pith:23ZEPV2Y
CoFrGeNet: Continued Fraction Architectures for Language Generation
Continued-fraction components replace attention and feed-forward layers in large transformers with half to two-thirds the parameters while matching or exceeding performance on language tasks.
arxiv:2601.21766 v4 · 2026-01-29 · cs.CL · cs.AI
Add to your LaTeX paper
\usepackage{pith}
\pithnumber{23ZEPV2YBMQQWAXTUCS4GTVTML}
Prints a linked badge after your title and injects PDF metadata. Compiles on arXiv. Learn more · Embed verified badge
Record completeness
Claims
Results show that the performance on downstream classification, Q&A, reasoning and text understanding tasks of our models is competitive and sometimes even superior to the original models with 2/3 to 1/2 the parameters and shorter pre-training time.
That continued-fraction components can preserve the modeling capacity of attention and feed-forward layers while using far fewer parameters, and that the custom gradient rules produce stable optimization across large-scale pre-training.
CoFrGeNet uses continued-fraction function classes to build transformer replacements that match or beat GPT-2 and Llama performance with half to two-thirds the parameters.
Formal links
Receipt and verification
| First computed | 2026-05-25T02:02:12.892377Z |
|---|---|
| Builder | pith-number-builder-2026-05-17-v1 |
| Signature | Pith Ed25519
(pith-v1-2026-05) · public key |
| Schema | pith-number/v1.0 |
Canonical hash
d6f247d7580b210b02f3a0a5c34eb362e434871a361617d108dca7ace156604d
Aliases
· · · · ·Agent API
Verify this Pith Number yourself
curl -sH 'Accept: application/ld+json' https://pith.science/pith/23ZEPV2YBMQQWAXTUCS4GTVTML \
| 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: d6f247d7580b210b02f3a0a5c34eb362e434871a361617d108dca7ace156604d
Canonical record JSON
{
"metadata": {
"abstract_canon_sha256": "cd8be869b46ce6ae8e1dc41fa4026452bb7fb98020eba61eb7978cd0b08053fc",
"cross_cats_sorted": [
"cs.AI"
],
"license": "http://creativecommons.org/licenses/by/4.0/",
"primary_cat": "cs.CL",
"submitted_at": "2026-01-29T14:16:39Z",
"title_canon_sha256": "c3fb0b68e932ede11292cdb8cf8460f267c04394665d0887589e98bfb3aef976"
},
"schema_version": "1.0",
"source": {
"id": "2601.21766",
"kind": "arxiv",
"version": 4
}
}