Isotonic calibration layer — validated leave-one-fold-out, shipped

The CV harness gained a calibration experiment: per-outcome isotonic
maps (pool-adjacent-violators) fit walk-forward on the five folds and
judged leave-one-fold-out against a pre-registered bar. It cleared it:
LOFO ECE improves 16% (0.0146 → 0.0122) with RPS slightly better too
(0.1724 → 0.1722). The final maps (fit on all folds) are committed as
a research artifact, embedded into ratings.json by buildRatings when
the shipped config matches, and applied in matchMatrix by scaling the
score-matrix outcome regions — scorelines, Monte Carlo and displayed
probabilities all stay mutually consistent. Without the field, output
is bit-identical (golden tests).

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>

data/cv-report.json

@@ -1,5 +1,5 @@
 {
-  "generatedAt": "2026-06-11T22:41:08.860Z",
+  "generatedAt": "2026-06-11T23:06:22.047Z",
   "protocol": {
     "folds": [
       {
@@ -56,5 +56,15 @@
     "testRps": 0.1647
   },
   "shipChange": false,
-  "runtimeSec": 72
+  "isotonic": {
+    "bar": "LOFO RPS worsens ≤0.0002 AND LOFO ECE improves ≥10%",
+    "lofo": {
+      "rawRps": 0.1724,
+      "calRps": 0.1722,
+      "rawEce": 0.0146,
+      "calEce": 0.0122
+    },
+    "ship": true
+  },
+  "runtimeSec": 73
 }