Pith Number

pith:6R467E6T

pith:2025:6R467E6TVIVI5JO5FIWQIO2VKZ

not attested not anchored not stored refs pending

Do Not Let Low-Probability Tokens Over-Dominate in RL for LLMs

Dongqi Han, Dongsheng Li, Xufang Luo, Yunjian Xu, Zhihe Yang, Zhiyuan He, Zilong Wang

arxiv:2505.12929 v1 · 2025-05-19 · cs.CL · cs.AI · 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{6R467E6TVIVI5JO5FIWQIO2VKZ}

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

When Implausible Tokens Get Reinforced: Tail-Aware Credit Calibration for LLM Reinforcement Learning

What are Key Factors for Updates in RL for LLM Reasoning?

From Reasoning Traces to Reusable Modules: Understanding Compositional Generalization in Language Model Reasoning

Trust Region On-Policy Distillation

Advantage Collapse in Group Relative Policy Optimization: Diagnosis and Mitigation

Receipt and verification

First computed	2026-07-05T11:05:11.993626Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

f479ef93d3aa2a8ea5dd2a2d043b555643f976b92504a26248f4ec34e550b015

Aliases

arxiv: 2505.12929 · arxiv_version: 2505.12929v1 · doi: 10.48550/arxiv.2505.12929 · pith_short_12: 6R467E6TVIVI · pith_short_16: 6R467E6TVIVI5JO5 · pith_short_8: 6R467E6T

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/6R467E6TVIVI5JO5FIWQIO2VKZ \
  | 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: f479ef93d3aa2a8ea5dd2a2d043b555643f976b92504a26248f4ec34e550b015

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "f204d9fca2c9e83bd116974f0d6aabf6e4729352a52a7fa4639d51c7340caec4",
    "cross_cats_sorted": [
      "cs.AI",
      "cs.LG"
    ],
    "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
    "primary_cat": "cs.CL",
    "submitted_at": "2025-05-19T10:14:08Z",
    "title_canon_sha256": "329ba22ef4faf0002e9306b72aae413a0174ef713c8411654eb9db536cc3396c"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2505.12929",
    "kind": "arxiv",
    "version": 1
  }
}