Paper Citation Record · LEDGER

When RLVR Shrinks the Reasoning Boundary: Diagnosing Pass@k Inversion

As of 22 August 2026, this Paper Citation Record lists 23 of 23 outbound references and 0 inbound Pith citation observations for arXiv:2607.20543.

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

pith.paper-citation-record.v1
2607.20543 v1

Coverage vector

measured 23 of 23 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-02T07:14:53.084480Z

measured 23 of 23 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-22T06:32:14.747728+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

23 of 23 outbound references displayed

verified exact0
verified fuzzy0
unresolved23
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation d4a1d0e2-fa81-418a-a580-9e9cd53aefda · outbound

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

When RLVR Shrinks the Reasoning Boundary: Diagnosing Pass@k Inversion Back to Basics: Revisiting REINFORCE Style Optimization for Learning from Human Feedback in LLMs

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-02T07:14:52.962418Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ab93d74a-9181-4856-9c4d-24c6a3300412 · outbound

This paper cites Evaluating Large Language Models Trained on Code.

When RLVR Shrinks the Reasoning Boundary: Diagnosing Pass@k Inversion Evaluating Large Language Models Trained on Code

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-02T07:14:52.968359Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bacf7d46-6f06-4ecf-8be7-69c1a5f7eb4d · outbound

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

When RLVR Shrinks the Reasoning Boundary: Diagnosing Pass@k Inversion The Entropy Mechanism of Reinforcement Learning for Reasoning Language Models

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-02T07:14:52.974227Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c4263efc-e780-4a88-91e7-e55119155782 · outbound

This paper cites Omni-MATH: A Universal Olympiad Level Mathematic Benchmark For Large Language Models.

When RLVR Shrinks the Reasoning Boundary: Diagnosing Pass@k Inversion Omni-MATH: A Universal Olympiad Level Mathematic Benchmark For Large Language Models

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-02T07:14:52.979212Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f381000e-02f5-4e38-8cfe-d9ce89303776 · outbound

This paper cites Soft actor- critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor.

When RLVR Shrinks the Reasoning Boundary: Diagnosing Pass@k Inversion Soft actor- critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-02T07:14:52.984929Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4adbbb55-7d08-476c-bbd5-bc638c57dcb5 · outbound

This paper cites Measuring Mathematical Problem Solving With the MATH Dataset.

When RLVR Shrinks the Reasoning Boundary: Diagnosing Pass@k Inversion Measuring Mathematical Problem Solving With the MATH Dataset

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-02T07:14:52.991147Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c438dce3-e397-4c15-a545-0243ad685036 · outbound

This paper cites REINFORCE++: Stabilizing Critic-Free Policy Optimization with Global Advantage Normalization.

When RLVR Shrinks the Reasoning Boundary: Diagnosing Pass@k Inversion REINFORCE++: Stabilizing Critic-Free Policy Optimization with Global Advantage Normalization

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-02T07:14:52.997903Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4d2689a0-509a-4c1f-98de-03ca1e3d9ba6 · outbound

This paper cites Reinforcement learning with KL penalties is better viewed as Bayesian inference.

When RLVR Shrinks the Reasoning Boundary: Diagnosing Pass@k Inversion Reinforcement learning with KL penalties is better viewed as Bayesian inference

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-02T07:14:53.003685Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c9b5b5ab-3351-4b8e-8e77-36f226585886 · outbound

This paper cites Conservative Q- learning for offline reinforcement learning.

When RLVR Shrinks the Reasoning Boundary: Diagnosing Pass@k Inversion Conservative Q- learning for offline reinforcement learning

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-02T07:14:53.008634Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 21403e57-5303-457e-920f-67a325d5f2b3 · outbound

This paper cites Tulu 3: Pushing Frontiers in Open Language Model Post-Training.

When RLVR Shrinks the Reasoning Boundary: Diagnosing Pass@k Inversion Tulu 3: Pushing Frontiers in Open Language Model Post-Training

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-02T07:14:53.014639Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation caa5c229-72ee-42f7-9314-b035d470078f · outbound

This paper cites ReMax: A Simple, Effective, and Efficient Reinforcement Learning Method for Aligning Large Language Models.

When RLVR Shrinks the Reasoning Boundary: Diagnosing Pass@k Inversion ReMax: A Simple, Effective, and Efficient Reinforcement Learning Method for Aligning Large Language Models

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-02T07:14:53.020270Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5a284f46-fa53-43e6-a885-84592237f648 · outbound

This paper cites Let's Verify Step by Step.

When RLVR Shrinks the Reasoning Boundary: Diagnosing Pass@k Inversion Let's Verify Step by Step

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-02T07:14:53.025574Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4df64507-abac-4e22-a073-fc1f704e22fb · outbound

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

When RLVR Shrinks the Reasoning Boundary: Diagnosing Pass@k Inversion Understanding R1-Zero-Like Training: A Critical Perspective

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-02T07:14:53.031461Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5dc83e24-01f4-4a0b-802b-6a0595fbe205 · outbound

This paper cites Manning, and Chelsea Finn.

When RLVR Shrinks the Reasoning Boundary: Diagnosing Pass@k Inversion Manning, and Chelsea Finn

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-02T07:14:53.037122Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 86fb70e2-15d2-4099-ac17-d04c00ab3f38 · outbound

This paper cites Vanishing gradients in reinforcement finetuning.

When RLVR Shrinks the Reasoning Boundary: Diagnosing Pass@k Inversion Vanishing gradients in reinforcement finetuning

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-02T07:14:53.041847Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7f1678a4-98ae-45fc-babc-2415442f5739 · outbound

This paper cites Proximal Policy Optimization Algorithms.

When RLVR Shrinks the Reasoning Boundary: Diagnosing Pass@k Inversion Proximal Policy Optimization Algorithms

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-02T07:14:53.046758Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ea90215b-1e69-4660-a087-aa37df089232 · outbound

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

When RLVR Shrinks the Reasoning Boundary: Diagnosing Pass@k Inversion DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-02T07:14:53.052186Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a47a8065-aa39-41cf-b2de-f2fa2ed0dc2d · outbound

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

When RLVR Shrinks the Reasoning Boundary: Diagnosing Pass@k Inversion HybridFlow: A Flexible and Efficient RLHF Framework

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-02T07:14:53.058307Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 968ff127-977e-4155-87ca-a1faf74458a4 · outbound

This paper cites Qwen2.5 Technical Report.

When RLVR Shrinks the Reasoning Boundary: Diagnosing Pass@k Inversion Qwen2.5 Technical Report

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-02T07:14:53.063364Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 91e01598-9ac0-470e-b5e6-3681d2c157b6 · outbound

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

When RLVR Shrinks the Reasoning Boundary: Diagnosing Pass@k Inversion DAPO: An Open-Source LLM Reinforcement Learning System at Scale

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-02T07:14:53.068293Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a0b8fd97-5e54-4efc-9280-b1c8ed3769a4 · outbound

This paper cites Understanding diversity collapse in RLVR via the lens of over- training.arXiv:2606.15455, 2026.

When RLVR Shrinks the Reasoning Boundary: Diagnosing Pass@k Inversion Understanding diversity collapse in RLVR via the lens of over- training.arXiv:2606.15455, 2026

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-02T07:14:53.074193Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b25c59c6-96e1-4bca-b08a-cfe6eda755dc · outbound

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

When RLVR Shrinks the Reasoning Boundary: Diagnosing Pass@k Inversion Does Reinforcement Learning Really Incentivize Reasoning Capacity in LLMs Beyond the Base Model?

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-02T07:14:53.079341Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fa86c831-0274-4832-9eba-19bc8f4e8c0e · outbound

This paper cites Echo Chamber: RL Post-training Amplifies Behaviors Learned in Pretraining.

When RLVR Shrinks the Reasoning Boundary: Diagnosing Pass@k Inversion Echo Chamber: RL Post-training Amplifies Behaviors Learned in Pretraining

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-02T07:14:53.084480Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

No inbound Pith citation observations are available.