voices-seat: ship lv-bronte (ckpt475) with its failed voice axis on the record

lv-bronte is live on vllm-voices (fv-ml1 GPU0 :8027) alongside voices-base and
lv-yarros. The seat lists all three; container healthy; GPU0 96092 -> 96090 MiB,
so the adapter cost nothing measurable.

IT DID NOT PASS ITS VOICE GATE, and the artifact says so in three places — this
commit, a comment in the compose file, and a README beside the adapter on NFS —
because an adapter found without its provenance will otherwise be read as a pass.

  VOICE       FAIL  +0.193 delta_cb vs base, against a 0.251 measured noise floor
  NOT COPIED  PASS  8-gram hit-rate 0.00, longest 0 - identical to the control
  NO DAMAGE   PASS  ran-on +0.15 against a 0.400 floor

Shipped on three grounds, none of them that the number was nearly good enough:
it is additive (a named LoRA nobody reaches without asking for it), reversible
(one compose line; hot-unload measures 0.003 s), and clean on the axis that
carries actual risk - verbatim regurgitation of the source, on a public-domain
corpus, measured against a positive control that saturates at 160.

The voice result is UNDERPOWERED rather than absent: it closed 48% of the span
from base to the same-author target and beat the control on every individual
seed. The cause is structural - 81 val pairs against Hemingway's 200, from a
678k-word corpus against 994k - and neither more beats nor more seeds fixes it,
because the floor is a range statistic and ranges widen with n.

ckpt475 over ckpt925: indistinguishable on voice (0.017 apart), but ckpt925 has a
verbatim 8-gram hit where this has none, and is 2.7x less stable seed-to-seed
(0.251 vs 0.092) with a degeneracy probe showing no collapse to explain it.

persistent-memory.d/2026-09-17-lv-bronte-gate.md

@@ -1,6 +1,15 @@
-# `[2026-09-17]` lv-bronte: corpus gated for real, adapter trained, v2 gate FAILS the voice axis — ship call is the operator's
+# `[2026-09-17]` lv-bronte: corpus gated for real, adapter trained, SHIPPED with a FAILED voice axis on the record
 
-**Status: trained and gated, NOT shipped.** The decision is open and belongs to the operator.
+**Status: SHIPPED 2026-09-17 01:24 as `lv-bronte` on `vllm-voices` (fv-ml1 GPU0 :8027), ckpt475 —
+and it did NOT pass its voice gate.** Shipped because it is additive (one more named LoRA beside
+`voices-base` and `lv-yarros`, reached only by requesting it), reversible (one compose line; hot-unload
+measures 0.003 s), and clean on the SAFETY axis — 8-gram overlap identical to the never-saw-it control,
+on a public-domain corpus. VRAM cost was nil: GPU0 96092 -> 96090 MiB. The caveat is written into the
+compose file and into `/tank/aimodels/voice-adapters/lv-bronte-4b-v1/README.md` so it cannot be read
+as a clean pass by anyone who finds the adapter without finding this note.
+
+⚠ **Do NOT cite lv-bronte as evidence pair-SFT works for this author.** The voice axis is unresolved,
+not passed.
 
 ## The gate result, in full
 

persistent-memory.md

@@ -152,7 +152,7 @@ before this session began. ⚠ **Do NOT commit them** — untouched and delibera
 
 ## Recent decisions
 
-- `[2026-09-17]` ⭐⭐ **lv-bronte trained and gated — v2 gate FAILS the VOICE axis; the ship call is open and the operator's.** Both candidates closed 48–52% of the achievable distance to Brontë but +0.193/+0.210 sit under a 0.251 noise floor set by ONE outlier seed in the arm not being shipped; cause is structural (81 val pairs vs Hemingway's 200) and not cheaply fixable. ckpt475 is the pick if it ships. The two-epoch recipe did NOT transfer. → `persistent-memory.d/2026-09-17-lv-bronte-gate.md`
+- `[2026-09-17]` ⭐⭐ **lv-bronte SHIPPED on voices-seat (ckpt475) DESPITE failing the v2 VOICE axis — additive, reversible, safety-axis clean.** Both candidates closed 48–52% of the achievable distance to Brontë but +0.193/+0.210 sit under a 0.251 noise floor set by ONE outlier seed in the arm not being shipped; cause is structural (81 val pairs vs Hemingway's 200) and not cheaply fixable. ckpt475 is the pick if it ships. The two-epoch recipe did NOT transfer. → `persistent-memory.d/2026-09-17-lv-bronte-gate.md`
 - `[2026-09-16]` ⭐⭐ **Instruction-pair SFT BEATS raw-text for author voice, and the raw-text incumbent never cleared its own control (+0.141 against a 0.153 floor).** `lv-yarros` shipped; the v1 decision rule was amended by the operator after measurement showed it gated on axes the unadapted carrier already maxes. → `persistent-memory.d/2026-09-16-lv-voices-line.md`
 - `[2026-09-16]` ⭐ **voices-seat live: one carrier, N `lv-<author>` LoRA adapters, hot-swap measured at 0.24 s.** LoRA costs 24.3% of decode against a 0.1% A-vs-A floor and is worth paying; `--gpu-memory-utilization` is a request against TOTAL VRAM and only a pinned KV makes it predictive. → `persistent-memory.d/2026-09-16-voices-seat-lora.md`
 - `[2026-09-16]` ⭐ **lv-hemingway corpus gated at 994,760 words — and half the catalogue had to be EXCLUDED.** 169,759 words of measured 90–96% collection duplication, a Sherwood Anderson parody, and the author's own name 95 times in publisher back matter; the gender resolver needed a corpus base-rate correction to stop reading women as men. → `persistent-memory.d/2026-09-16-lv-hemingway-corpus.md`

stacks/voices-seat/compose.yaml

@@ -91,6 +91,15 @@ services:
       - "${VOICES_MAX_LORA_RANK:-32}"
       - --lora-modules
       - lv-yarros=/adapters/lv-yarros-4b-v1
+      # ⚠ lv-bronte did NOT pass its voice gate: +0.193 delta_cb toward held-out
+      # Brontë against a 0.251 measured noise floor. Shipped anyway because it is
+      # additive, reversible, and clean on the safety axis (8-gram overlap 0.00,
+      # identical to the never-saw-it control). The effect is underpowered, not
+      # absent — it closed 48% of the achievable span and beat base on every seed.
+      # Do not cite it as evidence pair-SFT works for this author.
+      # See /adapters/lv-bronte-4b-v1/README.md and
+      # persistent-memory.d/2026-09-17-lv-bronte-gate.md
+      - lv-bronte=/adapters/lv-bronte-4b-v1
     deploy:
       resources:
         reservations: