Paper Citation Record · LEDGER

Selective Latent Thinking: Adaptive Compression of LLM Reasoning Chains

As of 22 August 2026, this Paper Citation Record lists 25 of 25 outbound references and 1 inbound Pith citation observation for arXiv:2605.25745.

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

pith.paper-citation-record.v1
2605.25745 v1

Coverage vector

measured 25 of 25 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-06-29T21:42:08.610000Z

measured 26 of 26 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 1 of 1 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-15T14:41:17.911429Z

measured 0 of 1 external citation measurements

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

Source: pith, observed 2026-08-15T14:41:18.231573Z

Reference resolution

25 of 25 outbound references displayed

verified exact21
verified fuzzy0
unresolved4
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 0fe43f3e-450b-47fe-9999-357dd4ae2610 · outbound

This paper cites L1: Controlling How Long A Reasoning Model Thinks With Reinforcement Learning.

Selective Latent Thinking: Adaptive Compression of LLM Reasoning Chains L1: Controlling How Long A Reasoning Model Thinks With Reinforcement Learning

Reference 1

Resolution: verified exact; local_arxiv, observed 2026-06-29T21:43:59.086669Z

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 974438fd-461b-4902-945f-cd5326eb68d5 · outbound

This paper cites Sketch-of-thought: Efficient llm reasoning with adaptive cognitive-inspired sketching.

Selective Latent Thinking: Adaptive Compression of LLM Reasoning Chains Sketch-of-thought: Efficient llm reasoning with adaptive cognitive-inspired sketching

Reference 2

Resolution: unresolved; no resolver link, observed 2026-06-29T21:42:08.610000Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 183e85d2-d286-4278-9cdd-a24f84f7e359 · outbound

This paper cites Medusa: Simple LLM Inference Acceleration Framework with Multiple Decoding Heads.

Selective Latent Thinking: Adaptive Compression of LLM Reasoning Chains Medusa: Simple LLM Inference Acceleration Framework with Multiple Decoding Heads

Reference 3

Resolution: verified exact; local_arxiv, observed 2026-06-29T21:43:59.080933Z

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 ecc208d2-eabf-4dc2-b4a6-2bd87795e974 · outbound

This paper cites Efficient reasoning models: A survey.

Selective Latent Thinking: Adaptive Compression of LLM Reasoning Chains Efficient reasoning models: A survey

Reference 4

Resolution: verified exact; arxiv_id, observed 2026-06-29T21:43:59.075766Z

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 109e1b04-37a2-4652-bd88-79051c70c601 · outbound

This paper cites Better & Faster Large Language Models via Multi-token Prediction.

Selective Latent Thinking: Adaptive Compression of LLM Reasoning Chains Better & Faster Large Language Models via Multi-token Prediction

Reference 5

Resolution: verified exact; local_arxiv, observed 2026-06-29T21:43:59.078406Z

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 b97ff6c7-5d82-43bc-af0b-59e557664add · outbound

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

Selective Latent Thinking: Adaptive Compression of LLM Reasoning Chains DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning

Reference 6

Resolution: verified exact; local_arxiv, observed 2026-06-29T21:43:59.098991Z

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 fb149b03-3c76-4e1a-8c98-d6fad3e32d8c · outbound

This paper cites Token-budget-aware llm reasoning.

Selective Latent Thinking: Adaptive Compression of LLM Reasoning Chains Token-budget-aware llm reasoning

Reference 7

Resolution: unresolved; no resolver link, observed 2026-06-29T21:42:08.610000Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c7aeb090-d9e6-46e1-85f1-59da879a8c92 · outbound

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

Selective Latent Thinking: Adaptive Compression of LLM Reasoning Chains Training Large Language Models to Reason in a Continuous Latent Space

Reference 8

Resolution: verified exact; local_arxiv, observed 2026-06-29T21:43:59.092647Z

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 22d0e4b5-e291-4313-b71a-8bd0bf7af72c · outbound

This paper cites OpenAI o1 System Card.

Selective Latent Thinking: Adaptive Compression of LLM Reasoning Chains OpenAI o1 System Card

Reference 9

Resolution: verified exact; local_arxiv, observed 2026-06-29T21:43:59.072667Z

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 bd0b2c95-d2d7-4d65-9519-c7d0d1874e71 · outbound

This paper cites EAGLE-3: Scaling up Inference Acceleration of Large Language Models via Training-Time Test.

Selective Latent Thinking: Adaptive Compression of LLM Reasoning Chains EAGLE-3: Scaling up Inference Acceleration of Large Language Models via Training-Time Test

Reference 10

Resolution: verified exact; local_arxiv, observed 2026-06-29T21:43:59.065498Z

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 6695664b-914a-4572-9330-2bd07904cf6e · outbound

This paper cites O1-Pruner: Length-Harmonizing Fine-Tuning for O1-Like Reasoning Pruning.

Selective Latent Thinking: Adaptive Compression of LLM Reasoning Chains O1-Pruner: Length-Harmonizing Fine-Tuning for O1-Like Reasoning Pruning

Reference 11

Resolution: verified exact; arxiv_id, observed 2026-06-29T21:43:59.064553Z

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 6bdd7854-1d68-4bdb-9c6b-cc40360b3fc8 · outbound

This paper cites Onelatent: Single-token compression for visual latent reasoning.CoRR, abs/2602.13738.

Selective Latent Thinking: Adaptive Compression of LLM Reasoning Chains Onelatent: Single-token compression for visual latent reasoning.CoRR, abs/2602.13738

Reference 12

Resolution: verified exact; arxiv_id, observed 2026-06-29T21:43:59.061450Z

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 f9af3921-7eb9-47fb-8f7f-c166bdcdaa17 · outbound

This paper cites Your LLM Knows the Future: Uncovering Its Multi-Token Prediction Potential.

Selective Latent Thinking: Adaptive Compression of LLM Reasoning Chains Your LLM Knows the Future: Uncovering Its Multi-Token Prediction Potential

Reference 13

Resolution: verified exact; arxiv_id, observed 2026-06-29T21:43:59.090000Z

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 9ea15bf4-8b15-45ff-b253-dd0cfee641b7 · outbound

This paper cites Efficient Reasoning with Hidden Thinking.

Selective Latent Thinking: Adaptive Compression of LLM Reasoning Chains Efficient Reasoning with Hidden Thinking

Reference 14

Resolution: verified exact; local_arxiv, observed 2026-06-29T21:43:59.070193Z

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 97a6cdd8-dc94-442d-baed-3519616208b7 · outbound

This paper cites CODI: Compressing Chain-of-Thought into Continuous Space via Self-Distillation.

Selective Latent Thinking: Adaptive Compression of LLM Reasoning Chains CODI: Compressing Chain-of-Thought into Continuous Space via Self-Distillation

Reference 15

Resolution: verified exact; local_arxiv, observed 2026-06-29T21:43:59.082941Z

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 24f1fe32-ae07-4d9c-81d3-79aee91bd3c4 · outbound

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

Selective Latent Thinking: Adaptive Compression of LLM Reasoning Chains Stop Overthinking: A Survey on Efficient Reasoning for Large Language Models

Reference 16

Resolution: verified exact; local_arxiv, observed 2026-06-29T21:43:59.056107Z

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 92260927-6b7a-4b1a-a3fd-fb2ceb57d17a · outbound

This paper cites arXiv preprint arXiv:2505.16552 (2025).

Selective Latent Thinking: Adaptive Compression of LLM Reasoning Chains arXiv preprint arXiv:2505.16552 (2025)

Reference 17

Resolution: verified exact; arxiv_id, observed 2026-06-29T21:43:59.047110Z

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 5a040682-aca1-4343-9246-4acf66e364b6 · outbound

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

Selective Latent Thinking: Adaptive Compression of LLM Reasoning Chains Kimi k1.5: Scaling Reinforcement Learning with LLMs

Reference 18

Resolution: verified exact; local_arxiv, observed 2026-06-29T21:43:59.053235Z

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 37bbe05f-47fc-49e0-ba55-30ca06a27d5b · outbound

This paper cites Render-of-Thought: Rendering Textual Chain-of-Thought as Images for Visual Latent Reasoning.

Selective Latent Thinking: Adaptive Compression of LLM Reasoning Chains Render-of-Thought: Rendering Textual Chain-of-Thought as Images for Visual Latent Reasoning

Reference 19

Resolution: verified exact; local_arxiv, observed 2026-06-29T21:43:59.067917Z

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 44d6179f-bc0d-4af0-a3d1-018b0ed9e3b1 · outbound

This paper cites Chain-of-thought prompting elicits reasoning in large language models.

Selective Latent Thinking: Adaptive Compression of LLM Reasoning Chains Chain-of-thought prompting elicits reasoning in large language models

Reference 20

Resolution: unresolved; no resolver link, observed 2026-06-29T21:42:08.610000Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 156894a0-4c8b-46cc-b98b-ccc2caeae6c3 · outbound

This paper cites Tokenskip: Controllable chain-of-thought compression in llms.arXiv preprint arXiv:2502.12067.

Selective Latent Thinking: Adaptive Compression of LLM Reasoning Chains Tokenskip: Controllable chain-of-thought compression in llms.arXiv preprint arXiv:2502.12067

Reference 21

Resolution: verified exact; arxiv_id, observed 2026-06-29T21:43:59.042578Z

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 393e81c2-649a-4ec1-9997-8d24228a4c01 · outbound

This paper cites Towards System 2 Reasoning in LLMs: Learning How to Think With Meta Chain-of-Thought.

Selective Latent Thinking: Adaptive Compression of LLM Reasoning Chains Towards System 2 Reasoning in LLMs: Learning How to Think With Meta Chain-of-Thought

Reference 22

Resolution: verified exact; arxiv_id, observed 2026-06-29T21:43:59.096395Z

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 f9cfab1d-3006-41a3-9a0b-e94411950dce · outbound

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

Selective Latent Thinking: Adaptive Compression of LLM Reasoning Chains Chain of Draft: Thinking Faster by Writing Less

Reference 23

Resolution: verified exact; arxiv_id, observed 2026-06-29T21:43:59.070231Z

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 ee564b3a-3310-4d43-858f-3cedfacdd3e6 · outbound

This paper cites Dynamic early exit in reasoning models.arXiv preprint arXiv:2504.15895, 2025a.

Selective Latent Thinking: Adaptive Compression of LLM Reasoning Chains Dynamic early exit in reasoning models.arXiv preprint arXiv:2504.15895, 2025a

Reference 24

Resolution: verified exact; arxiv_id, observed 2026-06-29T21:43:59.083753Z

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 029fc03e-d38e-4486-af97-0d1aa6a397a4 · outbound

This paper cites semantic routing.

Selective Latent Thinking: Adaptive Compression of LLM Reasoning Chains semantic routing

Reference 25

Resolution: unresolved; no resolver link, observed 2026-06-29T21:42:08.610000Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation 5aa68907-6727-4c31-9a66-c13a6fcc3a58 · inbound

Does Out-of-Sight Equal Out-of-Mind in CoT Monitorability? cites this paper.

Does Out-of-Sight Equal Out-of-Mind in CoT Monitorability? Selective Latent Thinking: Adaptive Compression of LLM Reasoning Chains

Reference 57

Resolution: metadata mismatch; local_arxiv, observed 2026-08-15T14:41:18.239816Z

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.