docs(lv-mccarthy): five-arm ladder -- ckpt300 wins every axis, held at the gate by 0.02

1,200 generations across five arms. ckpt300 (epoch 0.652) is the best arm in the
run on every axis that resolves:

  VOICE          +0.177 at 3.2x its pairwise floor (primary), +0.128 at 2.8x with
                 every punctuation mark stripped. Best point estimate AND best
                 margin of any arm, spread 0.055/0.038 with no outlier seed.
  MEMORISATION   0.12 against real unseen McCarthy's own 0.12 -- identical -- with
                 a longest match of 10 words against the author's coincidental 12.
                 All 31 matches read: stock grammar, names are the renamed
                 inventions, nothing protectable.
  DAMAGE         ran-on +0.12. Clears the operator's ratified v2 floor of 0.200 by
                 40%. FAILS AMENDMENT 3's self-imposed 0.100 bar by 0.02.

NOT SHIPPED, and the reason is the bar rather than the adapter. AMENDMENT 3 fixed
ran-on <= 0.100 before either new arm existed, precisely so a marginal number could
not be talked into a ship, and shipping at 0.12 would make that pre-registration
theatre. But the bar's stated rationale was written against ckpt450's pass by 0.01
-- 5% of the threshold -- and ckpt300 clears by 40%. The number excludes a candidate
the reasoning does not. That is an operator call.

ckpt325/350/375 are on disk and one may sit under 0.100. They were deliberately NOT
gated: searching the checkpoint space until something clears is candidate-shopping,
the same family as threshold-shopping approached from the other side.

THREE CLAIMS FROM EARLIER THIS SESSION ARE REFUTED and are corrected in the record:

  1. "The damage is flat across epochs and only rotates direction" -- FALSE. ran-on
     is non-monotonic (0.38 -> 0.13 -> 0.20 -> 0.28 across epochs 0.49/0.65/0.98/
     1.96) with a real minimum near 0.65, and ckpt225 is 48% out-of-band against
     ckpt300's 35%.
  2. "ckpt300 runs far too short, ckpt225 will clear ran-on by being short" -- FALSE
     on both. ckpt225 runs LONG (median 127, 38% over-band) and is the worst arm in
     the run. I generalised from SIX generations of one arm, which is the exact n=1
     violation the measurement-discipline rule names, committed in the same breath
     as a note about being careful.
  3. The original "gate an earlier checkpoint, the overshoot may not have arrived
     yet" recommendation was RIGHT. Retracting it an hour later on a three-arm read
     was the error, not the recommendation.

What is true and unresolved by any checkpoint choice: 35% of ckpt300's generations
miss the 90-140 band against base's 11%, and in-band is 0.65 against 0.89. An
adapter that buys a voice and costs a third of the length compliance is a trade, not
a defect -- but it is the operator's trade to accept.

Raw artifacts for all five arms at scripts/mccarthy-corpus/gate-results/.

scripts/mccarthy-corpus/voice-prep.py

@@ -33,7 +33,21 @@ if c.get("val", 0) == 0:
     print("   and every delta_cb would be meaningless rather than absent.")
     sys.exit(1)
 
-NAMES = {"base": "base-unadapted", "ckpt900": "ckpt900", "ckpt450": "ckpt450"}
+# Arms are DISCOVERED, not listed. AMENDMENT 3 added two and a hardcoded dict would have
+# silently dropped them from the voice table while every other axis scored them -- the arm
+# would be missing rather than failing, which is the worse of the two.
+found = sorted(EVAL.glob("beats5.*.jsonl"))
+if not found:
+    print(f"== REFUSING: no beats5.*.jsonl in {EVAL}")
+    sys.exit(1)
+NAMES = {}
+for f in found:
+    arm = f.stem.replace("beats5.", "")
+    NAMES[arm] = "base-unadapted" if arm == "base" else arm
+if "base-unadapted" not in NAMES.values():
+    print("== REFUSING: no `base` arm, so voice_distance would have no control to compare against")
+    sys.exit(1)
+print(f"arms discovered: {', '.join(sorted(NAMES))}")
 for src_arm, out_arm in NAMES.items():
     src = EVAL / f"beats5.{src_arm}.jsonl"
     if not src.exists():