Paper Citation Record · LEDGER

Mismatch Matters: On-Policy Distillation Beyond Token Agreement

As of 19 August 2026, this Paper Citation Record lists 31 of 31 outbound references and 0 inbound Pith citation observations for arXiv:2608.09836.

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

pith.paper-citation-record.v1
2608.09836 v1

Coverage vector

measured 31 of 31 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-11T05:51:08.345336Z

measured 31 of 31 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-18T06:34:40.430872+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

31 of 31 outbound references displayed

verified exact2
verified fuzzy5
unresolved23
parse uncertain0
malformed identifier1
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 4a285c96-4459-4750-9cd0-c10263ce4091 · outbound

This paper cites On-policy distillation of language models: Learning from self- generated mistakes.

Mismatch Matters: On-Policy Distillation Beyond Token Agreement On-policy distillation of language models: Learning from self- generated mistakes

Reference 1

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T05:51:09.647925Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 6cca286c-a5e5-4271-8fdf-62a12dc97635 · outbound

This paper cites Thus, the value ofωat which resonance occurs is2.

Mismatch Matters: On-Policy Distillation Beyond Token Agreement Thus, the value ofωat which resonance occurs is2

Reference 2

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T05:51:09.519997Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 75bc87cc-932b-47d2-9621-0654c9444156 · outbound

This paper cites Asymmetric On-Policy Distillation: Bridging Exploitation and Imitation at the Token Level.

Mismatch Matters: On-Policy Distillation Beyond Token Agreement Asymmetric On-Policy Distillation: Bridging Exploitation and Imitation at the Token Level

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-11T05:51:08.089540Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 455550fd-7372-4dd5-9935-60e2964d1fdc · outbound

This paper cites Rethinking on-policy self-distillation for thinking models.

Mismatch Matters: On-Policy Distillation Beyond Token Agreement Rethinking on-policy self-distillation for thinking models

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T05:51:09.618081Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation f1b484ce-64ad-4359-aa23-2a1c1621c1b0 · outbound

This paper cites Respecting Self-Uncertainty in On-Policy Self-Distillation for Efficient LLM Reasoning.

Mismatch Matters: On-Policy Distillation Beyond Token Agreement Respecting Self-Uncertainty in On-Policy Self-Distillation for Efficient LLM Reasoning

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-11T05:51:08.115933Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2f822c1f-fcc8-4982-ad77-7bb3bbde8024 · outbound

This paper cites Scaling reasoning efficiently via relaxed on-policy distillation.arXiv preprint arXiv:2603.11137,.

Mismatch Matters: On-Policy Distillation Beyond Token Agreement Scaling reasoning efficiently via relaxed on-policy distillation.arXiv preprint arXiv:2603.11137,

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-11T05:51:08.125373Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7ae8cd34-f023-46e2-b316-f29eeefae6a2 · outbound

This paper cites Rethinking On-Policy Distillation of Large Language Models: Phenomenology, Mechanism, and Recipe.

Mismatch Matters: On-Policy Distillation Beyond Token Agreement Rethinking On-Policy Distillation of Large Language Models: Phenomenology, Mechanism, and Recipe

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-11T05:51:08.134433Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c92bd30d-e5f0-44c4-b746-ece8326b6aa3 · outbound

This paper cites Teacher-Guided Policy Optimization for On-Policy Reasoning Distillation under Large Policy Divergence.

Mismatch Matters: On-Policy Distillation Beyond Token Agreement Teacher-Guided Policy Optimization for On-Policy Reasoning Distillation under Large Policy Divergence

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-11T05:51:08.142840Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cecc0ba3-14f5-4fa6-b960-f44e6b9a1f42 · outbound

This paper cites Demystifying OPD: Length Inflation and Stabilization Strategies for Large Language Models.

Mismatch Matters: On-Policy Distillation Beyond Token Agreement Demystifying OPD: Length Inflation and Stabilization Strategies for Large Language Models

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-11T05:51:08.150202Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7149cbe0-c2a0-4c8d-880c-1225c2c12ffe · outbound

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

Mismatch Matters: On-Policy Distillation Beyond Token Agreement HybridFlow: A Flexible and Efficient RLHF Framework

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-11T05:51:08.187057Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 393842cf-cd96-4df2-9507-1bfe0cd745ee · outbound

This paper cites Kimi k3: Open frontier intelligence.arXiv preprint arXiv:2607.24653,.

Mismatch Matters: On-Policy Distillation Beyond Token Agreement Kimi k3: Open frontier intelligence.arXiv preprint arXiv:2607.24653,

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-11T05:51:08.200354Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f870c4cb-5304-47c0-9fd0-0aaf1404c4e7 · outbound

This paper cites Not All Disagreement Is Learnable: Token Teachability in On-Policy Distillation.

Mismatch Matters: On-Policy Distillation Beyond Token Agreement Not All Disagreement Is Learnable: Token Teachability in On-Policy Distillation

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-11T05:51:08.212803Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a78dac6c-aa3f-46f8-839b-841e31dd885b · outbound

This paper cites MiMo-V2-Flash Technical Report.

Mismatch Matters: On-Policy Distillation Beyond Token Agreement MiMo-V2-Flash Technical Report

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-11T05:51:08.223854Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 41878fca-c832-401b-8092-02928c28fb08 · outbound

This paper cites Escaping the KL Agreement Trap in On-Policy Distillation.

Mismatch Matters: On-Policy Distillation Beyond Token Agreement Escaping the KL Agreement Trap in On-Policy Distillation

Reference 19

Resolution: verified exact; local_arxiv, observed 2026-08-11T05:51:08.733913Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 6aeff798-6864-4f7f-b65f-dc12f92c8567 · outbound

This paper cites Trust Region On-Policy Distillation.

Mismatch Matters: On-Policy Distillation Beyond Token Agreement Trust Region On-Policy Distillation

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-11T05:51:08.246583Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7500ed4c-24b3-476b-aee2-aa8493a9ea0e · outbound

This paper cites TIP: Token Importance in On-Policy Distillation.

Mismatch Matters: On-Policy Distillation Beyond Token Agreement TIP: Token Importance in On-Policy Distillation

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-11T05:51:08.253953Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d9ace98e-74d4-4dfe-afed-96d51b694a92 · outbound

This paper cites Qwen3 Technical Report.

Mismatch Matters: On-Policy Distillation Beyond Token Agreement Qwen3 Technical Report

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-11T05:51:08.264825Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4c60f8fe-b1aa-45ca-a74a-714979d12375 · outbound

This paper cites OPRD: On-Policy Representation Distillation.

Mismatch Matters: On-Policy Distillation Beyond Token Agreement OPRD: On-Policy Representation Distillation

Reference 23

Resolution: verified exact; local_arxiv, observed 2026-08-11T05:51:08.569317Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 7704910e-a454-4461-b7f5-41b3b40f9d95 · outbound

This paper cites GLM-5: from Vibe Coding to Agentic Engineering.

Mismatch Matters: On-Policy Distillation Beyond Token Agreement GLM-5: from Vibe Coding to Agentic Engineering

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-11T05:51:08.285450Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a9182e79-4014-4b03-aa6d-9a9c639af9ad · outbound

This paper cites Fast and effective on-policy distillation from reasoning prefixes.

Mismatch Matters: On-Policy Distillation Beyond Token Agreement Fast and effective on-policy distillation from reasoning prefixes

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T05:51:09.586258Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation da7dcbb2-7539-420f-a6f2-0cb13f4b9988 · outbound

This paper cites PowerOPD: Stabilizing On-Policy Distillation with Bounded Power Transformation.

Mismatch Matters: On-Policy Distillation Beyond Token Agreement PowerOPD: Stabilizing On-Policy Distillation with Bounded Power Transformation

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-11T05:51:08.302850Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fd2de4d4-e136-4b87-9485-ebda9c659693 · outbound

This paper cites Using P v ∇θq(v) = 0, we obtain Ev∼q [−h(a(v))∇θ logq(v)] =−2 X v s p(v) q(v) −1 ! ∇θq(v) =−2 X v s p(v) q(v) ∇θq(v) = 4∇θH 2(p, q), which proves Equation (2).

Mismatch Matters: On-Policy Distillation Beyond Token Agreement Using P v ∇θq(v) = 0, we obtain Ev∼q [−h(a(v))∇θ logq(v)] =−2 X v s p(v) q(v) −1 ! ∇θq(v) =−2 X v s p(v) q(v) ∇θq(v) = 4∇θH 2(p, q), which proves Equation (2)

Reference 28

Resolution: malformed identifier; raw_fallback, observed 2026-08-11T05:51:09.547585Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 693d852d-4c53-4388-bfb4-1fb9a7a21696 · outbound

This paper cites an unresolved cited work.

Mismatch Matters: On-Policy Distillation Beyond Token Agreement Unresolved cited work

Reference 30

Resolution: unresolved; raw_fallback, observed 2026-08-11T05:51:09.494679Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 38543c92-bf81-4dc7-aed5-8706073e1e31 · outbound

This paper cites 错” (“wrong.

Mismatch Matters: On-Policy Distillation Beyond Token Agreement 错” (“wrong

Reference 31

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T05:51:09.468455Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 59a5bc8e-5477-43a3-b08c-05cdb77b88a4 · outbound

This paper cites KL for a KL: On-Policy Distillation with Control Variate Baseline.

Mismatch Matters: On-Policy Distillation Beyond Token Agreement KL for a KL: On-Policy Distillation with Control Variate Baseline

Reference 2005

Resolution: unresolved; no resolver link, observed 2026-08-11T05:51:08.156946Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d719fe97-0e18-420b-a77c-ecbeb8d46223 · outbound

This paper cites Proximal Policy Optimization Algorithms.

Mismatch Matters: On-Policy Distillation Beyond Token Agreement Proximal Policy Optimization Algorithms

Reference 2011

Resolution: unresolved; no resolver link, observed 2026-08-11T05:51:08.165637Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b6ad4969-bcd1-4c7a-8696-c1ecb1549ca5 · outbound

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

Mismatch Matters: On-Policy Distillation Beyond Token Agreement DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models

Reference 2017

Resolution: unresolved; no resolver link, observed 2026-08-11T05:51:08.176291Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 45992377-186e-4f4d-84fd-ac90e3fded19 · outbound

This paper cites The Many Faces of On-Policy Distillation: Pitfalls, Mechanisms, and Fixes.

Mismatch Matters: On-Policy Distillation Beyond Token Agreement The Many Faces of On-Policy Distillation: Pitfalls, Mechanisms, and Fixes

Reference 2023

Resolution: unresolved; no resolver link, observed 2026-08-11T05:51:08.310589Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2153ce2d-4de2-4752-8376-2aea46f5c119 · outbound

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

Mismatch Matters: On-Policy Distillation Beyond Token Agreement DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning

Reference 2024

Resolution: unresolved; no resolver link, observed 2026-08-11T05:51:08.073022Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6a3d90a9-e2ad-46ca-ba95-054d87ba26ac · outbound

This paper cites Justrl: Scaling a 1.5 b llm with a simple rl recipe.arXiv preprint arXiv:2512.16649,.

Mismatch Matters: On-Policy Distillation Beyond Token Agreement Justrl: Scaling a 1.5 b llm with a simple rl recipe.arXiv preprint arXiv:2512.16649,

Reference 2025

Resolution: unresolved; no resolver link, observed 2026-08-11T05:51:08.083906Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 73ab0971-eaae-4263-9227-7bc0440ab3c5 · outbound

This paper cites Trajectory-Refined Distillation.

Mismatch Matters: On-Policy Distillation Beyond Token Agreement Trajectory-Refined Distillation

Reference 2026

Resolution: unresolved; no resolver link, observed 2026-08-11T05:51:08.096586Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

No inbound Pith citation observations are available.