Paper Citation Record · LEDGER

THOUGHTTERMINATOR: Benchmarking, Calibrating, and Mitigating Overthinking in Reasoning Models

As of 20 August 2026, this Paper Citation Record lists 31 of 31 outbound references and 5 inbound Pith citation observations for arXiv:2504.13367.

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

pith.paper-citation-record.v1
2504.13367 v1

Coverage vector

measured 31 of 31 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-16T12:14:48.950737Z

measured 36 of 36 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-19T06:32:44.657259+00:00

measured 5 of 5 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-07T12:35:43.292037Z

measured 1 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-08-05T02:28:24.338817Z

Reference resolution

31 of 31 outbound references displayed

verified exact0
verified fuzzy5
unresolved25
parse uncertain0
malformed identifier1
metadata mismatch0

External citation measurements

0
arxiv_reference, observed 2026-08-05T02:28:24.338817Z

Outbound references

Observation 43c2f155-1b99-4149-bfaa-030f7a739ab3 · outbound

This paper cites write newline.

THOUGHTTERMINATOR: Benchmarking, Calibrating, and Mitigating Overthinking in Reasoning Models write newline

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-16T12:14:48.696075Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d4dc3494-2e7f-460b-89c0-2fc42f74b2ae · outbound

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

THOUGHTTERMINATOR: Benchmarking, Calibrating, and Mitigating Overthinking in Reasoning Models Do NOT Think That Much for 2+3=? On the Overthinking of o1-Like LLMs

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-16T12:14:48.702938Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 131b31e2-6268-414d-a5fa-76286ca826cb · outbound

This paper cites Over-reasoning and redundant calculation of large language models.

THOUGHTTERMINATOR: Benchmarking, Calibrating, and Mitigating Overthinking in Reasoning Models Over-reasoning and redundant calculation of large language models

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T12:14:49.666718Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 8e826a7d-29de-4795-90b3-c6956d153280 · outbound

This paper cites Training Verifiers to Solve Math Word Problems.

THOUGHTTERMINATOR: Benchmarking, Calibrating, and Mitigating Overthinking in Reasoning Models Training Verifiers to Solve Math Word Problems

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-16T12:14:48.728995Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 40b657e6-77ab-432e-bf09-ce7f7a9b9f7f · outbound

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

THOUGHTTERMINATOR: Benchmarking, Calibrating, and Mitigating Overthinking in Reasoning Models DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-16T12:14:48.765172Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 89397f45-798e-4cc4-b659-dea66024f808 · outbound

This paper cites From Explicit CoT to Implicit CoT: Learning to Internalize CoT Step by Step.

THOUGHTTERMINATOR: Benchmarking, Calibrating, and Mitigating Overthinking in Reasoning Models From Explicit CoT to Implicit CoT: Learning to Internalize CoT Step by Step

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-16T12:14:48.806467Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8138f147-c3ab-43d0-b091-4447a71f61e3 · outbound

This paper cites Mercury: A code efficiency benchmark for code large language models.

THOUGHTTERMINATOR: Benchmarking, Calibrating, and Mitigating Overthinking in Reasoning Models Mercury: A code efficiency benchmark for code large language models

Reference 7

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T12:14:49.649927Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation ebc2cf72-08f3-4931-b578-8a19db43dc35 · outbound

This paper cites The Llama 3 Herd of Models.

THOUGHTTERMINATOR: Benchmarking, Calibrating, and Mitigating Overthinking in Reasoning Models The Llama 3 Herd of Models

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-16T12:14:48.825269Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 890f2dd9-ab3c-4901-85ab-af273b6b27af · outbound

This paper cites Efficiently Scaling LLM Reasoning with Certaindex.

THOUGHTTERMINATOR: Benchmarking, Calibrating, and Mitigating Overthinking in Reasoning Models Efficiently Scaling LLM Reasoning with Certaindex

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-16T12:14:48.831035Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 14891e74-26e4-459a-90ac-3eb649d0eb48 · outbound

This paper cites Measuring mathematical problem solving with the math dataset.

THOUGHTTERMINATOR: Benchmarking, Calibrating, and Mitigating Overthinking in Reasoning Models Measuring mathematical problem solving with the math dataset

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-16T12:14:48.836274Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a9687924-55a1-4f17-88e8-0144c8d3e4a6 · outbound

This paper cites OpenAI o1 System Card.

THOUGHTTERMINATOR: Benchmarking, Calibrating, and Mitigating Overthinking in Reasoning Models OpenAI o1 System Card

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-16T12:14:48.841825Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9ea386ff-7360-4b18-b448-7968903ce8cb · outbound

This paper cites Encouraging Divergent Thinking in Large Language Models through Multi-Agent Debate.

THOUGHTTERMINATOR: Benchmarking, Calibrating, and Mitigating Overthinking in Reasoning Models Encouraging Divergent Thinking in Large Language Models through Multi-Agent Debate

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-16T12:14:48.847707Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 08a3d596-66ee-4b56-83f2-0580513257f2 · outbound

This paper cites Let's Verify Step by Step.

THOUGHTTERMINATOR: Benchmarking, Calibrating, and Mitigating Overthinking in Reasoning Models Let's Verify Step by Step

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-16T12:14:48.853345Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 18416b25-db0e-4c2a-846a-818b13c5e27d · outbound

This paper cites Zebralogic: Benchmarking the logical reasoning ability of language models, 2024.

THOUGHTTERMINATOR: Benchmarking, Calibrating, and Mitigating Overthinking in Reasoning Models Zebralogic: Benchmarking the logical reasoning ability of language models, 2024

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T12:14:49.622475Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation b0895ca6-2b2a-4fea-99eb-56b6826f249b · outbound

This paper cites Can Language Models Learn to Skip Steps?.

THOUGHTTERMINATOR: Benchmarking, Calibrating, and Mitigating Overthinking in Reasoning Models Can Language Models Learn to Skip Steps?

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-16T12:14:48.864121Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 18ef791c-9136-41eb-bb59-eeeaf2c62948 · outbound

This paper cites Gemma: Open Models Based on Gemini Research and Technology.

THOUGHTTERMINATOR: Benchmarking, Calibrating, and Mitigating Overthinking in Reasoning Models Gemma: Open Models Based on Gemini Research and Technology

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-16T12:14:48.869627Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 05040b97-1084-40e0-9fa5-d14a24de9d5d · outbound

This paper cites s1: Simple test-time scaling.

THOUGHTTERMINATOR: Benchmarking, Calibrating, and Mitigating Overthinking in Reasoning Models s1: Simple test-time scaling

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-16T12:14:48.875230Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8da46fcd-b93a-47b4-bc08-1c3ed408f3ac · outbound

This paper cites Automatically correcting large language models: Surveying the landscape of diverse automated correction strategies.

THOUGHTTERMINATOR: Benchmarking, Calibrating, and Mitigating Overthinking in Reasoning Models Automatically correcting large language models: Surveying the landscape of diverse automated correction strategies

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T12:14:49.606259Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 09fe61dd-0ab5-4525-816d-8cbe1ee31d2f · outbound

This paper cites Qwq-32b: Embracing the power of reinforcement learning, March 2025.

THOUGHTTERMINATOR: Benchmarking, Calibrating, and Mitigating Overthinking in Reasoning Models Qwq-32b: Embracing the power of reinforcement learning, March 2025

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-16T12:14:48.886922Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f16e2643-33ed-428c-9448-276d20d50424 · outbound

This paper cites GPQA: A Graduate-Level Google-Proof Q&A Benchmark.

THOUGHTTERMINATOR: Benchmarking, Calibrating, and Mitigating Overthinking in Reasoning Models GPQA: A Graduate-Level Google-Proof Q&A Benchmark

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-16T12:14:48.891900Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e839c21f-89ab-424d-abcb-1bda4628b216 · outbound

This paper cites To CoT or not to CoT? Chain-of-thought helps mainly on math and symbolic reasoning.

THOUGHTTERMINATOR: Benchmarking, Calibrating, and Mitigating Overthinking in Reasoning Models To CoT or not to CoT? Chain-of-thought helps mainly on math and symbolic reasoning

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-16T12:14:48.897470Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 558dea1c-e9b8-4584-8e69-fd9aac865849 · outbound

This paper cites Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models.

THOUGHTTERMINATOR: Benchmarking, Calibrating, and Mitigating Overthinking in Reasoning Models Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-16T12:14:48.903190Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ac3de784-0977-4b60-8761-e7545f859678 · outbound

This paper cites Chain-of-Thought Prompting Elicits Reasoning in Large Language Models.

THOUGHTTERMINATOR: Benchmarking, Calibrating, and Mitigating Overthinking in Reasoning Models Chain-of-Thought Prompting Elicits Reasoning in Large Language Models

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-16T12:14:48.908634Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ba55d97d-57b5-48b0-b4ac-e7e288568540 · outbound

This paper cites Inference scaling laws: An empirical analysis of compute-optimal inference for problem-solving with language models.

THOUGHTTERMINATOR: Benchmarking, Calibrating, and Mitigating Overthinking in Reasoning Models Inference scaling laws: An empirical analysis of compute-optimal inference for problem-solving with language models

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T12:14:49.577326Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation bb2eac34-96ff-4878-8cbb-57175fa68ac2 · outbound

This paper cites Qwen2.5 Technical Report.

THOUGHTTERMINATOR: Benchmarking, Calibrating, and Mitigating Overthinking in Reasoning Models Qwen2.5 Technical Report

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-16T12:14:48.919605Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0f3c8050-3965-40e9-931c-3b6c50b10716 · outbound

This paper cites Towards thinking-optimal scaling of test-time compute for llm reasoning.

THOUGHTTERMINATOR: Benchmarking, Calibrating, and Mitigating Overthinking in Reasoning Models Towards thinking-optimal scaling of test-time compute for llm reasoning

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-16T12:14:48.925257Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9f6f807f-5a06-4f50-a79f-b2d089b54981 · outbound

This paper cites Think Smarter not Harder: Adaptive Reasoning with Inference Aware Optimization.

THOUGHTTERMINATOR: Benchmarking, Calibrating, and Mitigating Overthinking in Reasoning Models Think Smarter not Harder: Adaptive Reasoning with Inference Aware Optimization

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-16T12:14:48.930518Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1cdeee7e-923d-4e0c-a08e-82d9643bf942 · outbound

This paper cites DyVal: Dynamic Evaluation of Large Language Models for Reasoning Tasks.

THOUGHTTERMINATOR: Benchmarking, Calibrating, and Mitigating Overthinking in Reasoning Models DyVal: Dynamic Evaluation of Large Language Models for Reasoning Tasks

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-16T12:14:48.935323Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 52afbd10-403f-48a1-ae6b-0685b53e8fc9 · outbound

This paper cites @esa (Ref.

THOUGHTTERMINATOR: Benchmarking, Calibrating, and Mitigating Overthinking in Reasoning Models @esa (Ref

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-16T12:14:48.940185Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 40f9b3f5-fa2a-4150-b323-baef6c1e8ba7 · outbound

This paper cites an unresolved cited work.

THOUGHTTERMINATOR: Benchmarking, Calibrating, and Mitigating Overthinking in Reasoning Models Unresolved cited work

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-16T12:14:48.945251Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ddfa9544-8400-4079-bfc6-3dddd38848c9 · outbound

This paper cites JH cBP ]D aW Z *+b tW77wϙ 9w;Ri @ O.

THOUGHTTERMINATOR: Benchmarking, Calibrating, and Mitigating Overthinking in Reasoning Models JH cBP ]D aW Z *+b tW77wϙ 9w;Ri @ O

Reference 31

Resolution: malformed identifier; no resolver link, observed 2026-08-16T12:14:48.950737Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation 61691de3-89af-489a-b581-36ef3b0a6fab · inbound

AlphaOne: Reasoning Models Thinking Slow and Fast at Test Time cites this paper.

AlphaOne: Reasoning Models Thinking Slow and Fast at Test Time THOUGHTTERMINATOR: Benchmarking, Calibrating, and Mitigating Overthinking in Reasoning Models

Reference 46

Resolution: unresolved; no resolver link, observed 2026-08-07T12:35:43.292037Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 30c26e1a-4e14-4d49-b0b5-ba9f08e06c7d · inbound

How Far Are We from Optimal Reasoning Efficiency? cites this paper.

How Far Are We from Optimal Reasoning Efficiency? THOUGHTTERMINATOR: Benchmarking, Calibrating, and Mitigating Overthinking in Reasoning Models

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-07T05:49:38.203391Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 965ee1d5-4697-42e8-951f-79d218f4d34c · inbound

Do LLMs Overthink Basic Math Reasoning? Benchmarking the Accuracy-Efficiency Tradeoff in Language Models cites this paper.

Do LLMs Overthink Basic Math Reasoning? Benchmarking the Accuracy-Efficiency Tradeoff in Language Models THOUGHTTERMINATOR: Benchmarking, Calibrating, and Mitigating Overthinking in Reasoning Models

Reference 18

Resolution: verified exact; arxiv_id, observed 2026-05-19T06:27:07.339264Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 7efa6940-8689-4eaa-abf6-800d893ff98e · inbound

BudgetThinker: Empowering Budget-aware LLM Reasoning with Control Tokens cites this paper.

BudgetThinker: Empowering Budget-aware LLM Reasoning with Control Tokens THOUGHTTERMINATOR: Benchmarking, Calibrating, and Mitigating Overthinking in Reasoning Models

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-05T17:04:38.732463Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 14627de6-5ed9-4683-92de-60bac275179f · inbound

Dynamic Rollout Editing for Reducing Overthinking in RL-Trained Reasoning Models cites this paper.

Dynamic Rollout Editing for Reducing Overthinking in RL-Trained Reasoning Models THOUGHTTERMINATOR: Benchmarking, Calibrating, and Mitigating Overthinking in Reasoning Models

Reference 48

Resolution: verified exact; arxiv_id, observed 2026-06-27T01:20:20.464479Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.