Paper Citation Record · LEDGER

Alleviating Sparse Rewards by Modeling Step-Wise and Long-Term Sampling Effects in Flow-Based GRPO

As of 17 August 2026, this Paper Citation Record lists 20 of 20 outbound references and 1 inbound Pith citation observation for arXiv:2602.06422.

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

pith.paper-citation-record.v1
2602.06422 v2

Coverage vector

measured 20 of 20 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-03T03:58:50.730090Z

measured 21 of 21 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-17T06:30:58.91139+00:00

measured 1 of 1 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-06-30T20:38:28.328436Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-07-01T14:35:47.308416Z

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 cd4823fd-3f9a-4bc0-8804-05f6c0a19a57 · outbound

This paper cites Training Diffusion Models with Reinforcement Learning.

Alleviating Sparse Rewards by Modeling Step-Wise and Long-Term Sampling Effects in Flow-Based GRPO Training Diffusion Models with Reinforcement Learning

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-03T03:58:48.478031Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 97819a72-f58a-435f-a44d-2f374c6a8b0a · outbound

This paper cites an unresolved cited work.

Alleviating Sparse Rewards by Modeling Step-Wise and Long-Term Sampling Effects in Flow-Based GRPO Unresolved cited work

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-03T03:58:50.730090Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2e78b1ca-bb65-4826-9c13-564fee38b66d · outbound

This paper cites Seedream 2.0: A Native Chinese-English Bilingual Image Generation Foundation Model.

Alleviating Sparse Rewards by Modeling Step-Wise and Long-Term Sampling Effects in Flow-Based GRPO Seedream 2.0: A Native Chinese-English Bilingual Image Generation Foundation Model

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-03T03:58:48.835551Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 90896383-cba7-480c-8ca7-4346902e1dca · outbound

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

Alleviating Sparse Rewards by Modeling Step-Wise and Long-Term Sampling Effects in Flow-Based GRPO DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-03T03:58:48.943935Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f2b5f785-2e51-4051-a603-adbd2bd6ba1d · outbound

This paper cites TempFlow-GRPO: When Timing Matters for GRPO in Flow Models.

Alleviating Sparse Rewards by Modeling Step-Wise and Long-Term Sampling Effects in Flow-Based GRPO TempFlow-GRPO: When Timing Matters for GRPO in Flow Models

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-03T03:58:49.067234Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5be4e67f-1567-4acd-9a94-175afaf311c8 · outbound

This paper cites an unresolved cited work.

Alleviating Sparse Rewards by Modeling Step-Wise and Long-Term Sampling Effects in Flow-Based GRPO Unresolved cited work

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-03T03:58:50.688606Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cde24e99-d1f6-4383-bea0-86b457ff8e3d · outbound

This paper cites MixGRPO: Unlocking Flow-based GRPO Efficiency with Mixed ODE-SDE.

Alleviating Sparse Rewards by Modeling Step-Wise and Long-Term Sampling Effects in Flow-Based GRPO MixGRPO: Unlocking Flow-based GRPO Efficiency with Mixed ODE-SDE

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-03T03:58:49.354792Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d3bd812a-b04d-4bc6-ae04-74353ab868a8 · outbound

This paper cites Flow Matching for Generative Modeling.

Alleviating Sparse Rewards by Modeling Step-Wise and Long-Term Sampling Effects in Flow-Based GRPO Flow Matching for Generative Modeling

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-03T03:58:49.455396Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d961a994-2c86-4e5e-9bca-f7390645d529 · outbound

This paper cites Flow-GRPO: Training Flow Matching Models via Online RL.

Alleviating Sparse Rewards by Modeling Step-Wise and Long-Term Sampling Effects in Flow-Based GRPO Flow-GRPO: Training Flow Matching Models via Online RL

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-03T03:58:49.630032Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6e4b85ed-65c1-4eec-8794-4dff5e214a8d · outbound

This paper cites Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flow.

Alleviating Sparse Rewards by Modeling Step-Wise and Long-Term Sampling Effects in Flow-Based GRPO Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flow

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-03T03:58:49.747831Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 639bd713-4120-44cb-adc5-b7d95bd6d50b · outbound

This paper cites Grpo-guard: Mitigating implicit over-optimization in flow matching via regulated clipping.arXiv preprint arXiv:2510.22319, 2025a.

Alleviating Sparse Rewards by Modeling Step-Wise and Long-Term Sampling Effects in Flow-Based GRPO Grpo-guard: Mitigating implicit over-optimization in flow matching via regulated clipping.arXiv preprint arXiv:2510.22319, 2025a

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-03T03:58:50.127534Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a50eaa08-f5fb-4fdf-bef9-62c3a9ba542a · outbound

This paper cites DanceGRPO: Unleashing GRPO on Visual Generation.

Alleviating Sparse Rewards by Modeling Step-Wise and Long-Term Sampling Effects in Flow-Based GRPO DanceGRPO: Unleashing GRPO on Visual Generation

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-03T03:58:50.281427Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 33790b14-018f-4f69-ada6-8934bee8ee34 · outbound

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

Alleviating Sparse Rewards by Modeling Step-Wise and Long-Term Sampling Effects in Flow-Based GRPO DAPO: An Open-Source LLM Reinforcement Learning System at Scale

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-03T03:58:50.427811Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9f97412d-913d-4f1d-a1f2-cb5ea11b10c7 · outbound

This paper cites Group Sequence Policy Optimization.

Alleviating Sparse Rewards by Modeling Step-Wise and Long-Term Sampling Effects in Flow-Based GRPO Group Sequence Policy Optimization

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-03T03:58:50.564346Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5fe96f48-1dd4-4a36-9acf-bbd97a657803 · outbound

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

Alleviating Sparse Rewards by Modeling Step-Wise and Long-Term Sampling Effects in Flow-Based GRPO DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models

Reference 2017

Resolution: unresolved; no resolver link, observed 2026-08-03T03:58:50.055891Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cdac7abf-3952-4199-803f-d6e647d6d7c0 · outbound

This paper cites Proximal Policy Optimization Algorithms.

Alleviating Sparse Rewards by Modeling Step-Wise and Long-Term Sampling Effects in Flow-Based GRPO Proximal Policy Optimization Algorithms

Reference 2021

Resolution: unresolved; no resolver link, observed 2026-08-03T03:58:49.865910Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9b7e307a-80b3-4b1a-b673-c4319ec040da · outbound

This paper cites OpenAI o1 System Card.

Alleviating Sparse Rewards by Modeling Step-Wise and Long-Term Sampling Effects in Flow-Based GRPO OpenAI o1 System Card

Reference 2022

Resolution: unresolved; no resolver link, observed 2026-08-03T03:58:49.120237Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c77a963d-838a-47de-9571-b24da31e2d72 · outbound

This paper cites PaddleOCR 3.0 Technical Report.

Alleviating Sparse Rewards by Modeling Step-Wise and Long-Term Sampling Effects in Flow-Based GRPO PaddleOCR 3.0 Technical Report

Reference 2023

Resolution: unresolved; no resolver link, observed 2026-08-03T03:58:48.541300Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 777f14c1-41b3-445c-ac38-471d792bea4d · outbound

This paper cites Guiding a Diffusion Model with a Bad Version of Itself.

Alleviating Sparse Rewards by Modeling Step-Wise and Long-Term Sampling Effects in Flow-Based GRPO Guiding a Diffusion Model with a Bad Version of Itself

Reference 2024

Resolution: unresolved; no resolver link, observed 2026-08-03T03:58:49.195604Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 89b3d90f-74de-4370-8b2b-36f1f8542440 · outbound

This paper cites Densegrpo: From sparse to dense re- ward for flow matching model alignment.arXiv preprint arXiv:2601.20218,.

Alleviating Sparse Rewards by Modeling Step-Wise and Long-Term Sampling Effects in Flow-Based GRPO Densegrpo: From sparse to dense re- ward for flow matching model alignment.arXiv preprint arXiv:2601.20218,

Reference 2025

Resolution: unresolved; no resolver link, observed 2026-08-03T03:58:48.719811Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation 72c1ca81-5a6e-46b9-912c-239b718f6730 · inbound

RAVEN: Real-time Autoregressive Video Extrapolation with Consistency-model GRPO cites this paper.

RAVEN: Real-time Autoregressive Video Extrapolation with Consistency-model GRPO Alleviating Sparse Rewards by Modeling Step-Wise and Long-Term Sampling Effects in Flow-Based GRPO

Reference 93

Resolution: verified exact; arxiv_id, observed 2026-07-07T03:18:12.085101Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.