pith. sign in
Pith Number

pith:ACIPAPZY

pith:2026:ACIPAPZYL7MOMYKA4MVAYLQX3C
not attested not anchored not stored refs pending

Embedding Perturbation may Better Reflect Intermediate-Step Uncertainty in LLM Reasoning

Han Xu, Jiahao Wang, Pengfei He, Qihao Wen, Ravi Tandon, Yang Nan

Embedding perturbations on preceding tokens reveal uncertainty in LLM reasoning steps better than existing methods.

arxiv:2602.02427 v2 · 2026-02-02 · cs.LG

Add to your LaTeX paper
\usepackage{pith}
\pithnumber{ACIPAPZYL7MOMYKA4MVAYLQX3C}

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

an LLM's incorrect reasoning steps tend to contain tokens which are highly sensitive to the perturbations on the preceding token embeddings, indicating the model's uncertainty among multiple competing continuations

C2weakest assumption

That the observed sensitivity to embedding perturbations directly reflects the model's internal uncertainty in reasoning steps rather than being driven by other factors such as token frequency or architecture-specific artifacts.

C3one line summary

Embedding perturbation sensitivity provides a stronger signal for uncertainty in intermediate LLM reasoning steps than probability, sampling, or Bayesian baselines.

Formal links

2 machine-checked theorem links

Receipt and verification
First computed 2026-05-17T23:39:16.432927Z
Builder pith-number-builder-2026-05-17-v1
Signature Pith Ed25519 (pith-v1-2026-05) · public key
Schema pith-number/v1.0

Canonical hash

0090f03f385fd8e66140e32a0c2e17d8940b1c79c972160dc6fe81dac406c767

Aliases

arxiv: 2602.02427 · arxiv_version: 2602.02427v2 · doi: 10.48550/arxiv.2602.02427 · pith_short_12: ACIPAPZYL7MO · pith_short_16: ACIPAPZYL7MOMYKA · pith_short_8: ACIPAPZY
Agent API
Verify this Pith Number yourself
curl -sH 'Accept: application/ld+json' https://pith.science/pith/ACIPAPZYL7MOMYKA4MVAYLQX3C \
  | 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: 0090f03f385fd8e66140e32a0c2e17d8940b1c79c972160dc6fe81dac406c767
Canonical record JSON
{
  "metadata": {
    "abstract_canon_sha256": "85e5e3eea633bf39d658a3659a0f1928a9ba19b08e4f5c8bada3f5a6ddf99818",
    "cross_cats_sorted": [],
    "license": "http://creativecommons.org/licenses/by/4.0/",
    "primary_cat": "cs.LG",
    "submitted_at": "2026-02-02T18:27:26Z",
    "title_canon_sha256": "052935d791537b07cfb9f5d46b6fb642e3c0ab6124d30f7114e9c46e5eb899e9"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2602.02427",
    "kind": "arxiv",
    "version": 2
  }
}