Pith Number

pith:UKXF5G35

pith:2026:UKXF5G35BKCZTOC2NSAXFYNHZP

not attested not anchored not stored refs resolved

Evolving Layer-Specific Scalar Functions for Hardware-Aware Transformer Adaptation

Amirhossein Sadough, Kieran Carrigg, Marcel van Gerven, Sigur de Vries

Genetic programming evolves layer-specific scalar functions to replace layer normalization in Vision Transformers, recovering 84.25 percent Top-1 accuracy after only 20 epochs of re-alignment.

arxiv:2605.14047 v1 · 2026-05-13 · cs.CV · cs.AR

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

Add to your LaTeX paper

\usepackage{pith}
\pithnumber{UKXF5G35BKCZTOC2NSAXFYNHZP}

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

our evolved expressions accurately approximate the target normalization behaviours, capturing 91.6% of the variance (R²) compared to only 70.2% for homogeneous baselines, allowing our modified architecture to recover 84.25% Top-1 ImageNet-1K accuracy in only 20 epochs.

C2weakest assumption

That functions evolved via genetic programming from pre-trained weights will generalize to unseen inputs and that the post-training re-alignment strategy is sufficient to restore performance without full retraining from scratch.

C3one line summary

Genetic programming evolves heterogeneous layer-specific scalar functions to approximate layer normalization in pre-trained ViTs, capturing 91.6% variance versus 70.2% for uniform baselines and recovering 84.25% ImageNet Top-1 accuracy after 20 epochs of adaptation.

References

39 extracted · 39 resolved · 2 Pith anchors

[1] An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale 2010 · arXiv:2010.11929

[2] Object detection based on cnn and vision-transformer: A survey.IET Computer Vision, 19(1):e70028, 2025 2025

[3] End-to-end object detection with transformers 2020

[4] Semantic segmentation using vision transformers: A survey.Engineering Applications of Artificial Intelligence, 126:106669, 2023 2023

[5] Do vision transformers see like convolutional neural networks?Advances in Neural Information Processing Systems, 34:12116–12128, 2021 2021

Receipt and verification

First computed	2026-05-17T23:39:12.683460Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

a2ae5e9b7d0a8599b85a6c8172e1a7cbda8716a6d700936ff30e44d787180043

Aliases

arxiv: 2605.14047 · arxiv_version: 2605.14047v1 · doi: 10.48550/arxiv.2605.14047 · pith_short_12: UKXF5G35BKCZ · pith_short_16: UKXF5G35BKCZTOC2 · pith_short_8: UKXF5G35

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/UKXF5G35BKCZTOC2NSAXFYNHZP \
  | 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: a2ae5e9b7d0a8599b85a6c8172e1a7cbda8716a6d700936ff30e44d787180043

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "2f8572677c3b6d1b2bc044f83c85a0b18793b07d7eaf8a0d5ebaf8e5fe0dde26",
    "cross_cats_sorted": [
      "cs.AR"
    ],
    "license": "http://creativecommons.org/licenses/by-nc-nd/4.0/",
    "primary_cat": "cs.CV",
    "submitted_at": "2026-05-13T19:08:55Z",
    "title_canon_sha256": "0b25040dcf03e037b92079ae002f10664f1e943125c725bcceb93da1dbc63776"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2605.14047",
    "kind": "arxiv",
    "version": 1
  }
}