Pith Number

pith:JHMHFF5R

pith:2023:JHMHFF5RP7DN7ANYNXHN2RAW4Q

not attested not anchored not stored refs pending

Shadow Alignment: The Ease of Subverting Safely-Aligned Language Models

Dahua Lin, Linda Petzold, Qi Zhang, William Yang Wang, Xianjun Yang, Xiao Wang, Xun Zhao

arxiv:2310.02949 v1 · 2023-10-04 · cs.CL · cs.AI · cs.CR · 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{JHMHFF5RP7DN7ANYNXHN2RAW4Q}

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

35 papers in Pith

Skin-Deep: A Geometric Diagnostic for Alignment Fragility in Large Language Model Representations

Beyond Safe Data: Pretraining-Stage Alignment with Regular Safety Reflection

Do Activation Monitors Survive Model Updates? Benchmarking, Predicting, and Repairing Activation-Monitor Staleness

ALIGNBEAM : Inference-Time Alignment Transfer via Cross-Vocabulary Logit Mixing

Sch\"utzen: Evaluating LLM Safety in Bulgarian and German Contexts

Receipt and verification

First computed	2026-07-05T06:57:15.817757Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

49d87297b17fc6df81b86dcedd4416e4398953f5afcc75aed3a3c20f25f28710

Aliases

arxiv: 2310.02949 · arxiv_version: 2310.02949v1 · doi: 10.48550/arxiv.2310.02949 · pith_short_12: JHMHFF5RP7DN · pith_short_16: JHMHFF5RP7DN7ANY · pith_short_8: JHMHFF5R

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/JHMHFF5RP7DN7ANYNXHN2RAW4Q \
  | 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: 49d87297b17fc6df81b86dcedd4416e4398953f5afcc75aed3a3c20f25f28710

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "93581bc90d7e03c1a54b0c6e5a241a872150228feae6648637e1fde130501c3b",
    "cross_cats_sorted": [
      "cs.AI",
      "cs.CR",
      "cs.LG"
    ],
    "license": "http://creativecommons.org/licenses/by/4.0/",
    "primary_cat": "cs.CL",
    "submitted_at": "2023-10-04T16:39:31Z",
    "title_canon_sha256": "32267b5d46f9b61a065b3c5bb49538a40c7bf884871d6dd1ccf1ce3364f5e797"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2310.02949",
    "kind": "arxiv",
    "version": 1
  }
}