Paper Citation Record · LEDGER

TrimR: Verifier-based Training-Free Thinking Compression for Efficient Test-Time Scaling

As of 9 August 2026, this Paper Citation Record lists 36 of 36 outbound references and 8 inbound Pith citation observations for arXiv:2505.17155.

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

pith.paper-citation-record.v1
2505.17155 v2

Coverage vector

measured 36 of 36 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-07T15:00:39.557894Z

measured 44 of 44 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-09T06:31:02.800959+00:00

measured 8 of 8 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-05T13:48:21.999552Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-07-02T16:57:10.046343Z

Reference resolution

36 of 36 outbound references displayed

verified exact0
verified fuzzy4
unresolved32
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 4938c3c8-0baf-41bc-80fc-1252ffa9a6b4 · outbound

This paper cites an unresolved cited work.

TrimR: Verifier-based Training-Free Thinking Compression for Efficient Test-Time Scaling Unresolved cited work

Reference 1

Resolution: unresolved; raw_fallback, observed 2026-08-07T15:00:41.689324Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 61db4f76-52eb-48bc-b167-367e01e82b6b · outbound

This paper cites an unresolved cited work.

TrimR: Verifier-based Training-Free Thinking Compression for Efficient Test-Time Scaling Unresolved cited work

Reference 2

Resolution: unresolved; raw_fallback, observed 2026-08-07T15:00:41.560164Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation f77e0b24-0d3e-44f4-bae9-a2e144c4cbb5 · outbound

This paper cites Training language models to reason efficiently, 2025.

TrimR: Verifier-based Training-Free Thinking Compression for Efficient Test-Time Scaling Training language models to reason efficiently, 2025

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-07T15:00:35.420133Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d7fdc648-dd6f-48ff-9af4-f9cc53ddb0cd · outbound

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

TrimR: Verifier-based Training-Free Thinking Compression for Efficient Test-Time Scaling Do NOT Think That Much for 2+3=? On the Overthinking of o1-Like LLMs

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-07T15:00:35.490663Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c5aa9570-f12d-4cd8-bd51-dd5f7adbd967 · outbound

This paper cites Efficiently Scaling LLM Reasoning with Certaindex.

TrimR: Verifier-based Training-Free Thinking Compression for Efficient Test-Time Scaling Efficiently Scaling LLM Reasoning with Certaindex

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-07T15:00:35.543462Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation de6f64d6-ccf3-4dcf-b938-1a62ef31478e · outbound

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

TrimR: Verifier-based Training-Free Thinking Compression for Efficient Test-Time Scaling DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-07T15:00:35.622260Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c7b8289c-19b0-48b7-ba03-764259908cdb · outbound

This paper cites Token-Budget-Aware LLM Reasoning.

TrimR: Verifier-based Training-Free Thinking Compression for Efficient Test-Time Scaling Token-Budget-Aware LLM Reasoning

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-07T15:00:35.696509Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9920acc6-6221-456c-93c6-6166c0943264 · outbound

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

TrimR: Verifier-based Training-Free Thinking Compression for Efficient Test-Time Scaling Training Large Language Models to Reason in a Continuous Latent Space

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-07T15:00:35.804525Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 347184a9-f8c3-4699-b8e9-e30fc665b34b · outbound

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

TrimR: Verifier-based Training-Free Thinking Compression for Efficient Test-Time Scaling Measuring Mathematical Problem Solving With the MATH Dataset

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-07T15:00:35.873225Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 35b0c50e-6626-4681-9a11-cb62164950e7 · outbound

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

TrimR: Verifier-based Training-Free Thinking Compression for Efficient Test-Time Scaling ThinkPrune: Pruning Long Chain-of-Thought of LLMs via Reinforcement Learning

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-07T15:00:35.955208Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8d732f7a-7121-4639-87c0-d55c398ddc69 · outbound

This paper cites Semantic Uncertainty: Linguistic Invariances for Uncertainty Estimation in Natural Language Generation.

TrimR: Verifier-based Training-Free Thinking Compression for Efficient Test-Time Scaling Semantic Uncertainty: Linguistic Invariances for Uncertainty Estimation in Natural Language Generation

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-07T15:00:36.024423Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c6b9500c-08e7-4207-81b1-d2d7d7200aaa · outbound

This paper cites Gonzalez, Hao Zhang, and Ion Stoica.

TrimR: Verifier-based Training-Free Thinking Compression for Efficient Test-Time Scaling Gonzalez, Hao Zhang, and Ion Stoica

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-07T15:00:36.150138Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b0c88154-532e-48ef-be59-9373f2f57458 · outbound

This paper cites Let’s verify step by step.

TrimR: Verifier-based Training-Free Thinking Compression for Efficient Test-Time Scaling Let’s verify step by step

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-07T15:00:36.306800Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a6bef398-d6d4-415e-a675-14e741533813 · outbound

This paper cites Inference-time scaling for generalist reward modeling.

TrimR: Verifier-based Training-Free Thinking Compression for Efficient Test-Time Scaling Inference-time scaling for generalist reward modeling

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-07T15:00:36.453645Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 81762ead-249f-4aca-8442-37830a99087e · outbound

This paper cites Adaptive Inference-Time Compute: LLMs Can Predict if They Can Do Better, Even Mid-Generation.

TrimR: Verifier-based Training-Free Thinking Compression for Efficient Test-Time Scaling Adaptive Inference-Time Compute: LLMs Can Predict if They Can Do Better, Even Mid-Generation

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-07T15:00:36.638727Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 64c99127-1951-4a75-b387-082270710121 · outbound

This paper cites Deepseek-r1 thoughtology: Let’s< think> about llm reasoning.

TrimR: Verifier-based Training-Free Thinking Compression for Efficient Test-Time Scaling Deepseek-r1 thoughtology: Let’s< think> about llm reasoning

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-07T15:00:36.774944Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c1d34d6b-4868-4599-a546-7b4e13e749a5 · outbound

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

TrimR: Verifier-based Training-Free Thinking Compression for Efficient Test-Time Scaling Self-Training Elicits Concise Reasoning in Large Language Models

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-07T15:00:36.958178Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f40dae79-cc1e-4686-8f21-74ca95f6f4aa · outbound

This paper cites Openai o1 system card, December 2024.

TrimR: Verifier-based Training-Free Thinking Compression for Efficient Test-Time Scaling Openai o1 system card, December 2024

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:00:41.374231Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation bab46daf-8ed2-4687-a915-eebce0be762c · outbound

This paper cites SpecReason: Fast and Accurate Inference-Time Compute via Speculative Reasoning.

TrimR: Verifier-based Training-Free Thinking Compression for Efficient Test-Time Scaling SpecReason: Fast and Accurate Inference-Time Compute via Speculative Reasoning

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-07T15:00:37.256651Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 664eba5f-801e-4d3f-8ff4-3f25aa6dc6ad · outbound

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

TrimR: Verifier-based Training-Free Thinking Compression for Efficient Test-Time Scaling Gpqa: A graduate-level google-proof q&a benchmark

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-07T15:00:37.365726Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f591add5-f2d5-4d99-9324-20b01f2c4579 · outbound

This paper cites Fast Best-of-N Decoding via Speculative Rejection.

TrimR: Verifier-based Training-Free Thinking Compression for Efficient Test-Time Scaling Fast Best-of-N Decoding via Speculative Rejection

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-07T15:00:37.510921Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8ae1fccb-6ae4-4fea-92e2-47cb8af45618 · outbound

This paper cites Pangu pro moe: Mixture of grouped experts for efficient sparsity, 2025.

TrimR: Verifier-based Training-Free Thinking Compression for Efficient Test-Time Scaling Pangu pro moe: Mixture of grouped experts for efficient sparsity, 2025

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:00:41.190383Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation c076957c-f8ac-4be2-9483-ccce351dc9db · outbound

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

TrimR: Verifier-based Training-Free Thinking Compression for Efficient Test-Time Scaling Kimi k1.5: Scaling Reinforcement Learning with LLMs

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-07T15:00:37.779433Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f01c4868-1551-441b-ad20-f90f8dc78690 · outbound

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

TrimR: Verifier-based Training-Free Thinking Compression for Efficient Test-Time Scaling Qwq-32b: Embracing the power of reinforcement learning, March 2025

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-07T15:00:37.891709Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e5acae85-03df-4901-b7e9-29fc8d84fdbf · outbound

This paper cites Efficient Reasoning for LLMs through Speculative Chain-of-Thought.

TrimR: Verifier-based Training-Free Thinking Compression for Efficient Test-Time Scaling Efficient Reasoning for LLMs through Speculative Chain-of-Thought

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-07T15:00:37.987209Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2799711d-6d76-459c-b509-abb474de61b3 · outbound

This paper cites Sampling-efficient test-time scaling: Self-estimating the best-of-n sampling in early decoding.

TrimR: Verifier-based Training-Free Thinking Compression for Efficient Test-Time Scaling Sampling-efficient test-time scaling: Self-estimating the best-of-n sampling in early decoding

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-07T15:00:38.108294Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ee108cac-7ee0-45cc-a0d0-0a061f8d0b14 · outbound

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

TrimR: Verifier-based Training-Free Thinking Compression for Efficient Test-Time Scaling Inference scaling laws: An empirical analysis of compute-optimal inference for llm problem-solving

Reference 27

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:00:41.023005Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 5b592302-f65d-4675-a45c-b0b19ad6b29d · outbound

This paper cites Enhancing LLM Reasoning via Critique Models with Test-Time and Training-Time Supervision.

TrimR: Verifier-based Training-Free Thinking Compression for Efficient Test-Time Scaling Enhancing LLM Reasoning via Critique Models with Test-Time and Training-Time Supervision

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-07T15:00:38.405708Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7741e384-1c0d-4918-96a6-58c668139e13 · outbound

This paper cites Tokenskip: Controllable chain-of-thought compression in llms.

TrimR: Verifier-based Training-Free Thinking Compression for Efficient Test-Time Scaling Tokenskip: Controllable chain-of-thought compression in llms

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-07T15:00:38.547548Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 930509f1-9111-4db4-992b-68cc92b3c6f6 · outbound

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

TrimR: Verifier-based Training-Free Thinking Compression for Efficient Test-Time Scaling Chain of Draft: Thinking Faster by Writing Less

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-07T15:00:38.702521Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 16b72ca1-7573-4a6d-af0f-b602783562f4 · outbound

This paper cites Inftythink: Breaking the length limits of long-context reasoning in large language models.

TrimR: Verifier-based Training-Free Thinking Compression for Efficient Test-Time Scaling Inftythink: Breaking the length limits of long-context reasoning in large language models

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-07T15:00:38.863865Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ebb63f7e-a7b7-405e-83ca-e9b834da244a · outbound

This paper cites Qwen2 Technical Report.

TrimR: Verifier-based Training-Free Thinking Compression for Efficient Test-Time Scaling Qwen2 Technical Report

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-07T15:00:38.961045Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bac34b85-d1c9-4e33-9cc6-da66e92629fa · outbound

This paper cites Dynamic early exit in reasoning models.

TrimR: Verifier-based Training-Free Thinking Compression for Efficient Test-Time Scaling Dynamic early exit in reasoning models

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-07T15:00:39.114238Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b9d9b461-877f-440b-b121-35c986759125 · outbound

This paper cites Distilling System 2 into System 1.

TrimR: Verifier-based Training-Free Thinking Compression for Efficient Test-Time Scaling Distilling System 2 into System 1

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-07T15:00:39.276955Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation eb64e39e-19d9-4e54-9b0c-ae4d0eef3789 · outbound

This paper cites Lightthinker: Thinking step-by-step compression.

TrimR: Verifier-based Training-Free Thinking Compression for Efficient Test-Time Scaling Lightthinker: Thinking step-by-step compression

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-07T15:00:39.403056Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 80610814-90c2-4c98-9d47-d0ff1188728e · outbound

This paper cites \n\nBut”, “\n\nWait.

TrimR: Verifier-based Training-Free Thinking Compression for Efficient Test-Time Scaling \n\nBut”, “\n\nWait

Reference 36

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:00:40.850661Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Pith citing papers

Observation ef5db565-78d8-4b36-9ee7-2987b77b0a8f · 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 TrimR: Verifier-based Training-Free Thinking Compression for Efficient Test-Time Scaling

Reference 105

Resolution: verified exact; arxiv_id, observed 2026-05-14T01:29:57.311884Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation b75ec70c-a409-46f9-af64-e1c149f1ad54 · inbound

Scaling Up, Speeding Up: A Benchmark of Speculative Decoding for Efficient LLM Test-Time Scaling cites this paper.

Scaling Up, Speeding Up: A Benchmark of Speculative Decoding for Efficient LLM Test-Time Scaling TrimR: Verifier-based Training-Free Thinking Compression for Efficient Test-Time Scaling

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-05T13:48:21.999552Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d451bfb3-b955-4d1e-9e23-ff9d192583d4 · inbound

CRISP: Compressed Reasoning via Iterative Self-Policy Distillation cites this paper.

CRISP: Compressed Reasoning via Iterative Self-Policy Distillation TrimR: Verifier-based Training-Free Thinking Compression for Efficient Test-Time Scaling

Reference 15

Resolution: verified exact; arxiv_id, observed 2026-05-15T15:46:12.576689Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 8e20d8e8-29d2-41ce-a07a-7908ff4f5d9a · inbound

SAT: Balancing Reasoning Accuracy and Efficiency with Stepwise Adaptive Thinking cites this paper.

SAT: Balancing Reasoning Accuracy and Efficiency with Stepwise Adaptive Thinking TrimR: Verifier-based Training-Free Thinking Compression for Efficient Test-Time Scaling

Reference 18

Resolution: verified exact; arxiv_id, observed 2026-05-11T08:10:58.576083Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation e1e97b44-1ccd-4e94-8303-f41c634cc14b · 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 TrimR: Verifier-based Training-Free Thinking Compression for Efficient Test-Time Scaling

Reference 248

Resolution: verified exact; arxiv_id, observed 2026-05-11T20:06:09.518342Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 9787e9c6-30b7-4dc0-9ac6-eab2299d2540 · inbound

Breaking the Reward Barrier: Accelerating Tree-of-Thought Reasoning via Speculative Exploration cites this paper.

Breaking the Reward Barrier: Accelerating Tree-of-Thought Reasoning via Speculative Exploration TrimR: Verifier-based Training-Free Thinking Compression for Efficient Test-Time Scaling

Reference 35

Resolution: verified exact; arxiv_id, observed 2026-05-12T06:51:30.105150Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation a038321f-47f6-4d97-9eaa-08be9c8e8818 · inbound

Breaking the Reward Barrier: Accelerating Tree-of-Thought Reasoning via Speculative Exploration cites this paper.

Breaking the Reward Barrier: Accelerating Tree-of-Thought Reasoning via Speculative Exploration TrimR: Verifier-based Training-Free Thinking Compression for Efficient Test-Time Scaling

Reference 35

Resolution: verified exact; arxiv_id, observed 2026-05-15T05:15:03.439970Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 22c6436e-17d7-4104-9b37-7dde7a974f18 · inbound

DyCon: Dynamic Reasoning Control via Evolving Difficulty Modeling cites this paper.

DyCon: Dynamic Reasoning Control via Evolving Difficulty Modeling TrimR: Verifier-based Training-Free Thinking Compression for Efficient Test-Time Scaling

Reference 19

Resolution: verified exact; arxiv_id, observed 2026-07-02T16:57:10.048030Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.