Pith Number

pith:YDGB4BF2

pith:2025:YDGB4BF2C2TASQ3TV7ZGTI6XIN

not attested not anchored not stored refs pending

Detecting Strategic Deception Using Linear Probes

Bilal Chughtai, Marius Hobbhahn, Nicholas Goldowsky-Dill, Stefan Heimersheim

arxiv:2502.03407 v1 · 2025-02-05 · 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{YDGB4BF2C2TASQ3TV7ZGTI6XIN}

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

17 papers in Pith

"Did you lie?" Evaluating Lie Detectors across Model Scale and Belief-Verified Model Organisms

Conversable Complexity: Agentic LLM Collectives as Interpretable Substrates

Position: Behavioural Assurance Cannot Verify the Safety Claims Governance Now Demands

Pressure-Testing Deception Probes in LLMs: Scaling, Robustness, and the Geometry of Deceptive Representations

Preference Instability in Reward Models: Detection and Mitigation via Sparse Autoencoders

Receipt and verification

First computed	2026-07-05T10:10:04.472641Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

c0cc1e04ba16a6094373aff269a3d7436d4945a4ca4ee11e0828f91b24f7ab06

Aliases

arxiv: 2502.03407 · arxiv_version: 2502.03407v1 · doi: 10.48550/arxiv.2502.03407 · pith_short_12: YDGB4BF2C2TA · pith_short_16: YDGB4BF2C2TASQ3T · pith_short_8: YDGB4BF2

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/YDGB4BF2C2TASQ3TV7ZGTI6XIN \
  | 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: c0cc1e04ba16a6094373aff269a3d7436d4945a4ca4ee11e0828f91b24f7ab06

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "596bb947e33c992c61eb269cc7ed9ae681202a623f90ff17f7917dba57b828e8",
    "cross_cats_sorted": [],
    "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
    "primary_cat": "cs.LG",
    "submitted_at": "2025-02-05T17:49:40Z",
    "title_canon_sha256": "35c407a799af75675b9ade8c66efb76ccd4c1fe9c711485f2b734add52899a40"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2502.03407",
    "kind": "arxiv",
    "version": 1
  }
}