Paper Citation Record · LEDGER

Privileged Solutions or Context-Induced Teacher Behavior? Dissecting On-Policy Self-Distillation

As of 15 August 2026, this Paper Citation Record lists 27 of 27 outbound references and 0 inbound Pith citation observations for arXiv:2608.09228.

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

pith.paper-citation-record.v1
2608.09228 v1

Coverage vector

measured 27 of 27 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-11T21:15:10.410698Z

measured 27 of 27 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-15T06:32:42.880941+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

27 of 27 outbound references displayed

verified exact0
verified fuzzy9
unresolved16
parse uncertain0
malformed identifier2
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 289b7133-b041-4fcd-9451-6e1e67894a87 · outbound

This paper cites This intervention removes padding from the boundary between the prompt and response.

Privileged Solutions or Context-Induced Teacher Behavior? Dissecting On-Policy Self-Distillation This intervention removes padding from the boundary between the prompt and response

Reference 1

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T21:15:10.929328Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation a2cf4d47-f515-40fc-8dca-1d81a63d63d0 · outbound

This paper cites Reinforcement Learning via Self-Distillation.

Privileged Solutions or Context-Induced Teacher Behavior? Dissecting On-Policy Self-Distillation Reinforcement Learning via Self-Distillation

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-11T21:15:10.301138Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 913f08a7-c15d-4fee-b888-f3d2ac9641ae · outbound

This paper cites Yoon Kim and Alexander M.

Privileged Solutions or Context-Induced Teacher Behavior? Dissecting On-Policy Self-Distillation Yoon Kim and Alexander M

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T21:15:10.945412Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 93641fc3-d8f0-4cfa-92af-d7a1daac6cae · outbound

This paper cites When Are Teacher Tokens Reliable? Position-Weighted On-Policy Self-Distillation for Reasoning.

Privileged Solutions or Context-Induced Teacher Behavior? Dissecting On-Policy Self-Distillation When Are Teacher Tokens Reliable? Position-Weighted On-Policy Self-Distillation for Reasoning

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-11T21:15:10.320052Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5f1394af-238b-4ce4-9812-d7ab594ad747 · outbound

This paper cites Unifying distillation and privileged information.

Privileged Solutions or Context-Induced Teacher Behavior? Dissecting On-Policy Self-Distillation Unifying distillation and privileged information

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-11T21:15:10.324593Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4b3c1bcd-3bf3-44f0-923a-6763601a7465 · outbound

This paper cites === Unrelated physics Worked Example Solution End === Now solve the target mathematics problem independently.

Privileged Solutions or Context-Induced Teacher Behavior? Dissecting On-Policy Self-Distillation === Unrelated physics Worked Example Solution End === Now solve the target mathematics problem independently

Reference 10

Resolution: malformed identifier; raw_fallback, observed 2026-08-11T21:15:10.858063Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation a49989b8-9b31-4f9c-8a5b-de603543aca6 · outbound

This paper cites Purified OPSD: On-Policy Self-Distillation Without Losing How to Think.

Privileged Solutions or Context-Induced Teacher Behavior? Dissecting On-Policy Self-Distillation Purified OPSD: On-Policy Self-Distillation Without Losing How to Think

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-11T21:15:10.339155Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 215f035b-df78-4d83-9023-82d08f1a45e7 · outbound

This paper cites Self-Distillation Enables Continual Learning.

Privileged Solutions or Context-Induced Teacher Behavior? Dissecting On-Policy Self-Distillation Self-Distillation Enables Continual Learning

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-11T21:15:10.343847Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 65c605b8-ecdb-4f37-8f80-590cb4478592 · outbound

This paper cites Learning by Distilling Context.

Privileged Solutions or Context-Induced Teacher Behavior? Dissecting On-Policy Self-Distillation Learning by Distilling Context

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-11T21:15:10.349346Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 56a760fc-a489-4c2d-9e4c-91e1a30daa99 · outbound

This paper cites Gemma 2: Improving Open Language Models at a Practical Size.

Privileged Solutions or Context-Induced Teacher Behavior? Dissecting On-Policy Self-Distillation Gemma 2: Improving Open Language Models at a Practical Size

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-11T21:15:10.360395Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f8dffb3d-058c-45d7-a677-0d401cf8bcaa · outbound

This paper cites On-Policy Context Distillation for Language Models.

Privileged Solutions or Context-Induced Teacher Behavior? Dissecting On-Policy Self-Distillation On-Policy Context Distillation for Language Models

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-11T21:15:10.370271Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1cad0b44-4162-4ad5-9a32-e7fa5d542e1d · outbound

This paper cites ROSD: Reflective On-Policy Self-Distillation for Language Model Reasoning across Domains.

Privileged Solutions or Context-Induced Teacher Behavior? Dissecting On-Policy Self-Distillation ROSD: Reflective On-Policy Self-Distillation for Language Model Reasoning across Domains

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-11T21:15:10.374470Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 82017f4e-f851-48db-b75a-d1367e38c463 · outbound

This paper cites We evaluate checkpoint 100 with 12 samples per problem and 4 seeds.

Privileged Solutions or Context-Induced Teacher Behavior? Dissecting On-Policy Self-Distillation We evaluate checkpoint 100 with 12 samples per problem and 4 seeds

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T21:15:10.911304Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation e0acbcb2-d916-4147-a91b-0613fac6f896 · outbound

This paper cites The 400- update checkpoint obtains 51.39 Avg@12, a decrease of 3.96 percentage points from the 100-update result.

Privileged Solutions or Context-Induced Teacher Behavior? Dissecting On-Policy Self-Distillation The 400- update checkpoint obtains 51.39 Avg@12, a decrease of 3.96 percentage points from the 100-update result

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T21:15:10.894673Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation ee8a5264-8611-4607-9e65-6262474215a8 · outbound

This paper cites Accuracy metrics are four-seed means in percentages.

Privileged Solutions or Context-Induced Teacher Behavior? Dissecting On-Policy Self-Distillation Accuracy metrics are four-seed means in percentages

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T21:15:10.876799Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 8923c618-04c7-4de5-8085-4037227fe6eb · outbound

This paper cites This result does not isolate which property of the physics context causes the decline.

Privileged Solutions or Context-Induced Teacher Behavior? Dissecting On-Policy Self-Distillation This result does not isolate which property of the physics context causes the decline

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T21:15:10.838957Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 2a3e21ae-e6e8-48f8-858f-f63b60db8495 · outbound

This paper cites an unresolved cited work.

Privileged Solutions or Context-Induced Teacher Behavior? Dissecting On-Policy Self-Distillation Unresolved cited work

Reference 26

Resolution: unresolved; raw_fallback, observed 2026-08-11T21:15:10.822130Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation a878075b-e5a3-41e1-acba-5dc2a1bb4559 · outbound

This paper cites It also matches or exceeds target-solution OPSD on all three benchmarks.

Privileged Solutions or Context-Induced Teacher Behavior? Dissecting On-Policy Self-Distillation It also matches or exceeds target-solution OPSD on all three benchmarks

Reference 27

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T21:15:10.805032Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 07df70a2-eafa-4fd1-b63a-c61c94d92346 · outbound

This paper cites Qwen3 Technical Report.

Privileged Solutions or Context-Induced Teacher Behavior? Dissecting On-Policy Self-Distillation Qwen3 Technical Report

Reference 2009

Resolution: malformed identifier; no resolver link, observed 2026-08-11T21:15:10.365657Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 973a32d7-b7c9-4f0c-bb57-b5dd8aa64301 · outbound

This paper cites Distilling step-by-step! outperforming larger language models with less training data and smaller model sizes.

Privileged Solutions or Context-Induced Teacher Behavior? Dissecting On-Policy Self-Distillation Distilling step-by-step! outperforming larger language models with less training data and smaller model sizes

Reference 2014

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T21:15:10.976532Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 51c3de20-fd9e-43db-9911-ddcfcac2fcbd · outbound

This paper cites Semantic soft bootstrapping: Long context reasoning in llms without reinforcement learning.arXiv preprint arXiv:2512.05105,.

Privileged Solutions or Context-Induced Teacher Behavior? Dissecting On-Policy Self-Distillation Semantic soft bootstrapping: Long context reasoning in llms without reinforcement learning.arXiv preprint arXiv:2512.05105,

Reference 2015

Resolution: unresolved; no resolver link, observed 2026-08-11T21:15:10.329334Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 04ea44fc-ce86-4ab1-983d-6f21bdc734d8 · outbound

This paper cites doi: 10.18653/v1/D16-1139.

Privileged Solutions or Context-Induced Teacher Behavior? Dissecting On-Policy Self-Distillation doi: 10.18653/v1/D16-1139

Reference 2016

Resolution: unresolved; no resolver link, observed 2026-08-11T21:15:10.315535Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cbdf8099-a0f5-4958-b907-30d8f3ff5d34 · outbound

This paper cites Self-Supervised On-Policy Distillation for Reasoning Language Models.

Privileged Solutions or Context-Induced Teacher Behavior? Dissecting On-Policy Self-Distillation Self-Supervised On-Policy Distillation for Reasoning Language Models

Reference 2022

Resolution: unresolved; no resolver link, observed 2026-08-11T21:15:10.355139Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b3271aa9-2334-4dec-957a-860c3b0f2b52 · outbound

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

Privileged Solutions or Context-Induced Teacher Behavior? Dissecting On-Policy Self-Distillation Reinforced Self-Training (ReST) for Language Modeling

Reference 2023

Resolution: unresolved; no resolver link, observed 2026-08-11T21:15:10.291175Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 33f7e73b-fbbc-49df-a72a-74ac66dffd86 · outbound

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

Privileged Solutions or Context-Induced Teacher Behavior? Dissecting On-Policy Self-Distillation Reinforced Self-Training (ReST) for Language Modeling

Reference 2024

Resolution: unresolved; no resolver link, observed 2026-08-11T21:15:10.286057Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c974849f-93cb-4426-bf4e-9ba3419b14f9 · outbound

This paper cites Privileged Information Distillation for Language Models.

Privileged Solutions or Context-Induced Teacher Behavior? Dissecting On-Policy Self-Distillation Privileged Information Distillation for Language Models

Reference 2025

Resolution: unresolved; no resolver link, observed 2026-08-11T21:15:10.334200Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 43963a1e-13a9-4894-bca5-87684ed99c42 · outbound

This paper cites Rethinking On-Policy Self- Distillation for Thinking Models.

Privileged Solutions or Context-Induced Teacher Behavior? Dissecting On-Policy Self-Distillation Rethinking On-Policy Self- Distillation for Thinking Models

Reference 2026

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T21:15:10.961771Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Pith citing papers

No inbound Pith citation observations are available.