Pith Number

pith:F22CO2NG

pith:2022:F22CO2NGPFAFN7MQNIVMTAHV6T

not attested not anchored not stored refs pending

RL with KL penalties is better viewed as Bayesian inference

Christopher L Buckley, Ethan Perez, Tomasz Korbak

arxiv:2205.11275 v2 · 2022-05-23 · cs.LG · stat.ML

Open paper page JSON Open Graph Bundle Merged state Verified badge What is a Pith Number?

Add to your LaTeX paper

\usepackage{pith}
\pithnumber{F22CO2NGPFAFN7MQNIVMTAHV6T}

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

7 papers in Pith

A Unifying Lens on Reward Uncertainty in RLHF

Scaling Laws for Reward Model Overoptimization

The tractability landscape of diffusion alignment: regularization, rewards, and computational primitives

Exponential families from a single KL identity

On Distinguishing Capability Elicitation from Capability Creation in Post-Training: A Free-Energy Perspective

Receipt and verification

First computed	2026-07-05T05:08:52.043624Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

2eb42769a6794056fd906a2ac980f5f4cbfc8200fa2d6daa52854dfabce69fdd

Aliases

arxiv: 2205.11275 · arxiv_version: 2205.11275v2 · doi: 10.48550/arxiv.2205.11275 · pith_short_12: F22CO2NGPFAF · pith_short_16: F22CO2NGPFAFN7MQ · pith_short_8: F22CO2NG

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/F22CO2NGPFAFN7MQNIVMTAHV6T \
  | 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: 2eb42769a6794056fd906a2ac980f5f4cbfc8200fa2d6daa52854dfabce69fdd

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "60ad1e61578574f91cbf0f509033fb84e85ded7bd01d6f5cfb9c431f15bd081d",
    "cross_cats_sorted": [
      "stat.ML"
    ],
    "license": "http://creativecommons.org/licenses/by/4.0/",
    "primary_cat": "cs.LG",
    "submitted_at": "2022-05-23T12:47:13Z",
    "title_canon_sha256": "43dd403520cfb25f6110b9815ff8c47f30fdf9950d3c016ff8dd200215065cbd"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2205.11275",
    "kind": "arxiv",
    "version": 2
  }
}