Pith Number

pith:6M5JYGMH

pith:2026:6M5JYGMHE6QY4AVQVT7TL2OX7Z

not attested not anchored not stored refs resolved

Layer-wise Derivative Controlled Networks

Rowan Martnishn, Sean Anderson

ChainzRule replaces standard activations with a Polynomial Engine under layer-wise Differential Regularization to cut parameters while lowering gradient volatility.

arxiv:2605.15463 v1 · 2026-05-14 · 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{6M5JYGMHE6QY4AVQVT7TL2OX7Z}

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

ChainzRule outperformed standard models while using 15.5x fewer parameters; on MNIST it reduced peak gradient volatility by 23.1% and on Yelp Full it reached 70.17% accuracy under explicit DREG regularization.

C2weakest assumption

That the 'Fair Fight' benchmarks use identical training protocols, data splits, and hyperparameter tuning for baselines and that DREG preserves full representational capacity of the Polynomial Engine without post-hoc adjustments that favor the proposed model.

C3one line summary

ChainzRule with DREG regularization claims 15.5x fewer parameters than standard models, 23.1% lower peak gradient volatility on MNIST, and 70.17% accuracy on Yelp Full ordinal regression.

References

19 extracted · 19 resolved · 14 Pith anchors

[1] URLhttps://pmc.ncbi 2024 · doi:10.3389/fdata.2024.12705377

[2] Neural Ordinary Differential Equations · arXiv:1806.07366

[3] Neural Ordinary Differential Equations · doi:10.48550/arxiv.1806.07366

[4] Parseval Networks: Improving Robustness to Adversarial Examples · doi:10.48550/arxiv.1704.08847

[5] Sobolev training for neural networks · arXiv:1706.04859

Formal links

2 machine-checked theorem links

Receipt and verification

First computed	2026-05-20T00:00:59.852548Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

f33a9c198727a18e02b0acff35e9d7fe4dc3a3dd8501d8b2841897df6daa264a

Aliases

arxiv: 2605.15463 · arxiv_version: 2605.15463v1 · doi: 10.48550/arxiv.2605.15463 · pith_short_12: 6M5JYGMHE6QY · pith_short_16: 6M5JYGMHE6QY4AVQ · pith_short_8: 6M5JYGMH

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/6M5JYGMHE6QY4AVQVT7TL2OX7Z \
  | 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: f33a9c198727a18e02b0acff35e9d7fe4dc3a3dd8501d8b2841897df6daa264a

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "491b5f697383889b86ecee0b1434b3a25afae001d0cc677f359033aacfadee16",
    "cross_cats_sorted": [],
    "license": "http://creativecommons.org/publicdomain/zero/1.0/",
    "primary_cat": "cs.LG",
    "submitted_at": "2026-05-14T22:57:51Z",
    "title_canon_sha256": "5b0ccb7fbf378ee7a75551319777d324302f0b7bc8417586774696849b46b0de"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2605.15463",
    "kind": "arxiv",
    "version": 1
  }
}