pith:4E44RJ5Z
Dual-Dimensional Consistency: Balancing Budget and Quality in Adaptive Inference-Time Scaling
DDC reduces token consumption by over 10x in LLM reasoning while maintaining or exceeding baseline accuracy across five benchmarks via adaptive path quality filtering.
arxiv:2605.15100 v1 · 2026-05-14 · cs.AI
Add to your LaTeX paper
\usepackage{pith}
\pithnumber{4E44RJ5Z4HTGZRZO6DDYCVEOHF}
Prints a linked badge after your title and injects PDF metadata. Compiles on arXiv. Learn more · Embed verified badge
Record completeness
Claims
Evaluations across five benchmarks demonstrate that this approach reduces token consumption by over 10 times while maintaining or exceeding the accuracy of strong baselines across various LLMs.
The assumption that Confidence-Weighted Bayesian protocol combined with Trend-Aware Stratified Pruning will reliably concentrate compute on high-quality paths and filter hallucinations without discarding valid complex reasoning chains.
DDC reduces token consumption by over 10x in LLM reasoning while maintaining or exceeding baseline accuracy across five benchmarks via adaptive path quality filtering.
Receipt and verification
| First computed | 2026-05-17T21:40:25.823376Z |
|---|---|
| Last reissued | 2026-05-17T21:57:19.153888Z |
| Builder | pith-number-builder-2026-05-17-v1 |
| Signature | unsigned_v0 |
| Schema | pith-number/v1.0 |
Canonical hash
e139c8a7b9e1e66cc72ef0c781548e397202b6f48ee39256843533821ff40a9a
Aliases
· · · ·Agent API
Verify this Pith Number yourself
curl -sH 'Accept: application/ld+json' https://pith.science/pith/4E44RJ5Z4HTGZRZO6DDYCVEOHF \
| 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: e139c8a7b9e1e66cc72ef0c781548e397202b6f48ee39256843533821ff40a9a
Canonical record JSON
{
"metadata": {
"abstract_canon_sha256": "9701e68219796e9e081a93fdb4732af9364d967aecaa2c84ee0666ce8f388020",
"cross_cats_sorted": [],
"license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
"primary_cat": "cs.AI",
"submitted_at": "2026-05-14T17:19:37Z",
"title_canon_sha256": "5c73f0fba184df04ef8d25a76d97e7d66297d24eea947de7cbb6af73152e373a"
},
"schema_version": "1.0",
"source": {
"id": "2605.15100",
"kind": "arxiv",
"version": 1
}
}