Paper Citation Record · LEDGER

Leveraging Error Diversity in Group Rollouts for Reinforcement Learning

As of 4 August 2026, this Paper Citation Record lists 35 of 35 outbound references and 2 inbound Pith citation observations for arXiv:2605.17333.

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

pith.paper-citation-record.v1
2605.17333 v2

Coverage vector

measured 35 of 35 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-06-30T19:03:10.268534Z

measured 37 of 37 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-04T06:34:03.388597+00:00

measured 2 of 2 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-02T21:50:58.824041Z

measured 0 of 1 external citation measurements

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

Source: pith, observed 2026-07-02T02:06:27.263175Z

Reference resolution

35 of 35 outbound references displayed

verified exact25
verified fuzzy9
unresolved1
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 4b1ba4e5-b7ca-4f4b-aed8-b5f84a16258e · outbound

This paper cites Program Synthesis with Large Language Models.

Leveraging Error Diversity in Group Rollouts for Reinforcement Learning Program Synthesis with Large Language Models

Reference 1

Resolution: verified exact; local_arxiv, observed 2026-06-30T19:05:00.420630Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 9a366783-c26f-4655-a718-8b1a770589a0 · outbound

This paper cites Matharena: Evaluating llms on uncontaminated math competitions, february 2025.https://matharena.ai, 8.

Leveraging Error Diversity in Group Rollouts for Reinforcement Learning Matharena: Evaluating llms on uncontaminated math competitions, february 2025.https://matharena.ai, 8

Reference 2

Resolution: verified fuzzy; raw_fallback, observed 2026-07-08T01:34:27.166592Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 9a99b717-4914-450d-b475-106ec02b200c · outbound

This paper cites Post-training as reweighting: A stochastic view of reasoning trajectories in language models.

Leveraging Error Diversity in Group Rollouts for Reinforcement Learning Post-training as reweighting: A stochastic view of reasoning trajectories in language models

Reference 3

Resolution: verified exact; arxiv_id, observed 2026-06-30T19:05:00.423181Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 1e6cacf5-f354-4274-8065-8e7706cdfbb0 · outbound

This paper cites Evaluating Large Language Models Trained on Code.

Leveraging Error Diversity in Group Rollouts for Reinforcement Learning Evaluating Large Language Models Trained on Code

Reference 4

Resolution: verified exact; local_arxiv, observed 2026-06-30T19:05:00.410488Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 1ae4db99-e03f-4ad9-b81e-c18b5c139651 · outbound

This paper cites arXiv preprint arXiv:2505.09655 , year=.

Leveraging Error Diversity in Group Rollouts for Reinforcement Learning arXiv preprint arXiv:2505.09655 , year=

Reference 5

Resolution: verified exact; arxiv_id, observed 2026-06-30T19:05:00.408150Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation a087e67a-aee1-4f92-ba25-bba483404220 · outbound

This paper cites Reasoning with exploration: An entropy perspective.

Leveraging Error Diversity in Group Rollouts for Reinforcement Learning Reasoning with exploration: An entropy perspective

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-07-08T01:34:27.168504Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation bab5517e-8183-4245-920f-7286a4c45e73 · outbound

This paper cites American invitational mathematics examination-aime 2024.

Leveraging Error Diversity in Group Rollouts for Reinforcement Learning American invitational mathematics examination-aime 2024

Reference 7

Resolution: verified fuzzy; raw_fallback, observed 2026-07-08T01:34:27.170368Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 2ffba4e4-c132-4868-95e1-e07535b29155 · outbound

This paper cites Harder is better: Boost- ing mathematical reasoning via difficulty-aware grpo and multi-aspect question reformulation.

Leveraging Error Diversity in Group Rollouts for Reinforcement Learning Harder is better: Boost- ing mathematical reasoning via difficulty-aware grpo and multi-aspect question reformulation

Reference 8

Resolution: verified exact; arxiv_id, observed 2026-06-30T19:05:00.425821Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 515a2898-7620-4fc6-917e-df207c8fe663 · outbound

This paper cites Interleaved latent visual reasoning with selective perceptual modeling.

Leveraging Error Diversity in Group Rollouts for Reinforcement Learning Interleaved latent visual reasoning with selective perceptual modeling

Reference 9

Resolution: verified exact; arxiv_id, observed 2026-06-30T19:05:00.420310Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation cd543f84-2aed-4200-a98c-9b4d694d84d1 · outbound

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

Leveraging Error Diversity in Group Rollouts for Reinforcement Learning DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning

Reference 10

Resolution: verified exact; local_arxiv, observed 2026-06-30T19:05:00.433031Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation be741e74-6ada-4578-b50d-cafb9fb6b427 · outbound

This paper cites Reasoning through exploration: A reinforcement learning framework for robust function calling.

Leveraging Error Diversity in Group Rollouts for Reinforcement Learning Reasoning through exploration: A reinforcement learning framework for robust function calling

Reference 11

Resolution: verified exact; arxiv_id, observed 2026-06-30T19:05:00.372591Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 7640a5c3-5593-45b7-9692-81e770d0db2d · outbound

This paper cites Olympiadbench: A challenging benchmark for promoting agi with olympiad-level bilingual multimodal scientific problems.

Leveraging Error Diversity in Group Rollouts for Reinforcement Learning Olympiadbench: A challenging benchmark for promoting agi with olympiad-level bilingual multimodal scientific problems

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-07-08T01:34:27.162531Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation ca3964a8-5ba9-41df-9c34-a73d013d2318 · outbound

This paper cites OpenAI o1 System Card.

Leveraging Error Diversity in Group Rollouts for Reinforcement Learning OpenAI o1 System Card

Reference 13

Resolution: verified exact; local_arxiv, observed 2026-06-30T19:05:00.388344Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation bd7e061d-91b4-4aae-bd34-9b09ef6de84e · outbound

This paper cites LiveCodeBench: Holistic and Contamination Free Evaluation of Large Language Models for Code.

Leveraging Error Diversity in Group Rollouts for Reinforcement Learning LiveCodeBench: Holistic and Contamination Free Evaluation of Large Language Models for Code

Reference 14

Resolution: verified exact; local_arxiv, observed 2026-06-30T19:05:00.413123Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 7c1f0d5b-7377-427c-ab7f-b81e6b50be0e · outbound

This paper cites Setpo: Set-level policy optimization for diversity-preserving llm reasoning.

Leveraging Error Diversity in Group Rollouts for Reinforcement Learning Setpo: Set-level policy optimization for diversity-preserving llm reasoning

Reference 15

Resolution: verified exact; arxiv_id, observed 2026-06-30T19:05:00.435940Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 72e8effc-8268-4ac5-a301-fd26280d3594 · outbound

This paper cites DeepSeek-V3 Technical Report.

Leveraging Error Diversity in Group Rollouts for Reinforcement Learning DeepSeek-V3 Technical Report

Reference 16

Resolution: verified exact; local_arxiv, observed 2026-06-30T19:05:00.425260Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 828c286c-4b7f-42bc-bc3b-e780b5ada7e6 · outbound

This paper cites Code-r1: Reproducing r1 for code with reliable rewards.

Leveraging Error Diversity in Group Rollouts for Reinforcement Learning Code-r1: Reproducing r1 for code with reliable rewards

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-07-08T01:34:27.159023Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 36188bb1-2d4a-41c3-a9a1-e14b8d9f3a4f · outbound

This paper cites an unresolved cited work.

Leveraging Error Diversity in Group Rollouts for Reinforcement Learning Unresolved cited work

Reference 18

Resolution: unresolved; raw_fallback, observed 2026-07-08T01:34:27.160665Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 8d5fe6b1-9741-47ca-ae9e-077feedbf07f · outbound

This paper cites Diversity-aware training for test-time scaling.

Leveraging Error Diversity in Group Rollouts for Reinforcement Learning Diversity-aware training for test-time scaling

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-07-08T01:34:27.164596Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 5a8455af-7cf7-42a6-b624-df92f5cbc661 · outbound

This paper cites American mathematics competitions - amc.https://maa.org/.

Leveraging Error Diversity in Group Rollouts for Reinforcement Learning American mathematics competitions - amc.https://maa.org/

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-07-08T01:34:27.155163Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 73a0841b-21a0-4296-8266-2b0c081e654e · outbound

This paper cites American invitational mathematics examination-AIME 2025.https://maa.org/.

Leveraging Error Diversity in Group Rollouts for Reinforcement Learning American invitational mathematics examination-AIME 2025.https://maa.org/

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-07-08T01:34:27.157135Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 0b0e6343-3c06-41c6-9278-e0671f7d8c48 · outbound

This paper cites American invitational mathematics examination-AIME 2026.https://maa.org/.

Leveraging Error Diversity in Group Rollouts for Reinforcement Learning American invitational mathematics examination-AIME 2026.https://maa.org/

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-07-08T01:34:27.153189Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation a2c47669-c47c-4152-b605-5bb3e996df66 · outbound

This paper cites Ngrpo: Negative-enhanced group relative policy optimization.

Leveraging Error Diversity in Group Rollouts for Reinforcement Learning Ngrpo: Negative-enhanced group relative policy optimization

Reference 23

Resolution: verified exact; arxiv_id, observed 2026-06-30T19:05:00.402722Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation d0b9eb4a-8f38-4e2e-b05c-42ed6bf2bafe · outbound

This paper cites CodeElo: Benchmarking Competition-level Code Generation of LLMs with Human-comparable Elo Ratings.

Leveraging Error Diversity in Group Rollouts for Reinforcement Learning CodeElo: Benchmarking Competition-level Code Generation of LLMs with Human-comparable Elo Ratings

Reference 24

Resolution: verified exact; arxiv_id, observed 2026-06-30T19:05:00.422916Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation a8602bf4-fdd3-43d0-81b9-7ac7c85e116b · outbound

This paper cites Proximal Policy Optimization Algorithms.

Leveraging Error Diversity in Group Rollouts for Reinforcement Learning Proximal Policy Optimization Algorithms

Reference 25

Resolution: verified exact; local_arxiv, observed 2026-06-30T19:05:00.430705Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 7b6013b6-fc6d-4461-87c8-9f57e21f19c5 · outbound

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

Leveraging Error Diversity in Group Rollouts for Reinforcement Learning DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models

Reference 26

Resolution: verified exact; local_arxiv, observed 2026-06-30T19:05:00.394706Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation adae003e-4066-4f99-a89f-c9ac8719bf8d · outbound

This paper cites Pass@K Policy Optimization: Solving Harder Reinforcement Learning Problems.

Leveraging Error Diversity in Group Rollouts for Reinforcement Learning Pass@K Policy Optimization: Solving Harder Reinforcement Learning Problems

Reference 27

Resolution: verified exact; local_arxiv, observed 2026-06-30T19:05:00.378626Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 21f9fa6e-f89d-41a0-bc2c-22798f808b0d · outbound

This paper cites MMR-GRPO: Accelerating GRPO-Style Training through Diversity-Aware Reward Reweighting.

Leveraging Error Diversity in Group Rollouts for Reinforcement Learning MMR-GRPO: Accelerating GRPO-Style Training through Diversity-Aware Reward Reweighting

Reference 28

Resolution: verified exact; local_arxiv, observed 2026-06-30T19:05:00.401145Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 1b62b345-12eb-4937-b131-b52703c3bcec · outbound

This paper cites Unlocking Exploration in RLVR: Uncertainty-aware Advantage Shaping for Deeper Reasoning.

Leveraging Error Diversity in Group Rollouts for Reinforcement Learning Unlocking Exploration in RLVR: Uncertainty-aware Advantage Shaping for Deeper Reasoning

Reference 29

Resolution: verified exact; local_arxiv, observed 2026-06-30T19:05:00.415466Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 90f96817-8764-417f-915d-28ad14c00973 · outbound

This paper cites Grouter: Decoupling Routing from Representation for Accelerated MoE Training.

Leveraging Error Diversity in Group Rollouts for Reinforcement Learning Grouter: Decoupling Routing from Representation for Accelerated MoE Training

Reference 30

Resolution: verified exact; local_arxiv, observed 2026-06-30T19:05:00.369568Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 43f199f6-69b9-4a14-ad0a-0185143ee4d6 · outbound

This paper cites Qwen3 Technical Report.

Leveraging Error Diversity in Group Rollouts for Reinforcement Learning Qwen3 Technical Report

Reference 31

Resolution: verified exact; local_arxiv, observed 2026-06-30T19:05:00.408984Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 19724671-9237-4f97-9bd1-03974b406884 · outbound

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

Leveraging Error Diversity in Group Rollouts for Reinforcement Learning DAPO: An Open-Source LLM Reinforcement Learning System at Scale

Reference 32

Resolution: verified exact; local_arxiv, observed 2026-06-30T19:05:00.428210Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 522341bc-f461-4681-81fb-fff501ead888 · outbound

This paper cites RSPO: Risk-Seeking Policy Optimization for Pass@k and Max@k Metrics in Large Language Models.

Leveraging Error Diversity in Group Rollouts for Reinforcement Learning RSPO: Risk-Seeking Policy Optimization for Pass@k and Max@k Metrics in Large Language Models

Reference 33

Resolution: verified exact; arxiv_id, observed 2026-06-30T19:05:00.411604Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

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

This paper cites EDGE-GRPO: Entropy-Driven GRPO with Guided Error Correction for Advantage Diversity.

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 2026-08-04T06:34:03.388597+00:00.

Observation 7fb99a93-ad11-4443-8c89-252b3c0098a7 · outbound

This paper cites Reinforced Efficient Reasoning via Semantically Diverse Exploration.

Leveraging Error Diversity in Group Rollouts for Reinforcement Learning Reinforced Efficient Reasoning via Semantically Diverse Exploration

Reference 35

Resolution: verified exact; local_arxiv, observed 2026-06-30T19:05:00.390998Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Pith citing papers

Observation f3364cc3-5a39-48aa-8a57-b0a171f6c7c0 · inbound

Grouter: Decoupling Routing from Representation for Accelerated MoE Training cites this paper.

Grouter: Decoupling Routing from Representation for Accelerated MoE Training Leveraging Error Diversity in Group Rollouts for Reinforcement Learning

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-02T21:50:58.824041Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ba8ccdcc-64d8-4c07-b1a1-472c9b830409 · inbound

Right Makes Might: Aligning Verified Hidden States Empowers RL Reasoning cites this paper.

Right Makes Might: Aligning Verified Hidden States Empowers RL Reasoning Leveraging Error Diversity in Group Rollouts for Reinforcement Learning

Reference 12

Resolution: verified exact; local_arxiv, observed 2026-07-02T02:06:27.264764Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.