Pith Number

pith:LC5NIJSY

pith:2024:LC5NIJSY7Q7FSUOUYNFPE6MEPY

not attested not anchored not stored refs pending

Understanding the performance gap between online and offline alignment algorithms

Bernardo \'Avila Pires, Daniele Calandriello, Daniel Zhaohan Guo, Eugene Tarassov, Michal Valko, R\'emi Munos, Will Dabney, Yong Cheng, Yuan Cao, Yunhao Tang, Zeyu Zheng

arxiv:2405.08448 v1 · 2024-05-14 · cs.LG · 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{LC5NIJSY7Q7FSUOUYNFPE6MEPY}

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

9 papers in Pith

Learn from Your Mistakes: Tree-like Self-Play for Secure Code LLMs

Advancing Multi-Agent RAG Systems with Minimalist Reinforcement Learning

RLFTSim: Realistic and Controllable Multi-Agent Traffic Simulation via Reinforcement Learning Fine-Tuning

Sharpness-Guided Group Relative Policy Optimization via Probability Shaping

Beyond the 80/20 Rule: High-Entropy Minority Tokens Drive Effective Reinforcement Learning for LLM Reasoning

Receipt and verification

First computed	2026-07-05T08:19:00.562112Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

58bad42658fc3e5951d4c34af279847e06c1700b3dc089e2f2516757497c46d5

Aliases

arxiv: 2405.08448 · arxiv_version: 2405.08448v1 · doi: 10.48550/arxiv.2405.08448 · pith_short_12: LC5NIJSY7Q7F · pith_short_16: LC5NIJSY7Q7FSUOU · pith_short_8: LC5NIJSY

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/LC5NIJSY7Q7FSUOUYNFPE6MEPY \
  | 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: 58bad42658fc3e5951d4c34af279847e06c1700b3dc089e2f2516757497c46d5

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "627c3366a71ab4a95e9295c2e039ebd9c4c2f4e068c4a52ef9a006d799e7ac0f",
    "cross_cats_sorted": [
      "cs.AI"
    ],
    "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
    "primary_cat": "cs.LG",
    "submitted_at": "2024-05-14T09:12:30Z",
    "title_canon_sha256": "c4cfb6a0633ea9911b3b27204728cab702a3e6850a8d8a4c99910b0b4ee43a0d"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2405.08448",
    "kind": "arxiv",
    "version": 1
  }
}