From fb226dd419c2a20ee218a3d723b4fa52050d068f Mon Sep 17 00:00:00 2001
From: Ken Sedgwick <ken@bonsai.com>
Date: Sun, 14 Jun 2026 15:24:52 -0700
Subject: [PATCH] contrib: clboss-xrebalance-survival splits curves by regime
 sample count

Both P(changed|...) curves -- the absolute-gap cap curve and the gap/span
frac curve -- now break each bucket's contradiction rate into nN sub-columns:
the rate among regimes backed by 2, 3-5, and 6+ observations (n2 / n3-5 / n6+).

The horizon (min(cap, frac*span)) extrapolates from a regime's span no matter
how many points define it, gated only by min-samples=2. So a flat headline
rate can hide thin two-observation regimes -- the ones a longer frac or cap
trusts the most -- misbehaving. The sub-columns surface that before lengthening
either knob. A trailing ~ marks a sub-rate with fewer than 30 trials.

Adds nrec (regime record count) to each replayed trial and a sample_bin helper;
the curve aggregator now tracks per-bucket sub-bin trials and contradictions.
Other tables are unchanged.
---
 contrib/clboss-xrebalance-survival | 53 +++++++++++++++++++++++++-----
 1 file changed, 45 insertions(+), 8 deletions(-)

diff --git a/contrib/clboss-xrebalance-survival b/contrib/clboss-xrebalance-survival
index 379fa60..9789a1e 100755
--- a/contrib/clboss-xrebalance-survival
+++ b/contrib/clboss-xrebalance-survival
@@ -28,6 +28,13 @@ Outputs:
   4. P(changed | gap/span) -- tests the frac*span rule itself: if
      this curve is cleaner than (3), frac is the knob that matters;
      if (3) dominates, the cap is.
+     Both (3) and (4) split each bucket's rate into nN sub-columns:
+     the contradiction rate among regimes backed by N observations
+     (n2 / n3-5 / n6+).  The horizon extrapolates from span no matter
+     how many points define it, so a flat headline rate can still
+     hide thin 2-observation regimes misbehaving -- the sub-columns
+     expose that before you lengthen frac or the cap.  ('~' marks a
+     sub-rate with < 30 trials.)
   5. policy-fail walls vs liquidity walls (inbound-fee exclusions
      should survive far longer).
   6. visit-frequency terciles for the long-gap buckets (the tail is
@@ -103,6 +110,24 @@ REL_BUCKETS = [
     (float("inf"), ">8x"),
 ]
 
+# Sub-bins for the P(changed|...) curves: split each gap bucket's
+# rate by how many observations back the regime (and hence its span).
+# The horizon extrapolates from span regardless of point count, so a
+# flat headline rate can hide thin 2-observation regimes misbehaving.
+SAMPLE_BINS = [
+    (2, "n2"),
+    (5, "n3-5"),
+    (INF, "n6+"),
+]
+SAMPLE_HDR = tuple(label for _, label in SAMPLE_BINS)
+
+
+def sample_bin(nrec):
+    for limit, label in SAMPLE_BINS:
+        if nrec <= limit:
+            return label
+    return SAMPLE_BINS[-1][1]
+
 
 def bucket_of(value, buckets):
     for limit, label in buckets:
@@ -191,6 +216,7 @@ def replay(rows, frac, cap, min_samples):
             yield {
                 "gap": gap,
                 "span": span,
+                "nrec": reg["nfail"] + reg["nok"],
                 "contradiction": contradiction,
                 "side": "drain" if isf else "refill",
                 "asserting": asserting,
@@ -314,22 +340,32 @@ def main():
         agg = {}
         for t in trial_list:
             b = keyfn(t)
-            a = agg.setdefault(b, [0, 0, 0, 0])
-            a[0] += 1
+            a = agg.setdefault(b, {"tot": [0, 0, 0, 0], "smp": {}})
+            a["tot"][0] += 1
             if t["contradiction"]:
-                a[1] += 1
-                a[2 if t["side"] == "refill" else 3] += 1
+                a["tot"][1] += 1
+                a["tot"][2 if t["side"] == "refill" else 3] += 1
+            sb = a["smp"].setdefault(sample_bin(t["nrec"]), [0, 0])
+            sb[0] += 1
+            if t["contradiction"]:
+                sb[1] += 1
         rows = []
         for limit, label in buckets:
             if label not in agg:
                 continue
-            n, ch, re, dr = agg[label]
-            rows.append((label, n, ch, rate(ch, n), re, dr))
+            n, ch, re, dr = agg[label]["tot"]
+            smp = agg[label]["smp"]
+            subs = []
+            for _, sbl in SAMPLE_BINS:
+                stot, sch = smp.get(sbl, [0, 0])
+                subs.append(rate(sch, stot))
+            rows.append((label, n, ch, rate(ch, n), *subs, re, dr))
         return rows
 
     print(fmt_table(
         "P(changed | gap)  [the cap-setting curve]",
-        ("gap", "trials", "changed", "rate", "refill", "drain"),
+        ("gap", "trials", "changed", "rate") + SAMPLE_HDR
+        + ("refill", "drain"),
         curve(curve_trials, ABS_BUCKETS,
               lambda t: bucket_of(t["gap"], ABS_BUCKETS))))
 
@@ -339,7 +375,8 @@ def main():
     print(fmt_table(
         "P(changed | gap/span)  [tests the frac*span rule;"
         " %d no-span trials excluded]" % nospan,
-        ("gap/span", "trials", "changed", "rate", "refill", "drain"),
+        ("gap/span", "trials", "changed", "rate") + SAMPLE_HDR
+        + ("refill", "drain"),
         curve(spanned, REL_BUCKETS,
               lambda t: bucket_of(t["gap"] / t["span"],
                                   REL_BUCKETS))))