Paper Citation Record · LEDGER

A Model Can Help Itself: Reward-Free Self-Training for LLM Reasoning

As of 12 August 2026, this Paper Citation Record lists 30 of 30 outbound references and 2 inbound Pith citation observations for arXiv:2510.18814.

A citation records a reference. It does not transfer a finding from one paper to another.

pith.paper-citation-record.v1
2510.18814 v4

Coverage vector

measured 30 of 30 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-04T08:53:08.348473Z

measured 32 of 32 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-12T06:34:41.77262+00:00

measured 2 of 2 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-05-08T16:53:00.860162Z

measured 0 of 1 external citation measurements

A source-named dated measurement, never combined with another source.

Source: pith, observed 2026-05-11T20:16:08.415773Z

Reference resolution

30 of 30 outbound references displayed

verified exact0
verified fuzzy0
unresolved30
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation cf39d836-2137-4f3b-84d0-0e6d6bf2a823 · outbound

This paper cites GPT-4 Technical Report.

A Model Can Help Itself: Reward-Free Self-Training for LLM Reasoning GPT-4 Technical Report

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-04T08:53:05.173699Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b4076495-9561-4ac2-a970-59b3cd42d405 · outbound

This paper cites Reasoning Models Don't Always Say What They Think.

A Model Can Help Itself: Reward-Free Self-Training for LLM Reasoning Reasoning Models Don't Always Say What They Think

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-04T08:53:05.547904Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c6342b43-de70-4242-ba2b-59ae70103976 · outbound

This paper cites The Entropy Mechanism of Reinforcement Learning for Reasoning Language Models.

A Model Can Help Itself: Reward-Free Self-Training for LLM Reasoning The Entropy Mechanism of Reinforcement Learning for Reasoning Language Models

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-04T08:53:05.655329Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation da3e1e1d-bd81-450f-82b4-e482f3bb5800 · outbound

This paper cites The Llama 3 Herd of Models.

A Model Can Help Itself: Reward-Free Self-Training for LLM Reasoning The Llama 3 Herd of Models

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-04T08:53:05.768844Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 491c0c6c-141d-4f76-8c3e-12a663d4e1fe · outbound

This paper cites OpenThoughts: Data Recipes for Reasoning Models.

A Model Can Help Itself: Reward-Free Self-Training for LLM Reasoning OpenThoughts: Data Recipes for Reasoning Models

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-04T08:53:05.911880Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 98dabe1f-2958-439c-8e28-0816f7a67f9d · outbound

This paper cites OlympiadBench: A Challenging Benchmark for Promoting AGI with Olympiad-Level Bilingual Multimodal Scientific Problems.

A Model Can Help Itself: Reward-Free Self-Training for LLM Reasoning OlympiadBench: A Challenging Benchmark for Promoting AGI with Olympiad-Level Bilingual Multimodal Scientific Problems

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-04T08:53:06.053247Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b7b4f8c6-1178-4203-9f0b-22206d04bf26 · outbound

This paper cites GRPO) is similar under our experimental conditions.

A Model Can Help Itself: Reward-Free Self-Training for LLM Reasoning GRPO) is similar under our experimental conditions

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-04T08:53:08.348473Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9243bc89-0d0c-449c-99c0-035e7851e51f · outbound

This paper cites Understanding R1-Zero-Like Training: A Critical Perspective.

A Model Can Help Itself: Reward-Free Self-Training for LLM Reasoning Understanding R1-Zero-Like Training: A Critical Perspective

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-04T08:53:06.544194Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 27ceed12-5a91-4ccc-9808-3734ef39a896 · outbound

This paper cites s1: Simple test-time scaling.

A Model Can Help Itself: Reward-Free Self-Training for LLM Reasoning s1: Simple test-time scaling

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-04T08:53:06.710900Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1ccc0185-6031-48d4-ad19-5cd3fa13cedf · outbound

This paper cites Accessed: 2025-01-24.

A Model Can Help Itself: Reward-Free Self-Training for LLM Reasoning Accessed: 2025-01-24

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-04T08:53:06.881699Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a4ee002c-3ebc-47a7-a92a-24d383a522f7 · outbound

This paper cites Proximal Policy Optimization Algorithms.

A Model Can Help Itself: Reward-Free Self-Training for LLM Reasoning Proximal Policy Optimization Algorithms

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-04T08:53:07.031456Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ae146751-903f-4e7d-9bc4-c3984c324908 · outbound

This paper cites DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models.

A Model Can Help Itself: Reward-Free Self-Training for LLM Reasoning DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-04T08:53:07.327544Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5ec71e96-83f3-4424-80e2-8c52bf4bf450 · outbound

This paper cites The Illusion of Thinking: Understanding the Strengths and Limitations of Reasoning Models via the Lens of Problem Complexity.

A Model Can Help Itself: Reward-Free Self-Training for LLM Reasoning The Illusion of Thinking: Understanding the Strengths and Limitations of Reasoning Models via the Lens of Problem Complexity

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-04T08:53:07.434034Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9041d8d7-48e6-45f5-ab80-a72bc9f0c30a · outbound

This paper cites Stop Overthinking: A Survey on Efficient Reasoning for Large Language Models.

A Model Can Help Itself: Reward-Free Self-Training for LLM Reasoning Stop Overthinking: A Survey on Efficient Reasoning for Large Language Models

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-04T08:53:07.536180Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c4c81fab-bc18-4eac-aacc-45484db3baf2 · outbound

This paper cites Beyond the 80/20 Rule: High-Entropy Minority Tokens Drive Effective Reinforcement Learning for LLM Reasoning.

A Model Can Help Itself: Reward-Free Self-Training for LLM Reasoning Beyond the 80/20 Rule: High-Entropy Minority Tokens Drive Effective Reinforcement Learning for LLM Reasoning

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-04T08:53:07.648043Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a4abdab7-eff5-47e4-8935-3ee46b435881 · outbound

This paper cites Light-R1: Curriculum SFT, DPO and RL for Long COT from Scratch and Beyond.

A Model Can Help Itself: Reward-Free Self-Training for LLM Reasoning Light-R1: Curriculum SFT, DPO and RL for Long COT from Scratch and Beyond

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-04T08:53:07.747822Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f83abaae-1da9-4cdc-a873-9fb1f7b67d01 · outbound

This paper cites Qwen2.5 Technical Report.

A Model Can Help Itself: Reward-Free Self-Training for LLM Reasoning Qwen2.5 Technical Report

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-04T08:53:07.799133Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3b5f9f11-bbfc-48ce-bc9e-fd9644904b20 · outbound

This paper cites LIMO: Less is More for Reasoning.

A Model Can Help Itself: Reward-Free Self-Training for LLM Reasoning LIMO: Less is More for Reasoning

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-04T08:53:07.877463Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5c946287-8095-42a9-8015-c6cf3e942dce · outbound

This paper cites DAPO: An Open-Source LLM Reinforcement Learning System at Scale.

A Model Can Help Itself: Reward-Free Self-Training for LLM Reasoning DAPO: An Open-Source LLM Reinforcement Learning System at Scale

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-04T08:53:07.926195Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ff0600e3-ab3d-47dd-90b6-b523632f6565 · outbound

This paper cites Does Reinforcement Learning Really Incentivize Reasoning Capacity in LLMs Beyond the Base Model?.

A Model Can Help Itself: Reward-Free Self-Training for LLM Reasoning Does Reinforcement Learning Really Incentivize Reasoning Capacity in LLMs Beyond the Base Model?

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-04T08:53:07.999980Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a1cc2718-4317-4daa-aa01-d73bc473d594 · outbound

This paper cites SimpleRL-Zoo: Investigating and Taming Zero Reinforcement Learning for Open Base Models in the Wild.

A Model Can Help Itself: Reward-Free Self-Training for LLM Reasoning SimpleRL-Zoo: Investigating and Taming Zero Reinforcement Learning for Open Base Models in the Wild

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-04T08:53:08.054190Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 44cfdba6-2e01-470f-bbd1-8d739dea1c34 · outbound

This paper cites Group Sequence Policy Optimization.

A Model Can Help Itself: Reward-Free Self-Training for LLM Reasoning Group Sequence Policy Optimization

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-04T08:53:08.129407Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8f3f9da3-053c-43dd-a9cb-1d46c9d7af85 · outbound

This paper cites CONTENTS 1 Introduction 1 2 Preliminaries 3 2.1 Language Models.

A Model Can Help Itself: Reward-Free Self-Training for LLM Reasoning CONTENTS 1 Introduction 1 2 Preliminaries 3 2.1 Language Models

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-04T08:53:08.208235Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c3c5c9e1-aa6e-4f4b-81d0-08eee520b591 · outbound

This paper cites We also provide ablation study forτ eval in Section 4.3.3.

A Model Can Help Itself: Reward-Free Self-Training for LLM Reasoning We also provide ablation study forτ eval in Section 4.3.3

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-04T08:53:08.264018Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1d569e59-5604-43f3-ab7f-8d9ffc7f311f · outbound

This paper cites Spurious Rewards: Rethinking Training Signals in RLVR.

A Model Can Help Itself: Reward-Free Self-Training for LLM Reasoning Spurious Rewards: Rethinking Training Signals in RLVR

Reference 2017

Resolution: unresolved; no resolver link, observed 2026-08-04T08:53:07.162212Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c857a778-3de6-4291-857f-798d494a7e6c · outbound

This paper cites Open-Reasoner-Zero: An Open Source Approach to Scaling Up Reinforcement Learning on the Base Model.

A Model Can Help Itself: Reward-Free Self-Training for LLM Reasoning Open-Reasoner-Zero: An Open Source Approach to Scaling Up Reinforcement Learning on the Base Model

Reference 2021

Resolution: unresolved; no resolver link, observed 2026-08-04T08:53:06.305427Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 836a0a5e-7ca5-4377-ac97-b2b72f0e58b8 · outbound

This paper cites LLMs Can Easily Learn to Reason from Demonstrations Structure, not content, is what matters!.

A Model Can Help Itself: Reward-Free Self-Training for LLM Reasoning LLMs Can Easily Learn to Reason from Demonstrations Structure, not content, is what matters!

Reference 2022

Resolution: unresolved; no resolver link, observed 2026-08-04T08:53:06.449889Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d2895232-604d-418b-ba1e-5dcc43126f89 · outbound

This paper cites The Unreasonable Effectiveness of Entropy Minimization in LLM Reasoning.

A Model Can Help Itself: Reward-Free Self-Training for LLM Reasoning The Unreasonable Effectiveness of Entropy Minimization in LLM Reasoning

Reference 2023

Resolution: unresolved; no resolver link, observed 2026-08-04T08:53:05.285310Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fde9b704-daeb-40ec-8a0e-f1086bca7d6d · outbound

This paper cites Measuring Mathematical Problem Solving With the MATH Dataset.

A Model Can Help Itself: Reward-Free Self-Training for LLM Reasoning Measuring Mathematical Problem Solving With the MATH Dataset

Reference 2024

Resolution: unresolved; no resolver link, observed 2026-08-04T08:53:06.195668Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 076618a5-094f-4da6-80c7-4231b5d28439 · outbound

This paper cites Sparks of Artificial General Intelligence: Early experiments with GPT-4.

A Model Can Help Itself: Reward-Free Self-Training for LLM Reasoning Sparks of Artificial General Intelligence: Early experiments with GPT-4

Reference 2025

Resolution: unresolved; no resolver link, observed 2026-08-04T08:53:05.427930Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation 85b1f823-e10a-4142-a696-91ed2d311549 · inbound

Power Distribution Bridges Sampling, Self-Reward RL, and Self-Distillation cites this paper.

Power Distribution Bridges Sampling, Self-Reward RL, and Self-Distillation A Model Can Help Itself: Reward-Free Self-Training for LLM Reasoning

Reference 198

Resolution: metadata mismatch; local_arxiv, observed 2026-05-11T17:56:08.204338Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 879b653f-a7ec-4d1d-96a0-6cccdbc684cc · inbound

Beyond Negative Rollouts: Positive-Only Policy Optimization with Implicit Negative Gradients cites this paper.

Beyond Negative Rollouts: Positive-Only Policy Optimization with Implicit Negative Gradients A Model Can Help Itself: Reward-Free Self-Training for LLM Reasoning

Reference 55

Resolution: metadata mismatch; local_arxiv, observed 2026-05-11T20:16:08.418279Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.