Paper Citation Record · LEDGER

Preference-Based Self-Distillation: Beyond KL Matching via Reward Regularization

As of 4 August 2026, this Paper Citation Record lists 28 of 28 outbound references and 7 inbound Pith citation observations for arXiv:2605.05040.

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

pith.paper-citation-record.v1
2605.05040 v1

Coverage vector

measured 28 of 28 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-05-08T16:22:46.913172Z

measured 35 of 35 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-04T06:34:03.388597+00:00

measured 7 of 7 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-01T13:40:41.757803Z

measured 0 of 1 external citation measurements

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

Source: pith, observed 2026-07-03T16:28:38.434907Z

Reference resolution

28 of 28 outbound references displayed

verified exact20
verified fuzzy4
unresolved1
parse uncertain0
malformed identifier0
metadata mismatch3

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 4474d615-5a35-4844-b49f-9ae84066fe9b · outbound

This paper cites On-Policy Distillation of Language Models for Autonomous Vehicle Motion Planning.

Preference-Based Self-Distillation: Beyond KL Matching via Reward Regularization On-Policy Distillation of Language Models for Autonomous Vehicle Motion Planning

Reference 1

Resolution: verified exact; local_arxiv, observed 2026-05-11T18:16:10.878876Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 630c912b-ad0c-47d1-9028-18a1be8b467e · outbound

This paper cites Jiamu Bai, Xin Yu, Meilong Xu, Weitao Lu, Xin Pan, Kiwan Maeng, Daniel Kifer, Jian Wang, and Yu Wang.

Preference-Based Self-Distillation: Beyond KL Matching via Reward Regularization Jiamu Bai, Xin Yu, Meilong Xu, Weitao Lu, Xin Pan, Kiwan Maeng, Daniel Kifer, Jian Wang, and Yu Wang

Reference 2

Resolution: verified exact; doi, observed 2026-05-08T20:24:09.051021Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 8faf494b-48c4-4a43-bd64-d82676d7a9d2 · outbound

This paper cites OneSearch-V2: The Latent Reasoning Enhanced Self-distillation Generative Search Framework.

Preference-Based Self-Distillation: Beyond KL Matching via Reward Regularization OneSearch-V2: The Latent Reasoning Enhanced Self-distillation Generative Search Framework

Reference 3

Resolution: verified exact; arxiv_id, observed 2026-05-15T01:43:12.126898Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation c0428810-736e-46d0-9b3c-106fd2d52cab · outbound

This paper cites Hdpo: Hybrid distillation policy optimization via privileged self-distillation.

Preference-Based Self-Distillation: Beyond KL Matching via Reward Regularization Hdpo: Hybrid distillation policy optimization via privileged self-distillation

Reference 4

Resolution: verified exact; arxiv_id, observed 2026-05-11T18:16:10.854456Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 8d5f5526-0bc8-43d3-be39-ac30142f40cc · outbound

This paper cites Revisiting On-Policy Distillation: Empirical Failure Modes and Simple Fixes.

Preference-Based Self-Distillation: Beyond KL Matching via Reward Regularization Revisiting On-Policy Distillation: Empirical Failure Modes and Simple Fixes

Reference 5

Resolution: verified exact; local_arxiv, observed 2026-05-11T18:16:10.948921Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation d9515901-543c-4e25-9510-56747c002831 · outbound

This paper cites OpenThoughts: Data Recipes for Reasoning Models.

Preference-Based Self-Distillation: Beyond KL Matching via Reward Regularization OpenThoughts: Data Recipes for Reasoning Models

Reference 6

Resolution: verified exact; arxiv_id, observed 2026-05-12T04:57:51.597669Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation ee7fa4a1-f0ab-488a-9d7f-3c473b5bd133 · outbound

This paper cites PFedDST: Personalized Federated Learning with Decentralized Selection Training.

Preference-Based Self-Distillation: Beyond KL Matching via Reward Regularization PFedDST: Personalized Federated Learning with Decentralized Selection Training

Reference 7

Resolution: metadata mismatch; arxiv_id, observed 2026-05-11T18:16:10.973582Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 567fd72d-d9e7-49f2-a8a3-6d495536ef3d · outbound

This paper cites Reinforcement Learning via Self-Distillation.

Preference-Based Self-Distillation: Beyond KL Matching via Reward Regularization Reinforcement Learning via Self-Distillation

Reference 8

Resolution: verified exact; arxiv_id, observed 2026-05-12T04:29:18.795354Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 9d5a2af6-6dcb-4107-91c3-39c25dac3069 · outbound

This paper cites Why Does Self-Distillation (Sometimes) Degrade the Reasoning Capability of LLMs?.

Preference-Based Self-Distillation: Beyond KL Matching via Reward Regularization Why Does Self-Distillation (Sometimes) Degrade the Reasoning Capability of LLMs?

Reference 9

Resolution: verified exact; local_arxiv, observed 2026-05-11T18:16:10.921197Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation df82730e-31b0-4bb9-8542-16c0a6a29f35 · outbound

This paper cites Unifying group-relative and self-distillation policy optimization via sample routing.

Preference-Based Self-Distillation: Beyond KL Matching via Reward Regularization Unifying group-relative and self-distillation policy optimization via sample routing

Reference 10

Resolution: verified exact; arxiv_id, observed 2026-05-11T18:16:10.828081Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 2d9ae9a9-a5d8-4a79-bb35-f2cc6941ae39 · outbound

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

Preference-Based Self-Distillation: Beyond KL Matching via Reward Regularization On-policy distillation.Thinking Machines Lab: Con- nectionism

Reference 11

Resolution: verified exact; doi, observed 2026-05-08T20:24:09.044640Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 01af755b-8ef8-4f4e-b71c-8b107f072748 · outbound

This paper cites and Ravikumar, Pradeep and Wainwright, Martin J.

Preference-Based Self-Distillation: Beyond KL Matching via Reward Regularization and Ravikumar, Pradeep and Wainwright, Martin J

Reference 12

Resolution: metadata mismatch; doi, observed 2026-05-08T20:24:09.055047Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation c8adf3e0-6aa8-4421-ba5c-f644bfdc0e22 · outbound

This paper cites Online DPO: Online Direct Preference Optimization with Fast-Slow Chasing.

Preference-Based Self-Distillation: Beyond KL Matching via Reward Regularization Online DPO: Online Direct Preference Optimization with Fast-Slow Chasing

Reference 13

Resolution: verified exact; arxiv_id, observed 2026-05-11T18:16:10.962351Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 495db4f8-69f6-4cf1-ac3a-3ae3a45effac · outbound

This paper cites CRISP: Compressed Reasoning via Iterative Self-Policy Distillation.

Preference-Based Self-Distillation: Beyond KL Matching via Reward Regularization CRISP: Compressed Reasoning via Iterative Self-Policy Distillation

Reference 14

Resolution: metadata mismatch; local_arxiv, observed 2026-05-11T18:16:10.996011Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 35a7df0e-6aea-4477-9302-d7e7eda67e84 · outbound

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

Preference-Based Self-Distillation: Beyond KL Matching via Reward Regularization DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models

Reference 15

Resolution: verified exact; local_arxiv, observed 2026-05-11T18:16:10.835642Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 39d5b8f9-faab-425f-989a-5b24af4e0c76 · outbound

This paper cites Self-Distillation Enables Continual Learning.

Preference-Based Self-Distillation: Beyond KL Matching via Reward Regularization Self-Distillation Enables Continual Learning

Reference 16

Resolution: verified exact; arxiv_id, observed 2026-05-12T05:31:52.723793Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 7e0ba19f-1c61-46b8-bfe5-33b9a18640ab · outbound

This paper cites A Survey of On-Policy Distillation for Large Language Models.

Preference-Based Self-Distillation: Beyond KL Matching via Reward Regularization A Survey of On-Policy Distillation for Large Language Models

Reference 17

Resolution: verified exact; arxiv_id, observed 2026-05-13T02:47:19.238105Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 74db5023-b36d-4051-905b-025d7df7ca94 · outbound

This paper cites Skill-SD: Skill-Conditioned Self-Distillation for Multi-turn LLM Agents.

Preference-Based Self-Distillation: Beyond KL Matching via Reward Regularization Skill-SD: Skill-Conditioned Self-Distillation for Multi-turn LLM Agents

Reference 18

Resolution: verified exact; local_arxiv, observed 2026-05-11T18:16:10.847225Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 8c0199b6-0411-417c-994c-25e0da9c78da · outbound

This paper cites Self-Distilled RLVR.

Preference-Based Self-Distillation: Beyond KL Matching via Reward Regularization Self-Distilled RLVR

Reference 19

Resolution: verified exact; local_arxiv, observed 2026-05-11T18:16:10.782925Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 8057ce1c-bdcd-408b-8aff-517f74b16fba · outbound

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

Preference-Based Self-Distillation: Beyond KL Matching via Reward Regularization DAPO: An Open-Source LLM Reinforcement Learning System at Scale

Reference 20

Resolution: verified exact; local_arxiv, observed 2026-05-11T18:16:10.817694Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation f6e75022-a335-4d15-a081-e89bed8931fd · outbound

This paper cites Embarrassingly Simple Self-Distillation Improves Code Generation.

Preference-Based Self-Distillation: Beyond KL Matching via Reward Regularization Embarrassingly Simple Self-Distillation Improves Code Generation

Reference 21

Resolution: verified exact; arxiv_id, observed 2026-06-26T01:15:18.478768Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 90e88614-6bed-449f-8b19-c2a86e878f3a · outbound

This paper cites Self-Distilled Reasoner: On-Policy Self-Distillation for Large Language Models.

Preference-Based Self-Distillation: Beyond KL Matching via Reward Regularization Self-Distilled Reasoner: On-Policy Self-Distillation for Large Language Models

Reference 22

Resolution: verified exact; arxiv_id, observed 2026-05-12T03:54:31.187112Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation ec45e4a4-4f48-4097-955a-686854b0ab13 · outbound

This paper cites Iterative Data Smoothing: Mitigating Reward Overfitting and Overoptimization in RLHF.

Preference-Based Self-Distillation: Beyond KL Matching via Reward Regularization Iterative Data Smoothing: Mitigating Reward Overfitting and Overoptimization in RLHF

Reference 23

Resolution: verified exact; arxiv_id, observed 2026-05-11T18:16:10.933497Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation ae0a0656-b9cc-4b25-b2b6-9541c4759d6a · outbound

This paper cites Appendix E develops the technical details behind the statistical analysis in the main text.

Preference-Based Self-Distillation: Beyond KL Matching via Reward Regularization Appendix E develops the technical details behind the statistical analysis in the main text

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-05-26T10:07:34.528922Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 547ffe04-b74c-4323-8039-c3461eec9345 · outbound

This paper cites an unresolved cited work.

Preference-Based Self-Distillation: Beyond KL Matching via Reward Regularization Unresolved cited work

Reference 25

Resolution: unresolved; raw_fallback, observed 2026-05-26T10:07:34.535327Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation e6476b21-681f-466c-8ac3-196244b87de2 · outbound

This paper cites [2026a] whenever applicable so that the comparison against prior baselines isolates the effect of the proposed PBSD objective as cleanly as possible.

Preference-Based Self-Distillation: Beyond KL Matching via Reward Regularization [2026a] whenever applicable so that the comparison against prior baselines isolates the effect of the proposed PBSD objective as cleanly as possible

Reference 26

Resolution: verified fuzzy; raw_fallback, observed 2026-05-26T10:07:34.532204Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 517b923f-e1e3-4f87-8ba7-675bb2a4e767 · outbound

This paper cites Tool-use data.For the additional tool-use study, we follow the setup in Shenfeld et al.

Preference-Based Self-Distillation: Beyond KL Matching via Reward Regularization Tool-use data.For the additional tool-use study, we follow the setup in Shenfeld et al

Reference 27

Resolution: verified fuzzy; raw_fallback, observed 2026-05-26T10:07:34.538558Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation c11ee6f9-3076-42b1-bd70-682e600ffc2c · outbound

This paper cites Base (Student).

Preference-Based Self-Distillation: Beyond KL Matching via Reward Regularization Base (Student)

Reference 28

Resolution: verified fuzzy; raw_fallback, observed 2026-05-26T10:07:34.541532Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Pith citing papers

Observation dc822383-633f-4f61-a170-3acb28b804b1 · inbound

A Brief Overview: On-Policy Self-Distillation In Large Language Models cites this paper.

A Brief Overview: On-Policy Self-Distillation In Large Language Models Preference-Based Self-Distillation: Beyond KL Matching via Reward Regularization

Reference 54

Resolution: verified exact; local_arxiv, observed 2026-05-20T09:08:09.883187Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 6159c1c3-988f-4682-a15d-d069dcea0db3 · inbound

A Brief Overview: On-Policy Self-Distillation In Large Language Models cites this paper.

A Brief Overview: On-Policy Self-Distillation In Large Language Models Preference-Based Self-Distillation: Beyond KL Matching via Reward Regularization

Reference 54

Resolution: verified exact; local_arxiv, observed 2026-05-22T09:54:46.934280Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation e63f3d9a-5097-4b76-87f0-b60c9afd40c1 · inbound

RLCSD: Reinforcement Learning with Contrastive On-Policy Self-Distillation cites this paper.

RLCSD: Reinforcement Learning with Contrastive On-Policy Self-Distillation Preference-Based Self-Distillation: Beyond KL Matching via Reward Regularization

Reference 31

Resolution: metadata mismatch; local_arxiv, observed 2026-07-03T09:07:48.375369Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation c1e27acb-7add-46b5-b717-b3c636aedb14 · inbound

DemoPSD: Disagreement-Modulated Policy Self-Distillation cites this paper.

DemoPSD: Disagreement-Modulated Policy Self-Distillation Preference-Based Self-Distillation: Beyond KL Matching via Reward Regularization

Reference 25

Resolution: metadata mismatch; local_arxiv, observed 2026-07-03T16:28:38.436240Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 685b8c5c-e0e9-4cd6-a1bb-a24693448c5e · inbound

DemoPSD: Disagreement-Modulated Policy Self-Distillation cites this paper.

DemoPSD: Disagreement-Modulated Policy Self-Distillation Preference-Based Self-Distillation: Beyond KL Matching via Reward Regularization

Reference 25

Resolution: unresolved; no resolver link, observed 2026-07-12T08:00:10.945953Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9efda571-6255-4f55-ae5f-ead04887d3fa · inbound

DemoPSD: Disagreement-Modulated Policy Self-Distillation cites this paper.

DemoPSD: Disagreement-Modulated Policy Self-Distillation Preference-Based Self-Distillation: Beyond KL Matching via Reward Regularization

Reference 24

Resolution: unresolved; no resolver link, observed 2026-07-14T16:40:00.821341Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ed59648d-76be-4a61-9bd2-e75318123df3 · inbound

Contrastive On-Policy Distillation cites this paper.

Contrastive On-Policy Distillation Preference-Based Self-Distillation: Beyond KL Matching via Reward Regularization

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-01T13:40:41.757803Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.