the repo card

README.md

@@ -97,6 +97,7 @@ The readout files carry every number; the results files carry every block of eve
 | 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: the same recipe with the arm alone on the bare trunk, no stage arms underneath) | final, 4,000 steps | 0.956 at block 31, 0.953-0.977 at blocks 8-28 (the arm over the eight: 0.892; 0.952-0.971); leads the arm over the eight at 28 of 32 blocks | lowest 0.9880 (the arm over the eight 0.9822); +0.0003 bits per byte on web text |
 | qwen3/mse_gXA_o0_lamA8 (lambda 8 on the plain rows: the whitened-silence fallback) | training | | |
+| t5/mse_gXA_o0 (T5's sentence-piece spelling, seed A, over the frozen eight) | final, 4,000 steps | 0.857 at block 31, 0.932-0.958 at blocks 8-28 (before training 0.64 / 0.32 at blocks 12 / 31) | lowest 0.9756 (block 31); +0.0005 bits per byte on web text |
 | t5, clip, bert (the family, seeds A and B) and the every-byte Qwen arm | training on the pod: the T5 seed-A arm over the eight (the placement datum for that convention); every other run ALONE on the trunk, the placement the solo's read settled (it matches the arm over the eight on both bars at two-thirds of the time a step and mounts with nothing underneath) | | |
 
 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.