pith:XVWEDMQ3
LLM Jaggedness Unlocks Scientific Creativity
Uneven capabilities across LLMs allow model combinations to generate more scientific ideas than any single model.
arxiv:2605.10574 v2 · 2026-05-11 · cs.AI
Add to your LaTeX paper
\usepackage{pith}
\pithnumber{XVWEDMQ33PSSM6VXTHQXLIRZ7B}
Prints a linked badge after your title and injects PDF metadata. Compiles on arXiv. Learn more · Embed verified badge
Record completeness
Claims
we show that this jaggedness can be harnessed. We explore mechanisms of inference-time compute, knowledge pooling, and brainstorming to combine models effectively and construct meta-model ensembles that outperform any single model.
That the total number of valid responses is a reliable proxy for creative potential, and that human or automated judgment of uniqueness and coherence accurately captures scientific creativity without systematic bias.
LLMs exhibit jagged scientific creativity across models, prompts, and domains, and this unevenness can be leveraged via model ensembles to outperform any single model on idea generation.
Receipt and verification
| First computed | 2026-05-21T02:05:05.103096Z |
|---|---|
| Builder | pith-number-builder-2026-05-17-v1 |
| Signature | Pith Ed25519
(pith-v1-2026-05) · public key |
| Schema | pith-number/v1.0 |
Canonical hash
bd6c41b21bdbe5267ab799e175a239f8764b42b900220339987e236e0924285f
Aliases
· · · · ·Agent API
Verify this Pith Number yourself
curl -sH 'Accept: application/ld+json' https://pith.science/pith/XVWEDMQ33PSSM6VXTHQXLIRZ7B \
| 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: bd6c41b21bdbe5267ab799e175a239f8764b42b900220339987e236e0924285f
Canonical record JSON
{
"metadata": {
"abstract_canon_sha256": "61411a240af73605462fe32ae3315b900ee9a1f8ab8d3ca936170664cd5f930c",
"cross_cats_sorted": [],
"license": "http://creativecommons.org/licenses/by/4.0/",
"primary_cat": "cs.AI",
"submitted_at": "2026-05-11T13:47:48Z",
"title_canon_sha256": "923e4f649e9e323b741e5708b44b798a73e7ba9ea672cf389181e14941cf3f02"
},
"schema_version": "1.0",
"source": {
"id": "2605.10574",
"kind": "arxiv",
"version": 2
}
}