Pith Number

pith:YBUXGDWK

pith:2025:YBUXGDWKW3V76TCMPKIMLD6CTC

not attested not anchored not stored refs pending

RL-finetuning LLMs from on- and off-policy data with a single algorithm

David W. Zhang, Michal Valko, R\'emi Munos, Taco Cohen, Yunhao Tang

arxiv:2503.19612 v2 · 2025-03-25 · 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{YBUXGDWKW3V76TCMPKIMLD6CTC}

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

3 papers in Pith

Modularized Reinforcement Learning on LLMs: From MDP Creation to Exploration and Learning

Trust Region On-Policy Distillation

Reinforcement Learning for Compositional Generalization with Outcome-Level Optimization

Receipt and verification

First computed	2026-07-05T10:41:22.874555Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

c069730ecab6ebff4c4c7a90c58fc2988290847bf4f207d64a5a0677da070fba

Aliases

arxiv: 2503.19612 · arxiv_version: 2503.19612v2 · doi: 10.48550/arxiv.2503.19612 · pith_short_12: YBUXGDWKW3V7 · pith_short_16: YBUXGDWKW3V76TCM · pith_short_8: YBUXGDWK

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/YBUXGDWKW3V76TCMPKIMLD6CTC \
  | 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: c069730ecab6ebff4c4c7a90c58fc2988290847bf4f207d64a5a0677da070fba

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "14705feb80a7659726d6c3940f3bbf2ddd5d38d98ca6a405222e89903ac42fcf",
    "cross_cats_sorted": [],
    "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
    "primary_cat": "cs.LG",
    "submitted_at": "2025-03-25T12:52:38Z",
    "title_canon_sha256": "cc423010901ad6b183549e11eefd940067f2b011f0aab17ce82e4a124694c6b0"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2503.19612",
    "kind": "arxiv",
    "version": 2
  }
}