Pith Number

pith:W7J5BAKA

pith:2025:W7J5BAKA7ZMBEENX4LM3KRP6IH

not attested not anchored not stored refs pending

Ignore the KL Penalty! Boosting Exploration on Critical Tokens to Enhance RL Fine-Tuning

Jean Vassoyan, Nathana\"el Beau, Roman Plaud

arxiv:2502.06533 v1 · 2025-02-10 · cs.CL · 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{W7J5BAKA7ZMBEENX4LM3KRP6IH}

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

5 papers in Pith

Training-Trajectory-Aware Token Selection

Stabilizing Knowledge, Promoting Reasoning: Dual-Token Constraints for RLVR

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

HTPO: Towards Exploration-Exploitation Balanced Policy Optimization via Hierarchical Token-level Objective Control

AtManRL: Towards Faithful Reasoning via Differentiable Attention Saliency

Receipt and verification

First computed	2026-07-05T10:12:08.116924Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

b7d3d08140fe581211b7e2d9b545fe41c59d121481d24accc851ef8ffaaeb3d2

Aliases

arxiv: 2502.06533 · arxiv_version: 2502.06533v1 · doi: 10.48550/arxiv.2502.06533 · pith_short_12: W7J5BAKA7ZMB · pith_short_16: W7J5BAKA7ZMBEENX · pith_short_8: W7J5BAKA

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/W7J5BAKA7ZMBEENX4LM3KRP6IH \
  | 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: b7d3d08140fe581211b7e2d9b545fe41c59d121481d24accc851ef8ffaaeb3d2

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "f6ab39ca04b893e16e46f21dbd82cda17cda4289b6e6692009f7eabdabe665f8",
    "cross_cats_sorted": [
      "cs.LG"
    ],
    "license": "http://creativecommons.org/licenses/by/4.0/",
    "primary_cat": "cs.CL",
    "submitted_at": "2025-02-10T14:56:25Z",
    "title_canon_sha256": "fbc7a6a6fd3c407d3362244298d538e1937265f14276285b99c8e10110c8d638"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2502.06533",
    "kind": "arxiv",
    "version": 1
  }
}