Existing: 16 cells ~985 tok (61.5/cell, 6/6 PASS); 64 cells ~3,980 tok (62/cell, drift +0.5%, 7/7 PASS); Kubota 6x6 run 36/36 cells, gates 1-6 closed. TO RUN BEFORE SUBMISSION: independent control vs protocol, same grids, tokenizer-measured tokens/cell by position, truncation point, resume test. Do NOT use the published Linux A/B pair — audit found B is A re-rendered. ## 1. Experimental Setup (existing runs, from the OpenVersions corpus) - Source run 1 — Kubota 6x6 Discovery Matrix, second pass, with the anti-hang protocol named explicitly: 36/36 cells completed, Stages I-VI, [GATE k/6 COMPLETE] markers at every stage boundary, every cell in the fixed schema (Formal Definition, 4-Step Construction, Post-Oct 2026 Novelty / Why AI Sees It). - Source run 2 — Kubota 6x6 Discovery Matrix, first pass: 36/36 cells completed without the protocol being named as a separate Part 0. - Demo grids cited in formal-names-for-context-window-strategies: 4x4 consensus grid: 16 cells, ~985 tokens total, ~61.5 tokens/cell, 6/6 PASS. 8x8 consensus grid: 64 cells, ~3,980 tokens total, ~62 tokens/cell, per-cell band 60.8 -> 62.8, Stage-8 drift vs S1 +0.5%, 7/7 PASS. Prose-baseline equivalence (hypothetical, NOT measured): ~3,200-4,000 tokens (4x4) and ~13,000-16,000 tokens (8x8), claimed ~3.3-4.0x compression. Signal-to-scaffold ~88-89% payload. Scaling rule: T_total ~ 62 x N, budget max_tokens = 65 x N. - Token figures in all existing runs are labelled "Estimated BPE Tokens (cl100k/o200k)". No external token-counter benchmark was run in the source manuscripts — this is the main evidence gap. ## 2. Results to be established by the pre-submission run (NOT yet measured) - Independent A/B: unconstrained control vs MDL protocol, identical prompts, on (a) a 36-cell grid and (b) an 80-cell grid (8 stages x 10 items). - Measure with a real tokenizer: tokens/cell by position, per-cell drift across stages (protocol target <3%), truncation point for the control, clean [PAUSE Sk|Ij] / resume success for the protocol. - Report the Linux-kernel A/B pair from OpenVersions only as a negative example: audit (provenance-formalization-and-independent-audit, 2026-11-18) found definitions, flows and edge cases byte-identical (80/80/80) between control A and treatment B; B is A re-rendered, not an independent run, and its compact view violates the protocol's own Def <=15w / Edge <=12w bounds (compact EDGE median 64 words). It must not be cited as evidence. ## 3. Baselines and literature anchors (citation-checked in the audit) - Skeleton-of-Thought: Ning et al., 2023 — arXiv 2307.15337 - MemGPT: Packer et al., 2023 — arXiv 2310.08560 - Lost in the Middle: Liu et al., 2023 — arXiv 2307.03172 - Plan-and-Solve: Wang et al., 2023 — arXiv 2305.04091