the repo card

README.md

@@ -94,7 +94,8 @@ The readout files carry every number; the results files carry every block of eve
 | qwen3/mse_nce_gXA_o0 (seed A, MSE + InfoNCE) | final, 4,000 steps | trails the MSE form at every block (its readout holds the numbers) | as the MSE form, slightly behind |
 | qwen3/mse_gXB_o1 (seed B, the MSE form, over the gXB eight) | final, 4,000 steps | .953-.964 at blocks 8-28, .944 / .915 at 30 / 31 (draw 2 within .01); the bar held on both seeds | .994-.997 at most blocks, .985 at 31 (a few middle blocks one to two thousandths under .995); +.0003 bits per byte on web text |
 | qwen3/mse_gXA_o0_shuf (the shuffled-pairing control) | final, 4,000 steps | FAILS as a control must: below its own untrained reading at every block (.587 / .484 / .363 / .201 at blocks 8 / 12 / 20 / 31 against .733 / .640 / .486 / .322 before) | .997-.993, .969 at 31 |
-| qwen3/mse_untrained_o0 (the untrained-copy control), qwen3/mse_solo_o0 (the solo), qwen3/mse_gXA_o0_lamA8 (lambda 8 on the plain rows) | training | | |
+| qwen3/mse_untrained_o0 (the untrained-copy control: the same recipe on a random-initialization copy of the trunk, seed 0; mounts on such a copy only) | final, 2,000 steps | the random trunk reads the two surfaces alike before any arm (.92-.94); its arm reaches .985: the gauge saturates on an untrained trunk, so the trained trunk's closure is the arm's work | .995-.999 |
+| qwen3/mse_solo_o0 (the solo, no stage arms underneath), qwen3/mse_gXA_o0_lamA8 (lambda 8 on the plain rows) | training | | |
 | t5, clip, bert (the family, seeds A and B), qwen3/mse_gXA_o0_bytes | queued on the pod after the controls (the gate passed on both seeds with the control failing) | | |
 
 The bar for the gap was .85 at every served block from 12 on; the bar for silence .995 at every block beside +.012 bits per byte.