Pith Number

pith:ZFOZZZP7

pith:2026:ZFOZZZP7LMECGCNMCJHQ46TN53

not attested not anchored not stored refs pending

SelfGrader: LLM Jailbreak Detection via Anchored Token-Level Logits

Jiahao Xu, Olivera Kotevska, Rui Hu, Zikai Zhang

SelfGrader detects jailbreaks by grading queries with logits over digits 0-9

arxiv:2604.01473 v3 · 2026-04-01 · cs.CR · cs.AI

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

Add to your LaTeX paper

\usepackage{pith}
\pithnumber{ZFOZZZP7LMECGCNMCJHQ46TN53}

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

SelfGrader achieves up to a 22.66% reduction in ASR on LLaMA-3-8B, while maintaining significantly lower memory overhead (up to 173x) and latency (up to 26x).

C2weakest assumption

That the logit distribution over a fixed set of numerical tokens (0-9) provides a stable, human-aligned signal of query maliciousness without requiring full response generation or access to internal model features.

C3one line summary

SelfGrader detects LLM jailbreaks by interpreting logit distributions on numerical tokens with a dual maliciousness-benignness score, cutting attack success rates up to 22.66% while using up to 173x less memory and 26x less latency.

Formal links

2 machine-checked theorem links

Receipt and verification

First computed	2026-05-29T01:05:08.581411Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

c95d9ce5ff5b082309ac124f0e7a6deef92057d54fb060d1c743dd089ef43c28

Aliases

arxiv: 2604.01473 · arxiv_version: 2604.01473v3 · doi: 10.48550/arxiv.2604.01473 · pith_short_12: ZFOZZZP7LMEC · pith_short_16: ZFOZZZP7LMECGCNM · pith_short_8: ZFOZZZP7

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/ZFOZZZP7LMECGCNMCJHQ46TN53 \
  | 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: c95d9ce5ff5b082309ac124f0e7a6deef92057d54fb060d1c743dd089ef43c28

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "63e7128930bcca93eca5aaaa87c62467681600e5d0567086b2166f3d6f636b96",
    "cross_cats_sorted": [
      "cs.AI"
    ],
    "license": "http://creativecommons.org/licenses/by/4.0/",
    "primary_cat": "cs.CR",
    "submitted_at": "2026-04-01T23:29:12Z",
    "title_canon_sha256": "3a5d1bbce9842ed427c5a1c3ad2092e21d42b6c59d525b8fb56d38e4ae1f4a0e"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2604.01473",
    "kind": "arxiv",
    "version": 3
  }
}