pith:QDRDPX6V
Residual Stream Duality in Modern Transformer Architectures
The residual stream in Transformers is equivalent to causal short sliding-window attention when interpreted over layer depth instead of sequence positions.
arxiv:2603.16039 v2 · 2026-03-17 · cs.LG · cs.AI · cs.CL
Add to your LaTeX paper
\usepackage{pith}
\pithnumber{QDRDPX6VG2XO2EQ7GT4NP2GWOH}
Prints a linked badge after your title and injects PDF metadata. Compiles on arXiv. Learn more · Embed verified badge
Record completeness
Claims
a causal depth-wise residual attention read is exactly the same local operator as causal short sliding-window attention (ShortSWA), except written over depth rather than over sequence. This is the core residual stream duality behind Transformer².
That treating layer index as an ordered variable and reinterpreting fixed residual addition as causal depth-wise attention produces a meaningful and actionable operator equivalence, even though the paper states operator-level duality does not imply systems-level symmetry.
Residual stream addition over depth is the same local operator as causal short sliding-window attention over sequence positions.
Formal links
Cited by
Receipt and verification
| First computed | 2026-05-17T23:38:59.635560Z |
|---|---|
| Builder | pith-number-builder-2026-05-17-v1 |
| Signature | Pith Ed25519
(pith-v1-2026-05) · public key |
| Schema | pith-number/v1.0 |
Canonical hash
80e237dfd536aeed121f34f8d7e8d671f4b78230b02122d902ca88241561836d
Aliases
· · · · ·Agent API
Verify this Pith Number yourself
curl -sH 'Accept: application/ld+json' https://pith.science/pith/QDRDPX6VG2XO2EQ7GT4NP2GWOH \
| 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: 80e237dfd536aeed121f34f8d7e8d671f4b78230b02122d902ca88241561836d
Canonical record JSON
{
"metadata": {
"abstract_canon_sha256": "7effd2bd771efce4f30668994ead6c42326b4f138da9003c7778af433e90101c",
"cross_cats_sorted": [
"cs.AI",
"cs.CL"
],
"license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
"primary_cat": "cs.LG",
"submitted_at": "2026-03-17T00:56:29Z",
"title_canon_sha256": "ed2e4cdef73dafbdc8737d75e9c4617db3fe6195084c68ffb224e6e5ca58a20c"
},
"schema_version": "1.0",
"source": {
"id": "2603.16039",
"kind": "arxiv",
"version": 2
}
}