pith:MZTCH4TH
Generative structure search for efficient and diverse discovery of molecular and crystal structures
Generative structure search recovers diverse metastable molecular and crystal structures with more than tenfold lower sampling cost than random search.
arxiv:2604.27636 v2 · 2026-04-30 · cs.AI
Add to your LaTeX paper
\usepackage{pith}
\pithnumber{MZTCH4TH5HBX3IOERP327FQKXG}
Prints a linked badge after your title and injects PDF metadata. Compiles on arXiv. Learn more · Embed verified badge
Record completeness
Claims
Across molecular and crystalline systems, GSS recovers diverse metastable structures with more than tenfold lower sampling cost than RSS for broad coverage and remains effective for compositions outside the training distribution.
That learned score fields from diffusion models can be stably coupled with physical forces in a shared sampling process such that the hybrid retains the exploration benefits of RSS while gaining the speed of data-driven generation, without introducing systematic biases or missing physically relevant minima.
GSS unifies diffusion generation and random structure search into a single sampling process using learned scores and physical forces, recovering diverse metastable structures at over tenfold lower cost than pure RSS while working outside training distributions.
Receipt and verification
| First computed | 2026-05-26T01:03:31.485569Z |
|---|---|
| Builder | pith-number-builder-2026-05-17-v1 |
| Signature | Pith Ed25519
(pith-v1-2026-05) · public key |
| Schema | pith-number/v1.0 |
Canonical hash
666623f267e9c37da1c48bf7af960ab9bd53e8a12091083ac85f209863144c8d
Aliases
· · · · ·Agent API
Verify this Pith Number yourself
curl -sH 'Accept: application/ld+json' https://pith.science/pith/MZTCH4TH5HBX3IOERP327FQKXG \
| 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: 666623f267e9c37da1c48bf7af960ab9bd53e8a12091083ac85f209863144c8d
Canonical record JSON
{
"metadata": {
"abstract_canon_sha256": "eb5e8e661abacc44009b3183e9933fc4a01844ac8ecc742c8b46a47cf7d3ac20",
"cross_cats_sorted": [],
"license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
"primary_cat": "cs.AI",
"submitted_at": "2026-04-30T09:26:05Z",
"title_canon_sha256": "59e358f30196d357d85c6a06d693c7cfd5634dcbb2f2d7253f1265417abd1f41"
},
"schema_version": "1.0",
"source": {
"id": "2604.27636",
"kind": "arxiv",
"version": 2
}
}