pith:CUPB2KUC
Fix Initial Programs and Iteratively Refine Repair Instructions Toward Non-Elimination Multi-Turn Program Correction
Fixing initial codes and iteratively refining textual directions achieves comparable performance to state-of-the-art code correction methods and permits a formal safety proof.
arxiv:2604.23989 v2 · 2026-04-27 · cs.LG · cs.AI
Add to your LaTeX paper
\usepackage{pith}
\pithnumber{CUPB2KUCZZKM5J4MSP5UETCLVX}
Prints a linked badge after your title and injects PDF metadata. Compiles on arXiv. Learn more · Embed verified badge
Record completeness
Claims
Experiments on several code generation benchmarks suggest that IRTD achieves inference performance comparable to state-of-the-art methods. Because of the simplicity of IRTD, we theoretically establish the safety of IRTD using Oracle-Guided Inductive Synthesis (OGIS).
That the theoretical safety proof via Oracle-Guided Inductive Synthesis applies directly to the practical IRTD implementation and that benchmark results generalize without detailed statistical controls or error analysis.
IRTD fixes initial codes and iteratively refines textual directions to achieve safe multi-turn code correction with performance comparable to the more complex Scattered Forest Search method.
Receipt and verification
| First computed | 2026-06-24T01:15:03.049046Z |
|---|---|
| Builder | pith-number-builder-2026-05-17-v1 |
| Signature | Pith Ed25519
(pith-v1-2026-05) · public key |
| Schema | pith-number/v1.0 |
Canonical hash
151e1d2a82ce54cea78c93fb424c4badf7cdd05c20ac517259c992554d10e6de
Aliases
· · · · ·Agent API
Verify this Pith Number yourself
curl -sH 'Accept: application/ld+json' https://pith.science/pith/CUPB2KUCZZKM5J4MSP5UETCLVX \
| 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: 151e1d2a82ce54cea78c93fb424c4badf7cdd05c20ac517259c992554d10e6de
Canonical record JSON
{
"metadata": {
"abstract_canon_sha256": "a75fdc9b45a13d75175d2e1a4e212ac1c0dbd368a262a3b47cb0beb5fef13b11",
"cross_cats_sorted": [
"cs.AI"
],
"license": "http://creativecommons.org/licenses/by/4.0/",
"primary_cat": "cs.LG",
"submitted_at": "2026-04-27T03:07:34Z",
"title_canon_sha256": "79397225d84a9ac4a9526c03c4a93fa999653c1e5612ac53e4e358d873e7eaec"
},
"schema_version": "1.0",
"source": {
"id": "2604.23989",
"kind": "arxiv",
"version": 2
}
}