Pith Number

pith:6LTZIJQX

pith:2025:6LTZIJQXQ67KVDJJCN6AS4RGSK

not attested not anchored not stored refs pending

How Much Backtracking is Enough? Exploring the Interplay of SFT and RL in Enhancing LLM Reasoning

Bhuwan Dhingra, Hongyi James Cai, Junlin Wang, Xiaoyin Chen

arxiv:2505.24273 v1 · 2025-05-30 · 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{6LTZIJQXQ67KVDJJCN6AS4RGSK}

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

Search, Fail, Recover: A Training Framework for Correction-Aware Reasoning

Conformal Certification of Reasoning Trace Prefixes

Blending Supervised and Reinforcement Fine-Tuning with Prefix Sampling

RL-PLUS: Countering Capability Boundary Collapse of LLMs in Reinforcement Learning with Hybrid-policy Optimization

T$^2$PO: Uncertainty-Guided Exploration Control for Stable Multi-Turn Agentic Reinforcement Learning

Receipt and verification

First computed	2026-07-05T11:12:45.696313Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

f2e794261787beaa8d29137c097226928d2f2bdd55d7f38a957aa7a8004a4d47

Aliases

arxiv: 2505.24273 · arxiv_version: 2505.24273v1 · doi: 10.48550/arxiv.2505.24273 · pith_short_12: 6LTZIJQXQ67K · pith_short_16: 6LTZIJQXQ67KVDJJ · pith_short_8: 6LTZIJQX

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/6LTZIJQXQ67KVDJJCN6AS4RGSK \
  | 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: f2e794261787beaa8d29137c097226928d2f2bdd55d7f38a957aa7a8004a4d47

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "660e90bf69942a87a964461f11cdf32cfbb3cc1275083f9e90acbc2b51593b29",
    "cross_cats_sorted": [],
    "license": "http://creativecommons.org/licenses/by/4.0/",
    "primary_cat": "cs.AI",
    "submitted_at": "2025-05-30T06:49:00Z",
    "title_canon_sha256": "4e48f92558ab3814e21a43e6972645e95f1d9e708a2bac053372d078a6d6a3c2"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2505.24273",
    "kind": "arxiv",
    "version": 1
  }
}