Pith Number

pith:A4NFLQRD

pith:2026:A4NFLQRDAGIGNU44UJTMLL5LKS

not attested not anchored not stored refs resolved

Do Language Models Align with Brains? Prediction Scores Are Not Enough

Xiao Jia

Language-model representations fail L-PACT alignment gates once nuisance controls and brain-brain ceilings are applied.

arxiv:2605.14025 v1 · 2026-05-13 · q-bio.NC · 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{A4NFLQRDAGIGNU44UJTMLL5LKS}

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

In the analyzed derived artifact set, the tested language-model representations do not satisfy L-PACT alignment gates; apparent positives are converted into an auditable control-explained taxonomy rather than treated as structural alignment.

C2weakest assumption

That the chosen nuisance baselines, acoustic-envelope gates, and brain-brain ceilings fully capture all alternative explanations for observed model-to-brain prediction scores without excluding genuine alignment signals.

C3one line summary

Language model representations fail all L-PACT alignment gates once controls explain the apparent predictive and relational effects.

References

64 extracted · 64 resolved · 4 Pith anchors

[1] A. G. Huth, W. A. de Heer, T. L. Griffiths, F. E. Theunissen, J. L. Gallant, Natural speech reveals the semantic maps that tile human cerebral cortex.Nature532, 453–458 (2016) 2016

[2] S. Jain, A. G. Huth, Incorporating context into language encoding models for fMRI.Advances in Neural Information Processing Systems31(2018) 2018

[3] Schrimpf et al., The neural architecture of language: Integrative modeling converges on predictive processing 2021

[4] C. Caucheteux, J.-R. King, Brains and algorithms partially converge in natural language processing.Communica- tions Biology5, 134 (2022) 2022

[5] Goldstein et al., Shared computational principles for language processing in humans and deep language models 2022

Receipt and verification

First computed	2026-05-17T23:39:12.901795Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

071a55c223019066d39ca266c5afab548edc31ae5071185a1acd8871d7d2c784

Aliases

arxiv: 2605.14025 · arxiv_version: 2605.14025v1 · doi: 10.48550/arxiv.2605.14025 · pith_short_12: A4NFLQRDAGIG · pith_short_16: A4NFLQRDAGIGNU44 · pith_short_8: A4NFLQRD

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/A4NFLQRDAGIGNU44UJTMLL5LKS \
  | 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: 071a55c223019066d39ca266c5afab548edc31ae5071185a1acd8871d7d2c784

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "91fe95e83078724db174dd5a14bff86befd1c4bbcc5505dbf006eee329e6554c",
    "cross_cats_sorted": [
      "cs.AI"
    ],
    "license": "http://creativecommons.org/licenses/by/4.0/",
    "primary_cat": "q-bio.NC",
    "submitted_at": "2026-05-13T18:37:17Z",
    "title_canon_sha256": "abfeb83775623184653b80ac89e231bfe4c8d6bd9e7be89f3697102ee01cc0b4"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2605.14025",
    "kind": "arxiv",
    "version": 1
  }
}