Pith Number

pith:5UTQ3P6R

pith:2025:5UTQ3P6RDSIBFKATPGBSEW4ZAX

not attested not anchored not stored refs pending

Enhancing LLM Reasoning with Iterative DPO: A Comprehensive Empirical Investigation

Dongbin Zhao, Dongmei Jiang, Jiahao Lin, Linjing Li, Nan Xu, Qichao Zhang, Songjun Tu, Wei He, Xiangyuan Lan, Xiangyu Tian, Yuqian Fu

arxiv:2503.12854 v3 · 2025-03-17 · cs.CL

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

Add to your LaTeX paper

\usepackage{pith}
\pithnumber{5UTQ3P6RDSIBFKATPGBSEW4ZAX}

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

7 papers in Pith

Enhancing LLM Metacognition via Cognitive Pairwise Training

TPMM-DPO: Trajectory-aware Preference-guided Model Merging for Iterative Direct Preference Optimization

How Much Online RL is Enough? Informative Rollouts for Offline Preference Optimization in RLVR

Sample-efficient LLM Optimization with Reset Replay

LegalDrill: Diagnosis-Driven Synthesis for Legal Reasoning in Small Language Models

Receipt and verification

First computed	2026-07-05T11:44:02.789860Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

ed270dbfd11c9012a8137983225b9905fa0016fbefabe0a0333d06e583e6b988

Aliases

arxiv: 2503.12854 · arxiv_version: 2503.12854v3 · doi: 10.48550/arxiv.2503.12854 · pith_short_12: 5UTQ3P6RDSIB · pith_short_16: 5UTQ3P6RDSIBFKAT · pith_short_8: 5UTQ3P6R

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/5UTQ3P6RDSIBFKATPGBSEW4ZAX \
  | 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: ed270dbfd11c9012a8137983225b9905fa0016fbefabe0a0333d06e583e6b988

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "21754a4c1746339c351ea496ecb4892af7191d51907581c4a3184223bc5d5145",
    "cross_cats_sorted": [],
    "license": "http://creativecommons.org/licenses/by-nc-sa/4.0/",
    "primary_cat": "cs.CL",
    "submitted_at": "2025-03-17T06:28:25Z",
    "title_canon_sha256": "e0010db9d6ac1fd95fdb743da6ba443455b84fdb64b65e1bfc143db76e44b2ab"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2503.12854",
    "kind": "arxiv",
    "version": 3
  }
}