Paper Citation Record · LEDGER

BubbleSpec: Turning Long-Tail Bubbles into Speculative Rollout Drafts for Synchronous Reinforcement Learning

As of 6 August 2026, this Paper Citation Record lists 27 of 27 outbound references and 0 inbound Pith citation observations for arXiv:2605.08862.

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

pith.paper-citation-record.v1
2605.08862 v1

Coverage vector

measured 27 of 27 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-05-12T01:23:13.071107Z

measured 27 of 27 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-05T06:32:48.257954+00:00

measured 0 of 0 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links

measured 0 of 1 external citation measurements

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

Source: cited_works

Reference resolution

27 of 27 outbound references displayed

verified exact20
verified fuzzy3
unresolved1
parse uncertain0
malformed identifier0
metadata mismatch3

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation e05570b8-bc9a-4e10-a03d-c3e6e8b59ed5 · outbound

This paper cites Polaris: A post- training recipe for scaling reinforcement learning on ad- vanced reasoning models, 2025.URL https://hkunlp.

BubbleSpec: Turning Long-Tail Bubbles into Speculative Rollout Drafts for Synchronous Reinforcement Learning Polaris: A post- training recipe for scaling reinforcement learning on ad- vanced reasoning models, 2025.URL https://hkunlp

Reference 1

Resolution: verified fuzzy; raw_fallback, observed 2026-05-14T07:24:49.626886Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 5100b6ed-3547-4220-9fd4-f64ec2cdb5be · outbound

This paper cites Hydra: Sequentially-Dependent Draft Heads for Medusa Decoding.

BubbleSpec: Turning Long-Tail Bubbles into Speculative Rollout Drafts for Synchronous Reinforcement Learning Hydra: Sequentially-Dependent Draft Heads for Medusa Decoding

Reference 2

Resolution: verified exact; arxiv_id, observed 2026-05-12T08:01:30.715459Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 47ed2012-08f6-4c70-8cce-43db2b63052c · outbound

This paper cites Qwen2.5-VL Technical Report.

BubbleSpec: Turning Long-Tail Bubbles into Speculative Rollout Drafts for Synchronous Reinforcement Learning Qwen2.5-VL Technical Report

Reference 3

Resolution: verified exact; local_arxiv, observed 2026-05-12T08:01:30.903338Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation fe2067c4-2c78-4ae1-81d8-15965985ecca · outbound

This paper cites Medusa: Simple LLM Inference Acceleration Framework with Multiple Decoding Heads.

BubbleSpec: Turning Long-Tail Bubbles into Speculative Rollout Drafts for Synchronous Reinforcement Learning Medusa: Simple LLM Inference Acceleration Framework with Multiple Decoding Heads

Reference 4

Resolution: metadata mismatch; arxiv_id, observed 2026-05-13T10:36:18.892007Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 8d917e05-0452-4a23-8e23-8177d57a79de · outbound

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

BubbleSpec: Turning Long-Tail Bubbles into Speculative Rollout Drafts for Synchronous Reinforcement Learning AReaL: A Large-Scale Asynchronous Reinforcement Learning System for Language Reasoning

Reference 5

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 2026-08-05T06:32:48.257954+00:00.

Observation 32b95ca7-e9dc-4256-933a-b5ab4e5aecab · outbound

This paper cites Soft Adaptive Policy Optimization.

BubbleSpec: Turning Long-Tail Bubbles into Speculative Rollout Drafts for Synchronous Reinforcement Learning Soft Adaptive Policy Optimization

Reference 6

Resolution: verified exact; arxiv_id, observed 2026-05-15T07:14:32.897338Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation ea386b91-1233-496f-a36f-0bf3911ab6ef · outbound

This paper cites History Rhymes: Accelerating LLM Reinforcement Learning with RhymeRL.

BubbleSpec: Turning Long-Tail Bubbles into Speculative Rollout Drafts for Synchronous Reinforcement Learning History Rhymes: Accelerating LLM Reinforcement Learning with RhymeRL

Reference 7

Resolution: verified exact; arxiv_id, observed 2026-05-12T08:01:30.843384Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation f1b05fe5-3698-47e2-8fc0-1362b22e2cac · outbound

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

BubbleSpec: Turning Long-Tail Bubbles into Speculative Rollout Drafts for Synchronous Reinforcement Learning OpenRLHF: An Easy-to-use, Scalable and High-performance RLHF Framework

Reference 8

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 2026-08-05T06:32:48.257954+00:00.

Observation af40d67d-8f32-42b6-8d77-c2325c8385e9 · outbound

This paper cites Taming the long-tail: Efficient reasoning rl training with adaptive drafter.arXiv preprint arXiv:2511.16665.

BubbleSpec: Turning Long-Tail Bubbles into Speculative Rollout Drafts for Synchronous Reinforcement Learning Taming the long-tail: Efficient reasoning rl training with adaptive drafter.arXiv preprint arXiv:2511.16665

Reference 9

Resolution: verified exact; arxiv_id, observed 2026-05-12T08:01:30.894242Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 6a00875e-4e0d-479b-a8a8-3abf1ebd103a · outbound

This paper cites OpenAI o1 System Card.

BubbleSpec: Turning Long-Tail Bubbles into Speculative Rollout Drafts for Synchronous Reinforcement Learning OpenAI o1 System Card

Reference 10

Resolution: verified exact; local_arxiv, observed 2026-05-12T08:01:30.787686Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 3f2f4a67-2f64-4c34-8b46-44c4e5e3ebbb · outbound

This paper cites Understanding the Effects of RLHF on LLM Generalisation and Diversity.

BubbleSpec: Turning Long-Tail Bubbles into Speculative Rollout Drafts for Synchronous Reinforcement Learning Understanding the Effects of RLHF on LLM Generalisation and Diversity

Reference 11

Resolution: verified exact; arxiv_id, observed 2026-05-19T02:34:44.407176Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 914c09ce-b2cc-4343-875f-9fa281a1dc1e · outbound

This paper cites EAGLE: Speculative Sampling Requires Rethinking Feature Uncertainty.

BubbleSpec: Turning Long-Tail Bubbles into Speculative Rollout Drafts for Synchronous Reinforcement Learning EAGLE: Speculative Sampling Requires Rethinking Feature Uncertainty

Reference 12

Resolution: verified exact; arxiv_id, observed 2026-05-15T00:15:49.524886Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 0d7ffdfa-24d6-45e9-ac6b-83cbffc4dd0f · outbound

This paper cites EAGLE-3: Scaling up Inference Acceleration of Large Language Models via Training-Time Test.

BubbleSpec: Turning Long-Tail Bubbles into Speculative Rollout Drafts for Synchronous Reinforcement Learning EAGLE-3: Scaling up Inference Acceleration of Large Language Models via Training-Time Test

Reference 13

Resolution: verified exact; arxiv_id, observed 2026-05-15T18:52:19.804345Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 38067cc4-94fc-4f5a-a2ee-f5eda571a40a · outbound

This paper cites Spec-rl: Accelerating on-policy reinforcement learning with speculative rollouts.arXiv preprint arXiv:2509.23232, 2025a.

BubbleSpec: Turning Long-Tail Bubbles into Speculative Rollout Drafts for Synchronous Reinforcement Learning Spec-rl: Accelerating on-policy reinforcement learning with speculative rollouts.arXiv preprint arXiv:2509.23232, 2025a

Reference 14

Resolution: verified exact; arxiv_id, observed 2026-05-12T08:01:30.959383Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation ec2eace2-6a9f-4f50-bb0c-25f4a22b274b · outbound

This paper cites Faithful chain- of-thought reasoning.

BubbleSpec: Turning Long-Tail Bubbles into Speculative Rollout Drafts for Synchronous Reinforcement Learning Faithful chain- of-thought reasoning

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-05-14T07:24:49.631190Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation ed7516dc-0572-481a-b551-4871e40c5470 · outbound

This paper cites Defeating the training-inference mismatch via fp16.

BubbleSpec: Turning Long-Tail Bubbles into Speculative Rollout Drafts for Synchronous Reinforcement Learning Defeating the training-inference mismatch via fp16

Reference 16

Resolution: verified exact; arxiv_id, observed 2026-05-12T08:01:30.993342Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 5ba84f2b-f5dc-457e-aafc-24365278e0ca · outbound

This paper cites Proximal Policy Optimization Algorithms.

BubbleSpec: Turning Long-Tail Bubbles into Speculative Rollout Drafts for Synchronous Reinforcement Learning Proximal Policy Optimization Algorithms

Reference 17

Resolution: metadata mismatch; local_arxiv, observed 2026-05-12T08:01:30.924069Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 9c561d49-c98d-4e75-9a09-5e0ab25d70db · outbound

This paper cites Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameters.

BubbleSpec: Turning Long-Tail Bubbles into Speculative Rollout Drafts for Synchronous Reinforcement Learning Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameters

Reference 18

Resolution: verified exact; local_arxiv, observed 2026-05-12T08:01:30.936203Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 711743ff-97a3-423d-aea1-7aa6529bb2a3 · outbound

This paper cites Kimi k1.5: Scaling Reinforcement Learning with LLMs.

BubbleSpec: Turning Long-Tail Bubbles into Speculative Rollout Drafts for Synchronous Reinforcement Learning Kimi k1.5: Scaling Reinforcement Learning with LLMs

Reference 19

Resolution: verified exact; local_arxiv, observed 2026-05-12T08:01:30.969467Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation a1fd7f19-e681-4c2e-b9c0-38c35549ed28 · outbound

This paper cites Jet-RL: Enabling on-policy FP8 reinforcement learning with unified training and rollout precision flow.arXiv preprint arXiv:2601.14243.

BubbleSpec: Turning Long-Tail Bubbles into Speculative Rollout Drafts for Synchronous Reinforcement Learning Jet-RL: Enabling on-policy FP8 reinforcement learning with unified training and rollout precision flow.arXiv preprint arXiv:2601.14243

Reference 20

Resolution: verified exact; arxiv_id, observed 2026-05-12T08:01:30.749988Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 95ecc842-2b36-4188-b412-707249b926f4 · outbound

This paper cites Jones, Zheng Dong, and Peipei Zhou.

BubbleSpec: Turning Long-Tail Bubbles into Speculative Rollout Drafts for Synchronous Reinforcement Learning Jones, Zheng Dong, and Peipei Zhou

Reference 21

Resolution: metadata mismatch; arxiv_id, observed 2026-05-12T01:26:16.160665Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 7cc00459-56c1-4fde-b935-6ce7b469bc7e · outbound

This paper cites Gen- eration meets verification: Accelerating large language model inference with smart parallel auto-correct decod- ing.

BubbleSpec: Turning Long-Tail Bubbles into Speculative Rollout Drafts for Synchronous Reinforcement Learning Gen- eration meets verification: Accelerating large language model inference with smart parallel auto-correct decod- ing

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-05-14T07:24:49.635744Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation b09292b2-e795-4a3b-aedc-887f4605f136 · outbound

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

BubbleSpec: Turning Long-Tail Bubbles into Speculative Rollout Drafts for Synchronous Reinforcement Learning DAPO: An Open-Source LLM Reinforcement Learning System at Scale

Reference 23

Resolution: verified exact; local_arxiv, observed 2026-05-12T08:01:30.740386Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation f6446d80-5e02-4200-b38d-980f0fa53438 · outbound

This paper cites SimpleRL-Zoo: Investigating and Taming Zero Reinforcement Learning for Open Base Models in the Wild.

BubbleSpec: Turning Long-Tail Bubbles into Speculative Rollout Drafts for Synchronous Reinforcement Learning SimpleRL-Zoo: Investigating and Taming Zero Reinforcement Learning for Open Base Models in the Wild

Reference 24

Resolution: verified exact; arxiv_id, observed 2026-05-13T08:21:05.971096Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation f10b9858-4408-424d-b838-35a2ac468996 · outbound

This paper cites Group Sequence Policy Optimization.

BubbleSpec: Turning Long-Tail Bubbles into Speculative Rollout Drafts for Synchronous Reinforcement Learning Group Sequence Policy Optimization

Reference 25

Resolution: verified exact; local_arxiv, observed 2026-05-12T08:01:30.728922Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 2b31c08b-f0c0-41bb-b1a6-12f9e9f58af4 · outbound

This paper cites StreamRL: Scalable, Heterogeneous, and Elastic RL for LLMs with Disaggregated Stream Generation.

BubbleSpec: Turning Long-Tail Bubbles into Speculative Rollout Drafts for Synchronous Reinforcement Learning StreamRL: Scalable, Heterogeneous, and Elastic RL for LLMs with Disaggregated Stream Generation

Reference 26

Resolution: verified exact; arxiv_id, observed 2026-05-12T08:01:30.777660Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation fc0adcb2-c068-4a48-9360-207c7538cf3d · outbound

This paper cites an unresolved cited work.

BubbleSpec: Turning Long-Tail Bubbles into Speculative Rollout Drafts for Synchronous Reinforcement Learning Unresolved cited work

Reference 27

Resolution: unresolved; raw_fallback, observed 2026-05-14T07:24:49.622140Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Pith citing papers

No inbound Pith citation observations are available.