Paper Citation Record · LEDGER

Towards Efficient Large Language Reasoning Models via Extreme-Ratio Chain-of-Thought Compression

As of 7 August 2026, this Paper Citation Record lists 37 of 37 outbound references and 3 inbound Pith citation observations for arXiv:2602.08324.

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

pith.paper-citation-record.v1
2602.08324 v4

Coverage vector

measured 37 of 37 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-03T03:25:23.127224Z

measured 40 of 40 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-06T06:34:29.942622+00:00

measured 3 of 3 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-06T17:07:01.912817Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-05-12T08:51:25.771911Z

Reference resolution

37 of 37 outbound references displayed

verified exact0
verified fuzzy0
unresolved37
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation b787c03f-2f8c-4f87-9519-111c2c64fd39 · outbound

This paper cites Aimo validation amc (amc 2023 sub- set).

Towards Efficient Large Language Reasoning Models via Extreme-Ratio Chain-of-Thought Compression Aimo validation amc (amc 2023 sub- set)

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-03T03:25:21.652002Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6f823bb8-2644-4fb1-b4b4-beb4b53345dd · outbound

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

Towards Efficient Large Language Reasoning Models via Extreme-Ratio Chain-of-Thought Compression Do NOT Think That Much for 2+3=? On the Overthinking of o1-Like LLMs

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-03T03:25:21.948273Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 689fa491-2b48-482c-9e3a-c1250e06a65b · outbound

This paper cites Training Verifiers to Solve Math Word Problems.

Towards Efficient Large Language Reasoning Models via Extreme-Ratio Chain-of-Thought Compression Training Verifiers to Solve Math Word Problems

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-03T03:25:22.036858Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 93275367-85c0-44f0-86fb-34e2801cc0bf · outbound

This paper cites Missing Premise exacerbates Overthinking: Are Reasoning Models losing Critical Thinking Skill?.

Towards Efficient Large Language Reasoning Models via Extreme-Ratio Chain-of-Thought Compression Missing Premise exacerbates Overthinking: Are Reasoning Models losing Critical Thinking Skill?

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-03T03:25:22.240045Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 42201804-09fc-49d4-b13d-f17754432bd8 · outbound

This paper cites Thinkless: LLM Learns When to Think.

Towards Efficient Large Language Reasoning Models via Extreme-Ratio Chain-of-Thought Compression Thinkless: LLM Learns When to Think

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-03T03:25:22.412034Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6cdf3ff9-098a-4a9c-80ae-bfa056f7648e · outbound

This paper cites The Llama 3 Herd of Models.

Towards Efficient Large Language Reasoning Models via Extreme-Ratio Chain-of-Thought Compression The Llama 3 Herd of Models

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-03T03:25:22.577703Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 944adebc-fe28-4677-bdcc-cd6edcc65b4f · outbound

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

Towards Efficient Large Language Reasoning Models via Extreme-Ratio Chain-of-Thought Compression DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-03T03:25:22.800369Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 29853ef6-98c9-4dfc-9d7b-9fd3d019a526 · outbound

This paper cites Token-budget-aware llm reasoning.

Towards Efficient Large Language Reasoning Models via Extreme-Ratio Chain-of-Thought Compression Token-budget-aware llm reasoning

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-03T03:25:22.966268Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 944dddfa-7dcf-4033-82de-a0af1b45d601 · outbound

This paper cites Training Large Language Models to Reason in a Continuous Latent Space.

Towards Efficient Large Language Reasoning Models via Extreme-Ratio Chain-of-Thought Compression Training Large Language Models to Reason in a Continuous Latent Space

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-03T03:25:23.051877Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a7a60c79-0cca-42b5-bf27-deaf55c2957c · outbound

This paper cites Measuring Massive Multitask Language Understanding.

Towards Efficient Large Language Reasoning Models via Extreme-Ratio Chain-of-Thought Compression Measuring Massive Multitask Language Understanding

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-03T03:25:23.055603Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cc252d22-aa4f-4b2f-8835-637288b4c727 · outbound

This paper cites Distill- ing step-by-step! outperforming larger language models with less training data and smaller model sizes.

Towards Efficient Large Language Reasoning Models via Extreme-Ratio Chain-of-Thought Compression Distill- ing step-by-step! outperforming larger language models with less training data and smaller model sizes

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-03T03:25:23.059549Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2551d760-6d40-4c57-885f-b74047e6332f · outbound

This paper cites GPT-4o System Card.

Towards Efficient Large Language Reasoning Models via Extreme-Ratio Chain-of-Thought Compression GPT-4o System Card

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-03T03:25:23.066774Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2ab171ee-c6a5-40d3-bd4d-5fb41b370f7b · outbound

This paper cites A Chain-of-Thought Is as Strong as Its Weakest Link: A Benchmark for Verifiers of Reasoning Chains.

Towards Efficient Large Language Reasoning Models via Extreme-Ratio Chain-of-Thought Compression A Chain-of-Thought Is as Strong as Its Weakest Link: A Benchmark for Verifiers of Reasoning Chains

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-03T03:25:23.069996Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2b50410e-ef9f-4db9-afb8-0eab5dee48b2 · outbound

This paper cites OpenAI o1 System Card.

Towards Efficient Large Language Reasoning Models via Extreme-Ratio Chain-of-Thought Compression OpenAI o1 System Card

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-03T03:25:23.073538Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 33b6f1fa-13fa-4b47-9045-1a7d96d29872 · outbound

This paper cites LLMLingua: Compressing Prompts for Accelerated Inference of Large Language Models.

Towards Efficient Large Language Reasoning Models via Extreme-Ratio Chain-of-Thought Compression LLMLingua: Compressing Prompts for Accelerated Inference of Large Language Models

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-03T03:25:23.076743Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 078b5a79-d31b-40a2-91fc-5d0ebe7a4ad1 · outbound

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

Towards Efficient Large Language Reasoning Models via Extreme-Ratio Chain-of-Thought Compression How Well do LLMs Compress Their Own Chain-of-Thought? A Token Complexity Approach

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-03T03:25:23.079397Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2d11f3d9-71d8-4b9e-880f-5a737ed32fcd · outbound

This paper cites Camel: Communicative agents for “mind” exploration of large language model society.Advances in Neural In- formation Processing Systems, 36:51991–52008, 2023a.

Towards Efficient Large Language Reasoning Models via Extreme-Ratio Chain-of-Thought Compression Camel: Communicative agents for “mind” exploration of large language model society.Advances in Neural In- formation Processing Systems, 36:51991–52008, 2023a

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-03T03:25:23.082140Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 177561b4-6493-4f29-9d35-87c6eb984f55 · outbound

This paper cites LLMLingua-2: Data Distillation for Efficient and Faithful Task-Agnostic Prompt Compression.

Towards Efficient Large Language Reasoning Models via Extreme-Ratio Chain-of-Thought Compression LLMLingua-2: Data Distillation for Efficient and Faithful Task-Agnostic Prompt Compression

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-03T03:25:23.085492Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c9fa71df-135f-4ea9-a372-c5a149fd64de · outbound

This paper cites Are NLP Models really able to Solve Simple Math Word Problems?.

Towards Efficient Large Language Reasoning Models via Extreme-Ratio Chain-of-Thought Compression Are NLP Models really able to Solve Simple Math Word Problems?

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-03T03:25:23.089243Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f3d84f19-c962-47c5-9bab-fa16907ba3ba · outbound

This paper cites Style-Compress: An LLM-Based Prompt Compression Framework Considering Task-Specific Styles.

Towards Efficient Large Language Reasoning Models via Extreme-Ratio Chain-of-Thought Compression Style-Compress: An LLM-Based Prompt Compression Framework Considering Task-Specific Styles

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-03T03:25:23.091906Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a98dc63f-898c-48ee-b20d-03a20c88dc2c · outbound

This paper cites and Roth, D.

Towards Efficient Large Language Reasoning Models via Extreme-Ratio Chain-of-Thought Compression and Roth, D

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-03T03:25:23.094844Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c86d522e-4a0d-4f9f-825c-7f0ffecb28d6 · outbound

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

Towards Efficient Large Language Reasoning Models via Extreme-Ratio Chain-of-Thought Compression Stop Overthinking: A Survey on Efficient Reasoning for Large Language Models

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-03T03:25:23.100560Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5aca0811-63d2-48b0-a1eb-7d3a9b7c5039 · outbound

This paper cites Kimi K2: Open Agentic Intelligence.

Towards Efficient Large Language Reasoning Models via Extreme-Ratio Chain-of-Thought Compression Kimi K2: Open Agentic Intelligence

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-03T03:25:23.103962Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0bd65bd6-05fd-40e6-bfdb-9c149437f192 · outbound

This paper cites Wait, We Don't Need to "Wait"! Removing Thinking Tokens Improves Reasoning Efficiency.

Towards Efficient Large Language Reasoning Models via Extreme-Ratio Chain-of-Thought Compression Wait, We Don't Need to "Wait"! Removing Thinking Tokens Improves Reasoning Efficiency

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-03T03:25:23.107762Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7540ab61-7b11-48c2-9f55-80b9e1ebd974 · outbound

This paper cites SoftCoT: Soft Chain-of-Thought for Efficient Reasoning with LLMs.

Towards Efficient Large Language Reasoning Models via Extreme-Ratio Chain-of-Thought Compression SoftCoT: Soft Chain-of-Thought for Efficient Reasoning with LLMs

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-03T03:25:23.113752Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 82472bad-f486-48c4-8989-170418be3d6b · outbound

This paper cites Qwen3 Technical Report.

Towards Efficient Large Language Reasoning Models via Extreme-Ratio Chain-of-Thought Compression Qwen3 Technical Report

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-03T03:25:23.116384Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a087667f-21cd-453c-814c-2c39eca4adb7 · outbound

This paper cites CompAct: Compressing Retrieved Documents Actively for Question Answering.

Towards Efficient Large Language Reasoning Models via Extreme-Ratio Chain-of-Thought Compression CompAct: Compressing Retrieved Documents Actively for Question Answering

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-03T03:25:23.118918Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ed337479-3dd2-4505-9de1-f447ec5fd921 · outbound

This paper cites MetaMath: Bootstrap Your Own Mathematical Questions for Large Language Models.

Towards Efficient Large Language Reasoning Models via Extreme-Ratio Chain-of-Thought Compression MetaMath: Bootstrap Your Own Mathematical Questions for Large Language Models

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-03T03:25:23.121511Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6966de69-b04c-4b94-8a81-eacccd573cda · outbound

This paper cites Not All Tokens Are What You Need In Thinking.

Towards Efficient Large Language Reasoning Models via Extreme-Ratio Chain-of-Thought Compression Not All Tokens Are What You Need In Thinking

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-03T03:25:23.124002Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d8562d37-fc08-4436-b9a8-be6c2582204c · outbound

This paper cites BudgetγOurs (Wins) llmlingua-2 (Wins) Ours Pref.

Towards Efficient Large Language Reasoning Models via Extreme-Ratio Chain-of-Thought Compression BudgetγOurs (Wins) llmlingua-2 (Wins) Ours Pref

Reference 50

Resolution: unresolved; no resolver link, observed 2026-08-03T03:25:23.127224Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9364801c-1f5d-4e98-aed8-44f7a9aaf310 · outbound

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

Towards Efficient Large Language Reasoning Models via Extreme-Ratio Chain-of-Thought Compression Between Underthinking and Overthinking: An Empirical Study of Reasoning Length and correctness in LLMs

Reference 2015

Resolution: unresolved; no resolver link, observed 2026-08-03T03:25:23.097878Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6c8be02d-a32e-4279-95f1-5b3314e97aa2 · outbound

This paper cites Pangu Embedded: An Efficient Dual-system LLM Reasoner with Metacognition.

Towards Efficient Large Language Reasoning Models via Extreme-Ratio Chain-of-Thought Compression Pangu Embedded: An Efficient Dual-system LLM Reasoner with Metacognition

Reference 2020

Resolution: unresolved; no resolver link, observed 2026-08-03T03:25:21.840888Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 569f5b33-37f9-432c-a75d-c63ae61cff50 · outbound

This paper cites Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities.

Towards Efficient Large Language Reasoning Models via Extreme-Ratio Chain-of-Thought Compression Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities

Reference 2021

Resolution: unresolved; no resolver link, observed 2026-08-03T03:25:22.094581Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 07391250-0c93-4703-a1d4-5a988d70d5eb · outbound

This paper cites T., Wang, W., Li, Y ., and Li, W.

Towards Efficient Large Language Reasoning Models via Extreme-Ratio Chain-of-Thought Compression T., Wang, W., Li, Y ., and Li, W

Reference 2022

Resolution: unresolved; no resolver link, observed 2026-08-03T03:25:23.110772Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 92758fd6-999d-4a20-9112-4846162f7f83 · outbound

This paper cites Vision-R1: Incentivizing Reasoning Capability in Multimodal Large Language Models.

Towards Efficient Large Language Reasoning Models via Extreme-Ratio Chain-of-Thought Compression Vision-R1: Incentivizing Reasoning Capability in Multimodal Large Language Models

Reference 2023

Resolution: unresolved; no resolver link, observed 2026-08-03T03:25:23.063091Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c0bc6187-0996-4b39-aad7-4e3e148466d8 · outbound

This paper cites Derived from AMC12 2022–2023 problems; this work uses the 2023 subset.

Towards Efficient Large Language Reasoning Models via Extreme-Ratio Chain-of-Thought Compression Derived from AMC12 2022–2023 problems; this work uses the 2023 subset

Reference 2024

Resolution: unresolved; no resolver link, observed 2026-08-03T03:25:21.706216Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 64574e80-1e3a-4f5e-aa6e-71a943f578e6 · outbound

This paper cites Longformer: The Long-Document Transformer.

Towards Efficient Large Language Reasoning Models via Extreme-Ratio Chain-of-Thought Compression Longformer: The Long-Document Transformer

Reference 2025

Resolution: unresolved; no resolver link, observed 2026-08-03T03:25:21.768283Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation 8f051acc-4b4b-475f-b939-021194b0c8ec · inbound

Shorthand for Thought: Compressing LLM Reasoning via Entropy-Guided Supertokens cites this paper.

Shorthand for Thought: Compressing LLM Reasoning via Entropy-Guided Supertokens Towards Efficient Large Language Reasoning Models via Extreme-Ratio Chain-of-Thought Compression

Reference 10

Resolution: verified exact; arxiv_id, observed 2026-05-20T00:00:33.920223Z

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 e88854b1-0ecd-4d8f-9c0a-2b69aa6a0591 · inbound

ThinkReset: Learnable Intermediate Interface Construction for Bounded-Context Long-Horizon Reasoning cites this paper.

ThinkReset: Learnable Intermediate Interface Construction for Bounded-Context Long-Horizon Reasoning Towards Efficient Large Language Reasoning Models via Extreme-Ratio Chain-of-Thought Compression

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-03T00:54:35.872755Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3d84b4c5-e307-46b6-ab4b-e2182e7b85a1 · inbound

Fewer Tokens, Smaller Cache: Reward-Coordinated Efficient Reasoning cites this paper.

Fewer Tokens, Smaller Cache: Reward-Coordinated Efficient Reasoning Towards Efficient Large Language Reasoning Models via Extreme-Ratio Chain-of-Thought Compression

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-06T17:07:01.912817Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.