Pith. sign in
Pith Number

pith:GZC6EAZP

pith:2025:GZC6EAZPDRDSCBQFTTMDI4WVCO
not attested not anchored not stored refs pending

Squeeze the Soaked Sponge: Efficient Off-policy Reinforcement Finetuning for Large Language Model

Hongyao Tang, Jianye Hao, Jing Liang, Jinyi Liu, Lei Bai, Shuyue Hu, Yan Zheng, Yi Ma

arxiv:2507.06892 v3 · 2025-07-09 · cs.LG · cs.AI · cs.CL

Open paper page JSON Open Graph Bundle Merged state Verified badge What is a Pith Number?
Add to your LaTeX paper 
\usepackage{pith}
\pithnumber{GZC6EAZPDRDSCBQFTTMDI4WVCO}

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

8 papers in Pith

Modularized Reinforcement Learning on LLMs: From MDP Creation to Exploration and Learning
RLVR without Ineffective Samples: Group Prioritized Off-Policy Optimization for LLM Reasoning
A Survey of Reinforcement Learning for Large Reasoning Models
OP-GRPO: Efficient Off-Policy GRPO for Flow-Matching Models
Learning Agentic Policy from Action Guidance
Receipt and verification
First computed 2026-07-05T11:35:36.379677Z
Builder pith-number-builder-2026-05-17-v1
Signature Pith Ed25519 (pith-v1-2026-05) · public key
Schema pith-number/v1.0

Canonical hash

3645e2032f1c472106059cd83472d513b39c695f4f75a2ca9cd2c1b6294c7c30

Aliases

arxiv: 2507.06892 · arxiv_version: 2507.06892v3 · doi: 10.48550/arxiv.2507.06892 · pith_short_12: GZC6EAZPDRDS · pith_short_16: GZC6EAZPDRDSCBQF · pith_short_8: GZC6EAZP
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/GZC6EAZPDRDSCBQFTTMDI4WVCO \
  | 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: 3645e2032f1c472106059cd83472d513b39c695f4f75a2ca9cd2c1b6294c7c30
Canonical record JSON 
{
  "metadata": {
    "abstract_canon_sha256": "665761fadaaaf49c690dcf290b9fc12b2b11cbf486d34dcf88d6ff9fd3f6b9a6",
    "cross_cats_sorted": [
      "cs.AI",
      "cs.CL"
    ],
    "license": "http://creativecommons.org/licenses/by-nc-nd/4.0/",
    "primary_cat": "cs.LG",
    "submitted_at": "2025-07-09T14:29:45Z",
    "title_canon_sha256": "709bcd98843228718f5f149a7677eaf705385f62e21ed9b7353ad94f2e82f70e"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2507.06892",
    "kind": "arxiv",
    "version": 3
  }
}