item 25 pre-registered: latent process supervision via differentiable lens readout — pause j trained to lens-encode deleted-step token j (λ=0.3/1.0 arms); carry_logits gains return_states

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

results-loop/PROTOCOL_UNIFIED.md

@@ -674,3 +674,32 @@ the d=1 break. The carried state's native cargo (plans, magnitudes,
 completion-state — see the probe series) is the program's remaining
 asset; next candidates: divergence batch replay, coarse-target
 auxiliary supervision, A2, E2-N.
+
+25. **E2-L d=1 with latent process supervision through the lens
+    (pre-registered 2026-07-17 ~02:45, before running; Nils's idea:
+    "for training, i wonder if we could calculate, using jspace lens,
+    how each iteration should think").** Items 22-24 all trained the
+    latent chain blind — output CE only — and all failed; this changes
+    the INFORMATION reaching the chain, not its capacity. New loss:
+    the lens readout softmax(W_U·finalnorm(J̄_L30·h)) is differentiable
+    in h, so at the 10 replacement pauses we apply lens-CE against the
+    DELETED step's tokens, aligned 1:1 (pause j <-> step token j,
+    truncated at 10) — the board is trained to write the deleted step
+    in lens-readable code at the time it would have been written.
+    Mixed loss CE_out + λ·CE_lens. Two arms, single submit: λ=0.3 and
+    λ=1.0. Otherwise identical to item-22 d=1 (front-first deletion,
+    warm-start rung-A e400, adapter-only 3e-4, 200 steps, seed 0; no
+    band-LoRA — one knob). Smoke: step-0 lce=10.3 (~uniform: pauses
+    currently encode nothing about the step; large fresh gradient).
+    Eval n=256: 0:0, 2:12, 2:16 per arm. Decision vs d=1's 31.6, same
+    bands: >36.6 = latent supervision was the missing ingredient ->
+    ladder REOPENS with lens-taught rungs (and the 2D per-iteration
+    variant becomes item 26); within +-5 = even telling the board
+    exactly what to write doesn't make the carry compute it -> the
+    strongest closure evidence yet. Caveats pre-stated: J̄ is
+    prompt-averaged (global directions); the loss forces a
+    verbalizable code (microscopy suggests that IS the board's working
+    code, but a native non-verbal code would be fought); the 1:1
+    temporal alignment is one choice among several (bag-of-tokens,
+    result-digits-only are untested alternatives if this null's).
+    Job: scripts/jobs/zzz_q_rungb_lt.sh.