Pith Number

pith:LRQ7NKHR

pith:2024:LRQ7NKHRZVFHJBTPDC3ODQL4TJ

not attested not anchored not stored refs pending

Kernel Language Entropy: Fine-grained Uncertainty Quantification for LLMs from Semantic Similarities

Alexander Nikitin, Jannik Kossen, Pekka Marttinen, Yarin Gal

arxiv:2405.20003 v1 · 2024-05-30 · cs.LG · cs.AI · cs.CL

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

Add to your LaTeX paper

\usepackage{pith}
\pithnumber{LRQ7NKHRZVFHJBTPDC3ODQL4TJ}

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.

Cited by

7 papers in Pith

Reinforcement Learning with Metacognitive Feedback Elicits Faithful Uncertainty Expression in LLMs

Can LLMs Use Linguistic Uncertainty Markers to Reliably Reflect Intrinsic Confidence?

Unconditional Truthfulness: Learning Unconditional Uncertainty of Large Language Models

Token-Level Density-Based Uncertainty Quantification Methods for Eliciting Truthfulness of Large Language Models

REALISTA: Realistic Latent Adversarial Attacks that Elicit LLM Hallucinations

Receipt and verification

First computed	2026-07-05T08:25:15.168385Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

5c61f6a8f1cd4a74866f18b6e1c17c9a5c38340e52678b453c4969649967a2ac

Aliases

arxiv: 2405.20003 · arxiv_version: 2405.20003v1 · doi: 10.48550/arxiv.2405.20003 · pith_short_12: LRQ7NKHRZVFH · pith_short_16: LRQ7NKHRZVFHJBTP · pith_short_8: LRQ7NKHR

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/LRQ7NKHRZVFHJBTPDC3ODQL4TJ \
  | 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: 5c61f6a8f1cd4a74866f18b6e1c17c9a5c38340e52678b453c4969649967a2ac

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "a79bb1a76aab093dbd6a7b5e531e9209a8b4354f46f7e783a119741ed359fad0",
    "cross_cats_sorted": [
      "cs.AI",
      "cs.CL"
    ],
    "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
    "primary_cat": "cs.LG",
    "submitted_at": "2024-05-30T12:42:05Z",
    "title_canon_sha256": "cf207a971aa8fa925f8b1d12dc66068314c80fdd2acb88c37c38be2e032be8f3"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2405.20003",
    "kind": "arxiv",
    "version": 1
  }
}