pith:PAHCUCRS
Decompose, Structure, and Repair: A Neuro-Symbolic Framework for Autoformalization via Operator Trees
A neuro-symbolic framework improves autoformalization by mapping statements to operator trees for targeted error repair.
arxiv:2604.19000 v2 · 2026-04-21 · cs.LG · cs.AI
Add to your LaTeX paper
\usepackage{pith}
\pithnumber{PAHCUCRSJZQ2WTS7XI7XRMQGTE}
Prints a linked badge after your title and injects PDF metadata. Compiles on arXiv. Learn more · Embed verified badge
Record completeness
Claims
DSR establishes a new state-of-the-art, consistently outperforming baselines under equivalent computational budgets.
That mapping natural-language statements to structured operator trees enables precise localization and repair of errors via sub-tree refinement, as stated in the abstract description of the framework.
DSR restructures autoformalization as a decompose-structure-repair process using operator trees and achieves new state-of-the-art results on the introduced PRIME benchmark of 156 theorems.
Receipt and verification
| First computed | 2026-05-25T02:01:20.767917Z |
|---|---|
| Builder | pith-number-builder-2026-05-17-v1 |
| Signature | Pith Ed25519
(pith-v1-2026-05) · public key |
| Schema | pith-number/v1.0 |
Canonical hash
780e2a0a324e61ab4e5fba3f78b206992146480e0a42a990e3c50d1710ee44db
Aliases
· · · · ·Agent API
Verify this Pith Number yourself
curl -sH 'Accept: application/ld+json' https://pith.science/pith/PAHCUCRSJZQ2WTS7XI7XRMQGTE \
| 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: 780e2a0a324e61ab4e5fba3f78b206992146480e0a42a990e3c50d1710ee44db
Canonical record JSON
{
"metadata": {
"abstract_canon_sha256": "0771252b613443b591a4b0ea76ac9ee6d1dcc071b509ac1662029896a9322d93",
"cross_cats_sorted": [
"cs.AI"
],
"license": "http://creativecommons.org/licenses/by/4.0/",
"primary_cat": "cs.LG",
"submitted_at": "2026-04-21T02:36:55Z",
"title_canon_sha256": "1bdc7a8ecc11b40c48a710c351f1747b7ca44d78cf188b8e815737495f427a98"
},
"schema_version": "1.0",
"source": {
"id": "2604.19000",
"kind": "arxiv",
"version": 2
}
}