Paper Citation Record · LEDGER

ROSD: Reflective On-Policy Self-Distillation for Language Model Reasoning across Domains

As of 7 August 2026, this Paper Citation Record lists 9 of 9 outbound references and 3 inbound Pith citation observations for arXiv:2605.28014.

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

pith.paper-citation-record.v1
2605.28014 v1

Coverage vector

measured 9 of 9 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-06-29T13:04:28.418120Z

measured 12 of 12 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-06T06:34:29.942622+00:00

measured 3 of 3 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-04T22:02:30.513908Z

measured 0 of 1 external citation measurements

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

Source: pith, observed 2026-06-30T07:24:21.975072Z

Reference resolution

9 of 9 outbound references displayed

verified exact1
verified fuzzy0
unresolved4
parse uncertain0
malformed identifier0
metadata mismatch4

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 694fa727-c843-4f24-9b90-031be593f824 · outbound

This paper cites Self-Distillation Zero: Self-Revision Turns Binary Rewards into Dense Supervision.

ROSD: Reflective On-Policy Self-Distillation for Language Model Reasoning across Domains Self-Distillation Zero: Self-Revision Turns Binary Rewards into Dense Supervision

Reference 1

Resolution: metadata mismatch; local_arxiv, observed 2026-06-29T13:13:27.608752Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 33fc5d03-48c0-49bf-ac87-454fd7af2792 · outbound

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

ROSD: Reflective On-Policy Self-Distillation for Language Model Reasoning across Domains Understanding R1-Zero-Like Training: A Critical Perspective

Reference 2

Resolution: metadata mismatch; local_arxiv, observed 2026-06-29T13:13:27.605975Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 757a8a5d-70cb-46ba-a8cb-3b268cb123bb · outbound

This paper cites an unresolved cited work.

ROSD: Reflective On-Policy Self-Distillation for Language Model Reasoning across Domains Unresolved cited work

Reference 3

Resolution: unresolved; no resolver link, observed 2026-06-29T13:04:28.418120Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e583b04d-c8f6-4aa6-b446-f8750df598ba · outbound

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

ROSD: Reflective On-Policy Self-Distillation for Language Model Reasoning across Domains DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models

Reference 4

Resolution: metadata mismatch; local_arxiv, observed 2026-06-29T13:13:27.598454Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation f4896633-0afe-40a4-85b8-5d790a753626 · outbound

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

ROSD: Reflective On-Policy Self-Distillation for Language Model Reasoning across Domains Kimi k1.5: Scaling Reinforcement Learning with LLMs

Reference 5

Resolution: verified exact; local_arxiv, observed 2026-06-29T13:13:27.600926Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 07462d50-c2ce-4b3a-9c40-c63d1c7c4cd1 · outbound

This paper cites Qwen3 Technical Report.

ROSD: Reflective On-Policy Self-Distillation for Language Model Reasoning across Domains Qwen3 Technical Report

Reference 6

Resolution: metadata mismatch; local_arxiv, observed 2026-06-29T13:13:27.603192Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation df8451af-bf00-43f1-a93c-0c814ed66c77 · outbound

This paper cites We train for 10 epochs on the science question-answering tasks and 5 epochs on the ToolUse task, using a training batch size of.

ROSD: Reflective On-Policy Self-Distillation for Language Model Reasoning across Domains We train for 10 epochs on the science question-answering tasks and 5 epochs on the ToolUse task, using a training batch size of

Reference 7

Resolution: unresolved; no resolver link, observed 2026-06-29T13:04:28.418120Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b6d584bb-b163-4f66-980e-b89179123d6f · outbound

This paper cites All algorithms are eval- uated every 10 training steps.

ROSD: Reflective On-Policy Self-Distillation for Language Model Reasoning across Domains All algorithms are eval- uated every 10 training steps

Reference 8

Resolution: unresolved; no resolver link, observed 2026-06-29T13:04:28.418120Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a56641b6-f4fb-46fd-b6e2-b7a47ffb13ba · outbound

This paper cites Given a question and four options, please select the right answer.

ROSD: Reflective On-Policy Self-Distillation for Language Model Reasoning across Domains Given a question and four options, please select the right answer

Reference 9

Resolution: unresolved; no resolver link, observed 2026-06-29T13:04:28.418120Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation c0065342-62a5-46b4-9a64-867016beeb23 · inbound

UCOB: Learning to Utilize and Evolve Agentic Skills via Credit-Aware On-Policy Bidirectional Self-Distillation cites this paper.

UCOB: Learning to Utilize and Evolve Agentic Skills via Credit-Aware On-Policy Bidirectional Self-Distillation ROSD: Reflective On-Policy Self-Distillation for Language Model Reasoning across Domains

Reference 32

Resolution: metadata mismatch; local_arxiv, observed 2026-06-30T07:24:21.976321Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation aae79c50-4483-4cf4-ba8b-7467a79da262 · inbound

Better Starts, Better Ends: Bootstrapped Iterative Self-Reasoning Distillation for Compressed Reasoning cites this paper.

Better Starts, Better Ends: Bootstrapped Iterative Self-Reasoning Distillation for Compressed Reasoning ROSD: Reflective On-Policy Self-Distillation for Language Model Reasoning across Domains

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-01T22:30:30.736777Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 83bc18b7-8f62-4c40-8af9-570efdef245b · inbound

DAPD: Dual-Anchored Policy Distillation cites this paper.

DAPD: Dual-Anchored Policy Distillation ROSD: Reflective On-Policy Self-Distillation for Language Model Reasoning across Domains

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-04T22:02:30.513908Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.