Paper Citation Record · LEDGER

Rethinking On-Policy Self-Distillation for Thinking Models

As of 22 August 2026, this Paper Citation Record lists 21 of 21 outbound references and 4 inbound Pith citation observations for arXiv:2607.05184.

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

pith.paper-citation-record.v1
2607.05184 v1

Coverage vector

measured 21 of 21 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-07-08T01:04:59.662046Z

measured 25 of 25 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-21T06:32:19.484+00:00

measured 4 of 4 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-14T10:59:51.920749Z

measured 0 of 1 external citation measurements

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

Source: pith, observed 2026-08-04T22:02:35.499158Z

Reference resolution

21 of 21 outbound references displayed

verified exact7
verified fuzzy5
unresolved3
parse uncertain0
malformed identifier0
metadata mismatch6

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation cbba8739-0646-4fca-bb69-bfbedf14edfb · outbound

This paper cites Forking Paths in Neural Text Generation.

Rethinking On-Policy Self-Distillation for Thinking Models Forking Paths in Neural Text Generation

Reference 1

Resolution: metadata mismatch; local_arxiv, observed 2026-07-08T01:14:27.525524Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 396f6a89-249f-40bd-88a8-769fa5891127 · outbound

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

Rethinking On-Policy Self-Distillation for Thinking Models DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning

Reference 2

Resolution: verified exact; local_arxiv, observed 2026-07-08T01:14:27.516491Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation eb8f50b2-3593-4b2d-b1de-da1768b4882b · outbound

This paper cites Chakravarthy, Anikait Singh, Nathan Lile, and Noah D.

Rethinking On-Policy Self-Distillation for Thinking Models Chakravarthy, Anikait Singh, Nathan Lile, and Noah D

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-07-08T01:14:27.721941Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 9146e4db-699d-489e-b982-0736d154a3fb · outbound

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

Rethinking On-Policy Self-Distillation for Thinking Models Self-Distillation Zero: Self-Revision Turns Binary Rewards into Dense Supervision

Reference 4

Resolution: metadata mismatch; local_arxiv, observed 2026-07-08T01:14:27.515390Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation f542e8fc-6641-4546-b5c8-3f025de3e865 · outbound

This paper cites Reinforcement Learning via Self-Distillation.

Rethinking On-Policy Self-Distillation for Thinking Models Reinforcement Learning via Self-Distillation

Reference 5

Resolution: verified exact; local_arxiv, observed 2026-07-08T01:14:27.535875Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation c3e91af8-c3b6-41ab-9971-e775278d404b · outbound

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

Rethinking On-Policy Self-Distillation for Thinking Models Why Does Self-Distillation (Sometimes) Degrade the Reasoning Capability of LLMs?

Reference 6

Resolution: metadata mismatch; local_arxiv, observed 2026-07-08T01:14:27.528143Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation bdadb457-eb31-4c85-8b4e-19aedac412ad · outbound

This paper cites Critical Tokens Matter: Token-Level Contrastive Estimation Enhances LLM's Reasoning Capability.

Rethinking On-Policy Self-Distillation for Thinking Models Critical Tokens Matter: Token-Level Contrastive Estimation Enhances LLM's Reasoning Capability

Reference 7

Resolution: verified exact; local_arxiv, observed 2026-07-08T01:14:27.539267Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation e802dbe8-8581-4ab8-9b8b-9a0d04549f24 · outbound

This paper cites Pope: Learning to reason on hard problems via privileged on-policy exploration.

Rethinking On-Policy Self-Distillation for Thinking Models Pope: Learning to reason on hard problems via privileged on-policy exploration

Reference 8

Resolution: metadata mismatch; arxiv_id, observed 2026-07-08T01:14:27.537447Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 36b68aad-dc12-4f62-80a3-5482845b9328 · outbound

This paper cites Reuse your flops: Scaling rl on hard problems by conditioning on very off-policy prefixes.

Rethinking On-Policy Self-Distillation for Thinking Models Reuse your flops: Scaling rl on hard problems by conditioning on very off-policy prefixes

Reference 9

Resolution: verified exact; arxiv_id, observed 2026-07-08T01:14:27.529342Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation be81aa2d-827e-4823-aac3-1f8519c3e5f3 · outbound

This paper cites Self-Distillation Enables Continual Learning.

Rethinking On-Policy Self-Distillation for Thinking Models Self-Distillation Enables Continual Learning

Reference 10

Resolution: verified exact; local_arxiv, observed 2026-07-08T01:14:27.531170Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 1a4d5b85-22a0-4110-8d15-efd0c35c8128 · outbound

This paper cites Olmo 3.

Rethinking On-Policy Self-Distillation for Thinking Models Olmo 3

Reference 11

Resolution: metadata mismatch; local_arxiv, observed 2026-07-08T01:14:27.545307Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation afbf9a04-0dcf-4fd0-a8b4-6354c8bd52cf · outbound

This paper cites Understanding reasoning in thinking language models via steering vectors.

Rethinking On-Policy Self-Distillation for Thinking Models Understanding reasoning in thinking language models via steering vectors

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-07-08T01:14:27.732244Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 9e148a67-9f7d-4410-9d2a-018a29fd6c7e · outbound

This paper cites Qwen3 Technical Report.

Rethinking On-Policy Self-Distillation for Thinking Models Qwen3 Technical Report

Reference 13

Resolution: metadata mismatch; local_arxiv, observed 2026-07-08T01:14:27.542787Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation c8272c1a-c400-4d83-9492-cf6d3c41167c · outbound

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

Rethinking On-Policy Self-Distillation for Thinking Models Embarrassingly Simple Self-Distillation Improves Code Generation

Reference 14

Resolution: verified exact; local_arxiv, observed 2026-07-08T01:14:27.525726Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation a309d32f-8968-435e-b44c-7157562fe251 · outbound

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

Rethinking On-Policy Self-Distillation for Thinking Models Self-Distilled Reasoner: On-Policy Self-Distillation for Large Language Models

Reference 15

Resolution: verified exact; local_arxiv, observed 2026-07-08T01:14:27.501845Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 37258f2f-723a-488e-ad56-29a8a099477e · outbound

This paper cites an unresolved cited work.

Rethinking On-Policy Self-Distillation for Thinking Models Unresolved cited work

Reference 16

Resolution: unresolved; raw_fallback, observed 2026-07-08T01:14:27.730229Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 52c3f718-42b9-4900-b8bb-3706cb76ae18 · outbound

This paper cites an unresolved cited work.

Rethinking On-Policy Self-Distillation for Thinking Models Unresolved cited work

Reference 17

Resolution: unresolved; raw_fallback, observed 2026-07-08T01:14:27.720002Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation dd3ad507-5f89-409f-b287-639a407cfec3 · outbound

This paper cites The Average column averages the three benchmarks.

Rethinking On-Policy Self-Distillation for Thinking Models The Average column averages the three benchmarks

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-07-08T01:14:27.726381Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation d7c7a81d-4e28-47fb-90ac-2186c707c26b · outbound

This paper cites Epistemic-token OPD applies the same loss only to tokens in the epistemic-marker set.

Rethinking On-Policy Self-Distillation for Thinking Models Epistemic-token OPD applies the same loss only to tokens in the epistemic-marker set

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-07-08T01:14:27.723944Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation cbf32b64-d01a-4caf-b5e1-191965f8354f · outbound

This paper cites an unresolved cited work.

Rethinking On-Policy Self-Distillation for Thinking Models Unresolved cited work

Reference 20

Resolution: unresolved; raw_fallback, observed 2026-07-08T01:14:27.734544Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation dcfd014f-39a6-41f3-bcd6-0904ee2b91f3 · outbound

This paper cites Blue curves are base thinking models, orange curves are OPSD with full gold-demonstration context, and green curves are OPSD with final-answer-only privileged context.

Rethinking On-Policy Self-Distillation for Thinking Models Blue curves are base thinking models, orange curves are OPSD with full gold-demonstration context, and green curves are OPSD with final-answer-only privileged context

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-07-08T01:14:27.728454Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Pith citing papers

Observation 713f8264-9954-41ac-9f95-00c226482406 · inbound

DAPD: Dual-Anchored Policy Distillation cites this paper.

DAPD: Dual-Anchored Policy Distillation Rethinking On-Policy Self-Distillation for Thinking Models

Reference 76

Resolution: metadata mismatch; local_arxiv, observed 2026-08-04T22:02:35.540632Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation de8a8bae-340f-406b-b2b5-d2ebd0a6a75e · inbound

Agentic Reinforcement Learning with Observation-Calibrated Self-Distillation cites this paper.

Agentic Reinforcement Learning with Observation-Calibrated Self-Distillation Rethinking On-Policy Self-Distillation for Thinking Models

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-06T16:39:05.711475Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 75ab8712-8de3-4b5a-b064-92fb51e46615 · inbound

Simple-OPD: Demystifying Warm-up for On-policy Distillation cites this paper.

Simple-OPD: Demystifying Warm-up for On-policy Distillation Rethinking On-Policy Self-Distillation for Thinking Models

Reference 85

Resolution: unresolved; no resolver link, observed 2026-08-10T20:33:49.690977Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 770dfc69-243a-40f7-97cf-8d7b3ebea9e2 · inbound

Edit2TikZ: A Comprehensive and Challenging Benchmark for Scientific Figure Editing with TikZ cites this paper.

Edit2TikZ: A Comprehensive and Challenging Benchmark for Scientific Figure Editing with TikZ Rethinking On-Policy Self-Distillation for Thinking Models

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-14T10:59:51.920749Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.