Pith Number

pith:XZY4ZXL3

pith:2026:XZY4ZXL3XZ2D2LICCL4JKYQFZE

not attested not anchored not stored refs pending

Tracing the Dynamics of Refusal: Exploiting Latent Refusal Trajectories for Robust Jailbreak Detection

Che Wang, Jianbo Gao, Wei Yang Bryan Lim, Xulin Hu, Zhong Chen

Refusal in language models follows a persistent upstream trajectory that remains detectable even when attacks suppress the final output.

arxiv:2605.02958 v2 · 2026-05-02 · cs.CR · cs.AI · cs.CL · 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{XZY4ZXL3XZ2D2LICCL4JKYQFZE}

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

SALO effectively recovers defense capabilities against forced-decoding attacks, improving detection rates from ~0% to >90% where methods relying on terminal states perform poorly.

C2weakest assumption

That the refusal trajectory uncovered by causal tracing is a stable, generalizable signature rather than an artifact of the specific models, prompts, or attack implementations tested.

C3one line summary

Refusal in LLMs leaves a detectable upstream trajectory that SALO exploits to raise jailbreak detection from near zero to over 90 percent even under forced-decoding attacks.

Receipt and verification

First computed	2026-05-27T02:05:20.995842Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

be71ccdd7bbe743d2d0212f8956205c917e64bd2b553330318ae754b2634ae0a

Aliases

arxiv: 2605.02958 · arxiv_version: 2605.02958v2 · doi: 10.48550/arxiv.2605.02958 · pith_short_12: XZY4ZXL3XZ2D · pith_short_16: XZY4ZXL3XZ2D2LIC · pith_short_8: XZY4ZXL3

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/XZY4ZXL3XZ2D2LICCL4JKYQFZE \
  | 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: be71ccdd7bbe743d2d0212f8956205c917e64bd2b553330318ae754b2634ae0a

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "cf1283eaae0d3c3f8260207ad798c8cb1550b8dc42bd189aacf550e82cc713e6",
    "cross_cats_sorted": [
      "cs.AI",
      "cs.CL",
      "cs.LG"
    ],
    "license": "http://creativecommons.org/licenses/by/4.0/",
    "primary_cat": "cs.CR",
    "submitted_at": "2026-05-02T14:56:37Z",
    "title_canon_sha256": "7a717b3cf54a281cb8222adc6d592e0a68a6c5804b8f43693ec264675e837ec2"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2605.02958",
    "kind": "arxiv",
    "version": 2
  }
}