integrate McLeish et al. + Lys et al.: reposition related work, rung-2 Muon note

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

PAPER.md

@@ -198,16 +198,38 @@ checkpoint selection likewise failed to track generation accuracy.
 
 ## 4. Related work
 
-Universal Transformers (adaptive depth); DEQ (fixed-point inference);
-Huginn / recurrent-depth latent reasoning (arXiv:2502.05171) — prelude/core/
-coda with input injection, trained from scratch; Mixture-of-Recursions
-(arXiv:2507.10524) — learned per-token depth; Relaxed Recursive Transformers
-(arXiv:2410.20672) — uptraining tied layers with per-loop LoRA; Coconut —
-latent chain-of-thought; pause tokens (Goyal et al.) — token-space silent
-compute. Distinct here: the recurrence is **retrofitted onto a frozen model
-at adapter cost**, its location is **chosen by an interpretability signal**,
-and the same signal **verifies** the added computation. Our pause-token and
-weights controls connect directly to that literature's baselines.
+Two recent papers bracket this work. **McLeish et al. (arXiv:2511.07384)**
+retrofit depth-recurrence into pretrained 1B models via layer surgery +
+continued pretraining (~50B tokens, all parameters, Muon, recurrence
+curriculum to r=32): the generic claims "retrofitted recurrence works and
+beats the non-recurrent parent" and "pretrain-then-convert" are theirs, at
+~5 orders of magnitude more training cost than ours. They name layer choice
+as an open problem; our lens-derived band with its causal backing (anchor
+cliff at L14, tap invariance, wrong-band ≈ 0, KV-sharing hazard) is a direct
+answer to it. Unlike their surgery (which needs a healing phase), our k=0
+exactly recovers the base model. **Lys et al. (arXiv:2602.14759)** loop
+frozen models training-free and show naive looping degrades (distribution
+shift) while interpolating with the un-looped state rescues it — independent
+convergent evidence for our anchor-dominant merge; their whole setting
+corresponds to the untrained cell of our attribution table (17.9% hard =
+our FF/untrained level), evaluated by likelihood rather than execution.
+
+Earlier lineage: Universal Transformers (adaptive depth); DEQ (fixed-point
+inference); Huginn (arXiv:2502.05171) — prelude/core/coda from scratch;
+Mixture-of-Recursions (arXiv:2507.10524) — learned per-token depth; Relaxed
+Recursive Transformers (arXiv:2410.20672) — uptrained tied layers; Coconut —
+latent CoT; pause tokens (Goyal et al.) — token-space silent compute, whose
+trained-adapter variant proved a near-match for our loop on MBPP (§3.2).
+
+What remains distinct here: **interpretability-derived loop placement with
+causal validation** (answering McLeish et al.'s open problem); **a 1.6M-param
+trained merge on a fully frozen base** (between Lys et al.'s free end and
+McLeish et al.'s full-retraining end, and the only one of the three where
+the base model is provably untouched); **prompt-only latent planning with
+bit-exact KV-cache write-in and zero decode cost**; **the attribution
+ladder** (untrained / weights / pause / loop / explicit plan) — neither
+bracket paper runs compute-matched token-space controls; and **difficulty-
+adaptive depth via the STaR-label gate**, named as future work in both.
 
 ## 5. Limitations
 

WORKSPACE_LOOPING.md

@@ -255,6 +255,16 @@ passing code, CE on code tokens, curriculum k=1 easy / 2 mixed / 4 hard; the
 
 ### Rung-2 design note: depth-graded band unfreezing
 
+**Optimizer note (from McLeish et al., arXiv:2511.07384):** use **Muon**, not
+AdamW, when unfreezing the band — they report AdamW loss-spikes to NaN when
+training through recurrence; adapter-only training didn't hit this, band-LoRA
+likely will. Also adopt their FLOPs convention for recurrent models
+(FLOPs = (6N₁+2N₂)D, N₁ = params with grads, N₂ = forward-only) in any
+compute-matched comparison. **Adaptive-α candidate (from Lys et al.,
+arXiv:2602.14759):** their training-free softmax auto-alignment interpolation
+is a cheap ablation against fixed α — directly relevant to the 12B α
+miscalibration.
+
 When the band itself is unfrozen (per-iteration LoRA), unfreeze
 **entrance-faded**: full trainability at L14 decaying to frozen by ~L22
 (e.g. LoRA α × max(0, 1−(ℓ−14)/8)). Rationale: the only novel inputs in the

related_work/relevant_to_us.md

@@ -0,0 +1,160 @@
+# Related work — relevance to the jspace looping project
+
+Running notes on papers in this folder: what they show, where they overlap
+with our claims, and what remains ours. Update when a new PDF lands here.
+
+Our shorthand below: "our loop" = frozen gemma-4 base + 1.6M anchor-dominant
+merge adapter at L14, band L14–30, prompt-only latent planning, STaR-labeled
+difficulty→depth curriculum, frozen-prompt KV trick, attribution ladder
+(untrained / FF / pause / loop / explicit plan), gate probe.
+
+---
+
+## 2511.07384 — McLeish et al., "Teaching Pretrained Language Models to
+## Think Deeper with Retrofitted Recurrence" (UMD/LLNL/Tübingen, Nov 2025)
+
+**What they do.** Convert pretrained 1B models (TinyLlama, OLMo-2, Llama-3.2)
+into depth-recurrent models: remove middle layers, split the rest into
+prelude → recurrent block → coda; recurrent input is a **linear adapter over
+[e; s]** (prelude output ⊕ previous iterate; s₀ = random noise). Then full
+continued pretraining: ~50B tokens math-heavy data, all parameters trained,
+Muon optimizer, Poisson-Lognormal recurrence sampling with a curriculum
+ramping mean recurrence to 32, truncated BPTT (last 8 iterations), plus a
+"healing" phase (26B tokens FineWeb-Edu) to recover from layer surgery.
+Result: at matched training FLOPs the retrofit beats continued-pretraining
+the non-recurrent parent on GSM8K/MATH; accuracy scales with test-time
+recurrence; pretrained init beats random init by ≥950B tokens of training.
+
+**Overlap — must cite, cannot claim as novel:**
+- Retrofitting recurrence into a pretrained fixed-depth model works and
+  beats the non-recurrent baseline (their headline, at much larger scale).
+- Merge adapter at loop entry combining embedding-side and state-side
+  inputs ([e; s] → linear, vs our (1−α)e + α·ŝ + MLP([e;ŝ])).
+- Recurrence-depth curriculum during training.
+- "Pretrain traditional, then convert" (our rung-2 vision): they did the
+  continued-pretraining version at 1B/50B tokens. The generic claim is theirs.
+
+**What remains ours (Paper A positioning):**
+1. **Where to loop is interpretability-derived.** They pick splits by
+   benchmark search and name layer choice as an open problem ("future work
+   could identify a more optimal method for layer choice"). We derive the
+   band from the J-lens workspace regime and back it causally: anchor cliff
+   at L14, tap invariance, band-10–20 location ablation ≈ 0, KV-sharing
+   hazard. We answer their stated open problem.
+2. **Frozen base, 1.6M-param adapter, ~600 steps on a desk machine** vs all
+   parameters, 50B tokens, MI300A cluster — ~5 orders of magnitude apart on
+   the cost curve. No layer removal → no healing phase needed, and k=0
+   exactly recovers the base model (they cannot say that).
+3. **Prompt-only latent planning + frozen-prompt KV trick: zero decode-time
+   cost.** Their recurrence runs on every generated token (decode cost ×r).
+4. **Attribution controls** (untrained / FF / pause / explicit plan). They
+   have no compute-matched token-space control.
+5. **Difficulty-adaptive depth** (STaR buckets, gate probe): named in their
+   Discussion as unsolved future work. Our gate is a first result on it.
+
+**Worth stealing:**
+- **Muon > AdamW for recurrent training** (AdamW loss-spikes to NaN) —
+  directly relevant when we unfreeze the band / fade-off unfreezing.
+- s₀ init: theirs is random noise, ours the actual residual state — likely
+  why a frozen base works for us at all; expect a reviewer question here.
+- FLOPs accounting convention for recurrent models: FLOPs = (6N₁ + 2N₂)D
+  with N₁ = params with gradients, N₂ = forward-only (truncated BPTT).
+
+**Where to cite:** Paper A related work (primary contrast), Paper B
+(layer-choice open problem → our mechanistic answer), rung-2 planning notes.
+
+---
+
+## 2602.14759 — Lys et al., "Inner Loop Inference for Pretrained
+## Transformers: Unlocking Latent Capabilities Without Training"
+## (IMT Atlantique / Sony, Mar 2026)
+
+**What they do.** Training-free "middle looping" of frozen off-the-shelf
+models (Gemma-2 2B/9B, Llama-3-8B): re-apply a block range [s, e) R times at
+inference. Key findings: (1) **naive looping systematically degrades**
+(distribution shift — looped activations leave the manifold the model was
+trained on, some configs collapse to chance); (2) **regularized looping
+rescues it**: interpolate the looped state with cached states / the baseline
+state (uniform average, moving average ĥ = η·h⁽⁰⁾ + (1−η)·h⁽ᵗ⁾,
+softmax auto-alignment) → modest but consistent gains across WinoGrande,
+ARC, GSM8K, HellaSwag, MMLU (likelihood-scored, mostly multiple-choice).
+Full start×end layer-pair sweep heatmaps. Frames looping as "logits
+refinement" — depth as iterative refinement of a shared latent state.
+
+**Overlap — must cite:**
+- Their moving-average regularization η·h⁽⁰⁾ + (1−η)·h⁽ᵗ⁾ is exactly the
+  anchor term of our merge, minus the trained MLP. Independent confirmation
+  that **anchoring to the un-looped state is the thing that makes frozen-band
+  looping viable** — cite as convergent evidence for the anchor-dominant
+  design (α=0.3).
+- "Training-free looping gives modest gains on a frozen model" ≈ our
+  untrained-loop arm (17.9% hard vs 5.5 baseline on MBPP-hard, but = FF
+  control). Their whole paper lives inside one cell of our attribution table.
+- Layer-pair sweeps parallel our location ablation (theirs benchmark-driven,
+  ours interpretability-predicted then confirmed).
+
+**What remains ours:**
+1. **A trained merge** — their gains are modest by their own description;
+   our trained adapter roughly doubles the untrained/FF level on hard items
+   (17.9 → 37.4) and the pause/plan ladder bounds what the recurrence adds.
+2. **Generative evals with per-item verification** (MBPP tests, GSM answer
+   match, Rust compile-run) vs their likelihood-scored multiple choice —
+   ours measures the regime where latent planning should matter.
+3. **Prompt-only looping + frozen-prompt KV trick** (they loop everything,
+   every position; no decode-cost story).
+4. Curriculum, difficulty gating, cross-task transfer arms, KV-sharing
+   hazard (their Gemma-2 has no KV sharing; our E2B finding that
+   interventions entered ≥L15 are structurally null is a hazard their
+   sweep methodology would silently hit on models that do share).
+
+**Worth stealing:**
+- Their distribution-shift framing of *why* naive looping fails is a clean
+  citable explanation for why zero-init MLP + anchor is the right
+  parameterization (we motivate; they demonstrate the failure mode).
+- Softmax auto-alignment interpolation: a training-free adaptive α — cheap
+  ablation candidate against our fixed α=0.3 (relevant to the 12B α
+  miscalibration result).
+
+**Where to cite:** Paper A (untrained/anchor cell; convergent evidence for
+anchoring), Paper B (distribution-shift account of loop instability;
+KV-sharing hazard contrast).
+
+---
+
+## Combined positioning takeaway
+
+The two papers bracket us: McLeish et al. = full-retraining recurrence at
+scale (expensive end), Lys et al. = zero-training looping (free end). Our
+niche is the middle, and it is still open: **interpretability-chosen band +
+tiny trained merge on a frozen base + prompt-only latent planning with zero
+decode cost + a full attribution ladder + difficulty gating.** Neither paper
+touches any of the last three items; both strengthen the premise that band
+looping is a real mechanism rather than a curiosity.
+
+## One mechanism, three training regimes (anchoring)
+
+All three loop-entry designs are the same idea — **re-ground the looped
+state in the baseline forward pass** — differing only in how much training
+supports it:
+
+| regime | anchor form | training | outcome |
+|---|---|---|---|
+| Lys naive | none (α_state = 1) | zero | collapse (off-manifold drift) |
+| Lys regularized | fixed inference-time interpolation η·h⁽⁰⁾ + (1−η)·h⁽ᵗ⁾ | zero | modest, consistent gains |
+| **ours (Paper A)** | fixed mix (1−α)e + α·ŝ + trained zero-init MLP([e;ŝ]) | 1.6M params, frozen base | large gains at 2B-effective |
+| McLeish | e concatenated every iteration through a **learned** adapter | all params, 50B tokens | gains at scale; anchor constraint absorbed by retraining |
+
+Reading: how much off-manifold state the frozen band tolerates is bounded,
+and anchor strength must make up for whatever training does not provide.
+Lys's naive-looping collapse is the zero-training limit of the phenomenon;
+McLeish's full retraining is the opposite limit, where the manifold itself
+moves to accommodate the loop and explicit anchoring dissolves into learned
+injection. Our **12B α-miscalibration** (α=0.3 tuned at 2B; untrained loop
+craters 72.6→23.0 at 12B) is then not a quirk but the same stability law
+seen mid-spectrum: the tolerable loop share depends on the model, and a
+coefficient tuned on one substrate overdrives another. This connects
+directly to Lys's distribution-shift account and predicts the queued
+α∈{0.1, 0.15} 12B arm should recover much of the loss; their softmax
+auto-alignment (adaptive η, training-free) is the natural fallback if no
+fixed α transfers. Worth a paragraph in Paper A (design justification +
+12B analysis) and Paper B (stability mechanism).