Paper Citation Record · LEDGER

Think Clearly: Improving Reasoning via Redundant Token Pruning

As of 23 August 2026, this Paper Citation Record lists 16 of 16 outbound references and 2 inbound Pith citation observations for arXiv:2507.08806.

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

pith.paper-citation-record.v1
2507.08806 v1

Coverage vector

measured 16 of 16 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-07T00:23:18.761274Z

measured 18 of 18 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-22T06:32:14.747728+00:00

measured 2 of 2 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-06-28T23:13:15.593994Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-06-29T00:12:50.579209Z

Reference resolution

16 of 16 outbound references displayed

verified exact0
verified fuzzy1
unresolved14
parse uncertain0
malformed identifier1
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 209be614-bf2f-4e4a-8152-18d0bb36ce4b · outbound

This paper cites Deliberative Alignment: Reasoning Enables Safer Language Models.

Think Clearly: Improving Reasoning via Redundant Token Pruning Deliberative Alignment: Reasoning Enables Safer Language Models

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-07T00:23:17.986195Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e127b0b2-0807-45cd-99e0-64e5c77b1453 · outbound

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

Think Clearly: Improving Reasoning via Redundant Token Pruning DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-07T00:23:18.112703Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 73b35b8a-3fb6-4a2a-a2cc-9d4fbc9a8041 · outbound

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

Think Clearly: Improving Reasoning via Redundant Token Pruning Training Large Language Models to Reason in a Continuous Latent Space

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-07T00:23:18.238618Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0bbbe4e9-f948-457a-9418-52be2d6596e4 · outbound

This paper cites OpenAI o1 System Card.

Think Clearly: Improving Reasoning via Redundant Token Pruning OpenAI o1 System Card

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-07T00:23:18.457765Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 68a3ec76-a728-43d3-a209-688f3381f75f · outbound

This paper cites Transformers are Multi-State RNNs.

Think Clearly: Improving Reasoning via Redundant Token Pruning Transformers are Multi-State RNNs

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-07T00:23:18.564246Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5cb51790-2f5e-4aef-b239-fb43d2a12d50 · outbound

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

Think Clearly: Improving Reasoning via Redundant Token Pruning https://qwenlm.github.io/blog/ qwq-32b-preview/

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:23:19.025526Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation e45c445a-c739-4ec3-b2ad-2c02cd101810 · outbound

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

Think Clearly: Improving Reasoning via Redundant Token Pruning DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-07T00:23:18.738168Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a9ca7058-d9b0-4a0d-ba6d-d67f668e1201 · outbound

This paper cites Offline Reinforcement Learning for LLM Multi-Step Reasoning.

Think Clearly: Improving Reasoning via Redundant Token Pruning Offline Reinforcement Learning for LLM Multi-Step Reasoning

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-07T00:23:18.742674Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 780805b5-bb1e-423e-9bad-f75b79e90994 · outbound

This paper cites Effectively Controlling Reasoning Models through Thinking Intervention.

Think Clearly: Improving Reasoning via Redundant Token Pruning Effectively Controlling Reasoning Models through Thinking Intervention

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-07T00:23:18.747694Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8c455c61-e622-48db-b715-3f0ab16003a7 · outbound

This paper cites PyramidInfer: Pyramid KV Cache Compression for High-throughput LLM Inference.

Think Clearly: Improving Reasoning via Redundant Token Pruning PyramidInfer: Pyramid KV Cache Compression for High-throughput LLM Inference

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-07T00:23:18.752863Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7fea7b8d-44d8-4cbc-8f16-6f4a530c4f5a · outbound

This paper cites Specifically, we compute compressed budgets by multiplying LFull with target compression ratios of 25%, 50%.

Think Clearly: Improving Reasoning via Redundant Token Pruning Specifically, we compute compressed budgets by multiplying LFull with target compression ratios of 25%, 50%

Reference 300

Resolution: malformed identifier; raw_fallback, observed 2026-08-07T00:23:19.009883Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 5f350fed-0033-4731-a9ff-e35df758f504 · outbound

This paper cites Multi-hop Question Answering via Reasoning Chains.

Think Clearly: Improving Reasoning via Redundant Token Pruning Multi-hop Question Answering via Reasoning Chains

Reference 2019

Resolution: unresolved; no resolver link, observed 2026-08-07T00:23:17.847216Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 73678b22-af04-4e5e-ae50-6b25d8da9c40 · outbound

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

Think Clearly: Improving Reasoning via Redundant Token Pruning Measuring Mathematical Problem Solving With the MATH Dataset

Reference 2021

Resolution: unresolved; no resolver link, observed 2026-08-07T00:23:18.350265Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7aba488e-f72e-4576-8720-e8087df009fc · outbound

This paper cites AGIEval: A Human-Centric Benchmark for Evaluating Foundation Models.

Think Clearly: Improving Reasoning via Redundant Token Pruning AGIEval: A Human-Centric Benchmark for Evaluating Foundation Models

Reference 2023

Resolution: unresolved; no resolver link, observed 2026-08-07T00:23:18.756978Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 56767faf-511d-4806-9073-9a616c8f7e63 · outbound

This paper cites The Llama 3 Herd of Models.

Think Clearly: Improving Reasoning via Redundant Token Pruning The Llama 3 Herd of Models

Reference 2024

Resolution: unresolved; no resolver link, observed 2026-08-07T00:23:17.931772Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e5b29c5d-556e-45a6-a79d-d95d4a568e1a · outbound

This paper cites Monitoring Reasoning Models for Misbehavior and the Risks of Promoting Obfuscation.

Think Clearly: Improving Reasoning via Redundant Token Pruning Monitoring Reasoning Models for Misbehavior and the Risks of Promoting Obfuscation

Reference 2025

Resolution: unresolved; no resolver link, observed 2026-08-07T00:23:17.757511Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation 0cbc77ac-86ab-4344-abf7-5f9c801dfb08 · inbound

Towards Reasoning Era: A Survey of Long Chain-of-Thought for Reasoning Large Language Models cites this paper.

Towards Reasoning Era: A Survey of Long Chain-of-Thought for Reasoning Large Language Models Think Clearly: Improving Reasoning via Redundant Token Pruning

Reference 133

Resolution: verified exact; arxiv_id, observed 2026-05-12T08:40:42.024697Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 997dde5f-5dcc-44bc-9f54-065a0fbd3774 · inbound

VisionPulse: Dynamic Visual Sparsity for Efficient Multimodal Reasoning cites this paper.

VisionPulse: Dynamic Visual Sparsity for Efficient Multimodal Reasoning Think Clearly: Improving Reasoning via Redundant Token Pruning

Reference 2

Resolution: metadata mismatch; arxiv_id, observed 2026-06-29T00:12:50.580956Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.