Pith Number

pith:FGDSKN47

pith:2025:FGDSKN473HL4NEH7AXDK4NEUEX

not attested not anchored not stored refs pending

RL Is Neither a Panacea Nor a Mirage: Understanding Supervised vs. Reinforcement Learning Fine-Tuning for LLMs

Hangzhan Jin, Mohammad Hamdaqa, Sicheng Lv, Sifan Wu

arxiv:2508.16546 v1 · 2025-08-22 · cs.LG · cs.AI

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

Add to your LaTeX paper

\usepackage{pith}
\pithnumber{FGDSKN473HL4NEH7AXDK4NEUEX}

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

Sparsity Curse: Understanding RLVR Model Parameter Space from Model Merging

When RL Fails after SFT: Rejuvenating Model Plasticity for Robust SFT-to-RL Handoff

A Survey of Reinforcement Learning for Large Reasoning Models

Visual Reasoning through Tool-supervised Reinforcement Learning

Rethinking Generalization in Reasoning SFT: A Conditional Analysis on Optimization, Data, and Model Capability

Receipt and verification

First computed	2026-07-05T11:57:50.530665Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

298725379fd9d7c690ff05c6ae349425de5de04c0ba5aee7e0b3579ded2d0b5c

Aliases

arxiv: 2508.16546 · arxiv_version: 2508.16546v1 · doi: 10.48550/arxiv.2508.16546 · pith_short_12: FGDSKN473HL4 · pith_short_16: FGDSKN473HL4NEH7 · pith_short_8: FGDSKN47

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/FGDSKN473HL4NEH7AXDK4NEUEX \
  | 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: 298725379fd9d7c690ff05c6ae349425de5de04c0ba5aee7e0b3579ded2d0b5c

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "148befcaa82b8769f0259cf1cbb242e3c70548ed9792aff45a0ca7be782771a6",
    "cross_cats_sorted": [
      "cs.AI"
    ],
    "license": "http://creativecommons.org/publicdomain/zero/1.0/",
    "primary_cat": "cs.LG",
    "submitted_at": "2025-08-22T17:10:37Z",
    "title_canon_sha256": "297c7addee0d1385b07e4805b92aac0b21a0d812bed4193a26c64ed4fb850666"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2508.16546",
    "kind": "arxiv",
    "version": 1
  }
}