Paper Citation Record · LEDGER

RolloutPipe: Overlapping Pipelined Rollout and Training in Disaggregated On-Policy LLM Reinforcement Learning

As of 13 August 2026, this Paper Citation Record lists 18 of 18 outbound references and 1 inbound Pith citation observation for arXiv:2606.26997.

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

pith.paper-citation-record.v1
2606.26997 v2

Coverage vector

measured 18 of 18 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-07-12T11:52:35.159984Z

measured 19 of 19 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-13T06:32:02.005865+00:00

measured 1 of 1 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-01T09:49:28.700382Z

measured 0 of 1 external citation measurements

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

Source: cited_works

Reference resolution

18 of 18 outbound references displayed

verified exact0
verified fuzzy0
unresolved18
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 5149cbf7-dd78-4fc9-8aef-3cc9b5dbac56 · outbound

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

RolloutPipe: Overlapping Pipelined Rollout and Training in Disaggregated On-Policy LLM Reinforcement Learning AReaL: A Large-Scale Asynchronous Reinforcement Learning System for Language Reasoning

Reference 1

Resolution: unresolved; no resolver link, observed 2026-07-12T11:52:35.159984Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f20a299c-9529-4315-8846-7552fe3b3b62 · outbound

This paper cites Nature645(8081), 633–638 (2025).

RolloutPipe: Overlapping Pipelined Rollout and Training in Disaggregated On-Policy LLM Reinforcement Learning Nature645(8081), 633–638 (2025)

Reference 2

Resolution: unresolved; no resolver link, observed 2026-07-12T11:52:35.159984Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c8d59ed5-d847-4c63-880f-f18e47cd6fab · outbound

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

RolloutPipe: Overlapping Pipelined Rollout and Training in Disaggregated On-Policy LLM Reinforcement Learning AsyncFlow: An Asynchronous Streaming RL Framework for Efficient LLM Post-Training

Reference 3

Resolution: unresolved; no resolver link, observed 2026-07-12T11:52:35.159984Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d879b52d-318b-498c-9431-b6378b52b818 · outbound

This paper cites In: Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers).

RolloutPipe: Overlapping Pipelined Rollout and Training in Disaggregated On-Policy LLM Reinforcement Learning In: Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

Reference 4

Resolution: unresolved; no resolver link, observed 2026-07-12T11:52:35.159984Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2a10505b-911d-43f2-ae2d-a140b072a76f · outbound

This paper cites In: Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing: System Demonstrations.

RolloutPipe: Overlapping Pipelined Rollout and Training in Disaggregated On-Policy LLM Reinforcement Learning In: Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing: System Demonstrations

Reference 5

Resolution: unresolved; no resolver link, observed 2026-07-12T11:52:35.159984Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dbd7f5f7-7f30-4f50-8c94-4c8f84da2733 · outbound

This paper cites In: Proceedings of the 8th International Conference on Cognitive Computing.

RolloutPipe: Overlapping Pipelined Rollout and Training in Disaggregated On-Policy LLM Reinforcement Learning In: Proceedings of the 8th International Conference on Cognitive Computing

Reference 6

Resolution: unresolved; no resolver link, observed 2026-07-12T11:52:35.159984Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 317c6543-8b85-46ce-9683-45a91e1b69a2 · outbound

This paper cites In: Proceedings of the 9th International Conference on Cognitive Computing.

RolloutPipe: Overlapping Pipelined Rollout and Training in Disaggregated On-Policy LLM Reinforcement Learning In: Proceedings of the 9th International Conference on Cognitive Computing

Reference 7

Resolution: unresolved; no resolver link, observed 2026-07-12T11:52:35.159984Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a9c49bd3-2cb0-47ed-8709-5475382f5952 · outbound

This paper cites In: Proceedings of the 13th USENIX Symposium on Operating Systems Design and Implementation.

RolloutPipe: Overlapping Pipelined Rollout and Training in Disaggregated On-Policy LLM Reinforcement Learning In: Proceedings of the 13th USENIX Symposium on Operating Systems Design and Implementation

Reference 8

Resolution: unresolved; no resolver link, observed 2026-07-12T11:52:35.159984Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e7d5bbb7-071f-406f-8633-205d7cb1bea8 · outbound

This paper cites In: Proceedings of the InternationalConferenceforHighPerformanceComputing,Networking,StorageandAnalysis.

RolloutPipe: Overlapping Pipelined Rollout and Training in Disaggregated On-Policy LLM Reinforcement Learning In: Proceedings of the InternationalConferenceforHighPerformanceComputing,Networking,StorageandAnalysis

Reference 9

Resolution: unresolved; no resolver link, observed 2026-07-12T11:52:35.159984Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8210c385-9885-4d74-aa7c-a64ad2c01ab8 · outbound

This paper cites In: Advances in Neural Information Processing Systems.

RolloutPipe: Overlapping Pipelined Rollout and Training in Disaggregated On-Policy LLM Reinforcement Learning In: Advances in Neural Information Processing Systems

Reference 10

Resolution: unresolved; no resolver link, observed 2026-07-12T11:52:35.159984Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation becf97e3-52ba-42c8-a7f2-475418e78904 · outbound

This paper cites In: Proceedings of the Twentieth European Conference on Computer Systems.

RolloutPipe: Overlapping Pipelined Rollout and Training in Disaggregated On-Policy LLM Reinforcement Learning In: Proceedings of the Twentieth European Conference on Computer Systems

Reference 11

Resolution: unresolved; no resolver link, observed 2026-07-12T11:52:35.159984Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a02d4598-cc45-4561-856a-0f3c056ffb25 · outbound

This paper cites In: Proceedings of the 41st International Conference on Machine Learning.

RolloutPipe: Overlapping Pipelined Rollout and Training in Disaggregated On-Policy LLM Reinforcement Learning In: Proceedings of the 41st International Conference on Machine Learning

Reference 12

Resolution: unresolved; no resolver link, observed 2026-07-12T11:52:35.159984Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a0521a09-d440-426d-a722-4022c2cebdb6 · outbound

This paper cites an unresolved cited work.

RolloutPipe: Overlapping Pipelined Rollout and Training in Disaggregated On-Policy LLM Reinforcement Learning Unresolved cited work

Reference 13

Resolution: unresolved; no resolver link, observed 2026-07-12T11:52:35.159984Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fd864d3e-a2e7-4090-9387-a2ef3c8a4995 · outbound

This paper cites In: Proceedings of the 9th International Conference on Cognitive Computing.

RolloutPipe: Overlapping Pipelined Rollout and Training in Disaggregated On-Policy LLM Reinforcement Learning In: Proceedings of the 9th International Conference on Cognitive Computing

Reference 14

Resolution: unresolved; no resolver link, observed 2026-07-12T11:52:35.159984Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 95b975a3-86b4-443c-a811-9a560b0a5a5c · outbound

This paper cites In: Advances in Neural Information Processing Systems.

RolloutPipe: Overlapping Pipelined Rollout and Training in Disaggregated On-Policy LLM Reinforcement Learning In: Advances in Neural Information Processing Systems

Reference 15

Resolution: unresolved; no resolver link, observed 2026-07-12T11:52:35.159984Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1443aa22-f744-4d4d-ad1a-0b7b948733cb · outbound

This paper cites In: Findings of the Association for Computational Linguistics: North American Chapter of the Association for Computational Linguistics 2024.

RolloutPipe: Overlapping Pipelined Rollout and Training in Disaggregated On-Policy LLM Reinforcement Learning In: Findings of the Association for Computational Linguistics: North American Chapter of the Association for Computational Linguistics 2024

Reference 16

Resolution: unresolved; no resolver link, observed 2026-07-12T11:52:35.159984Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f2ab2b5b-2519-4fdc-8a89-130a64005db0 · outbound

This paper cites In: Proceedings 16 R.

RolloutPipe: Overlapping Pipelined Rollout and Training in Disaggregated On-Policy LLM Reinforcement Learning In: Proceedings 16 R

Reference 17

Resolution: unresolved; no resolver link, observed 2026-07-12T11:52:35.159984Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation acca909e-eb1f-41d0-b378-9dc8aa59e860 · outbound

This paper cites GitHub repository (2025),.

RolloutPipe: Overlapping Pipelined Rollout and Training in Disaggregated On-Policy LLM Reinforcement Learning GitHub repository (2025),

Reference 18

Resolution: unresolved; no resolver link, observed 2026-07-12T11:52:35.159984Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation 7164737e-8b03-4d42-8053-986528121718 · 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 RolloutPipe: Overlapping Pipelined Rollout and Training in Disaggregated On-Policy LLM Reinforcement Learning

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-01T09:49:28.700382Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.