Pith Number

pith:PRWSEKXD

pith:2023:PRWSEKXDNOW6BGQC6NYCKSUVM2

not attested not anchored not stored refs pending

Vision-Language Models as a Source of Rewards

Alexander Neitz, Clare Lyle, Dan Horgan, Dmitry Nikulin, Fabio Pardo, Feryal Behbahani, Gheorghe Comanici, Harris Chan, Himanshu Sahni, Hussain Masoom, Jack Parker-Holder, John Quan, Kate Baumli, Kay McKinney, Kristian Holsheimer, Lei Zhang, Luyu Wang, Maxime Gazeau, Michael Laskin, Richie Steigerwald, Satinder Baveja, Sebastian Flennerhag, Stephen Spencer, Tim Rockt\"aschel, Tom Schaul, Volodymyr Mnih, Yannick Schroecker

arxiv:2312.09187 v3 · 2023-12-14 · 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{PRWSEKXDNOW6BGQC6NYCKSUVM2}

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

2 papers in Pith

Learning Process Rewards via Success Visitation Matching for Efficient RL

QVal: Cheaply Evaluating Dense Supervision Signals for Long-Horizon LLM Agents

Receipt and verification

First computed	2026-07-05T08:43:24.951134Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

7c6d222ae36bade09a02f370254a9566829532129d16d732013b22217ccc2f85

Aliases

arxiv: 2312.09187 · arxiv_version: 2312.09187v3 · doi: 10.48550/arxiv.2312.09187 · pith_short_12: PRWSEKXDNOW6 · pith_short_16: PRWSEKXDNOW6BGQC · pith_short_8: PRWSEKXD

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/PRWSEKXDNOW6BGQC6NYCKSUVM2 \
  | 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: 7c6d222ae36bade09a02f370254a9566829532129d16d732013b22217ccc2f85

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "566b04f8c8a14ff1c8a9cce053add86dcbde597fcec0f9b8fb729696068226b6",
    "cross_cats_sorted": [],
    "license": "http://creativecommons.org/licenses/by/4.0/",
    "primary_cat": "cs.LG",
    "submitted_at": "2023-12-14T18:06:17Z",
    "title_canon_sha256": "6b8114e76a090bc5ddcc2263971c898c948f7d11462f6ba57da048cae4fc3a45"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2312.09187",
    "kind": "arxiv",
    "version": 3
  }
}