Paper Citation Record · LEDGER

Kalman Filter Enhanced GRPO for Reinforcement Learning-Based Language Model Reasoning

As of 10 August 2026, this Paper Citation Record lists 32 of 32 outbound references and 4 inbound Pith citation observations for arXiv:2505.07527.

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

pith.paper-citation-record.v1
2505.07527 v5

Coverage vector

measured 32 of 32 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-05-22T15:49:44.263123Z

measured 36 of 36 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-10T06:31:04.303077+00:00

measured 4 of 4 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-06-30T10:07:39.554999Z

measured 0 of 1 external citation measurements

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

Source: pith, observed 2026-06-30T12:44:40.165250Z

Reference resolution

32 of 32 outbound references displayed

verified exact15
verified fuzzy16
unresolved0
parse uncertain0
malformed identifier1
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 25961d7c-7140-45db-844c-b65f30441bcb · outbound

This paper cites GPT-4 Technical Report.

Kalman Filter Enhanced GRPO for Reinforcement Learning-Based Language Model Reasoning GPT-4 Technical Report

Reference 1

Resolution: verified exact; local_arxiv, observed 2026-05-22T15:51:45.675038Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 3bbc3474-3d89-46b1-81b0-83b7fa8e909d · outbound

This paper cites Self-Play Fine-Tuning Converts Weak Language Models to Strong Language Models.

Kalman Filter Enhanced GRPO for Reinforcement Learning-Based Language Model Reasoning Self-Play Fine-Tuning Converts Weak Language Models to Strong Language Models

Reference 2

Resolution: verified exact; local_arxiv, observed 2026-05-22T15:51:45.628910Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 5c392379-317a-4249-853b-1267ffc0f834 · outbound

This paper cites Deep reinforcement learning from human preferences.Advances in neural information processing systems, 30.

Kalman Filter Enhanced GRPO for Reinforcement Learning-Based Language Model Reasoning Deep reinforcement learning from human preferences.Advances in neural information processing systems, 30

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-05-22T15:51:46.207809Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation ed0f3391-e43e-45a7-8914-0450d9384e14 · outbound

This paper cites KTO: Model Alignment as Prospect Theoretic Optimization.

Kalman Filter Enhanced GRPO for Reinforcement Learning-Based Language Model Reasoning KTO: Model Alignment as Prospect Theoretic Optimization

Reference 4

Resolution: verified exact; local_arxiv, observed 2026-05-22T15:51:45.705241Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation ab189571-d92c-4e31-a563-b8f435f50c8e · outbound

This paper cites Addressing function approximation error in actor-critic methods.

Kalman Filter Enhanced GRPO for Reinforcement Learning-Based Language Model Reasoning Addressing function approximation error in actor-critic methods

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-05-22T15:51:46.223065Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation b7bcddd2-4d4b-4d9e-9b28-5725af001341 · outbound

This paper cites Reinforced Self-Training (ReST) for Language Modeling.

Kalman Filter Enhanced GRPO for Reinforcement Learning-Based Language Model Reasoning Reinforced Self-Training (ReST) for Language Modeling

Reference 6

Resolution: verified exact; local_arxiv, observed 2026-05-22T15:51:45.634446Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 5421bf75-b042-4d23-904e-9e889de9bd6d · outbound

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

Kalman Filter Enhanced GRPO for Reinforcement Learning-Based Language Model Reasoning DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning

Reference 7

Resolution: verified exact; local_arxiv, observed 2026-05-22T15:51:45.690186Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation b9a4d2fc-82d9-45f8-b5ea-511557d7374a · outbound

This paper cites Soft Actor-Critic Algorithms and Applications.

Kalman Filter Enhanced GRPO for Reinforcement Learning-Based Language Model Reasoning Soft Actor-Critic Algorithms and Applications

Reference 8

Resolution: verified exact; local_arxiv, observed 2026-05-22T15:51:45.699715Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T21:38:16.985704+00:00.

Observation 6d86d9e5-fff9-4d18-960b-482f72409ad1 · outbound

This paper cites Rlaif: Scaling reinforcement learning from human feedback with ai feedback.

Kalman Filter Enhanced GRPO for Reinforcement Learning-Based Language Model Reasoning Rlaif: Scaling reinforcement learning from human feedback with ai feedback

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-05-22T15:51:46.255448Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 9a230ab0-e798-42e9-805b-69b896b14f7b · outbound

This paper cites Let's Verify Step by Step.

Kalman Filter Enhanced GRPO for Reinforcement Learning-Based Language Model Reasoning Let's Verify Step by Step

Reference 10

Resolution: verified exact; local_arxiv, observed 2026-05-22T15:51:45.695064Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation d2aa0290-cb5c-4d89-a61d-df36ce13886e · outbound

This paper cites Continuous control with deep reinforcement learning.

Kalman Filter Enhanced GRPO for Reinforcement Learning-Based Language Model Reasoning Continuous control with deep reinforcement learning

Reference 11

Resolution: verified exact; local_arxiv, observed 2026-05-22T15:51:45.648565Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation aae992a3-4e35-49dd-aeec-e15126a143ae · outbound

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

Kalman Filter Enhanced GRPO for Reinforcement Learning-Based Language Model Reasoning Understanding R1-Zero-Like Training: A Critical Perspective

Reference 12

Resolution: verified exact; local_arxiv, observed 2026-05-22T15:51:45.670408Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation f098e854-5555-4e31-88ba-005aabf4d6a1 · outbound

This paper cites Asynchronous methods for deep reinforce- ment learning.

Kalman Filter Enhanced GRPO for Reinforcement Learning-Based Language Model Reasoning Asynchronous methods for deep reinforce- ment learning

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-05-22T15:51:46.243639Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 741670e6-7972-4a48-bedd-1e53fa95df16 · outbound

This paper cites Playing Atari with Deep Reinforcement Learning.

Kalman Filter Enhanced GRPO for Reinforcement Learning-Based Language Model Reasoning Playing Atari with Deep Reinforcement Learning

Reference 14

Resolution: verified exact; local_arxiv, observed 2026-05-22T15:51:45.679941Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 92ac8461-ff0a-4f85-b3c7-8770b39c976e · outbound

This paper cites Tiny-grpo math tasks dataset.

Kalman Filter Enhanced GRPO for Reinforcement Learning-Based Language Model Reasoning Tiny-grpo math tasks dataset

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-05-22T15:51:46.269712Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation ceaee7c1-da07-431c-ae74-1abfe8fef9fb · outbound

This paper cites Training language models to follow instructions with human feedback.Advances in neural information processing systems, 35:27730–27744.

Kalman Filter Enhanced GRPO for Reinforcement Learning-Based Language Model Reasoning Training language models to follow instructions with human feedback.Advances in neural information processing systems, 35:27730–27744

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-05-22T15:51:46.234274Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 6c6d88f8-2e9f-492e-840c-505b8c086ef6 · outbound

This paper cites Direct preference optimization: Your language model is secretly a reward model.

Kalman Filter Enhanced GRPO for Reinforcement Learning-Based Language Model Reasoning Direct preference optimization: Your language model is secretly a reward model

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-05-22T15:51:46.239415Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 9b90aaba-af82-4e8a-91b9-25e702432640 · outbound

This paper cites Trust region policy optimization.

Kalman Filter Enhanced GRPO for Reinforcement Learning-Based Language Model Reasoning Trust region policy optimization

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-05-22T15:51:46.247515Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 3a4c5fa6-4170-486d-839f-aa3baebb32a9 · outbound

This paper cites Proximal Policy Optimization Algorithms.

Kalman Filter Enhanced GRPO for Reinforcement Learning-Based Language Model Reasoning Proximal Policy Optimization Algorithms

Reference 19

Resolution: verified exact; local_arxiv, observed 2026-05-22T15:51:45.665672Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 098193a6-8410-4310-a8a4-e65b507792d0 · outbound

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

Kalman Filter Enhanced GRPO for Reinforcement Learning-Based Language Model Reasoning DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models

Reference 20

Resolution: verified exact; local_arxiv, observed 2026-05-22T15:51:45.659957Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 16cf6ee6-9cb2-46a2-990c-9b69aa0e85bb · outbound

This paper cites Policy gradient meth- ods for reinforcement learning with function approximation.Advances in neural information processing systems, 12.

Kalman Filter Enhanced GRPO for Reinforcement Learning-Based Language Model Reasoning Policy gradient meth- ods for reinforcement learning with function approximation.Advances in neural information processing systems, 12

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-05-22T15:51:46.215922Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation b21c3ea2-5585-4556-b2ca-62fa64fd7165 · outbound

This paper cites Mujoco: A physics engine for model-based control.

Kalman Filter Enhanced GRPO for Reinforcement Learning-Based Language Model Reasoning Mujoco: A physics engine for model-based control

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-05-22T15:51:46.211852Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation f2e1eab8-a5dc-448a-9fcc-ecfb27978475 · outbound

This paper cites OpenMathInstruct-1: A 1.8 Million Math Instruction Tuning Dataset.

Kalman Filter Enhanced GRPO for Reinforcement Learning-Based Language Model Reasoning OpenMathInstruct-1: A 1.8 Million Math Instruction Tuning Dataset

Reference 23

Resolution: verified exact; arxiv_id, observed 2026-05-22T15:51:45.642038Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 3a1261fc-ebbc-4e11-8e24-588501fc336d · outbound

This paper cites LLaMA: Open and Efficient Foundation Language Models.

Kalman Filter Enhanced GRPO for Reinforcement Learning-Based Language Model Reasoning LLaMA: Open and Efficient Foundation Language Models

Reference 24

Resolution: verified exact; local_arxiv, observed 2026-05-22T15:51:45.654922Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 3e6a0e3e-d178-4ce9-a48c-e126da7efb4c · outbound

This paper cites Deep reinforcement learning with double q-learning.

Kalman Filter Enhanced GRPO for Reinforcement Learning-Based Language Model Reasoning Deep reinforcement learning with double q-learning

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-05-22T15:51:46.262551Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 4a369a7f-6f62-4214-ad9c-d5e80188561f · outbound

This paper cites Aime problem set: 1983–2024.

Kalman Filter Enhanced GRPO for Reinforcement Learning-Based Language Model Reasoning Aime problem set: 1983–2024

Reference 26

Resolution: verified fuzzy; raw_fallback, observed 2026-05-22T15:51:46.230411Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 3a51b174-adb8-430c-9b7c-fc2801e4f4fe · outbound

This paper cites Multi-intersection traffic optimisation: A benchmark dataset and a strong baseline.IEEE Open Journal of Intelligent Transportation Systems, 3:126–136.

Kalman Filter Enhanced GRPO for Reinforcement Learning-Based Language Model Reasoning Multi-intersection traffic optimisation: A benchmark dataset and a strong baseline.IEEE Open Journal of Intelligent Transportation Systems, 3:126–136

Reference 27

Resolution: verified fuzzy; raw_fallback, observed 2026-05-22T15:51:46.226713Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation c5100b9e-2bab-498c-ab30-b5f518f8c777 · outbound

This paper cites Soft expert reward learning for vision-and-language navigation.

Kalman Filter Enhanced GRPO for Reinforcement Learning-Based Language Model Reasoning Soft expert reward learning for vision-and-language navigation

Reference 28

Resolution: verified fuzzy; raw_fallback, observed 2026-05-22T15:51:46.266182Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation ddf5a0f0-c074-401e-b154-fe352a500b3e · outbound

This paper cites Dueling network architectures for deep reinforcement learning.

Kalman Filter Enhanced GRPO for Reinforcement Learning-Based Language Model Reasoning Dueling network architectures for deep reinforcement learning

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-05-22T15:51:46.251172Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation c7cb80a5-9253-417f-a78f-1b3c45744716 · outbound

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

Kalman Filter Enhanced GRPO for Reinforcement Learning-Based Language Model Reasoning DAPO: An Open-Source LLM Reinforcement Learning System at Scale

Reference 30

Resolution: verified exact; local_arxiv, observed 2026-05-22T15:51:45.685027Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation b2df3508-e3b9-4a0e-ba58-aab5762e3347 · outbound

This paper cites fixed value.

Kalman Filter Enhanced GRPO for Reinforcement Learning-Based Language Model Reasoning fixed value

Reference 31

Resolution: malformed identifier; raw_fallback, observed 2026-05-22T15:51:46.219463Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 1cf9a237-883a-4fc7-abb5-459b8cad96c9 · outbound

This paper cites type": “Algebra.

Kalman Filter Enhanced GRPO for Reinforcement Learning-Based Language Model Reasoning type": “Algebra

Reference 32

Resolution: verified fuzzy; raw_fallback, observed 2026-05-22T15:51:46.258983Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Pith citing papers

Observation 8c11dbf0-e383-4487-848a-3fc79f54b69c · inbound

K-Score: Kalman Filter as a Principled Alternative to Reward Normalization in Reinforcement Learning cites this paper.

K-Score: Kalman Filter as a Principled Alternative to Reward Normalization in Reinforcement Learning Kalman Filter Enhanced GRPO for Reinforcement Learning-Based Language Model Reasoning

Reference 6

Resolution: verified exact; local_arxiv, observed 2026-05-11T19:21:09.801008Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation c9146da6-0b66-425c-93b1-55f60eab6a53 · inbound

Kernelized Advantage Estimation: From Nonparametric Statistics to LLM Reasoning cites this paper.

Kernelized Advantage Estimation: From Nonparametric Statistics to LLM Reasoning Kalman Filter Enhanced GRPO for Reinforcement Learning-Based Language Model Reasoning

Reference 23

Resolution: verified exact; local_arxiv, observed 2026-05-12T10:16:27.330837Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation bc0b0d50-775a-4cc3-95d7-dfcc27783808 · inbound

Kernelized Advantage Estimation: From Nonparametric Statistics to LLM Reasoning cites this paper.

Kernelized Advantage Estimation: From Nonparametric Statistics to LLM Reasoning Kalman Filter Enhanced GRPO for Reinforcement Learning-Based Language Model Reasoning

Reference 23

Resolution: verified exact; local_arxiv, observed 2026-05-20T23:49:14.938994Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 80214a48-80f4-4075-b238-ddc558fa6ac7 · inbound

BV-Blend: Uncertainty-Weighted Historical Baselines for Stable Critic-Free RL with Verifiable Rewards cites this paper.

BV-Blend: Uncertainty-Weighted Historical Baselines for Stable Critic-Free RL with Verifiable Rewards Kalman Filter Enhanced GRPO for Reinforcement Learning-Based Language Model Reasoning

Reference 127

Resolution: metadata mismatch; local_arxiv, observed 2026-06-30T12:44:40.166695Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.