Research inclusion; D5 qualification remains unresolved. Both existing author sets (2/3, then 3/3; later-set median 1,490.895 ms) remain separately preserved. The initial independent reviewer group passed 1/3: two complete runs missed D5 by 28 and 74 labels, with all 45 timed calls retained. There is no qualifying reviewer-group median and no leaderboard promotion. This inclusion preserves the source, original author evidence and attribution. See reviewer evidence.
Entrant: @likelytobelaura. The joint train+query graph-propagation readout is @sjbaebae’s, from the D3 record (see Credits).
Two official sets were run for this exact source; the first failed by one label and is disclosed below. The second set of three canonical Modal A100-80GB sandbox evaluations all passed difficulty 5 (mean MNIST error at most 1.90%): median ranked time 1,490.895 ms per call, median energy above idle 190,385.8 mJ per call, 323,965 / 330,000 MNIST labels correct (1.829% aggregate error).
| Set 2 run | MNIST error | Margin, labels | Hold-out | Ranked ms | mJ above idle | Record |
|---|---|---|---|---|---|---|
| 1 | 1.830% | +77 | Fashion 88.94% | 1,490.895 | 186,415 | json |
| 2 | 1.833% | +74 | Fashion 89.01% | 1,473.153 | 200,918 | json |
| 3 | 1.824% | +84 | KMNIST 96.97% | 1,496.069 | 190,386 | json |
Three distinct GPU UUIDs; every call within 2% of its dataset’s median time. verification.json recomputes every verdict and the ranked times from the raw per-call data.
The first set of three runs of the same source (identical SHA-256) passed 2 of 3. Run 3 labelled 107,909 of 110,000 correctly, one fewer than the 107,910 the band requires (1.901% error), and was disqualified. No run of either set was dropped or replaced; the second set was run afterwards as a separate, complete set of three.
| Set 1 run | MNIST error | Margin, labels | Ranked ms | Record |
|---|---|---|---|---|
| 1 | 1.837% | +69 | 1,535.147 | json |
| 2 | 1.809% | +100 | 1,533.598 | json |
| 3 | 1.901% | -1 | disqualified | json |
Across all six official runs the source labelled 647,863 / 660,000 correctly (1.839% aggregate error); five of six runs passed. Set 1 verification. The margin is thinner than the width-256 entries’, so an occasional failed run is to be expected.
Source: submission.py, 15,223 bytes, SHA-256 d3bc8a2bf543c8db7f90e57d9b974532eb4e15d3f5415c1f79015ac34a2075a9
(identical in all six records). mnist.check_source passes and mnist.review_flags reports nothing. Source only:
scalar hyperparameters, no arrays, no fitted data.
x W^T + b -> RMSNorm without gain -> ReLU -> dropout 0.05. 2,200 updates of 2,048 labelled rows (+1,024
pseudo-labelled rows once cross-teaching starts), cosine schedule, EMA of the weights.torch.optim.AdamW).classify runs _load (new draw, its tangents) and _reset (weights, EMA,
Muon momentum, AdamW moments, update counter, pseudo-labels, pools, init seed) before any update; the warm-up call
only compiles and captures graphs, and every call runs in a fresh process.train_x, train_y, test_x. Query rows are used without labels, as in the D3 record.mnist.draw) scored outside the method. The unused RMSNorm gain tensors stay at their reset value 1./tmp at call time.dev/quick.py, not official scores)| Step (seeds 401-416 unless noted) | Mean error | ms per call |
|---|---|---|
| Width 256, 2,200 updates (#120) | 1.838-1.849% | ~1,900 |
| Width 128, dropout 0.1 | 2.024% | 1,327 |
| + dropout 0.05 + widened final readout | 1.872% (two runs); 1.881% on fresh seeds 501-516 | ~1,290 |
| + hidden bias (this file) | 1.841% / 1.842% (two runs) | ~1,440 |
With width 128, more updates (to 5,000), stronger tangent jitter, 10-16 members, and re-tuning Muon learning rate, weight decay, EMA decay, cross-teaching coverage and start, mixup strength and the tangent neighbourhood gave nothing beyond noise.
From mnist-a100:
python run_modal.py submissions/tangent-relu-w128-bias-d5-20261013/submission.py:classify --difficulty 5 --runs 3 --json out/d5-w128-bias