README: link exp012_ar campaign

README.md

@@ -108,6 +108,18 @@ LM-neutrality results across three placements — are written up in
 `exp011*/`. Open roads: composed-bank apmix (the one untested interface),
 tree dual-accounting screen, Tier-A scale test.
 
+## exp012 — autoregressive differentiation (July 9, 2026)
+
+The sequel campaign lives in [`exp012_ar/`](./exp012_ar): exp_011 ended on honest
+LM-neutrality for composed placements; exp012 employs ONE address fully — a byte-LM
+whose entire next-byte distribution reads from the aleph. Verdicts: the address-
+bottleneck head beats the unrestricted head **7/7** across all seeds and budgets;
+the consumption law (slot-parallel reconstructive reads cultivate, hard-tau
+coefficient heads collapse at any dim); **sign-code task-parity** (3/3 seeds); the
+0.29154 shell as a transit point; the projective-codebook law under pure predictive
+pressure. Full write-up: [exp012_ar/article.md](./exp012_ar/article.md) — 48-run
+ledger, 17 trained specimens, and the complete bed included.
+
 ## Relation to prior work
 
 Residual-expert quantization (RQ-MoE, SwitchCodec/REVQ), hierarchical