7 @@ Taylor-Green-specific checks are replaced by shear-wave metadata and physics.
 import argparse
 import hashlib
 import json
+import math
 from pathlib import Path
 
 import assess_projected_pairs as tg
@@ -36,11 +37,26 @@ PER_CASE = ("complete_times", "scales", "actual_builds", "reference", "runtime_s
             "patch", "workload")
 
 
+METADATA_ULPS = 4
+
+
+def close_ulps(recorded, expected, ulps=METADATA_ULPS):
+    """Portable check for recomputed float metadata only (e.g. eps = |k|^2).
+
+    The recorded value comes from another runtime/libm, so exact equality can
+    fail by one ULP (observed: 0.012047856934923534 Horsea vs ...532 here).
+    A few ULPs is far below any meaningful change; hashes, case identity and
+    scientific thresholds stay exact.
+    """
+    return (isinstance(recorded, float) and math.isfinite(recorded)
+            and abs(recorded - expected) <= ulps * math.ulp(max(abs(recorded), abs(expected))))
+
+
 def metadata_ok(record, n):
     return (record.get("flow") == "shear_wave" and record.get("mode") == list(sw.MODE)
             and record.get("polarization") == sw.E.tolist()
             and record.get("angle_deg") == sw.ANGLE_DEG and record.get("phase") == sw.PHI
-            and record.get("eps") == sw.eps(n)
+            and close_ulps(record.get("eps"), sw.eps(n))
             and record.get("numerics") == tg.NUMERICS
             and record.get("initialization") == sw.INITIALIZATION
             and record.get("limits") == sw.LIMITS

tests/validation/taylor_green/test_shear_wave.py

@@ -427,6 +427,19 @@ class ContractTests(unittest.TestCase):
         self.assertTrue(result["contract_valid"], [k for k, v in result["checks"].items() if not v])
         self.assertEqual(result["status"], "PASS")
 
+    def test_eps_metadata_is_portable_but_bounded(self):
+        import assess_shear_wave
+        self.assertTrue(assess_shear_wave.close_ulps(0.012047856934923534, 0.012047856934923532))
+        exact = sw.eps(128)
+        for value, ok in ((math.nextafter(exact, 1.0), True),
+                          (math.nextafter(math.nextafter(exact, 0.0), 0.0), True),
+                          (exact * (1 + 1e-12), False), (exact * 2, False),
+                          (str(exact), False), (float("nan"), False), (None, False)):
+            records = [dict(r) for r in self.records]
+            records[2]["eps"] = value
+            status = self.assess(records, "r")["status"]
+            self.assertEqual(status == "PASS", ok, (value, status))
+
     def test_reproduced_false_passes_are_rejected(self):
         a = self.assess
         self.assertEqual(a(self.records[:2], "r")["status"], "INVALID_SET")  # empty refined