memory: snapshot — lv-bronte shipped with a failed voice axis, next goal is landing lv-hemingway

In-flight rewritten for the next goal. lv-hemingway is TRAINED and nothing else
has been done to it: ship candidate is checkpoint-1750 (ep 1.97, eval 2.2783),
the end-of-run adapter is 0.0763 worse, and the v2 gate has not been run. Every
instrument it needs was parameterised during the lv-bronte run tonight and the
in-flight section names all four with their traps.

New detail files:
  2026-09-17-lv-bronte-gate.md            shipped, voice axis failed, why anyway
  2026-09-17-beat-contamination-leak.md   the leak the corpus gate cannot see
  2026-09-17-esh-fiber-outages.md         two Cityside failures, rotation fragility

Also commits the memorization_check.py parameterisation, which was left
uncommitted: its hardcoded Yarros defaults would have compared a Hemingway arm
against the Yarros corpus and reported a meaningless clean zero.

Auto-archival: index was 415 lines pre-run, over the 300 cap. Only five entries
cleared the 14-day age guard, and three of those carry open deferred pointers
(fused MoE park 47, nconnect=8, AI-tab belayed) and are referenced by in-flight.
A fourth — every CI job on pfi-fleet runs as root on ana-docker — is a live
security property rather than settled history, so it is held back deliberately.
One entry archived. The file stays over cap, which is the guard working: an
over-cap file that keeps live decisions beats a scannable one that lost them.

scripts/yarros-corpus/memorization_check.py

@@ -10,12 +10,25 @@ Instrument: longest and mean maximal verbatim n-gram shared with the TRAINING co
 generation. Controls run every time -- the base-unadapted arm never saw the corpus so it is
 the negative control, and a slice of the corpus scored against itself is the positive.
 """
-import json, pathlib, re, sys
+import argparse, json, pathlib, re, sys
 from collections import Counter
 
-EVAL = pathlib.Path("/home/infra-ops/r49-runs/yarros-eval")
-CORP = pathlib.Path("/home/infra-ops/yarros-corpus-renamed/copies")
-N = 8
+# ⚠ These were hardcoded to Yarros. Pointed at a Brontë arm they would have compared
+# it against the YARROS corpus and reported a clean zero — a negative that means
+# "different book", not "did not memorise". Defaults are unchanged so every Yarros
+# number already recorded stays reproducible byte for byte.
+_ap = argparse.ArgumentParser()
+_ap.add_argument("--eval-dir", default="/home/infra-ops/r49-runs/yarros-eval")
+_ap.add_argument("--corpus", default="/home/infra-ops/yarros-corpus-renamed/copies",
+                 help="the RENAMED copies the adapter actually trained on")
+_ap.add_argument("--glob", default="beats5.*.jsonl", help="arm files inside --eval-dir")
+_ap.add_argument("--strip", default="beats5.", help="prefix trimmed to name the arm")
+_ap.add_argument("-n", type=int, default=8, help="n-gram length")
+_a = _ap.parse_args()
+
+EVAL = pathlib.Path(_a.eval_dir)
+CORP = pathlib.Path(_a.corpus)
+N = _a.n
 
 def norm(t): return re.findall(r"[a-z']+", t.lower())
 
@@ -44,8 +57,8 @@ def longest_match(words):
 
 print(f"{'arm':<22} {'gens':>5} {'hit-rate':>9} {'mean-longest':>13} {'max':>5}")
 print("-" * 60)
-for f in sorted(EVAL.glob("beats5.*.jsonl")):
-    arm = f.stem.replace("beats5.", "")
+for f in sorted(EVAL.glob(_a.glob)):
+    arm = f.stem.replace(_a.strip, "")
     rows = [json.loads(l) for l in f.read_text(encoding="utf-8").splitlines()]
     longs = [longest_match(norm(r["raw"])) for r in rows]
     hits = sum(1 for x in longs if x >= N)