pith:I3CPQ63N
Beyond Linearity in Attention Projections: The Case for Nonlinear Queries
Replacing the linear query projection with identity plus a small bottleneck MLP improves validation log-loss by 2.4 percent in GPT-style models.
arxiv:2603.13381 v3 · 2026-03-11 · cs.LG · cs.AI
Add to your LaTeX paper
\usepackage{pith}
\pithnumber{I3CPQ63NKWO2XCMKN6PTMHPTIJ}
Prints a linked badge after your title and injects PDF metadata. Compiles on arXiv. Learn more · Embed verified badge
Record completeness
Claims
Experiments on GPT-3 small style models show consistent improvement over the baseline (2.40% lower validation log-loss, 6.81% lower perplexity), comfortably outperforming a model with 12.5% more non-embedding parameters.
That the basis transformations absorbed by adjacent layers remain stable when the query projection is made nonlinear and that the small MLP does not introduce optimization instabilities at the tested scale.
Nonlinear query projections of the form X + MLP(X) improve transformer performance on small models with only d² + O(d) added parameters.
Receipt and verification
| First computed | 2026-05-27T01:04:57.215379Z |
|---|---|
| Builder | pith-number-builder-2026-05-17-v1 |
| Signature | Pith Ed25519
(pith-v1-2026-05) · public key |
| Schema | pith-number/v1.0 |
Canonical hash
46c4f87b6d559dab898a6f9f361df3427f32d746d42c902acd9afcbbdb567555
Aliases
· · · · ·Agent API
Verify this Pith Number yourself
curl -sH 'Accept: application/ld+json' https://pith.science/pith/I3CPQ63NKWO2XCMKN6PTMHPTIJ \
| jq -c '.canonical_record' \
| python3 -c "import sys,json,hashlib; b=json.dumps(json.loads(sys.stdin.read()), sort_keys=True, separators=(',',':'), ensure_ascii=False).encode(); print(hashlib.sha256(b).hexdigest())"
# expect: 46c4f87b6d559dab898a6f9f361df3427f32d746d42c902acd9afcbbdb567555
Canonical record JSON
{
"metadata": {
"abstract_canon_sha256": "08ed397f88febbe07b6a0ffb9f291c4479b617a901fa0ccc23215fbf80cc6831",
"cross_cats_sorted": [
"cs.AI"
],
"license": "http://creativecommons.org/licenses/by/4.0/",
"primary_cat": "cs.LG",
"submitted_at": "2026-03-11T03:13:10Z",
"title_canon_sha256": "c078383ab9c6950b4a8b2163a0b527fe12d53317c4b9abde170fb63f272e271d"
},
"schema_version": "1.0",
"source": {
"id": "2603.13381",
"kind": "arxiv",
"version": 3
}
}