Paper Citation Record · LEDGER

Thinking Fast and Right: Balancing Accuracy and Reasoning Length with Adaptive Rewards

As of 20 August 2026, this Paper Citation Record lists 35 of 35 outbound references and 8 inbound Pith citation observations for arXiv:2505.18298.

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

pith.paper-citation-record.v1
2505.18298 v1

Coverage vector

measured 35 of 35 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-07T14:37:03.196744Z

measured 43 of 43 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-20T06:33:59.587034+00:00

measured 8 of 8 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-06T21:45:10.270039Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-07-04T09:19:43.854814Z

Reference resolution

35 of 35 outbound references displayed

verified exact0
verified fuzzy4
unresolved31
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 442ab1f7-9fc6-484f-bc92-061aefa9a772 · outbound

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

Thinking Fast and Right: Balancing Accuracy and Reasoning Length with Adaptive Rewards L1: Controlling How Long A Reasoning Model Thinks With Reinforcement Learning

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-07T14:37:00.874264Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8f53ce4f-0aef-4a8a-8e9f-3731ce5fe379 · outbound

This paper cites Training language models to reason efficiently.arXiv preprint arXiv:2502.04463, 2025.

Thinking Fast and Right: Balancing Accuracy and Reasoning Length with Adaptive Rewards Training language models to reason efficiently.arXiv preprint arXiv:2502.04463, 2025

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-07T14:37:01.003276Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 72a9f013-a6a3-47ba-a1df-020837f1e845 · outbound

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

Thinking Fast and Right: Balancing Accuracy and Reasoning Length with Adaptive Rewards Do NOT Think That Much for 2+3=? On the Overthinking of o1-Like LLMs

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-07T14:37:01.107838Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b3663651-1041-422a-858d-3edb87b86a86 · outbound

This paper cites Training Verifiers to Solve Math Word Problems.

Thinking Fast and Right: Balancing Accuracy and Reasoning Length with Adaptive Rewards Training Verifiers to Solve Math Word Problems

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-07T14:37:01.174456Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 51308257-6ebd-4863-a821-4f87adf34c01 · outbound

This paper cites competitive programming platform.https://codeforces.com/, 2025.

Thinking Fast and Right: Balancing Accuracy and Reasoning Length with Adaptive Rewards competitive programming platform.https://codeforces.com/, 2025

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:37:04.503936Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation c970b6b3-d015-41fc-ba95-5c2ab9399b22 · outbound

This paper cites Efficient reasoning models: A survey.arXiv preprint arXiv:2504.10903, 2025.

Thinking Fast and Right: Balancing Accuracy and Reasoning Length with Adaptive Rewards Efficient reasoning models: A survey.arXiv preprint arXiv:2504.10903, 2025

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-07T14:37:01.267450Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5ee06ac6-e9c8-4669-a56a-d1e83aa8f32b · outbound

This paper cites Omni-MATH: A Universal Olympiad Level Mathematic Benchmark For Large Language Models.

Thinking Fast and Right: Balancing Accuracy and Reasoning Length with Adaptive Rewards Omni-MATH: A Universal Olympiad Level Mathematic Benchmark For Large Language Models

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-07T14:37:01.324509Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 38674f00-a0af-40af-b4f9-bd9e328a6162 · outbound

This paper cites Scaling laws for reward model overoptimization.

Thinking Fast and Right: Balancing Accuracy and Reasoning Length with Adaptive Rewards Scaling laws for reward model overoptimization

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-07T14:37:01.397009Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8832b3e4-85ff-4a45-9030-0a56a9b4c4ce · outbound

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

Thinking Fast and Right: Balancing Accuracy and Reasoning Length with Adaptive Rewards DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-07T14:37:01.478805Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b90ca9c3-e075-477f-9356-016a9a549240 · outbound

This paper cites Token-Budget-Aware LLM Reasoning.

Thinking Fast and Right: Balancing Accuracy and Reasoning Length with Adaptive Rewards Token-Budget-Aware LLM Reasoning

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-07T14:37:01.537382Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation be7cfda0-09a0-4455-874b-d240ddc9084d · outbound

This paper cites Olympiadbench: A challenging benchmark for promoting agi with olympiad-level bilingual multimodal scientific problems.

Thinking Fast and Right: Balancing Accuracy and Reasoning Length with Adaptive Rewards Olympiadbench: A challenging benchmark for promoting agi with olympiad-level bilingual multimodal scientific problems

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-07T14:37:01.603480Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dcef9361-7a71-4c42-88a1-def13466c23d · outbound

This paper cites Measuring Mathematical Problem Solving With the MATH Dataset.

Thinking Fast and Right: Balancing Accuracy and Reasoning Length with Adaptive Rewards Measuring Mathematical Problem Solving With the MATH Dataset

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-07T14:37:01.676325Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 664a0074-5786-45a7-a606-0116e12b066e · outbound

This paper cites ThinkPrune: Pruning Long Chain-of-Thought of LLMs via Reinforcement Learning.

Thinking Fast and Right: Balancing Accuracy and Reasoning Length with Adaptive Rewards ThinkPrune: Pruning Long Chain-of-Thought of LLMs via Reinforcement Learning

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-07T14:37:01.733717Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5856107e-8d78-40cd-af8d-bca9abfc7d6f · outbound

This paper cites C3ot: Generating shorter chain-of- thought without compromising effectiveness.

Thinking Fast and Right: Balancing Accuracy and Reasoning Length with Adaptive Rewards C3ot: Generating shorter chain-of- thought without compromising effectiveness

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-07T14:37:01.791923Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7ab5e3d9-f52c-45d2-b9af-3ab106d5cec7 · outbound

This paper cites Training Language Models to Self-Correct via Reinforcement Learning.

Thinking Fast and Right: Balancing Accuracy and Reasoning Length with Adaptive Rewards Training Language Models to Self-Correct via Reinforcement Learning

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-07T14:37:01.878223Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 31e03873-e1f0-4215-94d9-6e52937bf939 · outbound

This paper cites Let’s verify step by step.

Thinking Fast and Right: Balancing Accuracy and Reasoning Length with Adaptive Rewards Let’s verify step by step

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-07T14:37:01.939588Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation be441b8d-1204-4559-8db8-fb50648a4f2a · outbound

This paper cites O1-Pruner: Length-Harmonizing Fine-Tuning for O1-Like Reasoning Pruning.

Thinking Fast and Right: Balancing Accuracy and Reasoning Length with Adaptive Rewards O1-Pruner: Length-Harmonizing Fine-Tuning for O1-Like Reasoning Pruning

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-07T14:37:01.996062Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1076a454-ec4d-4c8c-b4cb-24c664984679 · outbound

This paper cites Tang, Manan Roongta, Colin Cai, Jeffrey Luo, Tianjun Zhang, Li Erran Li, Raluca Ada Popa, and Ion Stoica.

Thinking Fast and Right: Balancing Accuracy and Reasoning Length with Adaptive Rewards Tang, Manan Roongta, Colin Cai, Jeffrey Luo, Tianjun Zhang, Li Erran Li, Raluca Ada Popa, and Ion Stoica

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:37:04.310465Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 505ccb87-69d6-4fee-9cd0-1cc0f6d00f67 · outbound

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

Thinking Fast and Right: Balancing Accuracy and Reasoning Length with Adaptive Rewards Imitate, Explore, and Self-Improve: A Reproduction Report on Slow-thinking Reasoning Systems

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-07T14:37:02.150424Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8e1c8307-a8e8-4f91-836a-98a20af4269f · outbound

This paper cites Self-Training Elicits Concise Reasoning in Large Language Models.

Thinking Fast and Right: Balancing Accuracy and Reasoning Length with Adaptive Rewards Self-Training Elicits Concise Reasoning in Large Language Models

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-07T14:37:02.225034Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation abf27e81-4979-46ec-bfe9-c90a609f7654 · outbound

This paper cites Concise Thoughts: Impact of Output Length on LLM Reasoning and Cost.

Thinking Fast and Right: Balancing Accuracy and Reasoning Length with Adaptive Rewards Concise Thoughts: Impact of Output Length on LLM Reasoning and Cost

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-07T14:37:02.280834Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6b90efee-0b7f-4959-addf-336cbe67c12a · outbound

This paper cites Learning to reason with llms.https://openai.com/index/learning-to-reason-with-llms/, 2024.

Thinking Fast and Right: Balancing Accuracy and Reasoning Length with Adaptive Rewards Learning to reason with llms.https://openai.com/index/learning-to-reason-with-llms/, 2024

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:37:04.201016Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 60242fa7-0d39-445e-a632-bc67c3386528 · outbound

This paper cites Gpqa: A graduate-level google-proof q&a benchmark.

Thinking Fast and Right: Balancing Accuracy and Reasoning Length with Adaptive Rewards Gpqa: A graduate-level google-proof q&a benchmark

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-07T14:37:02.400867Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 08aef909-c430-4afe-9729-9393712e7ad7 · outbound

This paper cites Code Llama: Open Foundation Models for Code.

Thinking Fast and Right: Balancing Accuracy and Reasoning Length with Adaptive Rewards Code Llama: Open Foundation Models for Code

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-07T14:37:02.480031Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 158a1cca-3fa1-41c1-9c31-f17173af4c38 · outbound

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

Thinking Fast and Right: Balancing Accuracy and Reasoning Length with Adaptive Rewards DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-07T14:37:02.554391Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0f4b5653-1520-4686-9390-b95c16d4e23b · outbound

This paper cites Between Underthinking and Overthinking: An Empirical Study of Reasoning Length and correctness in LLMs.

Thinking Fast and Right: Balancing Accuracy and Reasoning Length with Adaptive Rewards Between Underthinking and Overthinking: An Empirical Study of Reasoning Length and correctness in LLMs

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-07T14:37:02.625061Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8c121087-817b-458e-85a1-5ec109884a4b · outbound

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

Thinking Fast and Right: Balancing Accuracy and Reasoning Length with Adaptive Rewards Stop Overthinking: A Survey on Efficient Reasoning for Large Language Models

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-07T14:37:02.693985Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f35abcbc-a4b1-4f97-bd70-f2bc9589c7f4 · outbound

This paper cites Qwq-32b-preview.https://qwenlm.github.io/blog/qwq-32b-preview/, 2025.

Thinking Fast and Right: Balancing Accuracy and Reasoning Length with Adaptive Rewards Qwq-32b-preview.https://qwenlm.github.io/blog/qwq-32b-preview/, 2025

Reference 28

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:37:04.090914Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 8ee41af2-69d6-45d3-bbe2-f7952706419e · outbound

This paper cites Harnessing the Reasoning Economy: A Survey of Efficient Reasoning for Large Language Models.

Thinking Fast and Right: Balancing Accuracy and Reasoning Length with Adaptive Rewards Harnessing the Reasoning Economy: A Survey of Efficient Reasoning for Large Language Models

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-07T14:37:02.822409Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 91d8a4e6-f946-45b6-a219-4417b9846b2b · outbound

This paper cites Self-Consistency Improves Chain of Thought Reasoning in Language Models.

Thinking Fast and Right: Balancing Accuracy and Reasoning Length with Adaptive Rewards Self-Consistency Improves Chain of Thought Reasoning in Language Models

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-07T14:37:02.885543Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9d748111-dfab-45c2-b6bb-fd5012ffa94b · outbound

This paper cites Chain-of-thought prompting elicits reasoning in large language models.

Thinking Fast and Right: Balancing Accuracy and Reasoning Length with Adaptive Rewards Chain-of-thought prompting elicits reasoning in large language models

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-07T14:37:02.944987Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b3f68f8b-fa53-436f-93dc-151615958a5f · outbound

This paper cites Unlocking Efficient Long-to-Short LLM Reasoning with Model Merging.

Thinking Fast and Right: Balancing Accuracy and Reasoning Length with Adaptive Rewards Unlocking Efficient Long-to-Short LLM Reasoning with Model Merging

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-07T14:37:03.004066Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1bd1b620-86a1-489e-bec5-64558b313831 · outbound

This paper cites Tokenskip: Controllable chain-of-thought compression in llms.arXiv preprint arXiv:2502.12067, 2025.

Thinking Fast and Right: Balancing Accuracy and Reasoning Length with Adaptive Rewards Tokenskip: Controllable chain-of-thought compression in llms.arXiv preprint arXiv:2502.12067, 2025

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-07T14:37:03.060411Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 56280a21-99c1-43fe-94e3-d410c4ac50c2 · outbound

This paper cites Towards thinking-optimal scaling of test-time compute for llm reasoning.arXiv preprint arXiv:2502.18080, 2025.

Thinking Fast and Right: Balancing Accuracy and Reasoning Length with Adaptive Rewards Towards thinking-optimal scaling of test-time compute for llm reasoning.arXiv preprint arXiv:2502.18080, 2025

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-07T14:37:03.121217Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 68153ac2-28be-4582-9590-89a703dc1273 · outbound

This paper cites Shorterbetter: Guiding reasoning models to find optimal inference length for efficient reasoning.arXiv preprint arXiv:2504.21370, 2025.

Thinking Fast and Right: Balancing Accuracy and Reasoning Length with Adaptive Rewards Shorterbetter: Guiding reasoning models to find optimal inference length for efficient reasoning.arXiv preprint arXiv:2504.21370, 2025

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-07T14:37:03.196744Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation d52c04d0-32e9-4730-b36a-609bd4a0a2d3 · inbound

Do Thinking Tokens Help or Trap? Towards More Efficient Large Reasoning Model cites this paper.

Do Thinking Tokens Help or Trap? Towards More Efficient Large Reasoning Model Thinking Fast and Right: Balancing Accuracy and Reasoning Length with Adaptive Rewards

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-06T21:45:10.270039Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 02d91076-4512-4bc6-ad22-2425111373bc · 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 Thinking Fast and Right: Balancing Accuracy and Reasoning Length with Adaptive Rewards

Reference 168

Resolution: unresolved; no resolver link, observed 2026-08-06T17:54:17.672973Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e800aca3-effb-423a-8206-db125821c2c5 · inbound

Learning to Reason Efficiently with Discounted Reinforcement Learning cites this paper.

Learning to Reason Efficiently with Discounted Reinforcement Learning Thinking Fast and Right: Balancing Accuracy and Reasoning Length with Adaptive Rewards

Reference 2010

Resolution: unresolved; no resolver link, observed 2026-08-04T07:59:53.678805Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 56fffa5f-907e-49f8-a5be-9506a292801d · inbound

GDPO: Group reward-Decoupled Normalization Policy Optimization for Multi-reward RL Optimization cites this paper.

GDPO: Group reward-Decoupled Normalization Policy Optimization for Multi-reward RL Optimization Thinking Fast and Right: Balancing Accuracy and Reasoning Length with Adaptive Rewards

Reference 45

Resolution: verified exact; arxiv_id, observed 2026-05-15T05:31:56.036833Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 4369648a-efbc-44ca-b123-55488db6a1dc · inbound

Implicit Compression Regularization: Concise Reasoning via Internal Shorter Distributions in RL Post-Training cites this paper.

Implicit Compression Regularization: Concise Reasoning via Internal Shorter Distributions in RL Post-Training Thinking Fast and Right: Balancing Accuracy and Reasoning Length with Adaptive Rewards

Reference 25

Resolution: verified exact; arxiv_id, observed 2026-05-11T04:35:59.701953Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation f1e542d4-bdda-4a54-853a-dcf3a992cc5b · inbound

CLORE: Content-Level Optimization for Reasoning Efficiency cites this paper.

CLORE: Content-Level Optimization for Reasoning Efficiency Thinking Fast and Right: Balancing Accuracy and Reasoning Length with Adaptive Rewards

Reference 42

Resolution: verified exact; arxiv_id, observed 2026-05-22T05:51:08.229808Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation bb273491-ab63-42ba-8e1b-99c1e0dfdacf · inbound

CARE: Competence-Aware Reward Shaping for Adaptive Reasoning Length in Video-MLLMs cites this paper.

CARE: Competence-Aware Reward Shaping for Adaptive Reasoning Length in Video-MLLMs Thinking Fast and Right: Balancing Accuracy and Reasoning Length with Adaptive Rewards

Reference 6

Resolution: verified exact; arxiv_id, observed 2026-07-04T03:29:31.439181Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 3782feab-adce-4d78-806e-cc9f1647c702 · 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 Thinking Fast and Right: Balancing Accuracy and Reasoning Length with Adaptive Rewards

Reference 20

Resolution: metadata mismatch; arxiv_id, observed 2026-07-04T09:19:43.856293Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.