Pith Number

pith:UQUMPFH4

pith:2025:UQUMPFH4EXMAQUL6UK35PVX3RV

not attested not anchored not stored refs pending

LLM Post-Training: A Deep Dive into Reasoning Large Language Models

Fahad Shahbaz Khan, Hisham Cholakkal, Komal Kumar, Ming-Hsuan Yang, Mubarak Shah, Omkar Thawakar, Phillip H.S. Torr, Rao Muhammad Anwer, Salman Khan, Tajamul Ashraf

arxiv:2502.21321 v2 · 2025-02-28 · cs.CL · cs.CV

Open paper page JSON Open Graph Bundle Merged state Verified badge What is a Pith Number?

Add to your LaTeX paper

\usepackage{pith}
\pithnumber{UQUMPFH4EXMAQUL6UK35PVX3RV}

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

34 papers in Pith

Reinforcement Learning without Ground-Truth Solutions can Improve LLMs

Modularized Reinforcement Learning on LLMs: From MDP Creation to Exploration and Learning

EfficientRollout: System-Aware Self-Speculative Decoding for RL Rollouts

Mental-R1: Aligning LLM Reasoning for Mental Health Assessment

Soft-Prompt Tuning for Fair and Efficient LLM Benchmark Evaluation

Receipt and verification

First computed	2026-07-05T10:37:45.409272Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

a428c794fc25d808517ea2b7d7d6fb8d5cfbb7747615c3089f4f73e5a1ccd88f

Aliases

arxiv: 2502.21321 · arxiv_version: 2502.21321v2 · doi: 10.48550/arxiv.2502.21321 · pith_short_12: UQUMPFH4EXMA · pith_short_16: UQUMPFH4EXMAQUL6 · pith_short_8: UQUMPFH4

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/UQUMPFH4EXMAQUL6UK35PVX3RV \
  | 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: a428c794fc25d808517ea2b7d7d6fb8d5cfbb7747615c3089f4f73e5a1ccd88f

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "105a363c0c34b977d16effbe1de4f17447fef7efff57c6ba0a18da349662b12f",
    "cross_cats_sorted": [
      "cs.CV"
    ],
    "license": "http://creativecommons.org/licenses/by/4.0/",
    "primary_cat": "cs.CL",
    "submitted_at": "2025-02-28T18:59:54Z",
    "title_canon_sha256": "a0e8e40c9ec3ea2aa5c083971ac7316fe29d2dafaca6c9d1cf25059764bf73f5"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2502.21321",
    "kind": "arxiv",
    "version": 2
  }
}