Paper Citation Record · LEDGER

Stabilizing Policy Optimization via Logits Convexity

As of 7 August 2026, this Paper Citation Record lists 20 of 20 outbound references and 2 inbound Pith citation observations for arXiv:2603.00963.

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

pith.paper-citation-record.v1
2603.00963 v2

Coverage vector

measured 20 of 20 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-02T19:53:09.484847Z

measured 22 of 22 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-06T06:34:29.942622+00:00

measured 2 of 2 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-07-12T20:58:19.104482Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-05-11T09:56:01.761633Z

Reference resolution

20 of 20 outbound references displayed

verified exact0
verified fuzzy0
unresolved20
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 404904fe-7036-4f2d-a49d-842460e67567 · outbound

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

Stabilizing Policy Optimization via Logits Convexity MiniMax-M1: Scaling Test-Time Compute Efficiently with Lightning Attention

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-02T19:53:07.595577Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 73a0700a-0d2e-4a57-a14a-421d727feebb · outbound

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

Stabilizing Policy Optimization via Logits Convexity The Entropy Mechanism of Reinforcement Learning for Reasoning Language Models

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-02T19:53:07.706557Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 59dbce43-6432-4300-b4d8-c551396d6bbe · outbound

This paper cites MiniLLM: On-Policy Distillation of Large Language Models.

Stabilizing Policy Optimization via Logits Convexity MiniLLM: On-Policy Distillation of Large Language Models

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-02T19:53:07.813705Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1ffb8ba8-62cd-47d8-aa2a-61471182c523 · outbound

This paper cites High-Dimensional Continuous Control Using Generalized Advantage Estimation.

Stabilizing Policy Optimization via Logits Convexity High-Dimensional Continuous Control Using Generalized Advantage Estimation

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-02T19:53:08.307029Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c822d43c-a000-4fea-8898-e4eba2f046e8 · outbound

This paper cites Ring-lite: Scalable Reasoning via C3PO-Stabilized Reinforcement Learning for LLMs.

Stabilizing Policy Optimization via Logits Convexity Ring-lite: Scalable Reasoning via C3PO-Stabilized Reinforcement Learning for LLMs

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-02T19:53:08.502936Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9b95b6dd-9cba-47c4-ba27-802b4ecd1a1f · outbound

This paper cites Qwen3 Technical Report.

Stabilizing Policy Optimization via Logits Convexity Qwen3 Technical Report

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-02T19:53:08.621723Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7951a39a-8e29-4105-9e88-6df39b8ef26c · outbound

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

Stabilizing Policy Optimization via Logits Convexity What's Behind PPO's Collapse in Long-CoT? Value Optimization Holds the Secret

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-02T19:53:08.739032Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 20f7ae9c-bff9-4157-9b2c-6b5ac5d508e4 · outbound

This paper cites R1-Reward: Training Multimodal Reward Model Through Stable Reinforcement Learning.

Stabilizing Policy Optimization via Logits Convexity R1-Reward: Training Multimodal Reward Model Through Stable Reinforcement Learning

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-02T19:53:08.856440Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0b4f0e5c-2109-440b-8fed-60bde5b5d0b8 · outbound

This paper cites Group Sequence Policy Optimization.

Stabilizing Policy Optimization via Logits Convexity Group Sequence Policy Optimization

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-02T19:53:08.971429Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 221083bd-c429-4d9a-9d64-47c01145b324 · outbound

This paper cites DPO Meets PPO: Reinforced Token Optimization for RLHF.

Stabilizing Policy Optimization via Logits Convexity DPO Meets PPO: Reinforced Token Optimization for RLHF

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-02T19:53:09.115910Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2391cd77-dfb3-4a1b-886f-c5b2b48ee6cd · outbound

This paper cites CARFT: Boosting LLM Reasoning via Contrastive Learning with Annotated Chain-of-Thought-based Reinforced Fine-Tuning.

Stabilizing Policy Optimization via Logits Convexity CARFT: Boosting LLM Reasoning via Contrastive Learning with Annotated Chain-of-Thought-based Reinforced Fine-Tuning

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-02T19:53:09.204030Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 15919a99-9074-41fb-b1e1-c97b3525a8ad · outbound

This paper cites To address this, they propose a pretraining procedure for the value model, and decouple the λ in GAE for the policy and value model computations.

Stabilizing Policy Optimization via Logits Convexity To address this, they propose a pretraining procedure for the value model, and decouple the λ in GAE for the policy and value model computations

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-02T19:53:09.278564Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 972b9aed-1cc3-410a-bc62-018c17593ba8 · outbound

This paper cites Similarly, Shao et al.

Stabilizing Policy Optimization via Logits Convexity Similarly, Shao et al

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-02T19:53:09.354384Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 04fcd6b7-ccd5-4a9d-ac89-fe4776e09aef · outbound

This paper cites Building upon the same idea, DCPO (Yang et al., 2025b) addresses the limitation in DAPO, where the same clip range is set for different positions.

Stabilizing Policy Optimization via Logits Convexity Building upon the same idea, DCPO (Yang et al., 2025b) addresses the limitation in DAPO, where the same clip range is set for different positions

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-02T19:53:09.484847Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 906355fb-d127-40b4-8a78-ba2ec430365a · outbound

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

Stabilizing Policy Optimization via Logits Convexity DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models

Reference 2017

Resolution: unresolved; no resolver link, observed 2026-08-02T19:53:08.385115Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 43196cf2-9d1d-4c7e-8452-a3ed04166d7f · outbound

This paper cites Crafting papers on machine learning.

Stabilizing Policy Optimization via Logits Convexity Crafting papers on machine learning

Reference 2018

Resolution: unresolved; no resolver link, observed 2026-08-02T19:53:08.113911Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8a908f5f-d786-4004-a0c4-5edab5a2b6e7 · outbound

This paper cites Generalist Reward Models: Found Inside Large Language Models.

Stabilizing Policy Optimization via Logits Convexity Generalist Reward Models: Found Inside Large Language Models

Reference 2022

Resolution: unresolved; no resolver link, observed 2026-08-02T19:53:08.222944Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation faadda65-7e26-489b-a2a4-0e551a95f1db · outbound

This paper cites DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning.

Stabilizing Policy Optimization via Logits Convexity DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning

Reference 2023

Resolution: unresolved; no resolver link, observed 2026-08-02T19:53:07.923480Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 69356ac8-eeec-4bed-9ebf-82ed49ed2f7a · outbound

This paper cites TLCR: Token-Level Continuous Reward for Fine-grained Reinforcement Learning from Human Feedback.

Stabilizing Policy Optimization via Logits Convexity TLCR: Token-Level Continuous Reward for Fine-grained Reinforcement Learning from Human Feedback

Reference 2024

Resolution: unresolved; no resolver link, observed 2026-08-02T19:53:07.503407Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 64088392-ed46-4f74-a279-93297f8bb234 · outbound

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

Stabilizing Policy Optimization via Logits Convexity REINFORCE++: Stabilizing Critic-Free Policy Optimization with Global Advantage Normalization

Reference 2025

Resolution: unresolved; no resolver link, observed 2026-08-02T19:53:08.005719Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation b0a4bd84-7b6f-40d8-85b9-1a1e00f6396a · inbound

Unleashing Implicit Rewards: Prefix-Value Learning for Distribution-Level Optimization cites this paper.

Unleashing Implicit Rewards: Prefix-Value Learning for Distribution-Level Optimization Stabilizing Policy Optimization via Logits Convexity

Reference 1

Resolution: verified exact; arxiv_id, observed 2026-06-02T03:04:05.363647Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 22b2d736-9ff7-4af2-aba3-6e4e5900bae4 · inbound

Unleashing Implicit Rewards: Prefix-Value Learning for Distribution-Level Optimization cites this paper.

Unleashing Implicit Rewards: Prefix-Value Learning for Distribution-Level Optimization Stabilizing Policy Optimization via Logits Convexity

Reference 1

Resolution: unresolved; no resolver link, observed 2026-07-12T20:58:19.104482Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.