Paper Citation Record · LEDGER

SmartThinker: Learning to Compress and Preserve Reasoning by Step-Level Length Control

As of 7 August 2026, this Paper Citation Record lists 45 of 45 outbound references and 2 inbound Pith citation observations for arXiv:2507.04348.

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

pith.paper-citation-record.v1
2507.04348 v2

Coverage vector

measured 45 of 45 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-06T19:56:12.693765Z

measured 47 of 47 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-07T06:34:17.273281+00:00

measured 2 of 2 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-05-12T08:40:40.910461Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-05-12T08:40:41.519148Z

Reference resolution

45 of 45 outbound references displayed

verified exact0
verified fuzzy0
unresolved45
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 87c4d026-d001-4594-9a12-152d9bd6882a · outbound

This paper cites , " * write output.state after.block = add.period write newline.

SmartThinker: Learning to Compress and Preserve Reasoning by Step-Level Length Control , " * write output.state after.block = add.period write newline

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-06T19:56:07.478095Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 17cfd17f-256f-49e5-825d-079ec7b32db6 · outbound

This paper cites write newline.

SmartThinker: Learning to Compress and Preserve Reasoning by Step-Level Length Control write newline

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-06T19:56:07.510678Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5a9320c9-b1b2-4ba7-8314-9d125f75acf1 · outbound

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

SmartThinker: Learning to Compress and Preserve Reasoning by Step-Level Length Control L1: Controlling How Long A Reasoning Model Thinks With Reinforcement Learning

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-06T19:56:07.574963Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ba270698-182f-4c97-9647-28078580cd1b · outbound

This paper cites an unresolved cited work.

SmartThinker: Learning to Compress and Preserve Reasoning by Step-Level Length Control Unresolved cited work

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-06T19:56:07.687766Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8962900f-e440-4b1d-acb8-36b18ed92c29 · outbound

This paper cites ReSearch: Learning to Reason with Search for LLMs via Reinforcement Learning.

SmartThinker: Learning to Compress and Preserve Reasoning by Step-Level Length Control ReSearch: Learning to Reason with Search for LLMs via Reinforcement Learning

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-06T19:56:07.843931Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 68c843f2-3526-4953-90f4-c1d7b75e6176 · outbound

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

SmartThinker: Learning to Compress and Preserve Reasoning by Step-Level Length Control Towards Reasoning Era: A Survey of Long Chain-of-Thought for Reasoning Large Language Models

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-06T19:56:08.050411Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5b041dec-6184-4ac8-8035-3c935f3d0ce6 · outbound

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

SmartThinker: Learning to Compress and Preserve Reasoning by Step-Level Length Control Do NOT Think That Much for 2+3=? On the Overthinking of o1-Like LLMs

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-06T19:56:08.287459Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7bb425ca-7757-4334-8401-3f1cc9aa14f7 · outbound

This paper cites The Danger of Overthinking: Examining the Reasoning-Action Dilemma in Agentic Tasks.

SmartThinker: Learning to Compress and Preserve Reasoning by Step-Level Length Control The Danger of Overthinking: Examining the Reasoning-Action Dilemma in Agentic Tasks

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-06T19:56:08.440220Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6d898a92-237a-487e-9dd3-77011c2e65ed · outbound

This paper cites Thinkless: LLM Learns When to Think.

SmartThinker: Learning to Compress and Preserve Reasoning by Step-Level Length Control Thinkless: LLM Learns When to Think

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-06T19:56:08.680429Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 77f159cb-46bd-42e1-9df3-81ab49be877e · outbound

This paper cites an unresolved cited work.

SmartThinker: Learning to Compress and Preserve Reasoning by Step-Level Length Control Unresolved cited work

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-06T19:56:08.760553Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 957e12f6-f41d-494b-b36b-0271a1856491 · outbound

This paper cites Efficiently Scaling LLM Reasoning with Certaindex.

SmartThinker: Learning to Compress and Preserve Reasoning by Step-Level Length Control Efficiently Scaling LLM Reasoning with Certaindex

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-06T19:56:08.863416Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c16388d5-345d-4fd9-bdb4-654fbeabd5ab · outbound

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

SmartThinker: Learning to Compress and Preserve Reasoning by Step-Level Length Control DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-06T19:56:09.011407Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 585537f7-73a5-4327-b89f-827ce3574e73 · outbound

This paper cites Token-Budget-Aware LLM Reasoning.

SmartThinker: Learning to Compress and Preserve Reasoning by Step-Level Length Control Token-Budget-Aware LLM Reasoning

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-06T19:56:09.165310Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 50d8b192-8840-4661-bb41-be20bb559d74 · outbound

This paper cites OlympiadBench: A Challenging Benchmark for Promoting AGI with Olympiad-Level Bilingual Multimodal Scientific Problems.

SmartThinker: Learning to Compress and Preserve Reasoning by Step-Level Length Control OlympiadBench: A Challenging Benchmark for Promoting AGI with Olympiad-Level Bilingual Multimodal Scientific Problems

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-06T19:56:09.322919Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation be5ae241-a737-441d-823b-1c39f088cc8c · outbound

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

SmartThinker: Learning to Compress and Preserve Reasoning by Step-Level Length Control Measuring Mathematical Problem Solving With the MATH Dataset

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-06T19:56:09.437194Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e888a6d6-7f90-4269-ae9b-a588a6ab494f · outbound

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

SmartThinker: Learning to Compress and Preserve Reasoning by Step-Level Length Control ThinkPrune: Pruning Long Chain-of-Thought of LLMs via Reinforcement Learning

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-06T19:56:09.525446Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dc2ce4a3-d2eb-4e5b-bdf4-b1e2c8f058d3 · outbound

This paper cites J.; Shen, Y.; Wallis, P.; Allen-Zhu, Z.; Li, Y.; Wang, S.; Wang, L.; Chen, W.; et al.

SmartThinker: Learning to Compress and Preserve Reasoning by Step-Level Length Control J.; Shen, Y.; Wallis, P.; Allen-Zhu, Z.; Li, Y.; Wang, S.; Wang, L.; Chen, W.; et al

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-06T19:56:09.655142Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e1ad6237-7150-4f3f-8a83-291c0029ce82 · outbound

This paper cites OpenAI o1 System Card.

SmartThinker: Learning to Compress and Preserve Reasoning by Step-Level Length Control OpenAI o1 System Card

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-06T19:56:09.810675Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3f601a50-bbf5-4966-b712-918ac98c0442 · outbound

This paper cites LiveCodeBench: Holistic and Contamination Free Evaluation of Large Language Models for Code.

SmartThinker: Learning to Compress and Preserve Reasoning by Step-Level Length Control LiveCodeBench: Holistic and Contamination Free Evaluation of Large Language Models for Code

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-06T19:56:09.972378Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c483a754-4f3b-4c62-8cfe-9f9bcfdfdfb4 · outbound

This paper cites an unresolved cited work.

SmartThinker: Learning to Compress and Preserve Reasoning by Step-Level Length Control Unresolved cited work

Reference 20

Resolution: unresolved; raw_fallback, observed 2026-08-06T19:56:13.654391Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 25cee0b4-c1d2-43d4-a887-187f91f61ddc · outbound

This paper cites RACE: Large-scale ReAding Comprehension Dataset From Examinations.

SmartThinker: Learning to Compress and Preserve Reasoning by Step-Level Length Control RACE: Large-scale ReAding Comprehension Dataset From Examinations

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-06T19:56:10.289215Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c192bcdf-1286-443a-8d2c-40228131030a · outbound

This paper cites an unresolved cited work.

SmartThinker: Learning to Compress and Preserve Reasoning by Step-Level Length Control Unresolved cited work

Reference 22

Resolution: unresolved; raw_fallback, observed 2026-08-06T19:56:13.647554Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 805c8b2d-1fc1-4513-8ebf-9c6fa38f3e21 · outbound

This paper cites TruthfulQA: Measuring How Models Mimic Human Falsehoods.

SmartThinker: Learning to Compress and Preserve Reasoning by Step-Level Length Control TruthfulQA: Measuring How Models Mimic Human Falsehoods

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-06T19:56:10.448326Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3d73eea1-4f5d-419a-99a8-0a1d1075a661 · outbound

This paper cites Understanding R1-Zero-Like Training: A Critical Perspective.

SmartThinker: Learning to Compress and Preserve Reasoning by Step-Level Length Control Understanding R1-Zero-Like Training: A Critical Perspective

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-06T19:56:10.535917Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a79c059b-a4cc-4707-a87c-17c37dc87bae · outbound

This paper cites Decoupled Weight Decay Regularization.

SmartThinker: Learning to Compress and Preserve Reasoning by Step-Level Length Control Decoupled Weight Decay Regularization

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-06T19:56:10.649664Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c729fc40-e11e-43ca-8a04-89ac9c5ada66 · outbound

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

SmartThinker: Learning to Compress and Preserve Reasoning by Step-Level Length Control AdaCoT: Pareto-Optimal Adaptive Chain-of-Thought Triggering via Reinforcement Learning

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-06T19:56:10.766374Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 00c8ce7c-3dd3-42e8-b0ed-539d688e4a89 · outbound

This paper cites Ada-R1: Hybrid-CoT via Bi-Level Adaptive Reasoning Optimization.

SmartThinker: Learning to Compress and Preserve Reasoning by Step-Level Length Control Ada-R1: Hybrid-CoT via Bi-Level Adaptive Reasoning Optimization

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-06T19:56:10.895596Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dacf0e43-456d-4498-be74-26346cade428 · outbound

This paper cites Improve Mathematical Reasoning in Language Models by Automated Process Supervision.

SmartThinker: Learning to Compress and Preserve Reasoning by Step-Level Length Control Improve Mathematical Reasoning in Language Models by Automated Process Supervision

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-06T19:56:10.901840Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 69ce7d35-5c89-4a97-931c-39020b5c5ed6 · outbound

This paper cites Y.; Roongta, M.; Cai, C.; Luo, J.; Zhang, T.; Li, L.

SmartThinker: Learning to Compress and Preserve Reasoning by Step-Level Length Control Y.; Roongta, M.; Cai, C.; Luo, J.; Zhang, T.; Li, L

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-06T19:56:10.910223Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 46c90150-b427-48a3-9694-3b22a8b26fe8 · outbound

This paper cites an unresolved cited work.

SmartThinker: Learning to Compress and Preserve Reasoning by Step-Level Length Control Unresolved cited work

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-06T19:56:11.021958Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 09bbf56f-cd31-4e62-90d6-1cf26dbaa500 · outbound

This paper cites an unresolved cited work.

SmartThinker: Learning to Compress and Preserve Reasoning by Step-Level Length Control Unresolved cited work

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-06T19:56:11.144411Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e14c2f65-26f4-4c82-a7b8-537b3e4dca32 · outbound

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

SmartThinker: Learning to Compress and Preserve Reasoning by Step-Level Length Control DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-06T19:56:11.260842Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 70af886a-f2c4-4f47-8861-3c05ad305184 · outbound

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

SmartThinker: Learning to Compress and Preserve Reasoning by Step-Level Length Control Stop Overthinking: A Survey on Efficient Reasoning for Large Language Models

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-06T19:56:11.387447Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7cddc7c7-6a3e-42f6-8473-ad49d7e386af · outbound

This paper cites an unresolved cited work.

SmartThinker: Learning to Compress and Preserve Reasoning by Step-Level Length Control Unresolved cited work

Reference 34

Resolution: unresolved; raw_fallback, observed 2026-08-06T19:56:13.632257Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 0b9b5249-c3bb-4d48-85f6-af76a6bc3c5b · outbound

This paper cites Agentic Reasoning: A Streamlined Framework for Enhancing LLM Reasoning with Agentic Tools.

SmartThinker: Learning to Compress and Preserve Reasoning by Step-Level Length Control Agentic Reasoning: A Streamlined Framework for Enhancing LLM Reasoning with Agentic Tools

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-06T19:56:11.606052Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f59bcfe8-425b-472b-85b4-598f2472217c · outbound

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

SmartThinker: Learning to Compress and Preserve Reasoning by Step-Level Length Control T.; Wang, W.; and Li, W

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-06T19:56:11.746816Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fedba185-06ba-4684-8cad-ba78f6dfc5ce · outbound

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

SmartThinker: Learning to Compress and Preserve Reasoning by Step-Level Length Control Chain of Draft: Thinking Faster by Writing Less

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-06T19:56:11.857325Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 87045524-8bb2-49f1-85a4-61f17bc3a6dd · outbound

This paper cites an unresolved cited work.

SmartThinker: Learning to Compress and Preserve Reasoning by Step-Level Length Control Unresolved cited work

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-06T19:56:11.961882Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ad0bc26a-f805-44a1-91ec-df47d777ea30 · outbound

This paper cites Qwen2.5-Math Technical Report: Toward Mathematical Expert Model via Self-Improvement.

SmartThinker: Learning to Compress and Preserve Reasoning by Step-Level Length Control Qwen2.5-Math Technical Report: Toward Mathematical Expert Model via Self-Improvement

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-06T19:56:12.062937Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 039ddf1c-aa30-4033-81ba-d40b5cc4215b · outbound

This paper cites LIMO: Less is More for Reasoning.

SmartThinker: Learning to Compress and Preserve Reasoning by Step-Level Length Control LIMO: Less is More for Reasoning

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-06T19:56:12.170017Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 33a4b96d-a482-4276-beae-6d0827f84a70 · outbound

This paper cites DAPO: An Open-Source LLM Reinforcement Learning System at Scale.

SmartThinker: Learning to Compress and Preserve Reasoning by Step-Level Length Control DAPO: An Open-Source LLM Reinforcement Learning System at Scale

Reference 41

Resolution: unresolved; no resolver link, observed 2026-08-06T19:56:12.302581Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8c3b4480-5a32-4ed7-b9ec-caec46455731 · outbound

This paper cites AdaptThink: Reasoning Models Can Learn When to Think.

SmartThinker: Learning to Compress and Preserve Reasoning by Step-Level Length Control AdaptThink: Reasoning Models Can Learn When to Think

Reference 42

Resolution: unresolved; no resolver link, observed 2026-08-06T19:56:12.451362Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a00afbad-86ec-453f-8309-4dc10bd4834f · outbound

This paper cites an unresolved cited work.

SmartThinker: Learning to Compress and Preserve Reasoning by Step-Level Length Control Unresolved cited work

Reference 43

Resolution: unresolved; no resolver link, observed 2026-08-06T19:56:12.603733Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d667b62d-7578-4aef-b5c6-9f713aae04d4 · outbound

This paper cites an unresolved cited work.

SmartThinker: Learning to Compress and Preserve Reasoning by Step-Level Length Control Unresolved cited work

Reference 44

Resolution: unresolved; no resolver link, observed 2026-08-06T19:56:12.614141Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 75aab90b-63ca-490d-aafd-8663cadd0091 · outbound

This paper cites an unresolved cited work.

SmartThinker: Learning to Compress and Preserve Reasoning by Step-Level Length Control Unresolved cited work

Reference 45

Resolution: unresolved; no resolver link, observed 2026-08-06T19:56:12.693765Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation d2f968aa-8abf-4763-a7f7-005cf66bfd4a · 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 SmartThinker: Learning to Compress and Preserve Reasoning by Step-Level Length Control

Reference 254

Resolution: verified exact; arxiv_id, observed 2026-05-12T08:40:41.521904Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 37bf9325-8400-4a28-8c05-6eeb25e102bb · inbound

LEAD: Length-Efficient Adaptive and Dynamic Reasoning for Large Language Models cites this paper.

LEAD: Length-Efficient Adaptive and Dynamic Reasoning for Large Language Models SmartThinker: Learning to Compress and Preserve Reasoning by Step-Level Length Control

Reference 17

Resolution: verified exact; arxiv_id, observed 2026-05-12T02:31:16.824046Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.