Paper Citation Record · LEDGER

On-Policy RL with Optimal Reward Baseline

As of 19 August 2026, this Paper Citation Record lists 15 of 15 outbound references and 12 inbound Pith citation observations for arXiv:2505.23585.

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

pith.paper-citation-record.v1
2505.23585 v2

Coverage vector

measured 15 of 15 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-07T12:46:50.980711Z

measured 27 of 27 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-19T06:32:44.657259+00:00

measured 12 of 12 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-06T14:07:10.581791Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-07-04T07:59:40.759572Z

Reference resolution

15 of 15 outbound references displayed

verified exact0
verified fuzzy3
unresolved12
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 2dcd3541-28e0-4613-beeb-c5457c7d466b · outbound

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

On-Policy RL with Optimal Reward Baseline DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-07T12:46:49.967939Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2e642235-367e-4ce6-96e0-6e50fc2734c9 · outbound

This paper cites Approximately optimal approximate reinforcement learning.

On-Policy RL with Optimal Reward Baseline Approximately optimal approximate reinforcement learning

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T12:46:51.636308Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 19022d9d-dd2a-46a8-b3ea-bad1333745d1 · outbound

This paper cites DeepSeek-V3 Technical Report.

On-Policy RL with Optimal Reward Baseline DeepSeek-V3 Technical Report

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-07T12:46:50.292119Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5bb3f326-21a2-4b99-bbd4-319545fc2b19 · outbound

This paper cites American invitational mathematics examination - aime.

On-Policy RL with Optimal Reward Baseline American invitational mathematics examination - aime

Reference 8

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T12:46:51.488207Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation d49e6d92-b1f3-46eb-8e7b-fd09ebf946af · outbound

This paper cites GPT-4 Technical Report.

On-Policy RL with Optimal Reward Baseline GPT-4 Technical Report

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-07T12:46:50.477043Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bf99ce1d-558d-41a9-be08-e083b247bb7c · outbound

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

On-Policy RL with Optimal Reward Baseline HybridFlow: A Flexible and Efficient RLHF Framework

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-07T12:46:50.703608Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c5fc5994-bdba-4e76-ba57-475127ed913e · outbound

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

On-Policy RL with Optimal Reward Baseline Kimi k1.5: Scaling Reinforcement Learning with LLMs

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-07T12:46:50.798376Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0f4e0d30-1fee-407c-b9f1-0db0ecc45304 · outbound

This paper cites Qwen3 Technical Report.

On-Policy RL with Optimal Reward Baseline Qwen3 Technical Report

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-07T12:46:50.980711Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 24f923a4-be90-4d91-9fbb-4fed684d2973 · outbound

This paper cites Neural text generation with unlikelihood training.

On-Policy RL with Optimal Reward Baseline Neural text generation with unlikelihood training

Reference 1992

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T12:46:51.316058Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation c3930687-7926-4244-a3bb-9abbaa758984 · outbound

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

On-Policy RL with Optimal Reward Baseline DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models

Reference 2017

Resolution: unresolved; no resolver link, observed 2026-08-07T12:46:50.635625Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a37069ee-a91e-4bf0-8578-d051882fec5f · outbound

This paper cites Proximal Policy Optimization Algorithms.

On-Policy RL with Optimal Reward Baseline Proximal Policy Optimization Algorithms

Reference 2020

Resolution: unresolved; no resolver link, observed 2026-08-07T12:46:50.540130Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 956640e0-8b55-45e4-96bf-058de5bdc983 · outbound

This paper cites Gemini: A Family of Highly Capable Multimodal Models.

On-Policy RL with Optimal Reward Baseline Gemini: A Family of Highly Capable Multimodal Models

Reference 2021

Resolution: unresolved; no resolver link, observed 2026-08-07T12:46:49.833777Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c10971a2-1dd0-4e53-b562-bd4a54572573 · outbound

This paper cites Language models are few-shot learners.Advances in neural information processing systems, 33:1877–1901,.

On-Policy RL with Optimal Reward Baseline Language models are few-shot learners.Advances in neural information processing systems, 33:1877–1901,

Reference 2022

Resolution: unresolved; no resolver link, observed 2026-08-07T12:46:49.876159Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation afc7fb7b-9b0f-46ce-9d99-f4240d1b0608 · outbound

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

On-Policy RL with Optimal Reward Baseline Understanding R1-Zero-Like Training: A Critical Perspective

Reference 2024

Resolution: unresolved; no resolver link, observed 2026-08-07T12:46:50.225237Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 370b104d-8aa6-45cb-a7fc-fc06aed6c4b3 · outbound

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

On-Policy RL with Optimal Reward Baseline REINFORCE++: Stabilizing Critic-Free Policy Optimization with Global Advantage Normalization

Reference 2025

Resolution: unresolved; no resolver link, observed 2026-08-07T12:46:50.044130Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation 2734aa74-a458-4f4d-93c9-0945d4426584 · inbound

UloRL:An Ultra-Long Output Reinforcement Learning Approach for Advancing Large Language Models' Reasoning Abilities cites this paper.

UloRL:An Ultra-Long Output Reinforcement Learning Approach for Advancing Large Language Models' Reasoning Abilities On-Policy RL with Optimal Reward Baseline

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-06T14:07:10.581791Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8793b3f4-1be9-4745-a4f2-e769ce5826b0 · inbound

Rethinking Entropy Interventions in RLVR: An Entropy Change Perspective cites this paper.

Rethinking Entropy Interventions in RLVR: An Entropy Change Perspective On-Policy RL with Optimal Reward Baseline

Reference 6

Resolution: verified exact; arxiv_id, observed 2026-05-18T07:41:03.216079Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 9db8ea4c-ef83-401e-a53e-06dc3fb98d35 · inbound

Policy Improvement Reinforcement Learning cites this paper.

Policy Improvement Reinforcement Learning On-Policy RL with Optimal Reward Baseline

Reference 17

Resolution: verified exact; arxiv_id, observed 2026-05-13T22:48:22.858481Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 0d264321-b1b6-4599-8e4a-c783024c61a8 · inbound

Kernelized Advantage Estimation: From Nonparametric Statistics to LLM Reasoning cites this paper.

Kernelized Advantage Estimation: From Nonparametric Statistics to LLM Reasoning On-Policy RL with Optimal Reward Baseline

Reference 8

Resolution: verified exact; arxiv_id, observed 2026-05-12T10:16:27.278990Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 752d6683-b8cb-479f-b559-908239a3875c · inbound

Kernelized Advantage Estimation: From Nonparametric Statistics to LLM Reasoning cites this paper.

Kernelized Advantage Estimation: From Nonparametric Statistics to LLM Reasoning On-Policy RL with Optimal Reward Baseline

Reference 8

Resolution: verified exact; arxiv_id, observed 2026-05-20T23:49:14.929225Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 32df8d68-545c-4bb8-aee5-2a2c4803d5fa · inbound

Beyond Uniform Credit Assignment: Selective Eligibility Traces for RLVR cites this paper.

Beyond Uniform Credit Assignment: Selective Eligibility Traces for RLVR On-Policy RL with Optimal Reward Baseline

Reference 23

Resolution: verified exact; arxiv_id, observed 2026-05-11T16:36:10.479798Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation bb1413e4-7d89-463c-8777-db47a92cb050 · inbound

Understanding and Preventing Entropy Collapse in RLVR with On-Policy Entropy Flow Optimization cites this paper.

Understanding and Preventing Entropy Collapse in RLVR with On-Policy Entropy Flow Optimization On-Policy RL with Optimal Reward Baseline

Reference 41

Resolution: verified exact; arxiv_id, observed 2026-05-13T01:42:02.898305Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 65121ee2-c018-4af9-8868-4743fd40aca8 · inbound

Holder Policy Optimisation cites this paper.

Holder Policy Optimisation On-Policy RL with Optimal Reward Baseline

Reference 52

Resolution: verified exact; arxiv_id, observed 2026-05-13T06:12:22.799052Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 6d678c24-3e73-4b0a-95e6-a526d8b673f7 · inbound

Holder Policy Optimisation cites this paper.

Holder Policy Optimisation On-Policy RL with Optimal Reward Baseline

Reference 52

Resolution: verified exact; arxiv_id, observed 2026-05-22T10:01:23.127974Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 7d1f1c99-71d2-4524-900f-75fea0fce1c7 · inbound

Keep Policy Gradient in Charge: Sibling-Guided Credit Distillation for Long-Horizon Tool-Use Agents cites this paper.

Keep Policy Gradient in Charge: Sibling-Guided Credit Distillation for Long-Horizon Tool-Use Agents On-Policy RL with Optimal Reward Baseline

Reference 17

Resolution: verified exact; arxiv_id, observed 2026-07-03T09:07:48.294529Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 7fb79ea2-5234-42bd-9488-99fc41b2e7a0 · inbound

Keep Policy Gradient in Charge: Sibling-Guided Credit Distillation for Long-Horizon Tool-Use Agents cites this paper.

Keep Policy Gradient in Charge: Sibling-Guided Credit Distillation for Long-Horizon Tool-Use Agents On-Policy RL with Optimal Reward Baseline

Reference 16

Resolution: verified exact; arxiv_id, observed 2026-07-01T07:55:31.197198Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation feac46a2-371a-4fc9-8797-50a800d304e6 · inbound

Modularized Reinforcement Learning on LLMs: From MDP Creation to Exploration and Learning cites this paper.

Modularized Reinforcement Learning on LLMs: From MDP Creation to Exploration and Learning On-Policy RL with Optimal Reward Baseline

Reference 65

Resolution: verified exact; arxiv_id, observed 2026-07-04T07:59:40.760859Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.