Paper Citation Record · LEDGER

e3: Learning to Explore Enables Extrapolation of Test-Time Compute for LLMs

As of 8 August 2026, this Paper Citation Record lists 92 of 92 outbound references and 11 inbound Pith citation observations for arXiv:2506.09026.

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

pith.paper-citation-record.v1
2506.09026 v2

Coverage vector

measured 92 of 92 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-07T05:03:33.393958Z

measured 103 of 103 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-08T06:32:00.761636+00:00

measured 11 of 11 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-06T21:21:41.937333Z

measured 1 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-08-05T02:28:24.338817Z

Reference resolution

92 of 92 outbound references displayed

verified exact2
verified fuzzy5
unresolved85
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

0
arxiv_reference, observed 2026-08-05T02:28:24.338817Z

Outbound references

Observation 563ffcf9-a85f-4873-935f-8451d9f9cbf1 · outbound

This paper cites On the theory of policy gradient methods: Optimality, approximation, and distribution shift.Journal of Machine Learning Research, 22(98):1–76, 2021.

e3: Learning to Explore Enables Extrapolation of Test-Time Compute for LLMs On the theory of policy gradient methods: Optimality, approximation, and distribution shift.Journal of Machine Learning Research, 22(98):1–76, 2021

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-07T05:03:25.231877Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bef38348-1375-4b6c-84e8-f52d09fd0b6d · outbound

This paper cites L1: Controlling How Long A Reasoning Model Thinks With Reinforcement Learning.

e3: Learning to Explore Enables Extrapolation of Test-Time Compute for LLMs L1: Controlling How Long A Reasoning Model Thinks With Reinforcement Learning

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-07T05:03:25.293292Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dadfa8ab-d078-4d79-bdbd-7b99b5afe111 · outbound

This paper cites Back to Basics: Revisiting REINFORCE Style Optimization for Learning from Human Feedback in LLMs.

e3: Learning to Explore Enables Extrapolation of Test-Time Compute for LLMs Back to Basics: Revisiting REINFORCE Style Optimization for Learning from Human Feedback in LLMs

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-07T05:03:25.334902Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 75d7da3b-4d43-4d9b-8a91-a506884db8d7 · outbound

This paper cites Evaluating Large Language Models Trained on Code.

e3: Learning to Explore Enables Extrapolation of Test-Time Compute for LLMs Evaluating Large Language Models Trained on Code

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-07T05:03:25.373350Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d8abdacc-97b9-40be-8a4e-b4f4c1bcec04 · outbound

This paper cites Deepseek-r1: Incentivizing reasoning capability in llms via reinforcement learning,.

e3: Learning to Explore Enables Extrapolation of Test-Time Compute for LLMs Deepseek-r1: Incentivizing reasoning capability in llms via reinforcement learning,

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-07T05:03:25.417829Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 34bfbdea-a97e-407a-aa9e-0084dca6ec06 · outbound

This paper cites RL$^2$: Fast Reinforcement Learning via Slow Reinforcement Learning.

e3: Learning to Explore Enables Extrapolation of Test-Time Compute for LLMs RL$^2$: Fast Reinforcement Learning via Slow Reinforcement Learning

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-07T05:03:25.549636Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 50086ad2-4bd5-4074-a2df-9092189d01b8 · outbound

This paper cites Open r1: A fully open reproduction of deepseek-r1, January 2025.

e3: Learning to Explore Enables Extrapolation of Test-Time Compute for LLMs Open r1: A fully open reproduction of deepseek-r1, January 2025

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-07T05:03:25.613833Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3dbd99e9-5309-4290-99df-a3a249b670c8 · outbound

This paper cites Stream of Search (SoS): Learning to Search in Language.

e3: Learning to Explore Enables Extrapolation of Test-Time Compute for LLMs Stream of Search (SoS): Learning to Search in Language

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-07T05:03:25.660715Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b874ac4e-68f7-4292-9003-d210c3136e34 · outbound

This paper cites Cognitive Behaviors that Enable Self-Improving Reasoners, or, Four Habits of Highly Effective STaRs.

e3: Learning to Explore Enables Extrapolation of Test-Time Compute for LLMs Cognitive Behaviors that Enable Self-Improving Reasoners, or, Four Habits of Highly Effective STaRs

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-07T05:03:25.755143Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dc605c3a-310f-4ff3-9b8f-329b499d21c4 · outbound

This paper cites Reward Learning for Efficient Reinforcement Learning in Extractive Document Summarisation.

e3: Learning to Explore Enables Extrapolation of Test-Time Compute for LLMs Reward Learning for Efficient Reinforcement Learning in Extractive Document Summarisation

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-07T05:03:25.809592Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5601a49a-b4a1-448d-b99c-c8f541ae153c · outbound

This paper cites Why Generalization in RL is Difficult: Epistemic POMDPs and Implicit Partial Observability.

e3: Learning to Explore Enables Extrapolation of Test-Time Compute for LLMs Why Generalization in RL is Difficult: Epistemic POMDPs and Implicit Partial Observability

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-07T05:03:25.861972Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5ee39a6f-de9c-45e7-b557-533f155b25a5 · outbound

This paper cites Unsupervised Meta-Learning for Reinforcement Learning.

e3: Learning to Explore Enables Extrapolation of Test-Time Compute for LLMs Unsupervised Meta-Learning for Reinforcement Learning

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-07T05:03:25.925948Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation be508c46-43de-44ef-ad57-19332c637362 · outbound

This paper cites Provably Efficient Maximum Entropy Exploration.

e3: Learning to Explore Enables Extrapolation of Test-Time Compute for LLMs Provably Efficient Maximum Entropy Exploration

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-07T05:03:25.984106Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fa5bae73-d49d-4d36-a620-4458f701bdf4 · outbound

This paper cites A sober look at progress in language model reasoning: Pitfalls and paths to reproducibility.

e3: Learning to Explore Enables Extrapolation of Test-Time Compute for LLMs A sober look at progress in language model reasoning: Pitfalls and paths to reproducibility

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-07T05:03:26.061189Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2244849d-c21a-4ff2-82fb-0ec8ec7e670a · outbound

This paper cites Self-Improvement in Language Models: The Sharpening Mechanism.

e3: Learning to Explore Enables Extrapolation of Test-Time Compute for LLMs Self-Improvement in Language Models: The Sharpening Mechanism

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-07T05:03:26.163556Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 55ff2b50-c5fd-4950-a02b-65d83d0fd24a · outbound

This paper cites Scaling Evaluation-time Compute with Reasoning Models as Evaluators.

e3: Learning to Explore Enables Extrapolation of Test-Time Compute for LLMs Scaling Evaluation-time Compute with Reasoning Models as Evaluators

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-07T05:03:26.243355Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c14075a3-af6b-4cea-a2df-df48b7991ca5 · outbound

This paper cites Can large language models explore in-context?.

e3: Learning to Explore Enables Extrapolation of Test-Time Compute for LLMs Can large language models explore in-context?

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-07T05:03:26.307343Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 12a9a868-d0cd-4408-b1a8-34f7e025060a · outbound

This paper cites Training Language Models to Self-Correct via Reinforcement Learning.

e3: Learning to Explore Enables Extrapolation of Test-Time Compute for LLMs Training Language Models to Self-Correct via Reinforcement Learning

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-07T05:03:26.372345Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6951c05a-5e10-4317-a2a4-0976c4bd09f1 · outbound

This paper cites Understanding the Complexity Gains of Single-Task RL with a Curriculum.

e3: Learning to Explore Enables Extrapolation of Test-Time Compute for LLMs Understanding the Complexity Gains of Single-Task RL with a Curriculum

Reference 19

Resolution: verified exact; local_arxiv, observed 2026-08-07T05:03:34.373383Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 0473c9c2-a41b-4010-bf25-5fd125a256b7 · outbound

This paper cites Long-context LLMs Struggle with Long In-context Learning.

e3: Learning to Explore Enables Extrapolation of Test-Time Compute for LLMs Long-context LLMs Struggle with Long In-context Learning

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-07T05:03:26.464454Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b2d64ab7-2198-4b1c-a6c5-4b0a9ea16206 · outbound

This paper cites Learning Abstract Models for Strategic Exploration and Fast Reward Transfer.

e3: Learning to Explore Enables Extrapolation of Test-Time Compute for LLMs Learning Abstract Models for Strategic Exploration and Fast Reward Transfer

Reference 21

Resolution: verified exact; local_arxiv, observed 2026-08-07T05:03:34.135617Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation cfe38482-8f06-465a-97f4-0d92e1ae9e09 · outbound

This paper cites ProRL: Prolonged Reinforcement Learning Expands Reasoning Boundaries in Large Language Models.

e3: Learning to Explore Enables Extrapolation of Test-Time Compute for LLMs ProRL: Prolonged Reinforcement Learning Expands Reasoning Boundaries in Large Language Models

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-07T05:03:26.538629Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 327cfcbf-ed19-48cf-9796-ee89fe80cad3 · outbound

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

e3: Learning to Explore Enables Extrapolation of Test-Time Compute for LLMs Understanding R1-Zero-Like Training: A Critical Perspective

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-07T05:03:26.569626Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 09b53ecd-4144-419a-8716-247b70a4f766 · outbound

This paper cites Acemath: Advancing frontier math reasoning with post-training and reward modeling.arXiv preprint, 2024.

e3: Learning to Explore Enables Extrapolation of Test-Time Compute for LLMs Acemath: Advancing frontier math reasoning with post-training and reward modeling.arXiv preprint, 2024

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-07T05:03:26.638436Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 92b2fbf2-884b-45a3-b961-3db8c7a8d3c7 · outbound

This paper cites Deepcoder: A fully open-source 14b coder at o3-mini level, 2025.

e3: Learning to Explore Enables Extrapolation of Test-Time Compute for LLMs Deepcoder: A fully open-source 14b coder at o3-mini level, 2025

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-07T05:03:26.690066Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e4aa8473-3a95-48d6-8c14-8069af19c0fa · outbound

This paper cites Tang, Manan Roongta, Colin Cai, Jeffrey Luo, Tianjun Zhang, Li Erran Li, Raluca Ada Popa, and Ion Stoica.

e3: Learning to Explore Enables Extrapolation of Test-Time Compute for LLMs Tang, Manan Roongta, Colin Cai, Jeffrey Luo, Tianjun Zhang, Li Erran Li, Raluca Ada Popa, and Ion Stoica

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-07T05:03:26.747061Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 10aa9ec4-ba0e-43c5-90e6-19807c442f98 · outbound

This paper cites s1: Simple test-time scaling,.

e3: Learning to Explore Enables Extrapolation of Test-Time Compute for LLMs s1: Simple test-time scaling,

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-07T05:03:26.842800Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 52911944-a89a-47e7-ae74-3accc39b8d79 · outbound

This paper cites EVOLvE: Evaluating and Optimizing LLMs For In-Context Exploration.

e3: Learning to Explore Enables Extrapolation of Test-Time Compute for LLMs EVOLvE: Evaluating and Optimizing LLMs For In-Context Exploration

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-07T05:03:26.952530Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c22a6a3f-f6ff-4d52-b80b-d5f983955527 · outbound

This paper cites s1: Simple test-time scaling.

e3: Learning to Explore Enables Extrapolation of Test-Time Compute for LLMs s1: Simple test-time scaling

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-07T05:03:26.907112Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a5ee57e0-46a5-4534-b3f4-40b377ee033f · outbound

This paper cites Maximizing Confidence Alone Improves Reasoning.

e3: Learning to Explore Enables Extrapolation of Test-Time Compute for LLMs Maximizing Confidence Alone Improves Reasoning

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-07T05:03:27.075191Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7788e3dc-c34d-47d8-9433-c4febbdd1c91 · outbound

This paper cites OpenAI o1 System Card.

e3: Learning to Explore Enables Extrapolation of Test-Time Compute for LLMs OpenAI o1 System Card

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-07T05:03:27.026991Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9501d6f4-81d4-425f-9b26-ef0835d084cd · outbound

This paper cites Optimizing anytime reasoning via budget relative policy optimization.arXiv preprint arXiv:2505.13438, 2025.

e3: Learning to Explore Enables Extrapolation of Test-Time Compute for LLMs Optimizing anytime reasoning via budget relative policy optimization.arXiv preprint arXiv:2505.13438, 2025

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-07T05:03:27.114011Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 82baf72a-03f8-433d-926d-851f97505323 · outbound

This paper cites John Wiley & Sons, Inc., 1994.

e3: Learning to Explore Enables Extrapolation of Test-Time Compute for LLMs John Wiley & Sons, Inc., 1994

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-07T05:03:27.081368Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 83245270-4548-4a11-8767-ddf00921963f · outbound

This paper cites Optimizing Test-Time Compute via Meta Reinforcement Fine-Tuning.

e3: Learning to Explore Enables Extrapolation of Test-Time Compute for LLMs Optimizing Test-Time Compute via Meta Reinforcement Fine-Tuning

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-07T05:03:27.410502Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 93881a94-72c1-4b83-815f-b6aa2f1a469a · outbound

This paper cites Recursive Introspection: Teaching Language Model Agents How to Self-Improve.

e3: Learning to Explore Enables Extrapolation of Test-Time Compute for LLMs Recursive Introspection: Teaching Language Model Agents How to Self-Improve

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-07T05:03:27.330777Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1782b1e6-2e5d-4e88-bd43-c2cc14ef8572 · outbound

This paper cites Rewarding Progress: Scaling Automated Process Verifiers for LLM Reasoning.

e3: Learning to Explore Enables Extrapolation of Test-Time Compute for LLMs Rewarding Progress: Scaling Automated Process Verifiers for LLM Reasoning

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-07T05:03:27.538173Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7082dd8b-ab49-4565-b43e-4b6fa9fd41ce · outbound

This paper cites Proximal Policy Optimization Algorithms.

e3: Learning to Explore Enables Extrapolation of Test-Time Compute for LLMs Proximal Policy Optimization Algorithms

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-07T05:03:27.481185Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d155d0d9-b405-46c5-9231-8f57d771e0eb · outbound

This paper cites Scaling Test-Time Compute Without Verification or RL is Suboptimal.

e3: Learning to Explore Enables Extrapolation of Test-Time Compute for LLMs Scaling Test-Time Compute Without Verification or RL is Suboptimal

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-07T05:03:27.653994Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8ba954c4-8f3f-4ec8-8b34-bcad6404e7b1 · outbound

This paper cites Opti- mizing llm test-time compute involves solving a meta-rl problem.https://blog.ml.cmu.edu/,.

e3: Learning to Explore Enables Extrapolation of Test-Time Compute for LLMs Opti- mizing llm test-time compute involves solving a meta-rl problem.https://blog.ml.cmu.edu/,

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-07T05:03:27.601303Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 93354397-44c3-457a-8c2b-ad6a5463736c · outbound

This paper cites Spurious rewards: Rethinking training signals in rlvr, 2025.

e3: Learning to Explore Enables Extrapolation of Test-Time Compute for LLMs Spurious rewards: Rethinking training signals in rlvr, 2025

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-07T05:03:27.887825Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation aed5a159-d96f-420e-8049-51292198c6ff · outbound

This paper cites Can large reasoning models self-train?, 2025.

e3: Learning to Explore Enables Extrapolation of Test-Time Compute for LLMs Can large reasoning models self-train?, 2025

Reference 41

Resolution: unresolved; no resolver link, observed 2026-08-07T05:03:27.763477Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f28761a3-3781-4ea6-ba56-de81838ac795 · outbound

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

e3: Learning to Explore Enables Extrapolation of Test-Time Compute for LLMs HybridFlow: A Flexible and Efficient RLHF Framework

Reference 42

Resolution: unresolved; no resolver link, observed 2026-08-07T05:03:28.093876Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d72ebdd1-a06d-45cf-ae99-5f5e48a5f708 · outbound

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

e3: Learning to Explore Enables Extrapolation of Test-Time Compute for LLMs DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models

Reference 43

Resolution: unresolved; no resolver link, observed 2026-08-07T05:03:27.977837Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3773da43-37af-48b7-9350-02da630331d1 · outbound

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

e3: Learning to Explore Enables Extrapolation of Test-Time Compute for LLMs Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameters

Reference 44

Resolution: unresolved; no resolver link, observed 2026-08-07T05:03:28.325951Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 207ae8f2-58cf-4814-a505-d16add4c7125 · outbound

This paper cites Efficient Reinforcement Finetuning via Adaptive Curriculum Learning.

e3: Learning to Explore Enables Extrapolation of Test-Time Compute for LLMs Efficient Reinforcement Finetuning via Adaptive Curriculum Learning

Reference 45

Resolution: unresolved; no resolver link, observed 2026-08-07T05:03:28.240528Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d722aab7-75a3-4e2c-b6c7-a7e5fb01397f · outbound

This paper cites A Minimaximalist Approach to Reinforcement Learning from Human Feedback.

e3: Learning to Explore Enables Extrapolation of Test-Time Compute for LLMs A Minimaximalist Approach to Reinforcement Learning from Human Feedback

Reference 46

Resolution: unresolved; no resolver link, observed 2026-08-07T05:03:28.528670Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b760d7ee-a2d3-4a3e-a999-b4747dad6391 · outbound

This paper cites Mind the Gap: Examining the Self-Improvement Capabilities of Large Language Models.

e3: Learning to Explore Enables Extrapolation of Test-Time Compute for LLMs Mind the Gap: Examining the Self-Improvement Capabilities of Large Language Models

Reference 47

Resolution: unresolved; no resolver link, observed 2026-08-07T05:03:28.400160Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 41efc73e-f3a3-4f0f-a89c-97b4007aa361 · outbound

This paper cites Preference Fine-Tuning of LLMs Should Leverage Suboptimal, On-Policy Data, ICML 2024.

e3: Learning to Explore Enables Extrapolation of Test-Time Compute for LLMs Preference Fine-Tuning of LLMs Should Leverage Suboptimal, On-Policy Data, ICML 2024

Reference 48

Resolution: unresolved; no resolver link, observed 2026-08-07T05:03:28.718332Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 014f4051-8c67-462c-929d-4f6ef5cb1548 · outbound

This paper cites All roads lead to likelihood: The value of reinforcement learning in fine-tuning.

e3: Learning to Explore Enables Extrapolation of Test-Time Compute for LLMs All roads lead to likelihood: The value of reinforcement learning in fine-tuning

Reference 49

Resolution: unresolved; no resolver link, observed 2026-08-07T05:03:28.616812Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 741f74ff-94a1-47c6-a190-cdf584061006 · outbound

This paper cites Open Thoughts.

e3: Learning to Explore Enables Extrapolation of Test-Time Compute for LLMs Open Thoughts

Reference 50

Resolution: unresolved; no resolver link, observed 2026-08-07T05:03:28.890910Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 878ef22e-f7fb-4336-9912-49ecb9b789eb · outbound

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

e3: Learning to Explore Enables Extrapolation of Test-Time Compute for LLMs Kimi k1.5: Scaling Reinforcement Learning with LLMs

Reference 51

Resolution: unresolved; no resolver link, observed 2026-08-07T05:03:28.800270Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f835cd85-0c80-4003-b734-4115945c1f75 · outbound

This paper cites Self-Consistency Improves Chain of Thought Reasoning in Language Models.

e3: Learning to Explore Enables Extrapolation of Test-Time Compute for LLMs Self-Consistency Improves Chain of Thought Reasoning in Language Models

Reference 52

Resolution: unresolved; no resolver link, observed 2026-08-07T05:03:29.161726Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 86ac5cef-66ee-4c4d-9405-8c67ec8399ff · outbound

This paper cites Beyond the 80/20 Rule: High-Entropy Minority Tokens Drive Effective Reinforcement Learning for LLM Reasoning.

e3: Learning to Explore Enables Extrapolation of Test-Time Compute for LLMs Beyond the 80/20 Rule: High-Entropy Minority Tokens Drive Effective Reinforcement Learning for LLM Reasoning

Reference 53

Resolution: unresolved; no resolver link, observed 2026-08-07T05:03:29.029441Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f0eaa6fe-7121-44d7-a84b-6ce3418d5c79 · outbound

This paper cites Logic-RL: Unleashing LLM Reasoning with Rule-Based Reinforcement Learning.

e3: Learning to Explore Enables Extrapolation of Test-Time Compute for LLMs Logic-RL: Unleashing LLM Reasoning with Rule-Based Reinforcement Learning

Reference 54

Resolution: unresolved; no resolver link, observed 2026-08-07T05:03:29.367441Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation da1e103d-0c2b-46f9-9ec7-68d171daa5b5 · outbound

This paper cites Reinforcement Learning for Reasoning in Large Language Models with One Training Example.

e3: Learning to Explore Enables Extrapolation of Test-Time Compute for LLMs Reinforcement Learning for Reasoning in Large Language Models with One Training Example

Reference 55

Resolution: unresolved; no resolver link, observed 2026-08-07T05:03:29.284245Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9f9f2196-f3c0-4924-9bb5-06e05a112b7d · outbound

This paper cites Tree of Thoughts: Deliberate Problem Solving with Large Language Models.

e3: Learning to Explore Enables Extrapolation of Test-Time Compute for LLMs Tree of Thoughts: Deliberate Problem Solving with Large Language Models

Reference 56

Resolution: unresolved; no resolver link, observed 2026-08-07T05:03:29.615178Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 968c06be-1c7f-4e33-a8d9-a2e465a1f2d2 · outbound

This paper cites Qwen3 Technical Report.

e3: Learning to Explore Enables Extrapolation of Test-Time Compute for LLMs Qwen3 Technical Report

Reference 57

Resolution: unresolved; no resolver link, observed 2026-08-07T05:03:29.500826Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8b61a26d-890a-4211-83ab-ee5887694417 · outbound

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

e3: Learning to Explore Enables Extrapolation of Test-Time Compute for LLMs DAPO: An Open-Source LLM Reinforcement Learning System at Scale

Reference 58

Resolution: unresolved; no resolver link, observed 2026-08-07T05:03:29.861106Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fbe2ba65-17b0-4fc9-a82c-421acd9a1363 · outbound

This paper cites Demystifying Long Chain-of-Thought Reasoning in LLMs.

e3: Learning to Explore Enables Extrapolation of Test-Time Compute for LLMs Demystifying Long Chain-of-Thought Reasoning in LLMs

Reference 59

Resolution: unresolved; no resolver link, observed 2026-08-07T05:03:29.742448Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 26d30ab5-fa15-4fc6-bc30-355c07bb69e5 · outbound

This paper cites Does Reinforcement Learning Really Incentivize Reasoning Capacity in LLMs Beyond the Base Model?.

e3: Learning to Explore Enables Extrapolation of Test-Time Compute for LLMs Does Reinforcement Learning Really Incentivize Reasoning Capacity in LLMs Beyond the Base Model?

Reference 60

Resolution: unresolved; no resolver link, observed 2026-08-07T05:03:30.047432Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 233747cc-2482-4e80-a50b-534029d8f11f · outbound

This paper cites Scaling Relationship on Learning Mathematical Reasoning with Large Language Models.

e3: Learning to Explore Enables Extrapolation of Test-Time Compute for LLMs Scaling Relationship on Learning Mathematical Reasoning with Large Language Models

Reference 61

Resolution: unresolved; no resolver link, observed 2026-08-07T05:03:29.931120Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5f7f6153-5475-49de-8a4c-b66f7025612a · outbound

This paper cites Star: Bootstrapping reasoning with reasoning.

e3: Learning to Explore Enables Extrapolation of Test-Time Compute for LLMs Star: Bootstrapping reasoning with reasoning

Reference 63

Resolution: unresolved; no resolver link, observed 2026-08-07T05:03:30.153724Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5d7413e4-ec3c-41e5-866f-878829bce260 · outbound

This paper cites Learning to Reason without External Rewards.

e3: Learning to Explore Enables Extrapolation of Test-Time Compute for LLMs Learning to Reason without External Rewards

Reference 64

Resolution: unresolved; no resolver link, observed 2026-08-07T05:03:30.482279Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6d5d42ea-cccc-42f2-9151-fa579a2a658d · outbound

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

e3: Learning to Explore Enables Extrapolation of Test-Time Compute for LLMs SimpleRL-Zoo: Investigating and Taming Zero Reinforcement Learning for Open Base Models in the Wild

Reference 65

Resolution: unresolved; no resolver link, observed 2026-08-07T05:03:30.353983Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d8b24c0e-a7a5-4ddb-bdfa-0e4246605f7a · outbound

This paper cites Looking at the other numbers: 77 - 70 = 7 97 - 73 = 24 (interesting, we already have.

e3: Learning to Explore Enables Extrapolation of Test-Time Compute for LLMs Looking at the other numbers: 77 - 70 = 7 97 - 73 = 24 (interesting, we already have

Reference 66

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:03:34.993578Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 73793d47-d65d-4c6b-be67-7ad5aa220217 · outbound

This paper cites an unresolved cited work.

e3: Learning to Explore Enables Extrapolation of Test-Time Compute for LLMs Unresolved cited work

Reference 67

Resolution: unresolved; raw_fallback, observed 2026-08-07T05:03:40.735256Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 16ec9fdc-ddb2-4d41-8eec-2bc04cbf672b · outbound

This paper cites We need to get from 37 to 466, which means we need to multiply by 12.5.

e3: Learning to Explore Enables Extrapolation of Test-Time Compute for LLMs We need to get from 37 to 466, which means we need to multiply by 12.5

Reference 68

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:03:40.511892Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation cba0c388-9ba8-48ee-91d6-0e00a7c42aaa · outbound

This paper cites an unresolved cited work.

e3: Learning to Explore Enables Extrapolation of Test-Time Compute for LLMs Unresolved cited work

Reference 69

Resolution: unresolved; raw_fallback, observed 2026-08-07T05:03:40.298433Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 7703ae3e-ae22-45dc-a9ec-624e83181129 · outbound

This paper cites an unresolved cited work.

e3: Learning to Explore Enables Extrapolation of Test-Time Compute for LLMs Unresolved cited work

Reference 70

Resolution: unresolved; raw_fallback, observed 2026-08-07T05:03:40.090080Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 38c15b0c-bec0-4193-848a-65acd990faf9 · outbound

This paper cites an unresolved cited work.

e3: Learning to Explore Enables Extrapolation of Test-Time Compute for LLMs Unresolved cited work

Reference 71

Resolution: unresolved; raw_fallback, observed 2026-08-07T05:03:39.898527Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 2b8878db-da0e-463d-b3f2-5872b395b83c · outbound

This paper cites an unresolved cited work.

e3: Learning to Explore Enables Extrapolation of Test-Time Compute for LLMs Unresolved cited work

Reference 72

Resolution: unresolved; raw_fallback, observed 2026-08-07T05:03:39.646657Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 48455646-a978-45c3-8a4c-22f364a55508 · outbound

This paper cites an unresolved cited work.

e3: Learning to Explore Enables Extrapolation of Test-Time Compute for LLMs Unresolved cited work

Reference 73

Resolution: unresolved; raw_fallback, observed 2026-08-07T05:03:39.438320Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation bcb27548-26d4-4336-8b9f-2c7770a86ee7 · outbound

This paper cites an unresolved cited work.

e3: Learning to Explore Enables Extrapolation of Test-Time Compute for LLMs Unresolved cited work

Reference 74

Resolution: unresolved; raw_fallback, observed 2026-08-07T05:03:39.216261Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation a42f1119-c124-4ced-840f-64137e979db0 · outbound

This paper cites an unresolved cited work.

e3: Learning to Explore Enables Extrapolation of Test-Time Compute for LLMs Unresolved cited work

Reference 75

Resolution: unresolved; raw_fallback, observed 2026-08-07T05:03:39.009793Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 66d47b82-d388-4183-a294-7b9d7472290d · outbound

This paper cites an unresolved cited work.

e3: Learning to Explore Enables Extrapolation of Test-Time Compute for LLMs Unresolved cited work

Reference 76

Resolution: unresolved; raw_fallback, observed 2026-08-07T05:03:38.877821Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 476391ed-9599-46d5-ac75-e69fa5892a14 · outbound

This paper cites an unresolved cited work.

e3: Learning to Explore Enables Extrapolation of Test-Time Compute for LLMs Unresolved cited work

Reference 77

Resolution: unresolved; raw_fallback, observed 2026-08-07T05:03:38.657484Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 7f1d463a-e987-489c-99e0-3e57a75edd6e · outbound

This paper cites an unresolved cited work.

e3: Learning to Explore Enables Extrapolation of Test-Time Compute for LLMs Unresolved cited work

Reference 78

Resolution: unresolved; raw_fallback, observed 2026-08-07T05:03:38.408750Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 75ba2295-f46d-4876-a35b-e71b4b53bfff · outbound

This paper cites an unresolved cited work.

e3: Learning to Explore Enables Extrapolation of Test-Time Compute for LLMs Unresolved cited work

Reference 79

Resolution: unresolved; raw_fallback, observed 2026-08-07T05:03:38.133653Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 66dfd81e-85ea-4ea7-bdde-1fa303f6a108 · outbound

This paper cites an unresolved cited work.

e3: Learning to Explore Enables Extrapolation of Test-Time Compute for LLMs Unresolved cited work

Reference 80

Resolution: unresolved; raw_fallback, observed 2026-08-07T05:03:37.931265Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation b2e2a2a8-3ad0-47ab-9d10-8fe797d320e0 · outbound

This paper cites an unresolved cited work.

e3: Learning to Explore Enables Extrapolation of Test-Time Compute for LLMs Unresolved cited work

Reference 81

Resolution: unresolved; raw_fallback, observed 2026-08-07T05:03:37.716974Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 884f3572-8433-4f42-9e4b-22f75dd0c333 · outbound

This paper cites an unresolved cited work.

e3: Learning to Explore Enables Extrapolation of Test-Time Compute for LLMs Unresolved cited work

Reference 82

Resolution: unresolved; raw_fallback, observed 2026-08-07T05:03:37.520483Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 437b83b2-677a-4490-8b68-89b6d5c1cd3c · outbound

This paper cites an unresolved cited work.

e3: Learning to Explore Enables Extrapolation of Test-Time Compute for LLMs Unresolved cited work

Reference 83

Resolution: unresolved; raw_fallback, observed 2026-08-07T05:03:37.291156Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 269eedb9-3091-40f7-8272-7aefe649550e · outbound

This paper cites an unresolved cited work.

e3: Learning to Explore Enables Extrapolation of Test-Time Compute for LLMs Unresolved cited work

Reference 84

Resolution: unresolved; raw_fallback, observed 2026-08-07T05:03:37.088649Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 3c5a907d-1706-4adc-88f4-31f4dc9dbfbd · outbound

This paper cites 31.5 (not helpful).

e3: Learning to Explore Enables Extrapolation of Test-Time Compute for LLMs 31.5 (not helpful)

Reference 85

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:03:36.816490Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 7db092d6-5cdf-4905-bf33-b562e09ffb1b · outbound

This paper cites an unresolved cited work.

e3: Learning to Explore Enables Extrapolation of Test-Time Compute for LLMs Unresolved cited work

Reference 86

Resolution: unresolved; raw_fallback, observed 2026-08-07T05:03:36.569151Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation cd6f2c5d-3087-473a-85c4-ca16269bc216 · outbound

This paper cites an unresolved cited work.

e3: Learning to Explore Enables Extrapolation of Test-Time Compute for LLMs Unresolved cited work

Reference 87

Resolution: unresolved; raw_fallback, observed 2026-08-07T05:03:36.358782Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 8fa66cf5-8f1c-40b3-b0a2-9e5cf583b650 · outbound

This paper cites an unresolved cited work.

e3: Learning to Explore Enables Extrapolation of Test-Time Compute for LLMs Unresolved cited work

Reference 88

Resolution: unresolved; raw_fallback, observed 2026-08-07T05:03:36.118343Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 2efbcaa7-2bed-4693-941a-5eb70b13dbd1 · outbound

This paper cites an unresolved cited work.

e3: Learning to Explore Enables Extrapolation of Test-Time Compute for LLMs Unresolved cited work

Reference 89

Resolution: unresolved; raw_fallback, observed 2026-08-07T05:03:35.933890Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 415a2322-a148-4db3-849e-c71a98eef83b · outbound

This paper cites Hmm, let me think about how to approach this.

e3: Learning to Explore Enables Extrapolation of Test-Time Compute for LLMs Hmm, let me think about how to approach this

Reference 90

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:03:35.609076Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 9759744a-aa27-460a-9737-6bad422b14a8 · outbound

This paper cites an unresolved cited work.

e3: Learning to Explore Enables Extrapolation of Test-Time Compute for LLMs Unresolved cited work

Reference 93

Resolution: unresolved; raw_fallback, observed 2026-08-07T05:03:34.743229Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation e8a353ca-341f-4290-925d-faf4647054df · outbound

This paper cites Again, multiply 347 by 5 and add two zeros.

e3: Learning to Explore Enables Extrapolation of Test-Time Compute for LLMs Again, multiply 347 by 5 and add two zeros

Reference 500

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:03:35.287512Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 7ca58a45-cbde-464b-9c44-32b754e36ef5 · outbound

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

e3: Learning to Explore Enables Extrapolation of Test-Time Compute for LLMs DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning

Reference 2025

Resolution: unresolved; no resolver link, observed 2026-08-07T05:03:25.469591Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation 9749439b-2f45-4577-a302-9162374af12e · inbound

ASTRO: Teaching Language Models to Reason by Reflecting and Backtracking In-Context cites this paper.

ASTRO: Teaching Language Models to Reason by Reflecting and Backtracking In-Context e3: Learning to Explore Enables Extrapolation of Test-Time Compute for LLMs

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-06T21:21:41.937333Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2dc96f34-873c-4b75-ae35-482082edbde9 · inbound

Pass@k Training for Adaptively Balancing Exploration and Exploitation of Large Reasoning Models cites this paper.

Pass@k Training for Adaptively Balancing Exploration and Exploitation of Large Reasoning Models e3: Learning to Explore Enables Extrapolation of Test-Time Compute for LLMs

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-05T20:21:08.163389Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 62e79bd9-5de4-4b91-b579-44a002b56daf · inbound

Outcome-based Exploration for LLM Reasoning cites this paper.

Outcome-based Exploration for LLM Reasoning e3: Learning to Explore Enables Extrapolation of Test-Time Compute for LLMs

Reference 2020

Resolution: unresolved; no resolver link, observed 2026-08-04T22:59:14.534182Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6a1e0385-5950-46db-a390-5826abdc1213 · inbound

Representation-Based Exploration for Language Models: From Test-Time to Post-Training cites this paper.

Representation-Based Exploration for Language Models: From Test-Time to Post-Training e3: Learning to Explore Enables Extrapolation of Test-Time Compute for LLMs

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-04T10:09:03.509893Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ac25798b-d911-4be4-9de9-432a70e14263 · inbound

Training Reasoning Models on Saturated Problems via Failure-Prefix Conditioning cites this paper.

Training Reasoning Models on Saturated Problems via Failure-Prefix Conditioning e3: Learning to Explore Enables Extrapolation of Test-Time Compute for LLMs

Reference 17

Resolution: verified exact; arxiv_id, observed 2026-05-16T10:27:44.448791Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 96a65a17-114f-4a3b-9585-6ae340cd7f01 · inbound

What Does Flow Matching Bring To TD Learning? cites this paper.

What Does Flow Matching Bring To TD Learning? e3: Learning to Explore Enables Extrapolation of Test-Time Compute for LLMs

Reference 55

Resolution: verified exact; arxiv_id, observed 2026-05-15T16:36:17.923996Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 97b7fe68-7dfb-4165-bc4e-0cade0795304 · inbound

Too Correct to Learn: Reinforcement Learning on Saturated Reasoning Data cites this paper.

Too Correct to Learn: Reinforcement Learning on Saturated Reasoning Data e3: Learning to Explore Enables Extrapolation of Test-Time Compute for LLMs

Reference 23

Resolution: verified exact; arxiv_id, observed 2026-05-10T05:36:01.402466Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 11b5d117-b3eb-4c77-8be0-13e8c12225c7 · inbound

OGPO: Sample Efficient Full-Finetuning of Generative Control Policies cites this paper.

OGPO: Sample Efficient Full-Finetuning of Generative Control Policies e3: Learning to Explore Enables Extrapolation of Test-Time Compute for LLMs

Reference 175

Resolution: verified exact; arxiv_id, observed 2026-05-09T06:10:42.517079Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 9de63b67-d0db-426d-ae15-87987fce5a98 · inbound

OGPO: Sample Efficient Full-Finetuning of Generative Control Policies cites this paper.

OGPO: Sample Efficient Full-Finetuning of Generative Control Policies e3: Learning to Explore Enables Extrapolation of Test-Time Compute for LLMs

Reference 42

Resolution: verified exact; arxiv_id, observed 2026-07-01T00:05:09.652333Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 978bf51c-3054-476a-bfff-6e3746dd43dd · inbound

On Advantage Estimates for Max@K Policy Gradients cites this paper.

On Advantage Estimates for Max@K Policy Gradients e3: Learning to Explore Enables Extrapolation of Test-Time Compute for LLMs

Reference 44

Resolution: verified exact; arxiv_id, observed 2026-07-02T12:06:56.433620Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 18fc5695-e22c-4d53-9796-fff3c94285ae · inbound

OrderGrad: Optimizing Beyond the Mean with Order-Statistic Policy Gradient Estimation cites this paper.

OrderGrad: Optimizing Beyond the Mean with Order-Statistic Policy Gradient Estimation e3: Learning to Explore Enables Extrapolation of Test-Time Compute for LLMs

Reference 83

Resolution: metadata mismatch; arxiv_id, observed 2026-07-02T12:16:56.964580Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.