Paper Citation Record · LEDGER

ReCUT: Balancing Reasoning Length and Accuracy in LLMs via Stepwise Trails and Preference Optimization

As of 7 August 2026, this Paper Citation Record lists 39 of 39 outbound references and 3 inbound Pith citation observations for arXiv:2506.10822.

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

pith.paper-citation-record.v1
2506.10822 v1

Coverage vector

measured 39 of 39 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-07T04:24:03.563539Z

measured 42 of 42 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-07T06:34:17.273281+00:00

measured 3 of 3 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-06T17:54:16.766414Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-07-04T09:19:43.891734Z

Reference resolution

39 of 39 outbound references displayed

verified exact0
verified fuzzy3
unresolved36
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 5404fa91-5fff-4202-b533-2710c7b4e10c · outbound

This paper cites L1: Controlling How Long A Reasoning Model Thinks With Reinforcement Learning.

ReCUT: Balancing Reasoning Length and Accuracy in LLMs via Stepwise Trails and Preference Optimization L1: Controlling How Long A Reasoning Model Thinks With Reinforcement Learning

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-07T04:24:01.152545Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 34ea02ed-bc12-4adf-bf32-fb438273c6a9 · outbound

This paper cites Towards Reasoning Era: A Survey of Long Chain-of-Thought for Reasoning Large Language Models.

ReCUT: Balancing Reasoning Length and Accuracy in LLMs via Stepwise Trails and Preference Optimization Towards Reasoning Era: A Survey of Long Chain-of-Thought for Reasoning Large Language Models

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-07T04:24:01.236638Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4fe7ae4c-3a13-42eb-a79e-3a7470f2ebdc · outbound

This paper cites Do NOT Think That Much for 2+3=? On the Overthinking of o1-Like LLMs.

ReCUT: Balancing Reasoning Length and Accuracy in LLMs via Stepwise Trails and Preference Optimization Do NOT Think That Much for 2+3=? On the Overthinking of o1-Like LLMs

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-07T04:24:01.308511Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2623af2b-e124-468e-b761-ea109da9f813 · outbound

This paper cites an unresolved cited work.

ReCUT: Balancing Reasoning Length and Accuracy in LLMs via Stepwise Trails and Preference Optimization Unresolved cited work

Reference 4

Resolution: unresolved; raw_fallback, observed 2026-08-07T04:24:05.446844Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation f51e2e38-bdd0-4d4a-a857-58ff832411a1 · outbound

This paper cites Training Verifiers to Solve Math Word Problems.

ReCUT: Balancing Reasoning Length and Accuracy in LLMs via Stepwise Trails and Preference Optimization Training Verifiers to Solve Math Word Problems

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-07T04:24:01.461204Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 98814e70-03e1-42da-824a-9817c40d10ef · outbound

This paper cites The Danger of Overthinking: Examining the Reasoning-Action Dilemma in Agentic Tasks.

ReCUT: Balancing Reasoning Length and Accuracy in LLMs via Stepwise Trails and Preference Optimization The Danger of Overthinking: Examining the Reasoning-Action Dilemma in Agentic Tasks

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-07T04:24:01.508410Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c975d91d-02ee-43e8-86ac-857102901f45 · outbound

This paper cites Stepwise Perplexity-Guided Refinement for Efficient Chain-of-Thought Reasoning in Large Language Models.

ReCUT: Balancing Reasoning Length and Accuracy in LLMs via Stepwise Trails and Preference Optimization Stepwise Perplexity-Guided Refinement for Efficient Chain-of-Thought Reasoning in Large Language Models

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-07T04:24:01.619558Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 43213829-d65c-4a63-b610-80379d7ad101 · outbound

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

ReCUT: Balancing Reasoning Length and Accuracy in LLMs via Stepwise Trails and Preference Optimization DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-07T04:24:01.705143Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 39b38077-a240-4858-a691-dd927ce51381 · outbound

This paper cites an unresolved cited work.

ReCUT: Balancing Reasoning Length and Accuracy in LLMs via Stepwise Trails and Preference Optimization Unresolved cited work

Reference 9

Resolution: unresolved; raw_fallback, observed 2026-08-07T04:24:05.256164Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation f011c757-b625-41f1-bb60-b830d868ee44 · outbound

This paper cites The Llama 3 Herd of Models.

ReCUT: Balancing Reasoning Length and Accuracy in LLMs via Stepwise Trails and Preference Optimization The Llama 3 Herd of Models

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-07T04:24:01.871204Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fe7e531b-9f6c-454b-b2ce-0d280933f93d · outbound

This paper cites an unresolved cited work.

ReCUT: Balancing Reasoning Length and Accuracy in LLMs via Stepwise Trails and Preference Optimization Unresolved cited work

Reference 11

Resolution: unresolved; raw_fallback, observed 2026-08-07T04:24:05.069974Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 5501d904-6679-4e88-8817-20592503c0dd · outbound

This paper cites Hu, Yelong Shen, Phillip Wallis, Zeyuan Allen - Zhu, Yuanzhi Li, Shean Wang, Lu Wang, and Weizhu Chen.

ReCUT: Balancing Reasoning Length and Accuracy in LLMs via Stepwise Trails and Preference Optimization Hu, Yelong Shen, Phillip Wallis, Zeyuan Allen - Zhu, Yuanzhi Li, Shean Wang, Lu Wang, and Weizhu Chen

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T04:24:04.919480Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 3750dc38-2bfd-4a39-a36a-020960dc4387 · outbound

This paper cites The Impact of Reasoning Step Length on Large Language Models.

ReCUT: Balancing Reasoning Length and Accuracy in LLMs via Stepwise Trails and Preference Optimization The Impact of Reasoning Step Length on Large Language Models

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-07T04:24:02.102954Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6bf73b08-5a11-4830-8323-5dd4b1e1cdb6 · outbound

This paper cites an unresolved cited work.

ReCUT: Balancing Reasoning Length and Accuracy in LLMs via Stepwise Trails and Preference Optimization Unresolved cited work

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-07T04:24:02.191167Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ba57bb8a-0c5c-4241-93b9-14de7bab1e93 · outbound

This paper cites How Well do LLMs Compress Their Own Chain-of-Thought? A Token Complexity Approach.

ReCUT: Balancing Reasoning Length and Accuracy in LLMs via Stepwise Trails and Preference Optimization How Well do LLMs Compress Their Own Chain-of-Thought? A Token Complexity Approach

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-07T04:24:02.269001Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 314ff115-b3cb-4b0a-ba0e-2c1b8acb06ca · outbound

This paper cites Search-o1: Agentic Search-Enhanced Large Reasoning Models.

ReCUT: Balancing Reasoning Length and Accuracy in LLMs via Stepwise Trails and Preference Optimization Search-o1: Agentic Search-Enhanced Large Reasoning Models

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-07T04:24:02.371341Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4c055b56-2701-4ae8-8fbb-2fc9eba799b1 · outbound

This paper cites Statistical Rejection Sampling Improves Preference Optimization.

ReCUT: Balancing Reasoning Length and Accuracy in LLMs via Stepwise Trails and Preference Optimization Statistical Rejection Sampling Improves Preference Optimization

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-07T04:24:02.421271Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fb5cb2b4-fc13-40e1-a1e6-e3e33cae6a07 · outbound

This paper cites an unresolved cited work.

ReCUT: Balancing Reasoning Length and Accuracy in LLMs via Stepwise Trails and Preference Optimization Unresolved cited work

Reference 18

Resolution: unresolved; raw_fallback, observed 2026-08-07T04:24:04.732686Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation ffdbcf01-12bc-429c-9fd0-0d23f918e9c8 · outbound

This paper cites An Empirical Study of Catastrophic Forgetting in Large Language Models During Continual Fine-tuning.

ReCUT: Balancing Reasoning Length and Accuracy in LLMs via Stepwise Trails and Preference Optimization An Empirical Study of Catastrophic Forgetting in Large Language Models During Continual Fine-tuning

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-07T04:24:02.545702Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation aed5cf32-2f4c-4e9c-a25a-9e81c25584a5 · outbound

This paper cites Imitate, Explore, and Self-Improve: A Reproduction Report on Slow-thinking Reasoning Systems.

ReCUT: Balancing Reasoning Length and Accuracy in LLMs via Stepwise Trails and Preference Optimization Imitate, Explore, and Self-Improve: A Reproduction Report on Slow-thinking Reasoning Systems

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-07T04:24:02.607794Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fee36d18-fa3d-4800-97c7-7a84c00bcc8f · outbound

This paper cites s1: Simple test-time scaling.

ReCUT: Balancing Reasoning Length and Accuracy in LLMs via Stepwise Trails and Preference Optimization s1: Simple test-time scaling

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-07T04:24:02.680283Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9a670ecf-dc91-42d6-865e-3d62d972189e · outbound

This paper cites GPT-4 Technical Report.

ReCUT: Balancing Reasoning Length and Accuracy in LLMs via Stepwise Trails and Preference Optimization GPT-4 Technical Report

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-07T04:24:02.731062Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 178eb223-ce63-4f13-8bf7-1b01694aeee0 · outbound

This paper cites Manning, Stefano Ermon, and Chelsea Finn.

ReCUT: Balancing Reasoning Length and Accuracy in LLMs via Stepwise Trails and Preference Optimization Manning, Stefano Ermon, and Chelsea Finn

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T04:24:04.573506Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation d5857fad-8f67-4e61-8da7-386a809794a3 · outbound

This paper cites an unresolved cited work.

ReCUT: Balancing Reasoning Length and Accuracy in LLMs via Stepwise Trails and Preference Optimization Unresolved cited work

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-07T04:24:02.825216Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3a0e35a4-9244-4757-95a2-62b8940ee970 · outbound

This paper cites an unresolved cited work.

ReCUT: Balancing Reasoning Length and Accuracy in LLMs via Stepwise Trails and Preference Optimization Unresolved cited work

Reference 25

Resolution: unresolved; raw_fallback, observed 2026-08-07T04:24:04.392950Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 6ea0fa13-aade-43d9-9070-26c983e3a6ae · outbound

This paper cites Proximal Policy Optimization Algorithms.

ReCUT: Balancing Reasoning Length and Accuracy in LLMs via Stepwise Trails and Preference Optimization Proximal Policy Optimization Algorithms

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-07T04:24:02.927593Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c616a405-5f18-42e8-8f10-c5c04c36e468 · outbound

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

ReCUT: Balancing Reasoning Length and Accuracy in LLMs via Stepwise Trails and Preference Optimization DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-07T04:24:02.970521Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6048d337-99a9-4d2e-8024-d4ff69da1082 · outbound

This paper cites Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameters.

ReCUT: Balancing Reasoning Length and Accuracy in LLMs via Stepwise Trails and Preference Optimization Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameters

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-07T04:24:03.025228Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e6d33c28-cd8c-4a02-b06a-252d6ae4fe64 · outbound

This paper cites Stop Overthinking: A Survey on Efficient Reasoning for Large Language Models.

ReCUT: Balancing Reasoning Length and Accuracy in LLMs via Stepwise Trails and Preference Optimization Stop Overthinking: A Survey on Efficient Reasoning for Large Language Models

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-07T04:24:03.079588Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5b20b30a-4686-4524-8fa6-7861393d7cf2 · outbound

This paper cites Kimi k1.5: Scaling Reinforcement Learning with LLMs.

ReCUT: Balancing Reasoning Length and Accuracy in LLMs via Stepwise Trails and Preference Optimization Kimi k1.5: Scaling Reinforcement Learning with LLMs

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-07T04:24:03.115259Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f8b9a322-79dc-4824-92e7-a0242ed02690 · outbound

This paper cites an unresolved cited work.

ReCUT: Balancing Reasoning Length and Accuracy in LLMs via Stepwise Trails and Preference Optimization Unresolved cited work

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-07T04:24:03.180660Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e50c0efe-b777-4e95-8282-549b71725a2d · outbound

This paper cites Stepwise Informativeness Search for Efficient and Effective LLM Reasoning.

ReCUT: Balancing Reasoning Length and Accuracy in LLMs via Stepwise Trails and Preference Optimization Stepwise Informativeness Search for Efficient and Effective LLM Reasoning

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-07T04:24:03.223176Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4f9daa93-d461-4eae-a47f-79353d10285d · outbound

This paper cites Chi, Quoc V.

ReCUT: Balancing Reasoning Length and Accuracy in LLMs via Stepwise Trails and Preference Optimization Chi, Quoc V

Reference 33

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T04:24:04.285467Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation a036fb45-bfb3-444b-a741-e8a060b5fdc6 · outbound

This paper cites an unresolved cited work.

ReCUT: Balancing Reasoning Length and Accuracy in LLMs via Stepwise Trails and Preference Optimization Unresolved cited work

Reference 34

Resolution: unresolved; raw_fallback, observed 2026-08-07T04:24:04.187564Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 4f56cec3-8647-4a4b-971d-23051d6b58d5 · outbound

This paper cites Chain of Draft: Thinking Faster by Writing Less.

ReCUT: Balancing Reasoning Length and Accuracy in LLMs via Stepwise Trails and Preference Optimization Chain of Draft: Thinking Faster by Writing Less

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-07T04:24:03.355899Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fe912320-4d28-4a1a-aeb6-06ddf9e965bd · outbound

This paper cites Qwen2.5 Technical Report.

ReCUT: Balancing Reasoning Length and Accuracy in LLMs via Stepwise Trails and Preference Optimization Qwen2.5 Technical Report

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-07T04:24:03.420787Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c1c8df38-0e13-4ce2-bede-c837bc669fd3 · outbound

This paper cites an unresolved cited work.

ReCUT: Balancing Reasoning Length and Accuracy in LLMs via Stepwise Trails and Preference Optimization Unresolved cited work

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-07T04:24:03.469910Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bb3dafcc-d682-44ba-874c-a37b49243a37 · outbound

This paper cites online" 'onlinestring :=.

ReCUT: Balancing Reasoning Length and Accuracy in LLMs via Stepwise Trails and Preference Optimization online" 'onlinestring :=

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-07T04:24:03.512395Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ab50e0db-9787-4f4f-b8b1-3c25ef1fbb95 · outbound

This paper cites write newline.

ReCUT: Balancing Reasoning Length and Accuracy in LLMs via Stepwise Trails and Preference Optimization write newline

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-07T04:24:03.563539Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation c6533a2e-66b8-495e-a0f5-78258de6cca8 · inbound

Towards Concise and Adaptive Thinking in Large Reasoning Models: A Survey cites this paper.

Towards Concise and Adaptive Thinking in Large Reasoning Models: A Survey ReCUT: Balancing Reasoning Length and Accuracy in LLMs via Stepwise Trails and Preference Optimization

Reference 89

Resolution: unresolved; no resolver link, observed 2026-08-06T17:54:16.766414Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 72452bd8-cde6-42b1-b99a-3d82cf6d34c6 · inbound

Beyond Penalizing Mistakes: Stabilizing Efficiency Training in Large Reasoning Models via Adaptive Correct-Only Rewards cites this paper.

Beyond Penalizing Mistakes: Stabilizing Efficiency Training in Large Reasoning Models via Adaptive Correct-Only Rewards ReCUT: Balancing Reasoning Length and Accuracy in LLMs via Stepwise Trails and Preference Optimization

Reference 25

Resolution: verified exact; arxiv_id, observed 2026-07-04T09:19:43.893126Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation d58fab11-0a67-4879-9243-c240d0895db4 · inbound

Contrastive On-Policy Distillation cites this paper.

Contrastive On-Policy Distillation ReCUT: Balancing Reasoning Length and Accuracy in LLMs via Stepwise Trails and Preference Optimization

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-01T13:40:39.777071Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.