Paper Citation Record · LEDGER

When Importance Sampling Misallocates Credit: Asymmetric Ratios for Outcome-Supervised RL

As of 19 July 2026, this Paper Citation Record lists 20 of 20 outbound references and 13 inbound Pith citation observations for arXiv:2510.06062.

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

pith.paper-citation-record.v1
2510.06062 v2

Coverage vector

measured 20 of 20 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-07-11T11:50:26.030339Z

measured 33 of 33 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-07-19T06:30:13.599613+00:00

measured 13 of 13 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-07-09T22:18:13.418579Z

measured 0 of 1 external citation measurements

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

Source: pith, observed 2026-07-09T22:26:37.216917Z

Reference resolution

20 of 20 outbound references displayed

verified exact8
verified fuzzy3
unresolved0
parse uncertain0
malformed identifier0
metadata mismatch9

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation c6916d2d-64c6-4933-839e-720cf355372d · outbound

This paper cites MiniMax-M1: Scaling Test-Time Compute Efficiently with Lightning Attention.

When Importance Sampling Misallocates Credit: Asymmetric Ratios for Outcome-Supervised RL MiniMax-M1: Scaling Test-Time Compute Efficiently with Lightning Attention

Reference 1

Resolution: metadata mismatch; local_arxiv, observed 2026-05-21T20:30:35.536429Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-19T06:30:13.599613+00:00.

Observation 837fe42b-9dff-41b4-8336-f1e5dbdef574 · outbound

This paper cites The Entropy Mechanism of Reinforcement Learning for Reasoning Language Models.

When Importance Sampling Misallocates Credit: Asymmetric Ratios for Outcome-Supervised RL The Entropy Mechanism of Reinforcement Learning for Reasoning Language Models

Reference 2

Resolution: metadata mismatch; local_arxiv, observed 2026-05-21T20:30:35.543637Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-19T06:30:13.599613+00:00.

Observation 43e7d9aa-e16e-4330-9fb3-75d090eccacb · outbound

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

When Importance Sampling Misallocates Credit: Asymmetric Ratios for Outcome-Supervised RL DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning

Reference 3

Resolution: verified exact; local_arxiv, observed 2026-05-21T20:30:35.533182Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-19T06:30:13.599613+00:00.

Observation d67ef9bc-3c4e-44f8-a40c-accf4cfadfc7 · outbound

This paper cites Skywork Open Reasoner 1 Technical Report.

When Importance Sampling Misallocates Credit: Asymmetric Ratios for Outcome-Supervised RL Skywork Open Reasoner 1 Technical Report

Reference 4

Resolution: metadata mismatch; local_arxiv, observed 2026-05-21T20:30:35.290742Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-19T06:30:13.599613+00:00.

Observation 0a934e0c-4bda-462a-ba83-401595a0c766 · outbound

This paper cites Efficient Memory Management for Large Language Model Serving with PagedAttention , booktitle =.

When Importance Sampling Misallocates Credit: Asymmetric Ratios for Outcome-Supervised RL Efficient Memory Management for Large Language Model Serving with PagedAttention , booktitle =

Reference 5

Resolution: metadata mismatch; arxiv_id, observed 2026-05-21T20:30:35.300541Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-19T06:30:13.599613+00:00.

Observation ade1cf8d-21a6-4a1f-a843-857ee90fe673 · outbound

This paper cites an unresolved cited work.

When Importance Sampling Misallocates Credit: Asymmetric Ratios for Outcome-Supervised RL Unresolved cited work

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-05-21T20:30:35.696257Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-19T06:30:13.599613+00:00.

Observation fcc9f190-c4b7-418f-b900-549b25fec25f · outbound

This paper cites Mankowitz, Esme Sutherland Robson, Pushmeet Kohli, Nando De Freitas, Koray Kavukcuoglu, and Oriol Vinyals.

When Importance Sampling Misallocates Credit: Asymmetric Ratios for Outcome-Supervised RL Mankowitz, Esme Sutherland Robson, Pushmeet Kohli, Nando De Freitas, Koray Kavukcuoglu, and Oriol Vinyals

Reference 7

Resolution: metadata mismatch; doi, observed 2026-05-21T20:30:35.294764Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-19T06:30:13.599613+00:00.

Observation 9619e9b8-149d-40fc-b8af-29a8728bebe8 · outbound

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

When Importance Sampling Misallocates Credit: Asymmetric Ratios for Outcome-Supervised RL ProRL: Prolonged Reinforcement Learning Expands Reasoning Boundaries in Large Language Models

Reference 8

Resolution: metadata mismatch; local_arxiv, observed 2026-05-21T20:30:35.530451Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-19T06:30:13.599613+00:00.

Observation 2a18a124-832f-43ac-b30b-6e04511b983b · outbound

This paper cites Can 1B LLM Surpass 405B LLM? Rethinking Compute-Optimal Test-Time Scaling.

When Importance Sampling Misallocates Credit: Asymmetric Ratios for Outcome-Supervised RL Can 1B LLM Surpass 405B LLM? Rethinking Compute-Optimal Test-Time Scaling

Reference 9

Resolution: verified exact; arxiv_id, observed 2026-05-21T20:30:35.518062Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-19T06:30:13.599613+00:00.

Observation aa994ca8-bedd-40d2-be5b-6aafcb817360 · outbound

This paper cites Proximal Policy Optimization Algorithms.

When Importance Sampling Misallocates Credit: Asymmetric Ratios for Outcome-Supervised RL Proximal Policy Optimization Algorithms

Reference 10

Resolution: verified exact; local_arxiv, observed 2026-05-21T20:30:35.550011Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-19T06:30:13.599613+00:00.

Observation e73a185f-2c59-4961-84fc-fa1df9968932 · outbound

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

When Importance Sampling Misallocates Credit: Asymmetric Ratios for Outcome-Supervised RL DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models

Reference 11

Resolution: verified exact; local_arxiv, observed 2026-05-21T20:30:35.540414Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-19T06:30:13.599613+00:00.

Observation cc404e30-0181-48d0-a3cf-5ca05a5c6ecf · outbound

This paper cites Hybridflow: A flexible and efficient rlhf framework.

When Importance Sampling Misallocates Credit: Asymmetric Ratios for Outcome-Supervised RL Hybridflow: A flexible and efficient rlhf framework

Reference 12

Resolution: metadata mismatch; arxiv_id, observed 2026-05-21T20:30:35.263155Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-19T06:30:13.599613+00:00.

Observation 350cbf6f-eced-4230-870f-6ec2430a160f · outbound

This paper cites Stabilizing Knowledge, Promoting Reasoning: Dual-Token Constraints for RLVR.

When Importance Sampling Misallocates Credit: Asymmetric Ratios for Outcome-Supervised RL Stabilizing Knowledge, Promoting Reasoning: Dual-Token Constraints for RLVR

Reference 13

Resolution: verified exact; local_arxiv, observed 2026-05-21T20:30:35.527450Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-19T06:30:13.599613+00:00.

Observation 5f5b6ca3-da9e-4f11-bfb1-9ef25971734e · outbound

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

When Importance Sampling Misallocates Credit: Asymmetric Ratios for Outcome-Supervised RL DAPO: An Open-Source LLM Reinforcement Learning System at Scale

Reference 14

Resolution: metadata mismatch; local_arxiv, observed 2026-05-21T20:30:35.285333Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-19T06:30:13.599613+00:00.

Observation aa34e41b-b028-4c4c-87b7-ebd7c5eb4527 · outbound

This paper cites VAPO: Efficient and Reliable Reinforcement Learning for Advanced Reasoning Tasks.

When Importance Sampling Misallocates Credit: Asymmetric Ratios for Outcome-Supervised RL VAPO: Efficient and Reliable Reinforcement Learning for Advanced Reasoning Tasks

Reference 15

Resolution: verified exact; local_arxiv, observed 2026-05-21T20:30:35.546640Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-19T06:30:13.599613+00:00.

Observation c9037920-5672-4486-984e-63abb982aecd · outbound

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

When Importance Sampling Misallocates Credit: Asymmetric Ratios for Outcome-Supervised RL SimpleRL-Zoo: Investigating and Taming Zero Reinforcement Learning for Open Base Models in the Wild

Reference 16

Resolution: verified exact; local_arxiv, observed 2026-05-21T20:30:35.524502Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-19T06:30:13.599613+00:00.

Observation 35924ace-f966-4dd4-94de-0fc27fbf2332 · outbound

This paper cites A Survey of Reinforcement Learning for Large Reasoning Models.

When Importance Sampling Misallocates Credit: Asymmetric Ratios for Outcome-Supervised RL A Survey of Reinforcement Learning for Large Reasoning Models

Reference 17

Resolution: metadata mismatch; local_arxiv, observed 2026-05-21T20:30:35.274924Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-19T06:30:13.599613+00:00.

Observation 287e9b65-1b50-4ae0-aaf9-1d529ae3146c · outbound

This paper cites Group Sequence Policy Optimization.

When Importance Sampling Misallocates Credit: Asymmetric Ratios for Outcome-Supervised RL Group Sequence Policy Optimization

Reference 18

Resolution: verified exact; local_arxiv, observed 2026-05-21T20:30:35.521394Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-19T06:30:13.599613+00:00.

Observation ba978783-ff9a-4bd1-a81e-84006ad18068 · outbound

This paper cites •DAPO(Yu et al., 2025): A strong OSRL algorithm built upon GRPO (Shao et al., 2024).

When Importance Sampling Misallocates Credit: Asymmetric Ratios for Outcome-Supervised RL •DAPO(Yu et al., 2025): A strong OSRL algorithm built upon GRPO (Shao et al., 2024)

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-05-21T20:30:35.691979Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-19T06:30:13.599613+00:00.

Observation 47938baa-b011-4cd9-b898-f17670c4a5c2 · outbound

This paper cites For coding, we employ DeepCoder (Luo et al., 2025a), CodeContests (Li et al., 2022), and CodeForces (Penedo et al.

When Importance Sampling Misallocates Credit: Asymmetric Ratios for Outcome-Supervised RL For coding, we employ DeepCoder (Luo et al., 2025a), CodeContests (Li et al., 2022), and CodeForces (Penedo et al

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-05-21T20:30:35.694087Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-19T06:30:13.599613+00:00.

Pith citing papers

Observation 88d8db98-04ae-413c-a74f-d520c54c0249 · inbound

STAPO: Stabilizing Reinforcement Learning for LLMs by Silencing Rare Spurious Tokens cites this paper.

STAPO: Stabilizing Reinforcement Learning for LLMs by Silencing Rare Spurious Tokens When Importance Sampling Misallocates Credit: Asymmetric Ratios for Outcome-Supervised RL

Reference 28

Resolution: verified exact; arxiv_id, observed 2026-05-20T00:00:25.356150Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-19T06:30:13.599613+00:00.

Observation 5d6c6851-6cd5-4edc-8f6b-73d91282500b · inbound

OGER: A Robust Offline-Guided Exploration Reward for Hybrid Reinforcement Learning cites this paper.

OGER: A Robust Offline-Guided Exploration Reward for Hybrid Reinforcement Learning When Importance Sampling Misallocates Credit: Asymmetric Ratios for Outcome-Supervised RL

Reference 8

Resolution: verified exact; arxiv_id, observed 2026-05-20T00:00:25.356150Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-19T06:30:13.599613+00:00.

Observation 8c479286-4409-453a-81c8-22345d9703cc · inbound

Bounded Ratio Reinforcement Learning cites this paper.

Bounded Ratio Reinforcement Learning When Importance Sampling Misallocates Credit: Asymmetric Ratios for Outcome-Supervised RL

Reference 30

Resolution: verified exact; arxiv_id, observed 2026-05-20T00:00:25.356150Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-19T06:30:13.599613+00:00.

Observation 25cb378c-f7eb-4da7-8bf1-4bccb1395ec8 · inbound

Balanced Aggregation: Understanding and Fixing Aggregation Bias in GRPO cites this paper.

Balanced Aggregation: Understanding and Fixing Aggregation Bias in GRPO When Importance Sampling Misallocates Credit: Asymmetric Ratios for Outcome-Supervised RL

Reference 19

Resolution: verified exact; arxiv_id, observed 2026-05-20T00:00:25.356150Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-19T06:30:13.599613+00:00.

Observation c4a4bfdd-8b1c-4119-86e7-800b336a3b29 · inbound

The Extrapolation Cliff in On-Policy Distillation of Near-Deterministic Structured Outputs cites this paper.

The Extrapolation Cliff in On-Policy Distillation of Near-Deterministic Structured Outputs When Importance Sampling Misallocates Credit: Asymmetric Ratios for Outcome-Supervised RL

Reference 39

Resolution: verified exact; arxiv_id, observed 2026-05-20T00:00:25.356150Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-19T06:30:13.599613+00:00.

Observation f7a37feb-abee-4813-881e-d0f92d949949 · inbound

StepCodeReasoner: Aligning Code Reasoning with Stepwise Execution Traces via Reinforcement Learning cites this paper.

StepCodeReasoner: Aligning Code Reasoning with Stepwise Execution Traces via Reinforcement Learning When Importance Sampling Misallocates Credit: Asymmetric Ratios for Outcome-Supervised RL

Reference 75

Resolution: metadata mismatch; arxiv_id, observed 2026-05-20T00:00:25.356150Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-19T06:30:13.599613+00:00.

Observation d1d7b383-b0bd-4240-a93f-669a63b9a4a9 · inbound

Rethinking Muon Beyond Pretraining: Spectral Failures and High-Pass Remedies for VLA and RLVR cites this paper.

Rethinking Muon Beyond Pretraining: Spectral Failures and High-Pass Remedies for VLA and RLVR When Importance Sampling Misallocates Credit: Asymmetric Ratios for Outcome-Supervised RL

Reference 34

Resolution: metadata mismatch; local_arxiv, observed 2026-05-20T07:18:07.221238Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-19T06:30:13.599613+00:00.

Observation e34a2f17-0ed7-4d71-ba82-b47be20c4cd8 · inbound

When to Stop Reusing: Dynamic Gradient Gating for Sample-Efficient RLVR cites this paper.

When to Stop Reusing: Dynamic Gradient Gating for Sample-Efficient RLVR When Importance Sampling Misallocates Credit: Asymmetric Ratios for Outcome-Supervised RL

Reference 31

Resolution: verified exact; local_arxiv, observed 2026-05-20T07:33:07.388058Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-19T06:30:13.599613+00:00.

Observation ab02dfc7-fdc2-4d79-b05a-3c9c1dd9e6b0 · inbound

Multi-Step Likelihood-Ratio Correction for Reinforcement Learning with Verifiable Rewards cites this paper.

Multi-Step Likelihood-Ratio Correction for Reinforcement Learning with Verifiable Rewards When Importance Sampling Misallocates Credit: Asymmetric Ratios for Outcome-Supervised RL

Reference 32

Resolution: verified exact; local_arxiv, observed 2026-05-21T05:59:41.078831Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-19T06:30:13.599613+00:00.

Observation b91137a3-0dbd-4d08-a95c-7173221044fe · inbound

Clipping Bottleneck: Stabilizing RLVR via Stochastic Recovery of Near-Boundary Signals cites this paper.

Clipping Bottleneck: Stabilizing RLVR via Stochastic Recovery of Near-Boundary Signals When Importance Sampling Misallocates Credit: Asymmetric Ratios for Outcome-Supervised RL

Reference 20

Resolution: verified exact; local_arxiv, observed 2026-05-22T07:51:15.747619Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-19T06:30:13.599613+00:00.

Observation 3b91f462-e27a-453a-9667-af6f74dc20a1 · inbound

EAPO: Entropy-Driven Adaptive Positive-Negative Sample Weighting for Policy Optimization in Open-Ended QA cites this paper.

EAPO: Entropy-Driven Adaptive Positive-Negative Sample Weighting for Policy Optimization in Open-Ended QA When Importance Sampling Misallocates Credit: Asymmetric Ratios for Outcome-Supervised RL

Reference 15

Resolution: metadata mismatch; local_arxiv, observed 2026-06-29T13:03:26.321365Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-19T06:30:13.599613+00:00.

Observation b10ce576-b196-4b3a-9133-3de48ddd63f7 · inbound

When RL Fails after SFT: Rejuvenating Model Plasticity for Robust SFT-to-RL Handoff cites this paper.

When RL Fails after SFT: Rejuvenating Model Plasticity for Robust SFT-to-RL Handoff When Importance Sampling Misallocates Credit: Asymmetric Ratios for Outcome-Supervised RL

Reference 105

Resolution: metadata mismatch; local_arxiv, observed 2026-07-02T22:27:26.474701Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-19T06:30:13.599613+00:00.

Observation f62037ce-208b-412f-8689-8761caf75da3 · inbound

UP: Unbounded Positive Asymmetric Optimization for Breaking the Exploration-Stability Dilemma cites this paper.

UP: Unbounded Positive Asymmetric Optimization for Breaking the Exploration-Stability Dilemma When Importance Sampling Misallocates Credit: Asymmetric Ratios for Outcome-Supervised RL

Reference 33

Resolution: verified exact; local_arxiv, observed 2026-07-09T22:26:37.218159Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-19T06:30:13.599613+00:00.