Pith Number

pith:BEGOZ5TP

pith:2025:BEGOZ5TPMQBUQOMR6WSU4OLVOO

not attested not anchored not stored refs pending

Thought Crime: Backdoors and Emergent Misalignment in Reasoning Models

James Chua, Jan Betley, Mia Taylor, Owain Evans

arxiv:2506.13206 v2 · 2025-06-16 · 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{BEGOZ5TPMQBUQOMR6WSU4OLVOO}

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

15 papers in Pith

Order Is Not Control

Emergent Misalignment Can Be Induced by Sycophancy and Reversed via Alignment Gating

Activation Steering Induces Emergent Misalignment: A More Comprehensive Evaluation

Shared Latent Structures Enable Unified Backdoor Detection and Mitigation in LLMs

The Piggyback Hypothesis of Generalization: Explaining and Mitigating Emergent Misalignment

Receipt and verification

First computed	2026-07-05T11:34:52.136735Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

090cecf66f6403483991f5a54e3975738bee159e2c001b7d9f1367c0c95af098

Aliases

arxiv: 2506.13206 · arxiv_version: 2506.13206v2 · doi: 10.48550/arxiv.2506.13206 · pith_short_12: BEGOZ5TPMQBU · pith_short_16: BEGOZ5TPMQBUQOMR · pith_short_8: BEGOZ5TP

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/BEGOZ5TPMQBUQOMR6WSU4OLVOO \
  | 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: 090cecf66f6403483991f5a54e3975738bee159e2c001b7d9f1367c0c95af098

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "aba7990f27950533650893ff4b31b131870ec442799bcdbc08cddec6b59dfb14",
    "cross_cats_sorted": [
      "cs.AI",
      "cs.CL"
    ],
    "license": "http://creativecommons.org/licenses/by/4.0/",
    "primary_cat": "cs.LG",
    "submitted_at": "2025-06-16T08:10:04Z",
    "title_canon_sha256": "93b1cbd8aefa7412c1ad18849fadc2a0ffd49511213df2c486dc47048ad97acc"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2506.13206",
    "kind": "arxiv",
    "version": 2
  }
}