pith:CEGTEPVJ
PiCSAR: Probabilistic Confidence Selection And Ranking for Reasoning Chains
A training-free score based on the joint log-likelihood of reasoning steps and final answer selects correct chains more reliably than prior methods.
arxiv:2508.21787 v3 · 2025-08-29 · cs.CL · cs.AI
Add to your LaTeX paper
\usepackage{pith}
\pithnumber{CEGTEPVJ35YBGDPQGU73H6QQJJ}
Prints a linked badge after your title and injects PDF metadata. Compiles on arXiv. Learn more · Embed verified badge
Record completeness
Claims
PiCSAR achieves substantial gains across diverse benchmarks (+10.18 on MATH500, +9.81 on AIME2025), outperforming baselines with at least 2x fewer samples in 16 out of 20 comparisons.
Correct reasoning chains exhibit significantly higher reasoning and answer confidence (as measured by joint log-likelihood) than incorrect ones, allowing the scoring function to identify them reliably.
PiCSAR ranks reasoning chains by joint log-likelihood of reasoning and answer to select better outputs, delivering large gains on math benchmarks with reduced sampling.
Formal links
Receipt and verification
| First computed | 2026-07-14T02:22:28.666784Z |
|---|---|
| Builder | pith-number-builder-2026-05-17-v1 |
| Signature | Pith Ed25519
(pith-v1-2026-05) · public key |
| Schema | pith-number/v1.0 |
Canonical hash
110d323ea9df70130df0353fb3fa104a6c052c984d7456a16fc1b4eee68d4bc8
Aliases
· · · · ·Agent API
Verify this Pith Number yourself
curl -sH 'Accept: application/ld+json' https://pith.science/pith/CEGTEPVJ35YBGDPQGU73H6QQJJ \
| 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: 110d323ea9df70130df0353fb3fa104a6c052c984d7456a16fc1b4eee68d4bc8
Canonical record JSON
{
"metadata": {
"abstract_canon_sha256": "e44f8eea31d98b461605e3f2ff11d0389556a1faf74a1a2d317edf259c145676",
"cross_cats_sorted": [
"cs.AI"
],
"license": "http://creativecommons.org/licenses/by/4.0/",
"primary_cat": "cs.CL",
"submitted_at": "2025-08-29T17:03:47Z",
"title_canon_sha256": "d4eb40fad596d1a0a907358e2c298c3e43fadd343b6929fd595d78c586929333"
},
"schema_version": "1.0",
"source": {
"id": "2508.21787",
"kind": "arxiv",
"version": 3
}
}