Paper Citation Record · LEDGER

EDGE-GRPO: Entropy-Driven GRPO with Guided Error Correction for Advantage Diversity

As of 22 August 2026, this Paper Citation Record lists 23 of 23 outbound references and 18 inbound Pith citation observations for arXiv:2507.21848.

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

pith.paper-citation-record.v1
2507.21848 v1

Coverage vector

measured 23 of 23 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-06T12:26:11.192134Z

measured 41 of 41 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-22T06:32:14.747728+00:00

measured 18 of 18 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-12T00:39:40.838440Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-07-03T09:47:59.935150Z

Reference resolution

23 of 23 outbound references displayed

verified exact0
verified fuzzy0
unresolved23
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation d77ac373-6e99-49ab-a72e-7a0cf74997cd · outbound

This paper cites Efficient Reasoning Through Suppression of Self-Affirmation Reflections in Large Reasoning Models.

EDGE-GRPO: Entropy-Driven GRPO with Guided Error Correction for Advantage Diversity Efficient Reasoning Through Suppression of Self-Affirmation Reflections in Large Reasoning Models

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-06T12:26:11.159006Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d0b5dd49-9c09-4373-a9ad-b18ec0b14f2e · outbound

This paper cites Reasoning with Exploration: An Entropy Perspective.

EDGE-GRPO: Entropy-Driven GRPO with Guided Error Correction for Advantage Diversity Reasoning with Exploration: An Entropy Perspective

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-06T12:26:11.126635Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2f9b77b4-4d73-438f-ae59-802b873f62e6 · outbound

This paper cites Process Reinforcement through Implicit Rewards.

EDGE-GRPO: Entropy-Driven GRPO with Guided Error Correction for Advantage Diversity Process Reinforcement through Implicit Rewards

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-06T12:26:11.130126Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ae609b57-5ef6-44cf-8f75-b48d85a05bab · outbound

This paper cites arXiv preprint arXiv:2504.05185.

EDGE-GRPO: Entropy-Driven GRPO with Guided Error Correction for Advantage Diversity arXiv preprint arXiv:2504.05185

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-06T12:26:11.133984Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 43d43ab2-3aa5-49da-8317-3a3b660ecc44 · outbound

This paper cites One-shot Entropy Minimization.

EDGE-GRPO: Entropy-Driven GRPO with Guided Error Correction for Advantage Diversity One-shot Entropy Minimization

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-06T12:26:11.136900Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ccdf164c-bf13-48e9-943b-2c4477f3f8e8 · outbound

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

EDGE-GRPO: Entropy-Driven GRPO with Guided Error Correction for Advantage Diversity DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-06T12:26:11.140006Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1f60f95d-8c20-4a20-b7b4-c6434b7f16bb · outbound

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

EDGE-GRPO: Entropy-Driven GRPO with Guided Error Correction for Advantage Diversity Open-Reasoner-Zero: An Open Source Approach to Scaling Up Reinforcement Learning on the Base Model

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-06T12:26:11.149829Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 636b9b26-0998-42ca-942d-608d8a23df06 · outbound

This paper cites OpenAI o1 System Card.

EDGE-GRPO: Entropy-Driven GRPO with Guided Error Correction for Advantage Diversity OpenAI o1 System Card

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-06T12:26:11.152824Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 43b0583d-889d-4377-9a2d-eec2da785756 · outbound

This paper cites s1: Simple test-time scaling.

EDGE-GRPO: Entropy-Driven GRPO with Guided Error Correction for Advantage Diversity s1: Simple test-time scaling

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-06T12:26:11.161943Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e8f6cb66-e737-4fd9-ae59-baf9f5a0791c · outbound

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

EDGE-GRPO: Entropy-Driven GRPO with Guided Error Correction for Advantage Diversity DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-06T12:26:11.167724Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d869d484-ae55-4538-8f5e-cefedf7cf522 · outbound

This paper cites Between Underthinking and Overthinking: An Empirical Study of Reasoning Length and correctness in LLMs.

EDGE-GRPO: Entropy-Driven GRPO with Guided Error Correction for Advantage Diversity Between Underthinking and Overthinking: An Empirical Study of Reasoning Length and correctness in LLMs

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-06T12:26:11.170585Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 10859b75-3b04-4d6a-8f61-5a3f70f0b845 · outbound

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

EDGE-GRPO: Entropy-Driven GRPO with Guided Error Correction for Advantage Diversity Kimi k1.5: Scaling Reinforcement Learning with LLMs

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-06T12:26:11.173550Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a5081309-1f68-478d-bee0-953e78a9b6a2 · outbound

This paper cites Think Twice: Enhancing LLM Reasoning by Scaling Multi-round Test-time Thinking.

EDGE-GRPO: Entropy-Driven GRPO with Guided Error Correction for Advantage Diversity Think Twice: Enhancing LLM Reasoning by Scaling Multi-round Test-time Thinking

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-06T12:26:11.177203Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 67b691d7-64df-43f5-9953-dbe20f528a52 · outbound

This paper cites arXiv preprint arXiv:2506.01713.

EDGE-GRPO: Entropy-Driven GRPO with Guided Error Correction for Advantage Diversity arXiv preprint arXiv:2506.01713

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-06T12:26:11.180394Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 35a5df91-f167-48b6-8b40-cd7dc059882d · outbound

This paper cites Qwen2.5-Math Technical Report: Toward Mathematical Expert Model via Self-Improvement.

EDGE-GRPO: Entropy-Driven GRPO with Guided Error Correction for Advantage Diversity Qwen2.5-Math Technical Report: Toward Mathematical Expert Model via Self-Improvement

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-06T12:26:11.183062Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7fe85726-aa59-461a-a040-c4053a797ed2 · outbound

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

EDGE-GRPO: Entropy-Driven GRPO with Guided Error Correction for Advantage Diversity DAPO: An Open-Source LLM Reinforcement Learning System at Scale

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-06T12:26:11.186011Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 79f6c4c2-a856-43d0-a4a3-0617e3b1b1ab · outbound

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

EDGE-GRPO: Entropy-Driven GRPO with Guided Error Correction for Advantage Diversity SimpleRL-Zoo: Investigating and Taming Zero Reinforcement Learning for Open Base Models in the Wild

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-06T12:26:11.188931Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1c632aa7-4cc9-45bc-b549-9787c239eba3 · outbound

This paper cites R1-Zero's "Aha Moment" in Visual Reasoning on a 2B Non-SFT Model.

EDGE-GRPO: Entropy-Driven GRPO with Guided Error Correction for Advantage Diversity R1-Zero's "Aha Moment" in Visual Reasoning on a 2B Non-SFT Model

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-06T12:26:11.192134Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 215984af-1c66-40ea-892b-a9c8e23202bf · outbound

This paper cites Proximal Policy Optimization Algorithms.

EDGE-GRPO: Entropy-Driven GRPO with Guided Error Correction for Advantage Diversity Proximal Policy Optimization Algorithms

Reference 2017

Resolution: unresolved; no resolver link, observed 2026-08-06T12:26:11.164984Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6a781e4e-ebb1-4424-b8b4-7cee598c08fd · outbound

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

EDGE-GRPO: Entropy-Driven GRPO with Guided Error Correction for Advantage Diversity Measuring Mathematical Problem Solving With the MATH Dataset

Reference 2021

Resolution: unresolved; no resolver link, observed 2026-08-06T12:26:11.146760Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 83f14dab-ca0d-4b49-8f7d-1a69efff6c58 · outbound

This paper cites Solving Quantitative Reasoning Problems with Language Models.

EDGE-GRPO: Entropy-Driven GRPO with Guided Error Correction for Advantage Diversity Solving Quantitative Reasoning Problems with Language Models

Reference 2022

Resolution: unresolved; no resolver link, observed 2026-08-06T12:26:11.155945Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation db9b1184-dcf1-439e-b20d-5f4c0624b0df · outbound

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

EDGE-GRPO: Entropy-Driven GRPO with Guided Error Correction for Advantage Diversity OlympiadBench: A Challenging Benchmark for Promoting AGI with Olympiad-Level Bilingual Multimodal Scientific Problems

Reference 2024

Resolution: unresolved; no resolver link, observed 2026-08-06T12:26:11.143506Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 69b01b73-13c2-4459-890e-334ee896733b · outbound

This paper cites SEED-GRPO: Semantic Entropy Enhanced GRPO for Uncertainty-Aware Policy Optimization.

EDGE-GRPO: Entropy-Driven GRPO with Guided Error Correction for Advantage Diversity SEED-GRPO: Semantic Entropy Enhanced GRPO for Uncertainty-Aware Policy Optimization

Reference 2025

Resolution: unresolved; no resolver link, observed 2026-08-06T12:26:11.122616Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation cf2cc2bc-117b-4cd6-847a-ba838efe361b · inbound

The Landscape of Agentic Reinforcement Learning for LLMs: A Survey cites this paper.

The Landscape of Agentic Reinforcement Learning for LLMs: A Survey EDGE-GRPO: Entropy-Driven GRPO with Guided Error Correction for Advantage Diversity

Reference 63

Resolution: verified exact; arxiv_id, observed 2026-05-18T19:21:48.764302Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 68eb5094-2f5b-4c44-a765-9f568ccab9f4 · inbound

Harnessing Uncertainty: Entropy-Modulated Policy Gradients for Long-Horizon LLM Agents cites this paper.

Harnessing Uncertainty: Entropy-Modulated Policy Gradients for Long-Horizon LLM Agents EDGE-GRPO: Entropy-Driven GRPO with Guided Error Correction for Advantage Diversity

Reference 44

Resolution: unresolved; no resolver link, observed 2026-08-04T19:29:00.634858Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 728510a6-8d25-44f4-9359-2b8725dd0455 · inbound

SCOPE-RL: Stable and Quantitative Control of Policy Entropy in RL Post-Training cites this paper.

SCOPE-RL: Stable and Quantitative Control of Policy Entropy in RL Post-Training EDGE-GRPO: Entropy-Driven GRPO with Guided Error Correction for Advantage Diversity

Reference 25

Resolution: verified exact; arxiv_id, observed 2026-05-21T20:30:35.435478Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 6766ed2b-4d7d-4775-9f0d-4641884c93d1 · inbound

VIDEOP2R: Video Understanding from Perception to Reasoning cites this paper.

VIDEOP2R: Video Understanding from Perception to Reasoning EDGE-GRPO: Entropy-Driven GRPO with Guided Error Correction for Advantage Diversity

Reference 70

Resolution: verified exact; arxiv_id, observed 2026-05-17T22:25:22.674800Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 558a877a-ae86-41e9-b42b-c1f3052f6287 · inbound

Compress the Easy, Explore the Hard: Difficulty-Aware Entropy Regularization for Efficient LLM Reasoning cites this paper.

Compress the Easy, Explore the Hard: Difficulty-Aware Entropy Regularization for Efficient LLM Reasoning EDGE-GRPO: Entropy-Driven GRPO with Guided Error Correction for Advantage Diversity

Reference 52

Resolution: unresolved; no resolver link, observed 2026-08-02T20:44:47.413838Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9622d80b-8959-4571-84e3-629ea3086da1 · inbound

StaRPO: Stability-Augmented Reinforcement Policy Optimization cites this paper.

StaRPO: Stability-Augmented Reinforcement Policy Optimization EDGE-GRPO: Entropy-Driven GRPO with Guided Error Correction for Advantage Diversity

Reference 45

Resolution: verified exact; arxiv_id, observed 2026-05-11T05:20:59.951337Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 4c9c248a-4723-453d-942f-2d66754ef541 · inbound

Hidden States Know Where Reasoning Diverges: Credit Assignment via Span-Level Wasserstein Distance cites this paper.

Hidden States Know Where Reasoning Diverges: Credit Assignment via Span-Level Wasserstein Distance EDGE-GRPO: Entropy-Driven GRPO with Guided Error Correction for Advantage Diversity

Reference 35

Resolution: verified exact; arxiv_id, observed 2026-05-11T20:46:13.056711Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 58666f63-cb06-4f1a-9b0a-b2b0612dda90 · inbound

Leveraging Error Diversity in Group Rollouts for Reinforcement Learning cites this paper.

Leveraging Error Diversity in Group Rollouts for Reinforcement Learning EDGE-GRPO: Entropy-Driven GRPO with Guided Error Correction for Advantage Diversity

Reference 34

Resolution: verified exact; arxiv_id, observed 2026-05-20T14:53:23.309046Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 89914b81-2235-4847-bb65-3a9f4ecd70db · inbound

Leveraging Error Diversity in Group Rollouts for Reinforcement Learning cites this paper.

Leveraging Error Diversity in Group Rollouts for Reinforcement Learning EDGE-GRPO: Entropy-Driven GRPO with Guided Error Correction for Advantage Diversity

Reference 34

Resolution: verified exact; arxiv_id, observed 2026-06-30T19:05:00.406585Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation b88c5685-4fd8-4dd7-9e91-768ecff1be67 · inbound

Advantage Collapse in Group Relative Policy Optimization: Diagnosis and Mitigation cites this paper.

Advantage Collapse in Group Relative Policy Optimization: Diagnosis and Mitigation EDGE-GRPO: Entropy-Driven GRPO with Guided Error Correction for Advantage Diversity

Reference 47

Resolution: verified exact; arxiv_id, observed 2026-05-21T06:09:41.261365Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation f711196d-2267-4ebf-9db1-99794f9289d3 · inbound

Advantage Collapse in Group Relative Policy Optimization: Diagnosis and Mitigation cites this paper.

Advantage Collapse in Group Relative Policy Optimization: Diagnosis and Mitigation EDGE-GRPO: Entropy-Driven GRPO with Guided Error Correction for Advantage Diversity

Reference 47

Resolution: verified exact; arxiv_id, observed 2026-07-01T15:15:47.310221Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation d573ebba-a89f-4ef3-9e76-5f893d5e3882 · inbound

Smaller Models are Natural Explorers for Policy-Level Diversity in GRPO cites this paper.

Smaller Models are Natural Explorers for Policy-Level Diversity in GRPO EDGE-GRPO: Entropy-Driven GRPO with Guided Error Correction for Advantage Diversity

Reference 31

Resolution: verified exact; arxiv_id, observed 2026-06-29T00:02:49.989463Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 1d0ebd72-b3e4-4607-a14a-536159c26a1a · inbound

Architecture-Aware Reinforcement Learning Makes Sliding-Window Attention Competitive in Math Reasoning cites this paper.

Architecture-Aware Reinforcement Learning Makes Sliding-Window Attention Competitive in Math Reasoning EDGE-GRPO: Entropy-Driven GRPO with Guided Error Correction for Advantage Diversity

Reference 5

Resolution: verified exact; arxiv_id, observed 2026-07-03T09:47:59.936872Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation e947bb10-d5b3-4419-b4d6-3f8825599d84 · inbound

Consistency as Inductive Bias: Learning Cross-View Invariance for Robust Multimodal Reasoning cites this paper.

Consistency as Inductive Bias: Learning Cross-View Invariance for Robust Multimodal Reasoning EDGE-GRPO: Entropy-Driven GRPO with Guided Error Correction for Advantage Diversity

Reference 52

Resolution: verified exact; arxiv_id, observed 2026-06-30T06:14:19.253487Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 71968d98-9133-4017-8a89-4e45d84158cd · inbound

Which Tokens Matter? Adaptive Token Selection for RLVR with the Relative Surprisal Index cites this paper.

Which Tokens Matter? Adaptive Token Selection for RLVR with the Relative Surprisal Index EDGE-GRPO: Entropy-Driven GRPO with Guided Error Correction for Advantage Diversity

Reference 33

Resolution: verified exact; arxiv_id, observed 2026-07-01T10:25:42.413060Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 0a8f6b9b-0cad-4138-b6d3-a4bc95a6b36a · inbound

When Correct Solutions Repeat: Rarity-Aware Credit Redistribution for GRPO cites this paper.

When Correct Solutions Repeat: Rarity-Aware Credit Redistribution for GRPO EDGE-GRPO: Entropy-Driven GRPO with Guided Error Correction for Advantage Diversity

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-05T18:43:17.536451Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bbb13f40-929a-4252-ab59-dd58226c2ec5 · inbound

When Correct Solutions Repeat: Rarity-Aware Credit Redistribution for GRPO cites this paper.

When Correct Solutions Repeat: Rarity-Aware Credit Redistribution for GRPO EDGE-GRPO: Entropy-Driven GRPO with Guided Error Correction for Advantage Diversity

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-08T00:52:47.185967Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3b81bcac-b01f-4ce5-917d-27972528646d · inbound

Ground-Truth Neighborhood Regularization for Reinforcement Learning Post-Training of Time Series Foundation Models cites this paper.

Ground-Truth Neighborhood Regularization for Reinforcement Learning Post-Training of Time Series Foundation Models EDGE-GRPO: Entropy-Driven GRPO with Guided Error Correction for Advantage Diversity

Reference 123

Resolution: unresolved; no resolver link, observed 2026-08-12T00:39:40.838440Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.