Paper Citation Record · LEDGER

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

As of 15 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 35 inbound Pith citation observations for arXiv:2503.01141.

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

pith.paper-citation-record.v1
2503.01141 v2

Coverage vector

measured 0 of 0 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links

measured 35 of 35 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-15T06:32:42.880941+00:00

measured 35 of 35 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-15T20:52:27.824350Z

measured 1 of 1 external citation measurements

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

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

Reference resolution

0 of 0 outbound references displayed

verified exact0
verified fuzzy0
unresolved0
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

1
pith, observed 2026-08-05T02:28:24.338817Z

Outbound references

No outbound reference observations are available for this paper version.

Pith citing papers

Observation 4ab46e37-6808-4078-adcb-06aeeede12c2 · inbound

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

Stop Overthinking: A Survey on Efficient Reasoning for Large Language Models How Well do LLMs Compress Their Own Chain-of-Thought? A Token Complexity Approach

Reference 83

Resolution: verified exact; arxiv_id, observed 2026-05-14T01:29:56.978183Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 776fd629-9eb6-44f0-b51e-a5c6e1992dcb · inbound

Not All Thoughts are Generated Equal: Efficient LLM Reasoning via Multi-Turn Reinforcement Learning cites this paper.

Not All Thoughts are Generated Equal: Efficient LLM Reasoning via Multi-Turn Reinforcement Learning How Well do LLMs Compress Their Own Chain-of-Thought? A Token Complexity Approach

Reference 55

Resolution: unresolved; no resolver link, observed 2026-08-15T20:52:27.824350Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3c2359e8-6bf5-4eaf-ad61-da81ef55338c · inbound

AdaCoT: Pareto-Optimal Adaptive Chain-of-Thought Triggering via Reinforcement Learning cites this paper.

AdaCoT: Pareto-Optimal Adaptive Chain-of-Thought Triggering via Reinforcement Learning How Well do LLMs Compress Their Own Chain-of-Thought? A Token Complexity Approach

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-15T20:51:49.297164Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5cbcb441-eacb-47ef-9162-40e8d2112cc9 · inbound

Prolonged Reasoning Is Not All You Need: Certainty-Based Adaptive Routing for Efficient LLM/MLLM Reasoning cites this paper.

Prolonged Reasoning Is Not All You Need: Certainty-Based Adaptive Routing for Efficient LLM/MLLM Reasoning How Well do LLMs Compress Their Own Chain-of-Thought? A Token Complexity Approach

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-07T15:29:14.562977Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8eeefb32-8546-441d-a421-fa6719881067 · inbound

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

Not All Tokens Are What You Need In Thinking How Well do LLMs Compress Their Own Chain-of-Thought? A Token Complexity Approach

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-07T14:45:12.973380Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8987be17-15f5-4a5f-b16b-26af886cf3ac · inbound

VeriThinker: Learning to Verify Makes Reasoning Model Efficient cites this paper.

VeriThinker: Learning to Verify Makes Reasoning Model Efficient How Well do LLMs Compress Their Own Chain-of-Thought? A Token Complexity Approach

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-07T14:42:12.178937Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 30336f93-f526-486f-a932-954128d5133c · inbound

System-1.5 Reasoning: Traversal in Language and Latent Spaces with Dynamic Shortcuts cites this paper.

System-1.5 Reasoning: Traversal in Language and Latent Spaces with Dynamic Shortcuts How Well do LLMs Compress Their Own Chain-of-Thought? A Token Complexity Approach

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-07T14:27:38.910871Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 403a5b76-5ee4-4c61-a5f3-96edc1b40eb2 · inbound

Can Past Experience Accelerate LLM Reasoning? cites this paper.

Can Past Experience Accelerate LLM Reasoning? How Well do LLMs Compress Their Own Chain-of-Thought? A Token Complexity Approach

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-07T13:53:56.890817Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 24d68348-f322-4e3b-af59-53b5ea542bf5 · inbound

Long or short CoT? Investigating Instance-level Switch of Large Reasoning Models cites this paper.

Long or short CoT? Investigating Instance-level Switch of Large Reasoning Models How Well do LLMs Compress Their Own Chain-of-Thought? A Token Complexity Approach

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-07T10:52:43.571421Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 075382ea-dd8f-4d57-8f07-0c324621f3d4 · inbound

Transforming Expert Knowledge into Scalable Ontology via Large Language Models cites this paper.

Transforming Expert Knowledge into Scalable Ontology via Large Language Models How Well do LLMs Compress Their Own Chain-of-Thought? A Token Complexity Approach

Reference 43

Resolution: unresolved; no resolver link, observed 2026-08-07T05:21:03.148000Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1effa212-a6a7-4461-8958-7e997de45ed1 · inbound

Fast on the Easy, Deep on the Hard: Efficient Reasoning via Powered Length Penalty cites this paper.

Fast on the Easy, Deep on the Hard: Efficient Reasoning via Powered Length Penalty How Well do LLMs Compress Their Own Chain-of-Thought? A Token Complexity Approach

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-07T04:38:09.478670Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c7667202-731f-4a95-8a9c-6945d5bf36b0 · inbound

PREMISE: Scalable and Strategic Prompt Optimization for Efficient Mathematical Reasoning in Large Models cites this paper.

PREMISE: Scalable and Strategic Prompt Optimization for Efficient Mathematical Reasoning in Large Models How Well do LLMs Compress Their Own Chain-of-Thought? A Token Complexity Approach

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-07T04:26:29.051959Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

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

ReCUT: Balancing Reasoning Length and Accuracy in LLMs via Stepwise Trails and Preference Optimization cites this paper.

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 c508e0f9-1bb8-4906-9b2b-9da57a366953 · inbound

Efficient Reasoning Through Suppression of Self-Affirmation Reflections in Large Reasoning Models cites this paper.

Efficient Reasoning Through Suppression of Self-Affirmation Reflections in Large Reasoning Models How Well do LLMs Compress Their Own Chain-of-Thought? A Token Complexity Approach

Reference 2023

Resolution: unresolved; no resolver link, observed 2026-08-07T00:57:01.431811Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 91f29c4a-bcc5-4e15-8794-2a82d943533f · inbound

Is Long-to-Short a Free Lunch? Investigating Inconsistency and Reasoning Efficiency in LRMs cites this paper.

Is Long-to-Short a Free Lunch? Investigating Inconsistency and Reasoning Efficiency in LRMs How Well do LLMs Compress Their Own Chain-of-Thought? A Token Complexity Approach

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-06T23:10:25.880397Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation aa3b00cc-ddab-4cda-8919-57662c1559f5 · inbound

A Theory of Inference Compute Scaling: Reasoning through Directed Stochastic Skill Search cites this paper.

A Theory of Inference Compute Scaling: Reasoning through Directed Stochastic Skill Search How Well do LLMs Compress Their Own Chain-of-Thought? A Token Complexity Approach

Reference 122

Resolution: unresolved; no resolver link, observed 2026-08-07T05:07:39.996793Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5c0c275e-816f-4fe9-92d5-9b3b91d06193 · inbound

Reasoning on a Budget: A Survey of Adaptive and Controllable Test-Time Compute in LLMs cites this paper.

Reasoning on a Budget: A Survey of Adaptive and Controllable Test-Time Compute in LLMs How Well do LLMs Compress Their Own Chain-of-Thought? A Token Complexity Approach

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-06T20:43:09.527822Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b1cff093-9b88-4da9-be5c-07ed63605c80 · inbound

CoRE: Enhancing Metacognition with Label-free Self-evaluation in LRMs cites this paper.

CoRE: Enhancing Metacognition with Label-free Self-evaluation in LRMs How Well do LLMs Compress Their Own Chain-of-Thought? A Token Complexity Approach

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-06T19:16:31.318760Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation eeb2d815-694a-47a1-afe4-d495821f0d78 · 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 How Well do LLMs Compress Their Own Chain-of-Thought? A Token Complexity Approach

Reference 92

Resolution: unresolved; no resolver link, observed 2026-08-06T17:54:16.926500Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 574e74cd-6a1e-41ad-b3c1-a22270773492 · inbound

Re:Form -- Reducing Human Annotations in Scalable Formal Software Verification with RL in LLMs: A Preliminary Study on Dafny cites this paper.

Re:Form -- Reducing Human Annotations in Scalable Formal Software Verification with RL in LLMs: A Preliminary Study on Dafny How Well do LLMs Compress Their Own Chain-of-Thought? A Token Complexity Approach

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-06T15:20:13.782725Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 961f2d5d-c8f6-4927-a288-4176ebef7c33 · inbound

Rethinking the Chain-of-Thought: The Roles of In-Context Learning and Pre-trained Priors cites this paper.

Rethinking the Chain-of-Thought: The Roles of In-Context Learning and Pre-trained Priors How Well do LLMs Compress Their Own Chain-of-Thought? A Token Complexity Approach

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-05T12:49:08.451125Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 53ffe2a6-1c30-4b63-99f7-f68e480c8e67 · inbound

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

Learning to Reason Efficiently with Discounted Reinforcement Learning How Well do LLMs Compress Their Own Chain-of-Thought? A Token Complexity Approach

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-04T07:59:52.911656Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f096145a-9803-44a8-b391-cb1cb44945ab · inbound

R2-Router: A New Paradigm for LLM Routing with Reasoning cites this paper.

R2-Router: A New Paradigm for LLM Routing with Reasoning How Well do LLMs Compress Their Own Chain-of-Thought? A Token Complexity Approach

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-03T05:17:30.015340Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 31776a65-cbc2-4a41-bdf3-4db73b6d2c6d · inbound

Reasoning about Reasoning: BAPO Bounds on Chain-of-Thought Token Complexity in LLMs cites this paper.

Reasoning about Reasoning: BAPO Bounds on Chain-of-Thought Token Complexity in LLMs How Well do LLMs Compress Their Own Chain-of-Thought? A Token Complexity Approach

Reference 1965

Resolution: malformed identifier; no resolver link, observed 2026-08-03T05:19:45.889513Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b16a5ea6-cba5-4782-8300-d858b58c058a · inbound

Towards Efficient Large Language Reasoning Models via Extreme-Ratio Chain-of-Thought Compression cites this paper.

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: verified exact; arxiv_id, observed 2026-05-21T13:44:11.436773Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

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

Towards Efficient Large Language Reasoning Models via Extreme-Ratio Chain-of-Thought Compression cites this paper.

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 ad88d40c-23df-4e43-8706-e7f47dca5537 · inbound

Intelligent Drill-Down: Large Language Model-Driven Drill-Down Technique for Human-AI Collaborative Visual Exploration cites this paper.

Intelligent Drill-Down: Large Language Model-Driven Drill-Down Technique for Human-AI Collaborative Visual Exploration How Well do LLMs Compress Their Own Chain-of-Thought? A Token Complexity Approach

Reference 28

Resolution: verified exact; arxiv_id, observed 2026-05-10T06:41:36.861051Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 0e63e27d-0aa5-402b-af25-2f9c0a12ceb5 · inbound

Post Reasoning: Improving the Performance of Non-Thinking Models at No Cost cites this paper.

Post Reasoning: Improving the Performance of Non-Thinking Models at No Cost How Well do LLMs Compress Their Own Chain-of-Thought? A Token Complexity Approach

Reference 109

Resolution: metadata mismatch; arxiv_id, observed 2026-05-11T20:06:09.377376Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation f6727f4c-34e4-401c-ab16-6ebfaeb57273 · inbound

Reasoning Compression with Mixed-Policy Distillation cites this paper.

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 2026-08-15T06:32:42.880941+00:00.

Observation d8dd3893-56d5-4d31-bb15-a86debe7bb4a · inbound

SLAT: Segment-Level Adaptive Trimming for Efficient CoT Reasoning cites this paper.

SLAT: Segment-Level Adaptive Trimming for Efficient CoT Reasoning How Well do LLMs Compress Their Own Chain-of-Thought? A Token Complexity Approach

Reference 13

Resolution: verified exact; arxiv_id, observed 2026-06-28T22:32:44.436704Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 963b4978-f4aa-401a-94ce-a46907a1bd5b · inbound

Thinking Economically: A Hierarchical Framework for Adaptive-Complexity Reasoning in LLMs cites this paper.

Thinking Economically: A Hierarchical Framework for Adaptive-Complexity Reasoning in LLMs How Well do LLMs Compress Their Own Chain-of-Thought? A Token Complexity Approach

Reference 53

Resolution: metadata mismatch; arxiv_id, observed 2026-06-28T17:12:25.244358Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 26cf7ce9-43bb-4cb4-a279-853901432f8d · inbound

ThoughtFold: Folding Reasoning Chains via Introspective Preference Learning cites this paper.

ThoughtFold: Folding Reasoning Chains via Introspective Preference Learning How Well do LLMs Compress Their Own Chain-of-Thought? A Token Complexity Approach

Reference 12

Resolution: verified exact; arxiv_id, observed 2026-07-02T03:26:28.750825Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 94a043c8-4983-4d23-a67b-97e9b9be399f · 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 How Well do LLMs Compress Their Own Chain-of-Thought? A Token Complexity Approach

Reference 23

Resolution: verified exact; arxiv_id, observed 2026-06-27T01:20:20.433389Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 0d24e869-e3be-468e-a517-2a4a6f159c49 · inbound

Prompt Compression via Activation Aggregation cites this paper.

Prompt Compression via Activation Aggregation How Well do LLMs Compress Their Own Chain-of-Thought? A Token Complexity Approach

Reference 15

Resolution: verified exact; local_arxiv, observed 2026-07-10T08:06:57.494774Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation e4ebe9b6-1058-4b5b-b329-185e335ac99a · inbound

Is Your Model Thinking or Just Stagnating? PUMA: Diagnosing Reasoning Pathology via Phase-Momentum Alignment cites this paper.

Is Your Model Thinking or Just Stagnating? PUMA: Diagnosing Reasoning Pathology via Phase-Momentum Alignment How Well do LLMs Compress Their Own Chain-of-Thought? A Token Complexity Approach

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-01T18:49:28.691150Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.