Typed states for the displayed outbound observations.
Source: paper_references, paper_reference_links, observed 2026-05-12T01:29:02.387691Z
Paper Citation Record · LEDGER
Reasoning Compression with Mixed-Policy Distillation
As of 6 August 2026, this Paper Citation Record lists 38 of 38 outbound references and 0 inbound Pith citation observations for arXiv:2605.08776.
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 2026-08-06T06:34:29.942622+00:00
Pith citing papers itemized under the disclosed page cap.
Source: paper_references, paper_reference_links
A source-named dated measurement, never combined with another source.
Source: cited_works
Reference resolution
38 of 38 outbound references displayed
- verified exact13
- verified fuzzy21
- unresolved0
- parse uncertain1
- malformed identifier1
- metadata mismatch2
External citation measurements
No source-named external measurement is stored.
Outbound references
Observation 5239fce8-56e5-45db-9027-10d4d79339f6 · outbound
This paper cites Chi, Quoc V.
Reasoning Compression with Mixed-Policy Distillation Chi, Quoc V
Reference 1
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-14T06:59:04.099620Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 9f5a3dff-e04e-47d2-8389-e468cc4194f6 · outbound
This paper cites Large language models are zero-shot reasoners.
Reasoning Compression with Mixed-Policy Distillation Large language models are zero-shot reasoners
Reference 2
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-14T06:59:04.113459Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 906c24a0-c143-4108-91c3-2b3e68c859fb · outbound
This paper cites DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning.
Reasoning Compression with Mixed-Policy Distillation DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning
Reference 3
- Resolution
- verified exact
- local_arxiv, observed 2026-05-12T07:56:28.127357Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 24f4f96b-4e31-4772-a346-26c320de25b5 · outbound
This paper cites Stop overthinking: A survey on efficient reasoning for large language models.Trans.
Reasoning Compression with Mixed-Policy Distillation Stop overthinking: A survey on efficient reasoning for large language models.Trans
Reference 4
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-14T06:59:04.108647Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation bb25c0ad-d5a7-45fb-9a78-cf825275f53e · outbound
This paper cites Wait, we don’t need to "wait"! removing thinking tokens improves reasoning efficiency.
Reasoning Compression with Mixed-Policy Distillation Wait, we don’t need to "wait"! removing thinking tokens improves reasoning efficiency
Reference 5
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-14T06:59:04.090986Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 36b0bca1-5b46-4e80-bd39-784faaa3023b · outbound
This paper cites The benefits of a concise chain of thought on problem-solving in large language models.
Reasoning Compression with Mixed-Policy Distillation The benefits of a concise chain of thought on problem-solving in large language models
Reference 6
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-14T06:59:04.095252Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation a1564186-707f-4e3e-9cc6-5b41571fe43f · outbound
This paper cites Chain of Draft: Thinking Faster by Writing Less.
Reasoning Compression with Mixed-Policy Distillation Chain of Draft: Thinking Faster by Writing Less
Reference 7
- Resolution
- metadata mismatch
- arxiv_id, observed 2026-05-12T07:56:28.199335Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 9f5fbbe9-9ba1-4de3-8e0d-9670933f7e90 · outbound
This paper cites C3ot: Generating shorter chain-of-thought without compromising effectiveness.
Reasoning Compression with Mixed-Policy Distillation C3ot: Generating shorter chain-of-thought without compromising effectiveness
Reference 8
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-14T06:59:04.103993Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation a6d706c0-ba27-4b97-80ac-8f93d0219e6f · outbound
This paper cites Tokenskip: Controllable chain-of-thought compression in llms.
Reasoning Compression with Mixed-Policy Distillation Tokenskip: Controllable chain-of-thought compression in llms
Reference 9
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-14T06:59:04.117779Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation e957e801-ff61-474d-a182-30d2420caa32 · outbound
This paper cites Concise Reasoning, Big Gains: Pruning Long Reasoning Trace with Difficulty-Aware Prompting.
Reasoning Compression with Mixed-Policy Distillation Concise Reasoning, Big Gains: Pruning Long Reasoning Trace with Difficulty-Aware Prompting
Reference 10
- Resolution
- verified exact
- arxiv_id, observed 2026-05-12T07:56:28.206267Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation a7e07d58-0a24-4fad-8290-d41b294264da · outbound
This paper cites Recut: Balancing reasoning length and accuracy in llms via stepwise trails and preference optimization.
Reasoning Compression with Mixed-Policy Distillation Recut: Balancing reasoning length and accuracy in llms via stepwise trails and preference optimization
Reference 11
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-14T06:59:04.086846Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 4a721cd9-76c9-4ae1-ae28-4d65a3cf2e54 · outbound
This paper cites DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models.
Reasoning Compression with Mixed-Policy Distillation DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
Reference 12
- Resolution
- verified exact
- local_arxiv, observed 2026-05-12T07:56:28.272051Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 803a5ec3-ef33-4874-93f2-2af4b5f69543 · outbound
This paper cites L1: Controlling How Long A Reasoning Model Thinks With Reinforcement Learning.
Reasoning Compression with Mixed-Policy Distillation L1: Controlling How Long A Reasoning Model Thinks With Reinforcement Learning
Reference 13
- Resolution
- verified exact
- arxiv_id, observed 2026-05-18T00:19:22.325854Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 7f5f5274-7069-4df7-a532-eba6699190e2 · outbound
This paper cites Thinkprune: Pruning long chain-of-thought of llms via reinforcement learning.Trans.
Reasoning Compression with Mixed-Policy Distillation Thinkprune: Pruning long chain-of-thought of llms via reinforcement learning.Trans
Reference 14
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-14T06:59:04.081456Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation d2645ce4-997d-4abf-9683-2d3070237991 · outbound
This paper cites CRISP: Compressed Reasoning via Iterative Self-Policy Distillation.
Reasoning Compression with Mixed-Policy Distillation CRISP: Compressed Reasoning via Iterative Self-Policy Distillation
Reference 15
- Resolution
- verified exact
- local_arxiv, observed 2026-05-12T07:56:28.173768Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 0cf3891f-a9f8-4041-9a52-b58291bade57 · outbound
This paper cites Openmathinstruct-2: Accelerating AI for math with massive open-source instruction data.
Reasoning Compression with Mixed-Policy Distillation Openmathinstruct-2: Accelerating AI for math with massive open-source instruction data
Reference 16
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-14T06:59:04.071867Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 2bb9c946-0fa7-4be5-993d-7d93c839458a · outbound
This paper cites Qwen3 Technical Report.
Reasoning Compression with Mixed-Policy Distillation Qwen3 Technical Report
Reference 17
- Resolution
- verified exact
- local_arxiv, observed 2026-05-12T07:56:28.182351Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 18f614ed-e3b1-4885-9b78-ed465c708402 · outbound
This paper cites OpenAI o1 System Card.
Reasoning Compression with Mixed-Policy Distillation OpenAI o1 System Card
Reference 18
- Resolution
- verified exact
- local_arxiv, observed 2026-05-12T07:56:28.220558Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation d4476742-a5ee-4df9-8521-86ba04693a24 · outbound
This paper cites Training Verifiers to Solve Math Word Problems.
Reasoning Compression with Mixed-Policy Distillation Training Verifiers to Solve Math Word Problems
Reference 19
- Resolution
- verified exact
- local_arxiv, observed 2026-05-12T07:56:28.278238Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 8895d4df-acbd-4e1d-86bb-ef10854bbdf5 · outbound
This paper cites Nguyen, Quang Pham, and Nghi D.
Reasoning Compression with Mixed-Policy Distillation Nguyen, Quang Pham, and Nghi D
Reference 20
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-14T06:59:04.076156Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 9e9a8cf4-2ced-47c9-8f2b-ea9c25b360c4 · outbound
This paper cites Longbench v2: Towards deeper understanding and reasoning on realistic long-context multitasks.
Reasoning Compression with Mixed-Policy Distillation Longbench v2: Towards deeper understanding and reasoning on realistic long-context multitasks
Reference 21
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-14T06:59:04.067394Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 05e092c1-6179-4af5-88eb-c8fd5ad07e34 · outbound
This paper cites Do NOT Think That Much for 2+3=? On the Overthinking of o1-Like LLMs.
Reasoning Compression with Mixed-Policy Distillation Do NOT Think That Much for 2+3=? On the Overthinking of o1-Like LLMs
Reference 22
- Resolution
- verified exact
- arxiv_id, observed 2026-05-13T15:51:30.429014Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 7d6af50d-2d8e-423a-aa47-bba7e3f2f151 · outbound
This paper cites arXiv preprint arXiv:2603.09906 , year=.
Reasoning Compression with Mixed-Policy Distillation arXiv preprint arXiv:2603.09906 , year=
Reference 23
- Resolution
- metadata mismatch
- arxiv_id, observed 2026-05-12T07:56:28.256127Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation f6727f4c-34e4-401c-ab16-6ebfaeb57273 · outbound
This paper cites How Well do LLMs Compress Their Own Chain-of-Thought? A Token Complexity Approach.
Reasoning Compression with Mixed-Policy Distillation How Well do LLMs Compress Their Own Chain-of-Thought? A Token Complexity Approach
Reference 24
- Resolution
- verified exact
- arxiv_id, observed 2026-05-12T07:56:28.234223Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 48faaedd-4bfe-47db-9be2-56981da3159e · outbound
This paper cites On-policy distillation of language models: Learning from self-generated mistakes.
Reasoning Compression with Mixed-Policy Distillation On-policy distillation of language models: Learning from self-generated mistakes
Reference 25
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-14T06:59:04.030470Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 2109f45f-7f28-4ce1-9a4d-4b18c9badbe0 · outbound
This paper cites an unresolved cited work.
Reasoning Compression with Mixed-Policy Distillation Unresolved cited work
Reference 26
- Resolution
- parse uncertain
- raw_fallback, observed 2026-05-14T06:59:04.122087Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 7aadeaee-71b3-4a33-a4a2-a1aa47ce0331 · outbound
This paper cites Minillm: Knowledge distillation of large language models.
Reasoning Compression with Mixed-Policy Distillation Minillm: Knowledge distillation of large language models
Reference 27
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-14T06:59:04.038592Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 6b78cb60-8b28-480e-af82-6aa6984cabf4 · outbound
This paper cites On-policy distillation.
Reasoning Compression with Mixed-Policy Distillation On-policy distillation
Reference 28
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-14T06:59:04.033964Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 7d3533df-8ed8-4f1a-ba3d-3842467ce009 · outbound
This paper cites On-Policy Context Distillation for Language Models.
Reasoning Compression with Mixed-Policy Distillation On-Policy Context Distillation for Language Models
Reference 29
- Resolution
- verified exact
- arxiv_id, observed 2026-05-13T20:48:41.492604Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 906fa986-bfe3-44eb-8b3f-ebee18385ad6 · outbound
This paper cites Sentence-bert: Sentence embeddings using siamese bert-networks.
Reasoning Compression with Mixed-Policy Distillation Sentence-bert: Sentence embeddings using siamese bert-networks
Reference 30
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-14T06:59:04.055042Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 1a907381-4167-4cc1-958d-243350e495d5 · outbound
This paper cites American invitational mathematics examination (aime) 2024.
Reasoning Compression with Mixed-Policy Distillation American invitational mathematics examination (aime) 2024
Reference 31
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-14T06:59:04.058799Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 3d9dc4f0-be9b-4c0e-86b1-00c74d2a1fc1 · outbound
This paper cites American invitational mathematics examination (aime) 2025.
Reasoning Compression with Mixed-Policy Distillation American invitational mathematics examination (aime) 2025
Reference 32
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-14T06:59:04.052122Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 28e6659f-ea38-427a-a1d5-0740c70acad5 · outbound
This paper cites Overconfident errors need stronger correction: Asymmetric confidence penalties for reinforcement learning.arXiv preprint arXiv:2602.21420, 2026a.
Reasoning Compression with Mixed-Policy Distillation Overconfident errors need stronger correction: Asymmetric confidence penalties for reinforcement learning.arXiv preprint arXiv:2602.21420, 2026a
Reference 33
- Resolution
- verified exact
- arxiv_id, observed 2026-05-12T07:56:28.161002Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 0dbe3366-048a-4aae-8c47-2d6ca33ac7b8 · outbound
This paper cites Protect our environment from information overload.Nature Human Behaviour, 8(3):402–403.
Reasoning Compression with Mixed-Policy Distillation Protect our environment from information overload.Nature Human Behaviour, 8(3):402–403
Reference 34
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-14T06:59:04.048275Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 143c1877-7029-4336-a7d0-ae4624394da3 · outbound
This paper cites Yang, Zachary DeVito, Martin Raison, Alykhan Tejani, Sasank Chilamkurthy, Benoit Steiner, Lu Fang, Junjie Bai, and Soumith Chintala.
Reasoning Compression with Mixed-Policy Distillation Yang, Zachary DeVito, Martin Raison, Alykhan Tejani, Sasank Chilamkurthy, Benoit Steiner, Lu Fang, Junjie Bai, and Soumith Chintala
Reference 35
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-14T06:59:04.043625Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation e3d7f1d7-44d6-4e39-a57b-fec434cec536 · outbound
This paper cites HuggingFace's Transformers: State-of-the-art Natural Language Processing.
Reasoning Compression with Mixed-Policy Distillation HuggingFace's Transformers: State-of-the-art Natural Language Processing
Reference 36
- Resolution
- verified exact
- local_arxiv, observed 2026-05-12T07:56:28.265448Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation d276b8ec-8e96-4695-867a-2a952046fe64 · outbound
This paper cites PhD thesis, UC Berkeley.
Reasoning Compression with Mixed-Policy Distillation PhD thesis, UC Berkeley
Reference 37
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-14T06:59:04.062543Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 866e854f-69c8-499a-8fc4-391bd17d07a4 · outbound
This paper cites Self-Distilled Reasoner: On-Policy Self-Distillation for Large Language Models.
Reasoning Compression with Mixed-Policy Distillation Self-Distilled Reasoner: On-Policy Self-Distillation for Large Language Models
Reference 38
- Resolution
- malformed identifier
- local_arxiv, observed 2026-05-12T07:56:28.240279Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Pith citing papers
No inbound Pith citation observations are available.