Pith Number

pith:TRUGLNEY

pith:2026:TRUGLNEYCVTCWBGR5NFDZCCGZC

not attested not anchored not stored refs pending

CheeseBench: Evaluating Large Language Models on Rodent Behavioral Neuroscience Paradigms

Zacharie Bugaud

Open-weight LLMs reach only 53 percent success on ASCII versions of classic rodent tasks where animals average 79 percent.

arxiv:2604.10825 v2 · 2026-04-12 · 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{TRUGLNEYCVTCWBGR5NFDZCCGZC}

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

Under this unified zero-shot ASCII protocol, current open-weight LLM agents remain well below approximate rodent reference values, particularly on tasks requiring spatial navigation and within-trial state tracking.

C2weakest assumption

The ASCII text renderings of the tasks accurately capture the core cognitive and perceptual demands of the original rodent behavioral paradigms without introducing artifacts that alter difficulty.

C3one line summary

LLMs reach 52.6% average success on text-based rodent neuroscience tasks, above random agents at 32.1% but below approximate rodent baselines at 78.9%.

Cited by

2 papers in Pith

NeuroState-Bench: A Human-Calibrated Benchmark for Commitment Integrity in LLM Agent Profiles

Receipt and verification

First computed	2026-05-20T00:02:11.383748Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

9c6865b49815662b04d1eb4a3c8846c8a88940d2d5b183bd1745e0fc9bbe1c1c

Aliases

arxiv: 2604.10825 · arxiv_version: 2604.10825v2 · doi: 10.48550/arxiv.2604.10825 · pith_short_12: TRUGLNEYCVTC · pith_short_16: TRUGLNEYCVTCWBGR · pith_short_8: TRUGLNEY

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/TRUGLNEYCVTCWBGR5NFDZCCGZC \
  | 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: 9c6865b49815662b04d1eb4a3c8846c8a88940d2d5b183bd1745e0fc9bbe1c1c

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "35e2ab0f93727970a58e0e2eca64eecb02bbba26445ccaf8c784cae24d4deca6",
    "cross_cats_sorted": [],
    "license": "http://creativecommons.org/licenses/by/4.0/",
    "primary_cat": "cs.AI",
    "submitted_at": "2026-04-12T21:37:26Z",
    "title_canon_sha256": "8f76097af32e619e69f6c0dad621447ae762ed1b9987f839b3732ab83cd5a33d"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2604.10825",
    "kind": "arxiv",
    "version": 2
  }
}