Pith Number

pith:Y45YWD6T

pith:2025:Y45YWD6TTG5A5G3TH23BP4TFOB

not attested not anchored not stored refs pending

SWEET-RL: Training Multi-Turn LLM Agents on Collaborative Reasoning Tasks

Jason Weston, Sainbayar Sukhbaatar, Sergey Levine, Song Jiang, Xian Li, Yifei Zhou, Yuandong Tian

arxiv:2503.15478 v1 · 2025-03-19 · 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{Y45YWD6TTG5A5G3TH23BP4TFOB}

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

14 papers in Pith

Unlocking Proactivity in Task-Oriented Dialogue

PAIR: Prefix-Aware Internal Reward Model for Multi-Turn Agent Optimization

The Landscape of Agentic Reinforcement Learning for LLMs: A Survey

RLBoost: Harvesting Preemptible Resources for Cost-Efficient Reinforcement Learning on LLMs

Receipt and verification

First computed	2026-07-05T10:35:27.158682Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

c73b8b0fd399ba0e9b733eb617f265705c2603fa4f084ca2832f6ee72ba6dfba

Aliases

arxiv: 2503.15478 · arxiv_version: 2503.15478v1 · doi: 10.48550/arxiv.2503.15478 · pith_short_12: Y45YWD6TTG5A · pith_short_16: Y45YWD6TTG5A5G3T · pith_short_8: Y45YWD6T

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/Y45YWD6TTG5A5G3TH23BP4TFOB \
  | 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: c73b8b0fd399ba0e9b733eb617f265705c2603fa4f084ca2832f6ee72ba6dfba

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "0ed552d53f383ea11db8448cf90f3882261c4197efa360374118d470835cde52",
    "cross_cats_sorted": [],
    "license": "http://creativecommons.org/licenses/by/4.0/",
    "primary_cat": "cs.LG",
    "submitted_at": "2025-03-19T17:55:08Z",
    "title_canon_sha256": "6e6d4c0b70697aed83a116067bb9186c310ed5df7164b183c8b9def354f8587c"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2503.15478",
    "kind": "arxiv",
    "version": 1
  }
}