Pith Number

pith:U7EFB22J

pith:2025:U7EFB22JO2J4IDTVUHJU76CAOS

not attested not anchored not stored refs resolved

mHC: Manifold-Constrained Hyper-Connections

Chenggang Zhao, Chengqi Deng, Damai Dai, Huanqi Cao, Huazuo Gao, Jiang Chang, Jiashi Li, Jingyang Yuan, Kuai Yu, Lean Wang, Liang Zhao, Shangyan Zhou, Shengding Hu, Wangding Zeng, Wenfeng Liang, Yixuan Wei, Yuqing Wang, Zhean Xu, Zhenda Xie, Zhengyan Zhang

Projecting hyper-connection residuals onto a manifold restores identity mapping for stable large-scale training.

arxiv:2512.24880 v2 · 2025-12-31 · cs.CL · cs.AI · cs.LG

Open paper page JSON Open Graph Bundle Merged state Verified badge What is a Pith Number?

Add to your LaTeX paper

\usepackage{pith}
\pithnumber{U7EFB22JO2J4IDTVUHJU76CAOS}

Prints a linked badge after your title and injects PDF metadata. Compiles on arXiv. Learn more · Embed verified badge

Record completeness

1 Bitcoin timestamp

2 Internet Archive

3 Author claim open · sign in to claim

4 Citations open

5 Replications open

✓ Portable graph bundle live · download bundle · merged state

The bundle contains the canonical record plus signed events. A mirror can host it anywhere and recompute the same current state with the deterministic merge algorithm.

Claims

C1strongest claim

Empirical experiments demonstrate that mHC is effective for training at scale, offering tangible performance improvements and superior scalability.

C2weakest assumption

That projecting the residual connection space of HC onto a specific manifold restores the identity mapping property while preserving the performance benefits of diversified connectivity patterns.

C3one line summary

mHC projects hyper-connection residual spaces onto a manifold to restore identity mapping, enabling stable large-scale training with performance gains over standard HC.

References

44 extracted · 44 resolved · 14 Pith anchors

[1] Proceedings of the IEEE conference on computer vision and pattern recognition , pages=

[2] European conference on computer vision , pages= 2016

[3] Proceedings of the IEEE conference on computer vision and pattern recognition , pages=

[4] FractalNet: Ultra-deep neural net- works without residuals · arXiv:1605.07648

[5] Advances in neural information processing systems , volume=

Formal links

2 machine-checked theorem links

Cited by

37 papers in Pith

S$^3$GNN: Efficient Global Mixing and Local Message Passing for Long-Range Graph Learning

Multi-Gate Residuals

SiameseNorm: Breaking the Barrier to Reconciling Pre/Post-Norm

TBP-mHC: full expressivity for manifold-constrained hyper connections through transportation polytopes

Exact Linear Attention

Receipt and verification

First computed	2026-05-17T23:38:52.547741Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

a7c850eb497693c40e75a1d34ff84074b5524167c32ff72f9632a4524f8fa5c2

Aliases

arxiv: 2512.24880 · arxiv_version: 2512.24880v2 · doi: 10.48550/arxiv.2512.24880 · pith_short_12: U7EFB22JO2J4 · pith_short_16: U7EFB22JO2J4IDTV · pith_short_8: U7EFB22J

Agent API

Resolver JSON Graph JSON Events JSON Schema Signing key

Verify this Pith Number yourself

curl -sH 'Accept: application/ld+json' https://pith.science/pith/U7EFB22JO2J4IDTVUHJU76CAOS \
  | 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: a7c850eb497693c40e75a1d34ff84074b5524167c32ff72f9632a4524f8fa5c2

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "695fd47b14de1eaf1636c62dc4b0d17786c118c29a5ee24449d7df3f1a067fc1",
    "cross_cats_sorted": [
      "cs.AI",
      "cs.LG"
    ],
    "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
    "primary_cat": "cs.CL",
    "submitted_at": "2025-12-31T14:16:26Z",
    "title_canon_sha256": "9993aff5599a2f3a5b8c8f95353f9664ca12b81962583c7dd2d607e1559256e4"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2512.24880",
    "kind": "arxiv",
    "version": 2
  }
}