Pith Number

pith:5CB62F5S

pith:2025:5CB62F5S426VGG2FZUHOBOMXII

not attested not anchored not stored refs pending

Deep Think with Confidence

Jiawei Zhao, Xuewei Wang, Yichao Fu, Yuandong Tian

DeepConf uses model-internal confidence to filter weak reasoning traces, reaching 99.9% accuracy on AIME 2025 while cutting tokens by 84.7%.

arxiv:2508.15260 v1 · 2025-08-21 · cs.LG

Open paper page JSON Open Graph Bundle Merged state Verified badge What is a Pith Number?

Add to your LaTeX paper

\usepackage{pith}
\pithnumber{5CB62F5S426VGG2FZUHOBOMXII}

Prints a linked badge after your title and injects PDF metadata. Compiles on arXiv. Learn more · Embed verified badge

Record completeness

1 Bitcoin timestamp

2 Internet Archive

3 Author claim open · sign in to claim

4 Citations open

5 Replications open

✓ Portable graph bundle live · download bundle · merged state

The bundle contains the canonical record plus signed events. A mirror can host it anywhere and recompute the same current state with the deterministic merge algorithm.

Claims

C1strongest claim

on challenging benchmarks such as AIME 2025, DeepConf@512 achieves up to 99.9% accuracy and reduces generated tokens by up to 84.7% compared to full parallel thinking.

C2weakest assumption

That model-internal confidence signals reliably indicate the quality or correctness of individual reasoning traces, allowing effective dynamic filtering without additional training or tuning.

C3one line summary

DeepConf filters low-quality reasoning traces using model-internal confidence signals, reaching up to 99.9% accuracy on AIME 2025 while reducing generated tokens by up to 84.7% versus full parallel sampling.

Cited by

27 papers in Pith

TokUR: Token-Level Uncertainty Estimation for Large Language Model Reasoning

Unified Data Selection for LLM Reasoning

Small Generalizable Prompt Predictive Models Can Steer Efficient RL Post-Training of Large Reasoning Models

GrACE: A Generative Approach to Better Confidence Elicitation and Efficient Test-Time Scaling in Large Language Models

Evolutionary Profiles for Protein Fitness Prediction

Receipt and verification

First computed	2026-05-17T23:38:48.026210Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

e883ed17b2e6bd531b45cd0ee0b9974214301e7121f8e8ad21dab941de352c22

Aliases

arxiv: 2508.15260 · arxiv_version: 2508.15260v1 · doi: 10.48550/arxiv.2508.15260 · pith_short_12: 5CB62F5S426V · pith_short_16: 5CB62F5S426VGG2F · pith_short_8: 5CB62F5S

Agent API

Resolver JSON Graph JSON Events JSON Schema Signing key

Verify this Pith Number yourself

curl -sH 'Accept: application/ld+json' https://pith.science/pith/5CB62F5S426VGG2FZUHOBOMXII \
  | 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: e883ed17b2e6bd531b45cd0ee0b9974214301e7121f8e8ad21dab941de352c22

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "dece95c2b7e1c506da16d2c512b9e0bf6c3b4fd1ef430486a5d981067387d028",
    "cross_cats_sorted": [],
    "license": "http://creativecommons.org/licenses/by/4.0/",
    "primary_cat": "cs.LG",
    "submitted_at": "2025-08-21T05:48:38Z",
    "title_canon_sha256": "d51da53a66a1207a671bc95f9f5b03e63ebb297d7d46f939aea43897eac3ed8c"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2508.15260",
    "kind": "arxiv",
    "version": 1
  }
}