Pith Number

pith:PWZJFKS5

pith:2025:PWZJFKS5H54WFOTLR7BPMRXGOS

not attested not anchored not stored refs resolved

A cross-species neural foundation model for end-to-end speech decoding

Chaofei Fan, Francis R Willett, Han Yu, Jingyuan Li, Lea Duncker, Liam Paninski, Linyang He, Nima Mesgarani, Scott Linderman, Tingkai Liu, Trung Le, Yizi Zhang

A cross-species pretrained neural encoder enables end-to-end decoding of brain activity into sentences at 10.22 percent word error rate.

arxiv:2511.21740 v5 · 2025-11-21 · cs.CL · 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{PWZJFKS5H54WFOTLR7BPMRXGOS}

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

Integrated end-to-end with audio large language models and trained with contrastive learning for cross-modal alignment, BIT reduces the word error rate (WER) of the prior end-to-end method from 24.69% to 10.22%.

C2weakest assumption

The representations learned by the cross-species pretrained neural encoder transfer effectively and without major domain shift to human attempted and imagined speech recordings used in the Brain-to-Text benchmarks.

C3one line summary

A cross-species pretrained neural encoder combined with end-to-end training and audio LLMs reduces word error rate in neural speech decoding from 24.69% to 10.22% while aligning attempted and imagined speech.

References

25 extracted · 25 resolved · 8 Pith anchors

[1] Qwen2-Audio Technical Report · arXiv:2407.10759

[2] Time-masked trans- formers with lightweight test-time adaptation for neural speech decoding.arXiv preprint arXiv:2507.02800,

[3] Towards an end-to-end framework for invasive brain signal decoding with large language models.arXiv preprint arXiv:2406.11568,

[4] The Curious Case of Neural Text Degeneration 1904 · arXiv:1904.09751

[5] Stabilizing brain- computer interfaces through alignment of latent dynamics 2022 · doi:10.1101/2022.04

Formal links

2 machine-checked theorem links

Cited by

2 papers in Pith

DANCE: Detect and Classify Events in EEG

MoDAl: Self-Supervised Neural Modality Discovery via Decorrelation for Speech Neuroprosthesis

Receipt and verification

First computed	2026-05-17T23:39:17.016781Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

7db292aa5d3f7962ba6b8fc2f646e674b070823c08611f0f0686311a49791fdd

Aliases

arxiv: 2511.21740 · arxiv_version: 2511.21740v5 · doi: 10.48550/arxiv.2511.21740 · pith_short_12: PWZJFKS5H54W · pith_short_16: PWZJFKS5H54WFOTL · pith_short_8: PWZJFKS5

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/PWZJFKS5H54WFOTLR7BPMRXGOS \
  | 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: 7db292aa5d3f7962ba6b8fc2f646e674b070823c08611f0f0686311a49791fdd

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "e5f815a0ec10f45c4c748ca0849fbca13846f2101c21b7a47c051e26bdf7c708",
    "cross_cats_sorted": [
      "cs.AI"
    ],
    "license": "http://creativecommons.org/licenses/by/4.0/",
    "primary_cat": "cs.CL",
    "submitted_at": "2025-11-21T21:25:54Z",
    "title_canon_sha256": "c121b2147897fb3756c9351b2dd1f12314a87174fb6eabc56739d505caac29cf"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2511.21740",
    "kind": "arxiv",
    "version": 5
  }
}