Pith Number

pith:YNAISRI2

pith:2023:YNAISRI23OUQJWJ23HSNYNC27D

not attested not anchored not stored refs pending

The Capacity for Moral Self-Correction in Large Language Models

Amanda Askell, Anna Chen, Anna Goldie, Azalia Mirhoseini, Ben Mann, Catherine Olsson, Christopher Olah, Danny Hernandez, Dario Amodei, Dawn Drain, Deep Ganguli, Dustin Li, Eli Tran-Johnson, Ethan Perez, Jack Clark, Jackson Kernion, Jamie Kerr, Jared Kaplan, Jared Mueller, Joshua Landau, Kamal Ndousse, Kamil\.e Luko\v{s}i\=ut\.e, Karina Nguyen, Liane Lovitt, Michael Sellitto, Nelson Elhage, Nicholas Joseph, Nicholas Schiefer, Noemi Mercado, Nova DasSarma, Oliver Rausch, Robert Lasenby, Robin Larson, Sam McCandlish, Sam Ringer, Samuel R. Bowman, Sandipan Kundu, Saurav Kadavath, Scott Johnston, Shauna Kravec, Sheer El Showk, Tamera Lanham, Thomas I. Liao, Timothy Telleen-Lawton, Tom Brown, Tom Henighan, Tristan Hume, Yuntao Bai, Zac Hatfield-Dodds

arxiv:2302.07459 v2 · 2023-02-15 · 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{YNAISRI23OUQJWJ23HSNYNC27D}

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

16 papers in Pith

Moral Sensitivity in LLMs: A Tiered Evaluation of Contextual Bias via Behavioral Profiling and Mechanistic Interpretability

Rethinking Uncertainty Estimation in LLMs: A Principled Single-Sequence Measure

We Think, Therefore We Align LLMs to Helpful, Harmless and Honest Before They Go Wrong

A Comprehensive Overview of Large Language Models

Beyond I'm Sorry, I Can't: Dissecting Large Language Model Refusal

Receipt and verification

First computed	2026-07-05T05:43:20.594601Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

c34089451adba904d93ad9e4dc345af8f2e136989da26f16edb6babea9ea37d2

Aliases

arxiv: 2302.07459 · arxiv_version: 2302.07459v2 · doi: 10.48550/arxiv.2302.07459 · pith_short_12: YNAISRI23OUQ · pith_short_16: YNAISRI23OUQJWJ2 · pith_short_8: YNAISRI2

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/YNAISRI23OUQJWJ23HSNYNC27D \
  | 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: c34089451adba904d93ad9e4dc345af8f2e136989da26f16edb6babea9ea37d2

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "be1feaef5ba4f40c94ce530f415d6616ca2a03ce634d80c374e03449047eef31",
    "cross_cats_sorted": [],
    "license": "http://creativecommons.org/licenses/by/4.0/",
    "primary_cat": "cs.CL",
    "submitted_at": "2023-02-15T04:25:40Z",
    "title_canon_sha256": "93429455384dd7cb0e6b2ee4016d13a64a787a29d6f00505fbf96b84a00bd588"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2302.07459",
    "kind": "arxiv",
    "version": 2
  }
}