Paper Citation Record · LEDGER

CVPO: Enhancing LLM Reinforcement Learning Reasoning via Value-Variance Adaptation and Dynamic Curriculum Learning

As of 15 August 2026, this Paper Citation Record lists 18 of 18 outbound references and 0 inbound Pith citation observations for arXiv:2608.03068.

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

pith.paper-citation-record.v1
2608.03068 v1

Coverage vector

measured 18 of 18 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-08T01:03:50.900234Z

measured 18 of 18 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-15T06:32:42.880941+00:00

measured 0 of 0 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links

measured 0 of 1 external citation measurements

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

Source: cited_works

Reference resolution

18 of 18 outbound references displayed

verified exact1
verified fuzzy1
unresolved16
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 198e8273-1157-42ea-87a4-f1de19bf9c72 · outbound

This paper cites DeepSeek-V3 Technical Report.

CVPO: Enhancing LLM Reinforcement Learning Reasoning via Value-Variance Adaptation and Dynamic Curriculum Learning DeepSeek-V3 Technical Report

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-08T01:03:50.820158Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f49a1024-cbde-4c97-a3d1-15074d109f82 · outbound

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

CVPO: Enhancing LLM Reinforcement Learning Reasoning via Value-Variance Adaptation and Dynamic Curriculum Learning Open-Reasoner-Zero: An Open Source Approach to Scaling Up Reinforcement Learning on the Base Model

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-08T01:03:50.835692Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c6307409-bfff-417d-96c1-a50c2b545310 · outbound

This paper cites Mihir Prabhudesai, Lili Chen, Alex Ippoliti, Katerina Fragkiadaki, Hao Liu, and Deepak Pathak.

CVPO: Enhancing LLM Reinforcement Learning Reasoning via Value-Variance Adaptation and Dynamic Curriculum Learning Mihir Prabhudesai, Lili Chen, Alex Ippoliti, Katerina Fragkiadaki, Hao Liu, and Deepak Pathak

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-08T01:03:50.840766Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d7e09ead-8a90-4a9e-95fc-49075a756c03 · outbound

This paper cites Maximizing Confidence Alone Improves Reasoning.

CVPO: Enhancing LLM Reinforcement Learning Reasoning via Value-Variance Adaptation and Dynamic Curriculum Learning Maximizing Confidence Alone Improves Reasoning

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-08T01:03:50.846084Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4bb7b8b2-740b-4747-ab40-041cd0009fed · outbound

This paper cites an unresolved cited work.

CVPO: Enhancing LLM Reinforcement Learning Reasoning via Value-Variance Adaptation and Dynamic Curriculum Learning Unresolved cited work

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-08T01:03:50.851038Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c48d44f1-d719-44e6-8d60-4d963273726d · outbound

This paper cites Offline Regularised Reinforcement Learning for Large Language Models Alignment.

CVPO: Enhancing LLM Reinforcement Learning Reasoning via Value-Variance Adaptation and Dynamic Curriculum Learning Offline Regularised Reinforcement Learning for Large Language Models Alignment

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-08T01:03:50.856286Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d7ab1b69-45a5-4627-893c-40d3a1179c0b · outbound

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

CVPO: Enhancing LLM Reinforcement Learning Reasoning via Value-Variance Adaptation and Dynamic Curriculum Learning Spurious Rewards: Rethinking Training Signals in RLVR

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-08T01:03:50.867049Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 06828e25-d770-4794-91aa-04f2467a6c68 · outbound

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

CVPO: Enhancing LLM Reinforcement Learning Reasoning via Value-Variance Adaptation and Dynamic Curriculum Learning DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-08T01:03:50.872022Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bb9eb6a6-0b0a-470f-be7b-34ee3c3bd211 · outbound

This paper cites Efficient Reinforcement Finetuning via Adaptive Curriculum Learning.

CVPO: Enhancing LLM Reinforcement Learning Reasoning via Value-Variance Adaptation and Dynamic Curriculum Learning Efficient Reinforcement Finetuning via Adaptive Curriculum Learning

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-08T01:03:50.877512Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 656f73ed-543a-4fa8-9343-6d6f4884cfd9 · outbound

This paper cites DGRO: Enhancing LLM Reasoning via Exploration-Exploitation Control and Reward Variance Management.

CVPO: Enhancing LLM Reinforcement Learning Reasoning via Value-Variance Adaptation and Dynamic Curriculum Learning DGRO: Enhancing LLM Reasoning via Exploration-Exploitation Control and Reward Variance Management

Reference 14

Resolution: verified exact; local_arxiv, observed 2026-08-08T01:03:51.005031Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 04e254a3-3d8f-4309-b802-dd0885ef1db6 · outbound

This paper cites Kimi k1.5: Scaling Reinforcement Learning with LLMs.

CVPO: Enhancing LLM Reinforcement Learning Reasoning via Value-Variance Adaptation and Dynamic Curriculum Learning Kimi k1.5: Scaling Reinforcement Learning with LLMs

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-08T01:03:50.887036Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 234fcb07-92af-4807-996e-7e34e791be50 · outbound

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

CVPO: Enhancing LLM Reinforcement Learning Reasoning via Value-Variance Adaptation and Dynamic Curriculum Learning DAPO: An Open-Source LLM Reinforcement Learning System at Scale

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-08T01:03:50.891503Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 47b2cca1-ef7f-429d-a4b9-b4f81fd44a93 · outbound

This paper cites What's Behind PPO's Collapse in Long-CoT? Value Optimization Holds the Secret.

CVPO: Enhancing LLM Reinforcement Learning Reasoning via Value-Variance Adaptation and Dynamic Curriculum Learning What's Behind PPO's Collapse in Long-CoT? Value Optimization Holds the Secret

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-08T01:03:50.895805Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f64dcd2a-c888-4b80-90f1-c759daa5af2f · outbound

This paper cites VAPO: Efficient and Reliable Reinforcement Learning for Advanced Reasoning Tasks.

CVPO: Enhancing LLM Reinforcement Learning Reasoning via Value-Variance Adaptation and Dynamic Curriculum Learning VAPO: Efficient and Reliable Reinforcement Learning for Advanced Reasoning Tasks

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-08T01:03:50.900234Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 53510328-38fc-4371-ab95-f428ae84eb73 · outbound

This paper cites Proximal Policy Optimization Algorithms.

CVPO: Enhancing LLM Reinforcement Learning Reasoning via Value-Variance Adaptation and Dynamic Curriculum Learning Proximal Policy Optimization Algorithms

Reference 2017

Resolution: unresolved; no resolver link, observed 2026-08-08T01:03:50.862158Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f05c8805-548d-48d0-8a4b-158208d944e1 · outbound

This paper cites InProceedings of the Neural Information Processing Systems Track on Datasets and Benchmarks 1, NeurIPS Datasets and Benchmarks 2021, December 2021, virtual.

CVPO: Enhancing LLM Reinforcement Learning Reasoning via Value-Variance Adaptation and Dynamic Curriculum Learning InProceedings of the Neural Information Processing Systems Track on Datasets and Benchmarks 1, NeurIPS Datasets and Benchmarks 2021, December 2021, virtual

Reference 2021

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T01:03:51.347930Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 471fe5c0-bde5-4e7e-a082-1e7ca1a9f9f6 · outbound

This paper cites MiniMax-M1: Scaling Test-Time Compute Efficiently with Lightning Attention.

CVPO: Enhancing LLM Reinforcement Learning Reasoning via Value-Variance Adaptation and Dynamic Curriculum Learning MiniMax-M1: Scaling Test-Time Compute Efficiently with Lightning Attention

Reference 2024

Resolution: unresolved; no resolver link, observed 2026-08-08T01:03:50.814168Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation da67af90-fa16-46a0-a5c0-349c22f72ca6 · outbound

This paper cites REINFORCE++: Stabilizing Critic-Free Policy Optimization with Global Advantage Normalization.

CVPO: Enhancing LLM Reinforcement Learning Reasoning via Value-Variance Adaptation and Dynamic Curriculum Learning REINFORCE++: Stabilizing Critic-Free Policy Optimization with Global Advantage Normalization

Reference 2025

Resolution: unresolved; no resolver link, observed 2026-08-08T01:03:50.829866Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

No inbound Pith citation observations are available.