Pith Number

pith:UYMJ37DD

pith:2026:UYMJ37DDBC2BS4SPXSYDE6RBXO

not attested not anchored not stored refs resolved

From Clever Hans to Scientific Discovery: Interpreting EEG Foundational Transformers with LRP

Bogdan Franczyk, Justus Meyer zu Bexten, Nico Scherf, Simon M. Hofmann

LRP on EEG foundation models can verify decisions and generate new biological hypotheses.

arxiv:2605.11885 v1 · 2026-05-12 · cs.AI · q-bio.NC

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

Add to your LaTeX paper

\usepackage{pith}
\pithnumber{UYMJ37DDBC2BS4SPXSYDE6RBXO}

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

We find that LRP can both verify EEG-FM decisions and surface novel, biologically plausible hypotheses from them.

C2weakest assumption

That the LRP heatmaps correspond to biologically meaningful signals rather than model artifacts or post-hoc interpretation ambiguities in the complex EEG domain.

C3one line summary

LRP on EEG transformers reveals Clever Hans artifacts in motor imagery tasks and a recurring central electrode cluster as a candidate sensorimotor signature of arousal.

References

66 extracted · 66 resolved · 1 Pith anchors

[1] Dingkun Liu et al.EEG Foundation Models: Progresses, Benchmarking, and Open Problems. Feb. 5, 2026.DOI:10.48550/arXiv.2601.17883. arXiv:2601.17883 [cs]. Pre-published 2026 · doi:10.48550/arxiv.2601.17883

[2] Large Brain Model for Learning Generic Represen- tations with Tremendous EEG Data in BCI 2023

[3] Cbramod: A criss-cross brain foundation model for eeg decoding 2025 · doi:10.48550/arxiv.2412.07236

[4] An Accurate and Rapidly Calibrating Speech Neuroprosthesis 2024

[5] On Pixel-Wise Explanations for Non-Linear Classifier Decisions by Layer- Wise Relevance Propagation 2015 · doi:10.1371/journal.pone.0130140

Receipt and verification

First computed	2026-05-20T00:00:42.922227Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

a6189dfc6308b419724fbcb0327a21bba78ff65d5b24f9b1bf3742f6626a92fa

Aliases

arxiv: 2605.11885 · arxiv_version: 2605.11885v1 · doi: 10.48550/arxiv.2605.11885 · pith_short_12: UYMJ37DDBC2B · pith_short_16: UYMJ37DDBC2BS4SP · pith_short_8: UYMJ37DD

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/UYMJ37DDBC2BS4SPXSYDE6RBXO \
  | 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: a6189dfc6308b419724fbcb0327a21bba78ff65d5b24f9b1bf3742f6626a92fa

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "ce4e732286553f0e252d998d094984f690a65a7fc9516c6d4dbbdffad2b47ec3",
    "cross_cats_sorted": [
      "q-bio.NC"
    ],
    "license": "http://creativecommons.org/licenses/by/4.0/",
    "primary_cat": "cs.AI",
    "submitted_at": "2026-05-12T09:59:14Z",
    "title_canon_sha256": "6131a09a8e081b37cdb816184e03f69ae40554dca2a86d41b69437cb56a3d51a"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2605.11885",
    "kind": "arxiv",
    "version": 1
  }
}