Paper Citation Record · LEDGER

One-Way Policy Optimization for Self-Evolving LLMs

As of 5 August 2026, this Paper Citation Record lists 21 of 21 outbound references and 1 inbound Pith citation observation for arXiv:2605.22156.

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

pith.paper-citation-record.v1
2605.22156 v1

Coverage vector

measured 21 of 21 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-05-22T08:01:05.911650Z

measured 22 of 22 standing notices

One-hop event checks from named stored sources.

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

measured 1 of 1 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-02T07:23:30.215870Z

measured 0 of 1 external citation measurements

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

Source: cited_works

Reference resolution

21 of 21 outbound references displayed

verified exact19
verified fuzzy0
unresolved0
parse uncertain0
malformed identifier1
metadata mismatch1

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 44906f4b-b4bc-4132-b2a4-7acccd1d3ac0 · outbound

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

One-Way Policy Optimization for Self-Evolving LLMs MiniMax-M1: Scaling Test-Time Compute Efficiently with Lightning Attention

Reference 1

Resolution: verified exact; local_arxiv, observed 2026-05-22T08:01:15.588609Z

Source-reported events for the cited work

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

Observation d9315f31-6061-459b-b04f-c92e4489b73b · outbound

This paper cites Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities.

One-Way Policy Optimization for Self-Evolving LLMs Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities

Reference 2

Resolution: verified exact; local_arxiv, observed 2026-05-22T08:01:15.504835Z

Source-reported events for the cited work

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

Observation d3ec8921-d40b-4556-8241-8312b01460a5 · outbound

This paper cites Reinforced Self-Training (ReST) for Language Modeling.

One-Way Policy Optimization for Self-Evolving LLMs Reinforced Self-Training (ReST) for Language Modeling

Reference 3

Resolution: metadata mismatch; local_arxiv, observed 2026-05-22T08:01:15.500354Z

Source-reported events for the cited work

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

Observation d87eb0ca-b935-41bc-b11c-5effbd7a2150 · outbound

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

One-Way Policy Optimization for Self-Evolving LLMs DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning

Reference 4

Resolution: verified exact; local_arxiv, observed 2026-05-22T08:01:15.532477Z

Source-reported events for the cited work

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

Observation 838b9c2f-661a-4e92-b41e-787ffd25f5aa · outbound

This paper cites A sober look at progress in language model reasoning: Pitfalls and paths to repro- ducibility.arXiv preprint arXiv:2504.07086.

One-Way Policy Optimization for Self-Evolving LLMs A sober look at progress in language model reasoning: Pitfalls and paths to repro- ducibility.arXiv preprint arXiv:2504.07086

Reference 5

Resolution: verified exact; arxiv_id, observed 2026-05-22T08:01:15.496215Z

Source-reported events for the cited work

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

Observation a1765dc9-b917-4675-bccc-74c6cc5f96e3 · outbound

This paper cites On the direction of rlvr updates for llm reasoning: Identification and exploitation.

One-Way Policy Optimization for Self-Evolving LLMs On the direction of rlvr updates for llm reasoning: Identification and exploitation

Reference 6

Resolution: verified exact; arxiv_id, observed 2026-05-22T08:01:15.487068Z

Source-reported events for the cited work

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

Observation 86465566-b956-45ce-89f9-5f4a0b3e4965 · outbound

This paper cites Qwen2.5-Coder Technical Report.

One-Way Policy Optimization for Self-Evolving LLMs Qwen2.5-Coder Technical Report

Reference 7

Resolution: verified exact; local_arxiv, observed 2026-05-22T08:01:15.559609Z

Source-reported events for the cited work

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

Observation b755f437-3838-4efd-b328-b6a832c6c774 · outbound

This paper cites OpenAI o1 System Card.

One-Way Policy Optimization for Self-Evolving LLMs OpenAI o1 System Card

Reference 8

Resolution: verified exact; local_arxiv, observed 2026-05-22T08:01:15.491515Z

Source-reported events for the cited work

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

Observation e7c4a0ce-b494-4da4-b36a-755779ab3bd0 · outbound

This paper cites On-policy distillation.Thinking Machines Lab: Con- nectionism.

One-Way Policy Optimization for Self-Evolving LLMs On-policy distillation.Thinking Machines Lab: Con- nectionism

Reference 9

Resolution: verified exact; doi, observed 2026-05-22T08:01:15.044250Z

Source-reported events for the cited work

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

Observation 9554dc8e-6f30-4035-a952-7b05cd74a3ba · outbound

This paper cites Fipo: Eliciting deep reasoning with future-kl influenced policy optimization.

One-Way Policy Optimization for Self-Evolving LLMs Fipo: Eliciting deep reasoning with future-kl influenced policy optimization

Reference 10

Resolution: verified exact; arxiv_id, observed 2026-05-22T08:01:15.541515Z

Source-reported events for the cited work

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

Observation d09a2380-f0d0-4713-ae77-44f835805bdd · outbound

This paper cites Sparse but critical: A token-level analysis of distributional shifts in rlvr fine-tuning of llms.

One-Way Policy Optimization for Self-Evolving LLMs Sparse but critical: A token-level analysis of distributional shifts in rlvr fine-tuning of llms

Reference 11

Resolution: verified exact; arxiv_id, observed 2026-05-22T08:01:15.519492Z

Source-reported events for the cited work

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

Observation 6f27696a-61bc-4463-8705-cf33591c635b · outbound

This paper cites Proximal Policy Optimization Algorithms.

One-Way Policy Optimization for Self-Evolving LLMs Proximal Policy Optimization Algorithms

Reference 12

Resolution: verified exact; local_arxiv, observed 2026-05-22T08:01:15.554340Z

Source-reported events for the cited work

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

Observation 5f32f5c9-9b31-4470-8148-6501ad6412ca · outbound

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

One-Way Policy Optimization for Self-Evolving LLMs DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models

Reference 13

Resolution: verified exact; local_arxiv, observed 2026-05-22T08:01:15.523399Z

Source-reported events for the cited work

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

Observation 07623a88-bd20-4eef-8c06-94a642055627 · outbound

This paper cites Kimi K2: Open Agentic Intelligence.

One-Way Policy Optimization for Self-Evolving LLMs Kimi K2: Open Agentic Intelligence

Reference 14

Resolution: verified exact; local_arxiv, observed 2026-05-22T08:01:15.545821Z

Source-reported events for the cited work

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

Observation 657bde64-5f1e-40e0-be6b-cb2fb25d9541 · outbound

This paper cites MiMo-V2-Flash Technical Report.

One-Way Policy Optimization for Self-Evolving LLMs MiMo-V2-Flash Technical Report

Reference 15

Resolution: verified exact; local_arxiv, observed 2026-05-22T08:01:15.513978Z

Source-reported events for the cited work

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

Observation b3a484d2-b832-4b9e-baa0-f76a8cebdf82 · outbound

This paper cites KDRL: Post-Training Reasoning LLMs via Unified Knowledge Distillation and Reinforcement Learning.

One-Way Policy Optimization for Self-Evolving LLMs KDRL: Post-Training Reasoning LLMs via Unified Knowledge Distillation and Reinforcement Learning

Reference 16

Resolution: verified exact; arxiv_id, observed 2026-05-22T08:01:15.509689Z

Source-reported events for the cited work

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

Observation a5e60214-0376-4e5e-a286-0c3200dd1fce · outbound

This paper cites Qwen2.5-Math Technical Report: Toward Mathematical Expert Model via Self-Improvement.

One-Way Policy Optimization for Self-Evolving LLMs Qwen2.5-Math Technical Report: Toward Mathematical Expert Model via Self-Improvement

Reference 17

Resolution: verified exact; local_arxiv, observed 2026-05-22T08:01:15.536711Z

Source-reported events for the cited work

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

Observation 3d9a9f6e-4919-4b1c-8675-77baf533b850 · outbound

This paper cites Qwen3 Technical Report.

One-Way Policy Optimization for Self-Evolving LLMs Qwen3 Technical Report

Reference 18

Resolution: verified exact; local_arxiv, observed 2026-05-22T08:01:15.582276Z

Source-reported events for the cited work

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

Observation e4eb10b9-7510-470a-8ac1-d280943eb846 · outbound

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

One-Way Policy Optimization for Self-Evolving LLMs DAPO: An Open-Source LLM Reinforcement Learning System at Scale

Reference 19

Resolution: verified exact; local_arxiv, observed 2026-05-22T08:01:15.527668Z

Source-reported events for the cited work

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

Observation e90d2e06-902c-4836-b0ff-8ea552de5d1c · outbound

This paper cites Group Sequence Policy Optimization.

One-Way Policy Optimization for Self-Evolving LLMs Group Sequence Policy Optimization

Reference 20

Resolution: verified exact; local_arxiv, observed 2026-05-22T08:01:15.592991Z

Source-reported events for the cited work

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

Observation 9fa3fdf8-75ef-443a-a160-cd62699f2212 · outbound

This paper cites For the training dataset, we utilize dapo-math-17kacross all main experiments.

One-Way Policy Optimization for Self-Evolving LLMs For the training dataset, we utilize dapo-math-17kacross all main experiments

Reference 21

Resolution: malformed identifier; arxiv_id, observed 2026-05-22T08:01:15.549942Z

Source-reported events for the cited work

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

Pith citing papers

Observation 9b5031bc-8e80-4294-bedd-c73a5983a727 · inbound

ARMOR: Stabilizing On-Policy LLM RL with Off-Policy Anchor Samples cites this paper.

ARMOR: Stabilizing On-Policy LLM RL with Off-Policy Anchor Samples One-Way Policy Optimization for Self-Evolving LLMs

Reference 62

Resolution: unresolved; no resolver link, observed 2026-08-02T07:23:30.215870Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.