Pith Number

pith:DOJBNU2Z

pith:2026:DOJBNU2ZAMAZKP474LOEFAXDL4

not attested not anchored not stored refs resolved

Spectral Priors vs. Attention: Investigating the Utility of Attention Mechanisms in EEG-Based Diagnosis

Gowtham Atluri, Tawsik Jawad, Vikram Ravindra

Spectral isolation in EEG signals allows traditional machine learning models to match or surpass attention-based deep learning for disease classification.

arxiv:2605.15433 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{DOJBNU2ZAMAZKP474LOEFAXDL4}

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

features derived from frequency and time frequency domain allow traditional machine learning models to match or exceed the performance of SOTA deep learning models; Attention mechanism is unable to distill the stable feature signatures that characterize healthy neural activity in both resting and task EEGs; the limitations of attention based models in finding relevant spectral features appear to be fundamental in that providing frequency selective time domain input do not appreciably improve their performance.

C2weakest assumption

The open-source EEG datasets used are sufficiently representative of clinical variability and that class separability improvements come specifically from the spectral isolation rather than from other unstated preprocessing or model choices.

C3one line summary

Spectral features from EEG frequency and time-frequency domains enable traditional ML models to match or exceed SOTA deep learning performance, while attention shows fundamental limits in capturing stable neural signatures.

References

27 extracted · 27 resolved · 4 Pith anchors

[1] Simplified welch algorithm for spectrum monitoring 2020

[2] Nearest neighbors in high-dimensional data: The emergence and influence of hubs 2009

[3] Linear and Quadratic Discriminant Analysis: Tutorial 2019 · arXiv:1906.02590

[4] Medformer: A multi-granularity patching transformer for medical time-series classification 2024

[5] Autoformer: Decomposition transformers with auto-correlation for long-term series forecasting 2021

Receipt and verification

First computed	2026-05-20T00:00:58.408468Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

1b9216d3590301953f9fe2dc4282e35f3e777f0691c81466cfd2f302eb7e90da

Aliases

arxiv: 2605.15433 · arxiv_version: 2605.15433v1 · doi: 10.48550/arxiv.2605.15433 · pith_short_12: DOJBNU2ZAMAZ · pith_short_16: DOJBNU2ZAMAZKP47 · pith_short_8: DOJBNU2Z

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/DOJBNU2ZAMAZKP474LOEFAXDL4 \
  | 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: 1b9216d3590301953f9fe2dc4282e35f3e777f0691c81466cfd2f302eb7e90da

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "5c9940206f06b178bec56b6734f0df9cdf1a256d31abbc3f80493507f20dca1c",
    "cross_cats_sorted": [],
    "license": "http://creativecommons.org/licenses/by/4.0/",
    "primary_cat": "cs.LG",
    "submitted_at": "2026-05-14T21:26:07Z",
    "title_canon_sha256": "74aebedea58f319f0046963f9a78e002ae4c50f7f603a33ef6de1fd7bc79f551"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2605.15433",
    "kind": "arxiv",
    "version": 1
  }
}