Paper Citation Record · LEDGER

Relax: An Asynchronous Reinforcement Learning Engine for Omni-Modal Post-Training at Scale

As of 12 August 2026, this Paper Citation Record lists 22 of 22 outbound references and 5 inbound Pith citation observations for arXiv:2604.11554.

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

pith.paper-citation-record.v1
2604.11554 v2

Coverage vector

measured 22 of 22 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-05-10T16:07:52.017037Z

measured 27 of 27 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-12T06:34:41.77262+00:00

measured 5 of 5 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-01T21:32:02.473074Z

measured 0 of 1 external citation measurements

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

Source: pith, observed 2026-07-09T03:05:55.340981Z

Reference resolution

22 of 22 outbound references displayed

verified exact16
verified fuzzy1
unresolved1
parse uncertain0
malformed identifier0
metadata mismatch4

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 1ae3668c-a270-4107-8c10-7735919be773 · outbound

This paper cites Stabilizing MoE Reinforcement Learning by Aligning Training and Inference Routers.

Relax: An Asynchronous Reinforcement Learning Engine for Omni-Modal Post-Training at Scale Stabilizing MoE Reinforcement Learning by Aligning Training and Inference Routers

Reference 1

Resolution: verified exact; arxiv_id, observed 2026-05-11T09:16:03.310604Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 714e39aa-db5f-4aef-aeb5-1c9337d642b9 · outbound

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

Relax: An Asynchronous Reinforcement Learning Engine for Omni-Modal Post-Training at Scale DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning

Reference 2

Resolution: verified exact; local_arxiv, observed 2026-05-11T09:16:03.341044Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation b274a53d-5f5f-4918-a1b5-a213f762e5d9 · outbound

This paper cites Proximal Policy Optimization Algorithms.

Relax: An Asynchronous Reinforcement Learning Engine for Omni-Modal Post-Training at Scale Proximal Policy Optimization Algorithms

Reference 3

Resolution: verified exact; local_arxiv, observed 2026-05-11T09:16:03.301588Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation db06b6f2-ac58-48de-bc7c-201a510860e9 · outbound

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

Relax: An Asynchronous Reinforcement Learning Engine for Omni-Modal Post-Training at Scale DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models

Reference 4

Resolution: verified exact; local_arxiv, observed 2026-05-11T09:16:03.321578Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 389b0b5c-4d69-4e40-ab41-6bacfd400e4b · outbound

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

Relax: An Asynchronous Reinforcement Learning Engine for Omni-Modal Post-Training at Scale DAPO: An Open-Source LLM Reinforcement Learning System at Scale

Reference 5

Resolution: verified exact; local_arxiv, observed 2026-05-11T09:16:03.332879Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 69cea288-5a44-4e2d-9c81-121c0dbd02d6 · outbound

This paper cites HybridFlow: A Flexible and Efficient RLHF Framework.

Relax: An Asynchronous Reinforcement Learning Engine for Omni-Modal Post-Training at Scale HybridFlow: A Flexible and Efficient RLHF Framework

Reference 6

Resolution: verified exact; local_arxiv, observed 2026-05-11T09:16:03.315145Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation b83aa4c6-ea2d-4b2d-ab97-d57879b95d3a · outbound

This paper cites OpenRLHF: An Easy-to-use, Scalable and High-performance RLHF Framework.

Relax: An Asynchronous Reinforcement Learning Engine for Omni-Modal Post-Training at Scale OpenRLHF: An Easy-to-use, Scalable and High-performance RLHF Framework

Reference 7

Resolution: verified exact; arxiv_id, observed 2026-05-15T03:28:57.414349Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation a80d0625-6c83-4771-ae17-5c4bf08115af · outbound

This paper cites AReaL: A Large-Scale Asynchronous Reinforcement Learning System for Language Reasoning.

Relax: An Asynchronous Reinforcement Learning Engine for Omni-Modal Post-Training at Scale AReaL: A Large-Scale Asynchronous Reinforcement Learning System for Language Reasoning

Reference 8

Resolution: verified exact; arxiv_id, observed 2026-05-15T14:24:22.137431Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation aa820f69-54c1-4543-b167-7b144dec4266 · outbound

This paper cites AsyncFlow: An Asynchronous Streaming RL Framework for Efficient LLM Post-Training.

Relax: An Asynchronous Reinforcement Learning Engine for Omni-Modal Post-Training at Scale AsyncFlow: An Asynchronous Streaming RL Framework for Efficient LLM Post-Training

Reference 9

Resolution: verified exact; arxiv_id, observed 2026-05-11T09:16:03.252155Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 3a2c3f59-b823-4fc0-9825-6df5dccc7e83 · outbound

This paper cites Reinforcement Learning Optimization for Large-Scale Learning: An Efficient and User-Friendly Scaling Library.

Relax: An Asynchronous Reinforcement Learning Engine for Omni-Modal Post-Training at Scale Reinforcement Learning Optimization for Large-Scale Learning: An Efficient and User-Friendly Scaling Library

Reference 10

Resolution: verified exact; arxiv_id, observed 2026-05-11T09:16:03.246392Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 3b3b2430-9bd8-4b90-b944-7c5de00d4679 · outbound

This paper cites type": "function.

Relax: An Asynchronous Reinforcement Learning Engine for Omni-Modal Post-Training at Scale type": "function

Reference 11

Resolution: metadata mismatch; arxiv_id, observed 2026-05-11T09:16:03.270343Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 591aac5d-eb66-468d-bf3e-096d54507a30 · outbound

This paper cites slime: An llm post-training framework for rl scaling.

Relax: An Asynchronous Reinforcement Learning Engine for Omni-Modal Post-Training at Scale slime: An llm post-training framework for rl scaling

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T16:51:59.969766Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation c5e76a10-61fa-4300-8191-63716353c914 · outbound

This paper cites Ray: A Distributed Framework for Emerging AI Applications.

Relax: An Asynchronous Reinforcement Learning Engine for Omni-Modal Post-Training at Scale Ray: A Distributed Framework for Emerging AI Applications

Reference 13

Resolution: metadata mismatch; arxiv_id, observed 2026-05-11T09:16:03.296707Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 323d3a8a-39db-4ade-95b4-8f65f6b6faac · outbound

This paper cites Deep reinforcement learning from human preferences.

Relax: An Asynchronous Reinforcement Learning Engine for Omni-Modal Post-Training at Scale Deep reinforcement learning from human preferences

Reference 14

Resolution: metadata mismatch; arxiv_id, observed 2026-05-16T08:39:30.882444Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation b387c5ab-57a5-4f31-8afe-d48cc3ad668d · outbound

This paper cites Training language models to follow instructions with human feedback.

Relax: An Asynchronous Reinforcement Learning Engine for Omni-Modal Post-Training at Scale Training language models to follow instructions with human feedback

Reference 15

Resolution: verified exact; local_arxiv, observed 2026-05-11T09:16:03.207345Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation aa881d94-6290-4ec3-84c3-a3051ebe5043 · outbound

This paper cites Towards Reasoning Era: A Survey of Long Chain-of-Thought for Reasoning Large Language Models.

Relax: An Asynchronous Reinforcement Learning Engine for Omni-Modal Post-Training at Scale Towards Reasoning Era: A Survey of Long Chain-of-Thought for Reasoning Large Language Models

Reference 16

Resolution: verified exact; arxiv_id, observed 2026-05-12T08:40:42.146675Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 8ec5f994-e0ca-49e6-95ef-2cd0bf0003bb · outbound

This paper cites Megatron-LM: Training Multi-Billion Parameter Language Models Using Model Parallelism.

Relax: An Asynchronous Reinforcement Learning Engine for Omni-Modal Post-Training at Scale Megatron-LM: Training Multi-Billion Parameter Language Models Using Model Parallelism

Reference 17

Resolution: verified exact; local_arxiv, observed 2026-05-11T09:16:03.240975Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation e29febe5-7e34-4270-a0c3-f8dbc3898095 · outbound

This paper cites SGLang: Efficient Execution of Structured Language Model Programs.

Relax: An Asynchronous Reinforcement Learning Engine for Omni-Modal Post-Training at Scale SGLang: Efficient Execution of Structured Language Model Programs

Reference 18

Resolution: metadata mismatch; arxiv_id, observed 2026-05-12T08:20:01.305558Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation b2f940ef-fad4-45de-a12e-be7f400cce3d · outbound

This paper cites PyTorch FSDP: Experiences on Scaling Fully Sharded Data Parallel.

Relax: An Asynchronous Reinforcement Learning Engine for Omni-Modal Post-Training at Scale PyTorch FSDP: Experiences on Scaling Fully Sharded Data Parallel

Reference 19

Resolution: verified exact; arxiv_id, observed 2026-05-12T04:15:20.153254Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 609eb919-2099-427a-962b-6cb59eedc62b · outbound

This paper cites Inference-time scaling for generalist reward modeling.

Relax: An Asynchronous Reinforcement Learning Engine for Omni-Modal Post-Training at Scale Inference-time scaling for generalist reward modeling

Reference 20

Resolution: verified exact; arxiv_id, observed 2026-05-11T09:16:03.235452Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 87eebf59-fac5-45cc-b15c-4399c9236ab6 · outbound

This paper cites EchoInk-R1: Exploring Audio-Visual Reasoning in Multimodal LLMs via Reinforcement Learning.

Relax: An Asynchronous Reinforcement Learning Engine for Omni-Modal Post-Training at Scale EchoInk-R1: Exploring Audio-Visual Reasoning in Multimodal LLMs via Reinforcement Learning

Reference 21

Resolution: verified exact; arxiv_id, observed 2026-05-11T09:16:03.279034Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 71c61e6f-ee4f-4fe5-a518-e46df2326e7a · outbound

This paper cites an unresolved cited work.

Relax: An Asynchronous Reinforcement Learning Engine for Omni-Modal Post-Training at Scale Unresolved cited work

Reference 22

Resolution: unresolved; raw_fallback, observed 2026-05-17T16:51:59.972786Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Pith citing papers

Observation f287ec78-98c1-4c7c-a4b5-d6bdf99027d9 · inbound

MinT: Managed Infrastructure for Training and Serving Millions of LLMs cites this paper.

MinT: Managed Infrastructure for Training and Serving Millions of LLMs Relax: An Asynchronous Reinforcement Learning Engine for Omni-Modal Post-Training at Scale

Reference 25

Resolution: verified exact; local_arxiv, observed 2026-05-14T19:27:51.877050Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 884a07e3-0ce2-459d-b434-52d7660279fd · inbound

MinT: Managed Infrastructure for Training and Serving Millions of LLMs cites this paper.

MinT: Managed Infrastructure for Training and Serving Millions of LLMs Relax: An Asynchronous Reinforcement Learning Engine for Omni-Modal Post-Training at Scale

Reference 26

Resolution: verified exact; local_arxiv, observed 2026-06-30T22:05:06.192120Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 6e2c39ff-7e1f-479a-b9c1-8b983d4ab74c · inbound

Scaling Mixture-of-Experts Video Pretraining for Embodied Intelligence cites this paper.

Scaling Mixture-of-Experts Video Pretraining for Embodied Intelligence Relax: An Asynchronous Reinforcement Learning Engine for Omni-Modal Post-Training at Scale

Reference 124

Resolution: verified exact; local_arxiv, observed 2026-07-09T03:05:55.342846Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 0e0cbcdd-cab6-4b7a-adf8-2a79aacbd96a · inbound

JoyNexus: Service-Oriented Multi-Tenant Post-Training for VLA Models cites this paper.

JoyNexus: Service-Oriented Multi-Tenant Post-Training for VLA Models Relax: An Asynchronous Reinforcement Learning Engine for Omni-Modal Post-Training at Scale

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-01T21:32:02.473074Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7b849eeb-c909-49a0-82db-ab62884f9c63 · inbound

Molt: A Scalable PyTorch-Native Training Framework for Agentic Reinforcement Learning cites this paper.

Molt: A Scalable PyTorch-Native Training Framework for Agentic Reinforcement Learning Relax: An Asynchronous Reinforcement Learning Engine for Omni-Modal Post-Training at Scale

Reference 58

Resolution: unresolved; no resolver link, observed 2026-08-01T09:49:31.413822Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.