Pith Number

pith:J2OEYM5X

pith:2026:J2OEYM5X3HBEIJXEIJ5WLSGKIE

not attested not anchored not stored refs resolved

ECG-NAT: A Self-supervised Neighborhood Attention Transformer for Multi-lead Electrocardiogram Classification

Amjad Seyedi, Fardin Akhlaghian Tab, Fatemeh Daneshfar, Mahsa Gazeran, Sayvan Soleymanbaigi

ECG-NAT uses masked autoencoder pretraining on unlabeled signals and dual-loss fine-tuning to classify multi-lead ECG arrhythmias at 88.1 percent accuracy from only 1 percent labeled data.

arxiv:2605.13194 v1 · 2026-05-13 · cs.LG · cs.AI

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

Add to your LaTeX paper

\usepackage{pith}
\pithnumber{J2OEYM5X3HBEIJXEIJ5WLSGKIE}

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

ECG-NAT achieves robust performance on benchmark datasets, with 88.1% accuracy using only 1% labeled data, demonstrating strong efficacy in low-resource settings.

C2weakest assumption

That generative pretraining via masked autoencoder on multiple diverse unlabeled datasets produces robust domain-invariant representations that transfer effectively to the downstream classification task under the dual-loss fine-tuning regime.

C3one line summary

ECG-NAT combines masked autoencoder pretraining with hierarchical neighborhood attention and dual-loss fine-tuning to reach 88.1% accuracy on ECG classification using just 1% labeled data.

References

51 extracted · 51 resolved · 1 Pith anchors

[1] Detection of cardiovascular diseases in ecg images using machine learning and deep learning methods.IEEE transactions on artificial intelligence, 4(2):373–382, 2022 2022

[2] Bentham Science Publishers, 2013 2013

[3] Patricia Paglini-Oliva, MS Lo Presti, and H Walter Rivarola.Electrocardiography as a diagnos- tic method for Chagas disease in patients and experimental models. InTech, 2012 2012

[4] Convolutional neural network based automatic screening tool for cardiovascular diseases using different intervals of ECG signals 2021

[5] Chuang Han, Jiajia Sun, Yingnan Bian, Wenge Que, and Li Shi. Automated detection and localization of myocardial infarction with interpretability analysis based on deep learning.IEEE Transactions on In 2023

Receipt and verification

First computed	2026-05-18T03:08:48.761966Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

4e9c4c33b7d9c24426e4427b65c8ca411e289f156f947f1bc77ca6193a6dd404

Aliases

arxiv: 2605.13194 · arxiv_version: 2605.13194v1 · doi: 10.48550/arxiv.2605.13194 · pith_short_12: J2OEYM5X3HBE · pith_short_16: J2OEYM5X3HBEIJXE · pith_short_8: J2OEYM5X

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/J2OEYM5X3HBEIJXEIJ5WLSGKIE \
  | 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: 4e9c4c33b7d9c24426e4427b65c8ca411e289f156f947f1bc77ca6193a6dd404

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "68f58632a23dbf4326258e219bdad618c7070bca1087d25c95fde4417cdf5a49",
    "cross_cats_sorted": [
      "cs.AI"
    ],
    "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
    "primary_cat": "cs.LG",
    "submitted_at": "2026-05-13T08:50:00Z",
    "title_canon_sha256": "32765a0ce88f108cf3f709eb0e9b16ea6bb33cdcc44fa2317742ab51de9d04ec"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2605.13194",
    "kind": "arxiv",
    "version": 1
  }
}