Pith Number

pith:AKF4OPQB

pith:2026:AKF4OPQBKR3BCAQ2NJBA3CSSZB

not attested not anchored not stored refs pending

Tracing Moral Foundations in Large Language Models

Bowen Yi, Chenxiao Yu, Farzan Karimi-Malekabadi, Jinyi Ye, Morteza Dehghani, Shrikanth Narayanan, Suhaib Abdurahman, Yue Zhao

Large language models develop internal representations of moral foundations that align with human judgments and emerge naturally during pretraining.

arxiv:2601.05437 v3 · 2026-01-09 · cs.CL · 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{AKF4OPQBKR3BCAQ2NJBA3CSSZB}

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

Models represent and distinguish moral foundations in a manner that aligns with human judgments, and this moral geometry naturally emerges from pretraining and is selectively rewired by post-training; steering along dense vectors or sparse SAE features produces predictable shifts in foundation-relevant behavior.

C2weakest assumption

That the chosen Moral Foundations Theory categories and the SAE feature extraction faithfully capture the models' internal moral concepts rather than imposing an external taxonomy or detecting spurious correlations.

C3one line summary

Moral foundations in LLMs form distributed, layered representations that align with human perceptions, emerge from pretraining, and causally influence outputs when steered via dense vectors or sparse features.

Formal links

2 machine-checked theorem links

Cited by

1 paper in Pith

Psychological Steering of Large Language Models

Receipt and verification

First computed	2026-05-20T01:05:05.847808Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

028bc73e01547611021a6a420d8a52c86b195b7e4a0a6509d5d62dbfbfa6e618

Aliases

arxiv: 2601.05437 · arxiv_version: 2601.05437v3 · doi: 10.48550/arxiv.2601.05437 · pith_short_12: AKF4OPQBKR3B · pith_short_16: AKF4OPQBKR3BCAQ2 · pith_short_8: AKF4OPQB

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/AKF4OPQBKR3BCAQ2NJBA3CSSZB \
  | 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: 028bc73e01547611021a6a420d8a52c86b195b7e4a0a6509d5d62dbfbfa6e618

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "accb73257ce2140233708fa4eeba075f1a7a2e7f3015638fb48435f9a6b5e175",
    "cross_cats_sorted": [
      "cs.AI"
    ],
    "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
    "primary_cat": "cs.CL",
    "submitted_at": "2026-01-09T00:09:28Z",
    "title_canon_sha256": "e4cfaa10f742e09c1c84a8bdd68bf0fc85dc926c52fcf0a995e66309236c203b"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2601.05437",
    "kind": "arxiv",
    "version": 3
  }
}