Typed states for the displayed outbound observations.
Source: paper_references, paper_reference_links
Paper Citation Record · LEDGER
Why Does Self-Distillation (Sometimes) Degrade the Reasoning Capability of LLMs?
As of 5 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 51 inbound Pith citation observations for arXiv:2603.24472.
A citation records a reference. It does not transfer a finding from one paper to another.
Coverage vector
One-hop event checks from named stored sources.
Source: scholarly_work_events, retraction_status_cache, observed 2026-08-05T06:32:48.257954+00:00
Pith citing papers itemized under the disclosed page cap.
Source: paper_references, paper_reference_links, observed 2026-08-05T04:18:15.268459Z
A source-named dated measurement, never combined with another source.
Source: pith, observed 2026-07-10T00:26:39.269322Z
Reference resolution
0 of 0 outbound references displayed
- verified exact0
- verified fuzzy0
- unresolved0
- parse uncertain0
- malformed identifier0
- metadata mismatch0
External citation measurements
No source-named external measurement is stored.
Outbound references
No outbound reference observations are available for this paper version.
Pith citing papers
Observation c1fcf864-8175-41a4-87a5-4721055c6e48 · inbound
Demystifying OPD: Length Inflation and Stabilization Strategies for Large Language Models cites this paper.
Demystifying OPD: Length Inflation and Stabilization Strategies for Large Language Models Why Does Self-Distillation (Sometimes) Degrade the Reasoning Capability of LLMs?
Reference 9
- Resolution
- verified exact
- local_arxiv, observed 2026-05-11T06:46:25.667356Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Observation 63c34bef-947c-4ad0-a5d7-d3532cbff5bd · inbound
Rethinking On-Policy Distillation of Large Language Models: Phenomenology, Mechanism, and Recipe cites this paper.
Rethinking On-Policy Distillation of Large Language Models: Phenomenology, Mechanism, and Recipe Why Does Self-Distillation (Sometimes) Degrade the Reasoning Capability of LLMs?
Reference 13
- Resolution
- verified exact
- local_arxiv, observed 2026-05-11T11:11:06.654703Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Observation 9b3b0ec3-bb8d-4b92-913c-5786fc743a10 · inbound
How to Fine-Tune a Reasoning Model? A Teacher-Student Cooperation Framework to Synthesize Student-Consistent SFT Data cites this paper.
How to Fine-Tune a Reasoning Model? A Teacher-Student Cooperation Framework to Synthesize Student-Consistent SFT Data Why Does Self-Distillation (Sometimes) Degrade the Reasoning Capability of LLMs?
Reference 26
- Resolution
- verified exact
- local_arxiv, observed 2026-05-15T00:18:21.813100Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Observation a50598b2-429e-4133-bab5-7ed85e944b32 · inbound
AtManRL: Towards Faithful Reasoning via Differentiable Attention Saliency cites this paper.
AtManRL: Towards Faithful Reasoning via Differentiable Attention Saliency Why Does Self-Distillation (Sometimes) Degrade the Reasoning Capability of LLMs?
Reference 9
- Resolution
- verified exact
- local_arxiv, observed 2026-05-10T08:22:37.723976Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Observation d5c11abb-d573-4498-800d-80f459680e75 · inbound
Multilingual Safety Alignment via Self-Distillation cites this paper.
Multilingual Safety Alignment via Self-Distillation Why Does Self-Distillation (Sometimes) Degrade the Reasoning Capability of LLMs?
Reference 14
- Resolution
- metadata mismatch
- local_arxiv, observed 2026-05-09T05:45:22.455008Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Observation f919ae42-9dd9-4994-8b35-2ac166d6f795 · inbound
Multilingual Safety Alignment via Self-Distillation cites this paper.
Multilingual Safety Alignment via Self-Distillation Why Does Self-Distillation (Sometimes) Degrade the Reasoning Capability of LLMs?
Reference 14
- Resolution
- metadata mismatch
- local_arxiv, observed 2026-05-11T04:41:00.870883Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Observation 9d5a2af6-6dcb-4107-91c3-39c25dac3069 · inbound
Preference-Based Self-Distillation: Beyond KL Matching via Reward Regularization cites this paper.
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 2026-08-05T06:32:48.257954+00:00.
Observation 866cb465-3091-4ebf-aacc-a8e3e1b27e57 · inbound
KL for a KL: On-Policy Distillation with Control Variate Baseline cites this paper.
KL for a KL: On-Policy Distillation with Control Variate Baseline Why Does Self-Distillation (Sometimes) Degrade the Reasoning Capability of LLMs?
Reference 16
- Resolution
- verified exact
- local_arxiv, observed 2026-05-11T03:40:54.262998Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Observation e5cfe589-43af-45b6-91da-fe89ffc697c7 · inbound
On-Policy Distillation with Best-of-N Teacher Rollout Selection cites this paper.
On-Policy Distillation with Best-of-N Teacher Rollout Selection Why Does Self-Distillation (Sometimes) Degrade the Reasoning Capability of LLMs?
Reference 22
- Resolution
- verified exact
- local_arxiv, observed 2026-05-12T07:36:27.786285Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Observation 2bd05964-0d53-4e10-8ae4-73fb5830aced · inbound
On-Policy Distillation with Best-of-N Teacher Rollout Selection cites this paper.
On-Policy Distillation with Best-of-N Teacher Rollout Selection Why Does Self-Distillation (Sometimes) Degrade the Reasoning Capability of LLMs?
Reference 22
- Resolution
- verified exact
- local_arxiv, observed 2026-05-14T21:12:59.057387Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Observation 846a93f1-a330-40e3-be1f-8963f2aec8d6 · inbound
TRACE: Distilling Where It Matters via Token-Routed Self On-Policy Alignment cites this paper.
TRACE: Distilling Where It Matters via Token-Routed Self On-Policy Alignment Why Does Self-Distillation (Sometimes) Degrade the Reasoning Capability of LLMs?
Reference 7
- Resolution
- verified exact
- local_arxiv, observed 2026-05-12T02:56:18.634110Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Observation 38c14afe-d670-4d9a-b719-93cf3d30400e · inbound
Rebellious Student: Reversing Teacher Signals for Reasoning Exploration with Self-Distilled RLVR cites this paper.
Rebellious Student: Reversing Teacher Signals for Reasoning Exploration with Self-Distilled RLVR Why Does Self-Distillation (Sometimes) Degrade the Reasoning Capability of LLMs?
Reference 11
- Resolution
- verified exact
- local_arxiv, observed 2026-05-12T04:21:22.561357Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Observation cb8accb8-4d0b-4ef8-98a9-10a793ffc49e · inbound
Selective Off-Policy Reference Tuning with Plan Guidance cites this paper.
Selective Off-Policy Reference Tuning with Plan Guidance Why Does Self-Distillation (Sometimes) Degrade the Reasoning Capability of LLMs?
Reference 49
- Resolution
- verified exact
- local_arxiv, observed 2026-05-13T01:47:05.147366Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Observation 511120f4-4d18-4659-bbc0-44f098419d73 · inbound
Selective Off-Policy Reference Tuning with Plan Guidance cites this paper.
Selective Off-Policy Reference Tuning with Plan Guidance Why Does Self-Distillation (Sometimes) Degrade the Reasoning Capability of LLMs?
Reference 49
- Resolution
- verified exact
- local_arxiv, observed 2026-05-14T21:22:59.323040Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Observation 2c614824-c65c-41fe-b1fe-5985de517e59 · inbound
Anti-Self-Distillation for Reasoning RL via Pointwise Mutual Information cites this paper.
Anti-Self-Distillation for Reasoning RL via Pointwise Mutual Information Why Does Self-Distillation (Sometimes) Degrade the Reasoning Capability of LLMs?
Reference 8
- Resolution
- verified exact
- local_arxiv, observed 2026-05-13T01:47:04.756504Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Observation 11a2c5f2-7eda-40f5-8100-c9dee6a87142 · inbound
Multi-Rollout On-Policy Distillation via Peer Successes and Failures cites this paper.
Multi-Rollout On-Policy Distillation via Peer Successes and Failures Why Does Self-Distillation (Sometimes) Degrade the Reasoning Capability of LLMs?
Reference 39
- Resolution
- metadata mismatch
- local_arxiv, observed 2026-05-14T21:32:59.876539Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Observation 8568ff48-e04f-4c31-a6b2-f4fc27e1238d · inbound
Learning with Rare Success but Rich Feedback via Reflection-Enhanced Self-Distillation cites this paper.
Learning with Rare Success but Rich Feedback via Reflection-Enhanced Self-Distillation Why Does Self-Distillation (Sometimes) Degrade the Reasoning Capability of LLMs?
Reference 7
- Resolution
- verified exact
- local_arxiv, observed 2026-05-14T21:28:00.249118Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Observation 05e5fcc2-7374-42cb-ae64-9390de3aa4b7 · inbound
Respecting Self-Uncertainty in On-Policy Self-Distillation for Efficient LLM Reasoning cites this paper.
Respecting Self-Uncertainty in On-Policy Self-Distillation for Efficient LLM Reasoning Why Does Self-Distillation (Sometimes) Degrade the Reasoning Capability of LLMs?
Reference 5
- Resolution
- verified exact
- local_arxiv, observed 2026-05-14T19:52:52.422843Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Observation b4a81eaa-addc-484b-9a52-272695c65853 · inbound
Learning from Failures: Correction-Oriented Policy Optimization with Verifiable Rewards cites this paper.
Learning from Failures: Correction-Oriented Policy Optimization with Verifiable Rewards Why Does Self-Distillation (Sometimes) Degrade the Reasoning Capability of LLMs?
Reference 13
- Resolution
- verified exact
- local_arxiv, observed 2026-05-15T01:43:27.595678Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Observation f0b142f2-ceb4-446d-8f56-b624fa9a0424 · inbound
Learning from Language Feedback via Variational Policy Distillation cites this paper.
Learning from Language Feedback via Variational Policy Distillation Why Does Self-Distillation (Sometimes) Degrade the Reasoning Capability of LLMs?
Reference 14
- Resolution
- verified exact
- local_arxiv, observed 2026-05-20T20:39:00.362241Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Observation de5c9cf8-eee8-4fb5-85d3-896d0d9148eb · inbound
MixSD: Mixed Contextual Self-Distillation for Knowledge Injection cites this paper.
MixSD: Mixed Contextual Self-Distillation for Knowledge Injection Why Does Self-Distillation (Sometimes) Degrade the Reasoning Capability of LLMs?
Reference 11
- Resolution
- metadata mismatch
- local_arxiv, observed 2026-05-19T21:12:47.032286Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Observation 030e9b04-aa7e-48cd-9965-717c18376b76 · inbound
MixSD: Mixed Contextual Self-Distillation for Knowledge Injection cites this paper.
MixSD: Mixed Contextual Self-Distillation for Knowledge Injection Why Does Self-Distillation (Sometimes) Degrade the Reasoning Capability of LLMs?
Reference 11
- Resolution
- metadata mismatch
- local_arxiv, observed 2026-05-22T10:14:47.875482Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Observation d16b4c0b-2ef3-4326-9b3f-594c76512169 · 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 Why Does Self-Distillation (Sometimes) Degrade the Reasoning Capability of LLMs?
Reference 23
- Resolution
- verified exact
- local_arxiv, observed 2026-05-20T09:08:10.033457Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Observation 1f65c38d-6664-4c02-9525-6095da4806d5 · 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 Why Does Self-Distillation (Sometimes) Degrade the Reasoning Capability of LLMs?
Reference 23
- Resolution
- verified exact
- local_arxiv, observed 2026-05-22T09:54:47.006756Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Observation 936d8f0b-b104-4917-8605-696a331409fa · inbound
Tailoring Teaching to Aptitude: Direction-Adaptive Self-Distillation for LLM Reasoning cites this paper.
Tailoring Teaching to Aptitude: Direction-Adaptive Self-Distillation for LLM Reasoning Why Does Self-Distillation (Sometimes) Degrade the Reasoning Capability of LLMs?
Reference 21
- Resolution
- verified exact
- local_arxiv, observed 2026-05-22T08:11:17.634261Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Observation 7ea9cf5b-6d39-4a07-85d6-c6c2a7bbd9d4 · inbound
Filter, Then Reweight: Rethinking Optimization Granularity in On-Policy Distillation cites this paper.
Filter, Then Reweight: Rethinking Optimization Granularity in On-Policy Distillation Why Does Self-Distillation (Sometimes) Degrade the Reasoning Capability of LLMs?
Reference 34
- Resolution
- metadata mismatch
- local_arxiv, observed 2026-07-01T22:36:17.384806Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Observation 05165148-a52e-4163-99fc-e3eeb7374f66 · inbound
Constitutional On-Policy Safe Distillation cites this paper.
Constitutional On-Policy Safe Distillation Why Does Self-Distillation (Sometimes) Degrade the Reasoning Capability of LLMs?
Reference 24
- Resolution
- verified exact
- local_arxiv, observed 2026-07-02T01:36:25.519567Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Observation 1334b41c-7138-4f18-95c9-016c8ae1dc90 · inbound
Physics-Guided Policy Optimization with Self-Distillation cites this paper.
Physics-Guided Policy Optimization with Self-Distillation Why Does Self-Distillation (Sometimes) Degrade the Reasoning Capability of LLMs?
Reference 6
- Resolution
- verified exact
- local_arxiv, observed 2026-07-02T02:36:26.845621Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Observation 4d36cec5-8546-4bcb-aeb3-ba631c61616e · inbound
Language Models Need Sleep: Learning to Self-Modify and Consolidate Memories cites this paper.
Language Models Need Sleep: Learning to Self-Modify and Consolidate Memories Why Does Self-Distillation (Sometimes) Degrade the Reasoning Capability of LLMs?
Reference 129
- Resolution
- metadata mismatch
- local_arxiv, observed 2026-07-02T02:26:26.754038Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Observation 25815609-1393-4319-b04e-f9323e2e106f · inbound
Language Models Need Sleep: Learning to Self-Modify and Consolidate Memories cites this paper.
Language Models Need Sleep: Learning to Self-Modify and Consolidate Memories Why Does Self-Distillation (Sometimes) Degrade the Reasoning Capability of LLMs?
Reference 129
- Resolution
- unresolved
- no resolver link, observed 2026-07-13T07:44:25.325808Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 7bfbec51-a20d-4813-b33e-8b3f771fe877 · inbound
Reinforcement Learning from Rich Feedback with Distributional DAgger cites this paper.
Reinforcement Learning from Rich Feedback with Distributional DAgger Why Does Self-Distillation (Sometimes) Degrade the Reasoning Capability of LLMs?
Reference 14
- Resolution
- verified exact
- local_arxiv, observed 2026-07-02T07:46:45.925082Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Observation 25b44261-e5df-40ad-a3d3-904e1c611656 · inbound
OPRD: On-Policy Representation Distillation cites this paper.
OPRD: On-Policy Representation Distillation Why Does Self-Distillation (Sometimes) Degrade the Reasoning Capability of LLMs?
Reference 19
- Resolution
- verified exact
- local_arxiv, observed 2026-07-02T11:56:55.253740Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Observation 70849500-5e7e-4f7d-aa6c-25caf480ac13 · inbound
OmniOPSD: Rationale-Privileged On-Policy Self-Distillation for Affective Computing cites this paper.
OmniOPSD: Rationale-Privileged On-Policy Self-Distillation for Affective Computing Why Does Self-Distillation (Sometimes) Degrade the Reasoning Capability of LLMs?
Reference 4
- Resolution
- unresolved
- no resolver link, observed 2026-07-12T13:55:58.460765Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 8e8bfeae-f655-4541-a86e-df00a45368be · inbound
Zone of Proximal Policy Optimization: Teacher in Prompts, Not Gradients cites this paper.
Zone of Proximal Policy Optimization: Teacher in Prompts, Not Gradients Why Does Self-Distillation (Sometimes) Degrade the Reasoning Capability of LLMs?
Reference 22
- Resolution
- verified exact
- local_arxiv, observed 2026-07-03T20:48:55.953362Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Observation 731c3730-8a9b-4913-a323-582ea2951abf · inbound
Learning from Own Solutions: Self-Conditioned Credit Assignment for Reinforcement Learning with Verifiable Rewards cites this paper.
Learning from Own Solutions: Self-Conditioned Credit Assignment for Reinforcement Learning with Verifiable Rewards Why Does Self-Distillation (Sometimes) Degrade the Reasoning Capability of LLMs?
Reference 11
- Resolution
- metadata mismatch
- local_arxiv, observed 2026-07-03T23:39:04.438909Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Observation e6bbf87d-3bf1-408b-8cb8-8556994f040e · inbound
Procedural Memory Distillation: Online Reflection for Self-Improving Language Models cites this paper.
Procedural Memory Distillation: Online Reflection for Self-Improving Language Models Why Does Self-Distillation (Sometimes) Degrade the Reasoning Capability of LLMs?
Reference 12
- Resolution
- verified exact
- local_arxiv, observed 2026-07-03T20:18:56.102957Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Observation 21ecdc99-aac9-4a65-95ed-eb78c6da9aae · inbound
Purified OPSD: On-Policy Self-Distillation Without Losing How to Think cites this paper.
Purified OPSD: On-Policy Self-Distillation Without Losing How to Think Why Does Self-Distillation (Sometimes) Degrade the Reasoning Capability of LLMs?
Reference 10
- Resolution
- verified exact
- local_arxiv, observed 2026-07-03T13:58:21.048797Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Observation 9d40ba8a-d939-4b3a-b217-a7ecb28a0b09 · inbound
DemoPSD: Disagreement-Modulated Policy Self-Distillation cites this paper.
DemoPSD: Disagreement-Modulated Policy Self-Distillation Why Does Self-Distillation (Sometimes) Degrade the Reasoning Capability of LLMs?
Reference 11
- Resolution
- verified exact
- local_arxiv, observed 2026-07-03T16:28:38.420145Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Observation 1420105e-e1a2-4d48-8fe3-90accb33f07c · inbound
DemoPSD: Disagreement-Modulated Policy Self-Distillation cites this paper.
DemoPSD: Disagreement-Modulated Policy Self-Distillation Why Does Self-Distillation (Sometimes) Degrade the Reasoning Capability of LLMs?
Reference 11
- 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 09fa4929-3897-42bc-b056-bd927d85679f · inbound
DemoPSD: Disagreement-Modulated Policy Self-Distillation cites this paper.
DemoPSD: Disagreement-Modulated Policy Self-Distillation Why Does Self-Distillation (Sometimes) Degrade the Reasoning Capability of LLMs?
Reference 11
- 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 c3e91af8-c3b6-41ab-9971-e775278d404b · inbound
Rethinking On-Policy Self-Distillation for Thinking Models cites this paper.
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 2026-08-05T06:32:48.257954+00:00.
Observation f38f8daa-68dd-4570-abed-bb87ed99bee1 · inbound
Weak-to-Strong Generalization via Direct On-Policy Distillation cites this paper.
Weak-to-Strong Generalization via Direct On-Policy Distillation Why Does Self-Distillation (Sometimes) Degrade the Reasoning Capability of LLMs?
Reference 58
- Resolution
- verified exact
- local_arxiv, observed 2026-07-07T12:33:45.168462Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Observation c5cc2cab-e0d2-4d53-a4cd-ec2741f3039b · inbound
Weak-to-Strong Generalization via Direct On-Policy Distillation cites this paper.
Weak-to-Strong Generalization via Direct On-Policy Distillation Why Does Self-Distillation (Sometimes) Degrade the Reasoning Capability of LLMs?
Reference 55
- Resolution
- unresolved
- no resolver link, observed 2026-07-11T07:01:56.628017Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 927d8ccf-df69-42f1-9435-a32544abaf53 · inbound
Geometric Self-Distillation for Reasoning Generalization cites this paper.
Geometric Self-Distillation for Reasoning Generalization Why Does Self-Distillation (Sometimes) Degrade the Reasoning Capability of LLMs?
Reference 9
- Resolution
- verified exact
- local_arxiv, observed 2026-07-10T00:26:39.270869Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Observation 46c5f84a-6302-4da1-b772-3ffcdda5e07e · inbound
Diagnosing and Mitigating Thinking Collapse in On-Policy Self-Distillation cites this paper.
Diagnosing and Mitigating Thinking Collapse in On-Policy Self-Distillation Why Does Self-Distillation (Sometimes) Degrade the Reasoning Capability of LLMs?
Reference 1
- Resolution
- unresolved
- no resolver link, observed 2026-07-14T09:08:42.969885Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation ca6f1c13-f71e-4410-addf-1862f0d31f09 · inbound
On-Policy Delta Distillation cites this paper.
On-Policy Delta Distillation Why Does Self-Distillation (Sometimes) Degrade the Reasoning Capability of LLMs?
Reference 50
- Resolution
- unresolved
- no resolver link, observed 2026-08-02T00:00:10.604016Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation dd30c851-1b36-49c9-be0f-c6f257d31214 · inbound
Why Does Feedback-Augmented Self-Distillation Fail to Improve Retrieval-Interleaved Search Agents? cites this paper.
Why Does Feedback-Augmented Self-Distillation Fail to Improve Retrieval-Interleaved Search Agents? Why Does Self-Distillation (Sometimes) Degrade the Reasoning Capability of LLMs?
Reference 4
- Resolution
- unresolved
- no resolver link, observed 2026-08-01T17:42:16.061395Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 27557ec8-3224-4e3a-878c-f0633e72cae4 · inbound
LLM-as-a-Coach: Experiential Learning for Non-Verifiable Tasks cites this paper.
LLM-as-a-Coach: Experiential Learning for Non-Verifiable Tasks Why Does Self-Distillation (Sometimes) Degrade the Reasoning Capability of LLMs?
Reference 21
- Resolution
- unresolved
- no resolver link, observed 2026-08-01T16:07:59.676822Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation ac387a91-c932-4b01-92b2-fc46337d6360 · inbound
$\beta$-OPSD: Deriving with Policy Optimization, Training with Self-Distillation cites this paper.
$\beta$-OPSD: Deriving with Policy Optimization, Training with Self-Distillation Why Does Self-Distillation (Sometimes) Degrade the Reasoning Capability of LLMs?
Reference 8
- Resolution
- unresolved
- no resolver link, observed 2026-07-31T03:08:53.649699Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 2b5dd57a-e0bf-4553-b330-d49629def9bd · inbound
Is More Privileged Information Better? From Solution Traces to Problem-Solving Structure in Self-Distilled Reasoning cites this paper.
Is More Privileged Information Better? From Solution Traces to Problem-Solving Structure in Self-Distilled Reasoning Why Does Self-Distillation (Sometimes) Degrade the Reasoning Capability of LLMs?
Reference 15
- Resolution
- unresolved
- no resolver link, observed 2026-08-05T00:37:18.865054Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 9024278d-9b20-4eaf-ac2d-ac6e9a26f4bb · inbound
TurnSight: Turn-Level Hindsight Self-Distillation for Tool-Integrated Reasoning cites this paper.
TurnSight: Turn-Level Hindsight Self-Distillation for Tool-Integrated Reasoning Why Does Self-Distillation (Sometimes) Degrade the Reasoning Capability of LLMs?
Reference 4
- Resolution
- unresolved
- no resolver link, observed 2026-08-05T04:18:15.268459Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.