Paper Citation Record · LEDGER

When Can Large Reasoning Models Save Thinking? Mechanistic Analysis of Behavioral Divergence in Reasoning

As of 8 August 2026, this Paper Citation Record lists 32 of 32 outbound references and 1 inbound Pith citation observation for arXiv:2505.15276.

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

pith.paper-citation-record.v1
2505.15276 v1

Coverage vector

measured 32 of 32 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-07T15:25:48.530304Z

measured 33 of 33 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-08T06:32:00.761636+00:00

measured 1 of 1 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-06T17:54:18.134126Z

measured 0 of 1 external citation measurements

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

Source: pith, observed 2026-08-06T17:54:18.275368Z

Reference resolution

32 of 32 outbound references displayed

verified exact2
verified fuzzy1
unresolved29
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 2dda9f82-5159-478a-ae2d-f3c3c17c6ce3 · outbound

This paper cites online" 'onlinestring :=.

When Can Large Reasoning Models Save Thinking? Mechanistic Analysis of Behavioral Divergence in Reasoning online" 'onlinestring :=

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-07T15:25:46.895611Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7158a73c-ebe4-45e1-93b2-be49ce94950e · outbound

This paper cites write newline.

When Can Large Reasoning Models Save Thinking? Mechanistic Analysis of Behavioral Divergence in Reasoning write newline

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-07T15:25:46.969543Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 48c4bc4c-40b1-44be-b2ad-630f09d1fb9c · outbound

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

When Can Large Reasoning Models Save Thinking? Mechanistic Analysis of Behavioral Divergence in Reasoning L1: Controlling How Long A Reasoning Model Thinks With Reinforcement Learning

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-07T15:25:47.031959Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5b9c94d2-0d15-47b6-8e69-c531f8a9a3e7 · outbound

This paper cites Mathify: Evaluating Large Language Models on Mathematical Problem Solving Tasks.

When Can Large Reasoning Models Save Thinking? Mechanistic Analysis of Behavioral Divergence in Reasoning Mathify: Evaluating Large Language Models on Mathematical Problem Solving Tasks

Reference 4

Resolution: verified exact; local_arxiv, observed 2026-08-07T15:25:49.048617Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 20e7d7f3-19c8-4d16-9ee3-bb473ff2a0bf · outbound

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

When Can Large Reasoning Models Save Thinking? Mechanistic Analysis of Behavioral Divergence in Reasoning Towards Reasoning Era: A Survey of Long Chain-of-Thought for Reasoning Large Language Models

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-07T15:25:47.124956Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e382bb8b-1608-4342-8047-fb596c48d096 · outbound

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

When Can Large Reasoning Models Save Thinking? Mechanistic Analysis of Behavioral Divergence in Reasoning Do NOT Think That Much for 2+3=? On the Overthinking of o1-Like LLMs

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-07T15:25:47.164256Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d2310bac-7a86-408e-8d27-06de66e977c8 · outbound

This paper cites Training Verifiers to Solve Math Word Problems.

When Can Large Reasoning Models Save Thinking? Mechanistic Analysis of Behavioral Divergence in Reasoning Training Verifiers to Solve Math Word Problems

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-07T15:25:47.232594Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 15a6e827-8ae6-4fef-8909-da8cdff998a2 · outbound

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

When Can Large Reasoning Models Save Thinking? Mechanistic Analysis of Behavioral Divergence in Reasoning DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-07T15:25:47.288878Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation aca8fdb3-7bbe-4418-8bd1-be865449d35b · outbound

This paper cites DeepSeek-V3 Technical Report.

When Can Large Reasoning Models Save Thinking? Mechanistic Analysis of Behavioral Divergence in Reasoning DeepSeek-V3 Technical Report

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-07T15:25:47.342960Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b712f6aa-865f-473d-9a73-b63fa25cb259 · outbound

This paper cites an unresolved cited work.

When Can Large Reasoning Models Save Thinking? Mechanistic Analysis of Behavioral Divergence in Reasoning Unresolved cited work

Reference 10

Resolution: unresolved; raw_fallback, observed 2026-08-07T15:25:49.712232Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 50be68a5-40f7-4b38-9608-f33181707c9f · outbound

This paper cites Token-Budget-Aware LLM Reasoning.

When Can Large Reasoning Models Save Thinking? Mechanistic Analysis of Behavioral Divergence in Reasoning Token-Budget-Aware LLM Reasoning

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-07T15:25:47.430493Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1129153e-f04f-4541-b2a7-011376510d2a · outbound

This paper cites an unresolved cited work.

When Can Large Reasoning Models Save Thinking? Mechanistic Analysis of Behavioral Divergence in Reasoning Unresolved cited work

Reference 12

Resolution: unresolved; raw_fallback, observed 2026-08-07T15:25:49.622337Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation d9144f32-3f6a-4124-be0e-a342cd2fc897 · outbound

This paper cites u ttler, Mike Lewis, Wen - tau Yih, Tim Rockt \.

When Can Large Reasoning Models Save Thinking? Mechanistic Analysis of Behavioral Divergence in Reasoning u ttler, Mike Lewis, Wen - tau Yih, Tim Rockt \

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:25:49.536008Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 0f55d79f-5fa8-49ea-ac05-5c2d547af32e · outbound

This paper cites an unresolved cited work.

When Can Large Reasoning Models Save Thinking? Mechanistic Analysis of Behavioral Divergence in Reasoning Unresolved cited work

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-07T15:25:47.589088Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2e861286-df0e-46ba-81ff-33c224f1fb8b · outbound

This paper cites Thought Manipulation: External Thought Can Be Efficient for Large Reasoning Models.

When Can Large Reasoning Models Save Thinking? Mechanistic Analysis of Behavioral Divergence in Reasoning Thought Manipulation: External Thought Can Be Efficient for Large Reasoning Models

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-07T15:25:47.648989Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0f19dfa3-fc17-4a23-a171-8e08ee6f2f17 · outbound

This paper cites an unresolved cited work.

When Can Large Reasoning Models Save Thinking? Mechanistic Analysis of Behavioral Divergence in Reasoning Unresolved cited work

Reference 16

Resolution: verified exact; doi, observed 2026-08-07T15:25:48.887165Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation ed311d06-cbb6-4948-85d6-d3ed102d0f6a · outbound

This paper cites Reasoning Models Can Be Effective Without Thinking.

When Can Large Reasoning Models Save Thinking? Mechanistic Analysis of Behavioral Divergence in Reasoning Reasoning Models Can Be Effective Without Thinking

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-07T15:25:47.751542Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3bb919ec-520d-4399-9a11-2bcc38e7ad96 · outbound

This paper cites an unresolved cited work.

When Can Large Reasoning Models Save Thinking? Mechanistic Analysis of Behavioral Divergence in Reasoning Unresolved cited work

Reference 18

Resolution: unresolved; raw_fallback, observed 2026-08-07T15:25:49.433158Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 01a15e2f-0756-49a4-82f8-488e8436cf95 · outbound

This paper cites s1: Simple test-time scaling.

When Can Large Reasoning Models Save Thinking? Mechanistic Analysis of Behavioral Divergence in Reasoning s1: Simple test-time scaling

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-07T15:25:47.857077Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 48de6ff9-a166-4975-9094-d89072981ec9 · outbound

This paper cites GPT-4 Technical Report.

When Can Large Reasoning Models Save Thinking? Mechanistic Analysis of Behavioral Divergence in Reasoning GPT-4 Technical Report

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-07T15:25:47.902365Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 217a0895-3f8b-4188-b848-6c89f635a91b · outbound

This paper cites an unresolved cited work.

When Can Large Reasoning Models Save Thinking? Mechanistic Analysis of Behavioral Divergence in Reasoning Unresolved cited work

Reference 21

Resolution: unresolved; raw_fallback, observed 2026-08-07T15:25:49.344098Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 9862e8ad-de5e-4de1-a60f-572ecbcd0629 · outbound

This paper cites The Ultimate Guide to Fine-Tuning LLMs from Basics to Breakthroughs: An Exhaustive Review of Technologies, Research, Best Practices, Applied Research Challenges and Opportunities.

When Can Large Reasoning Models Save Thinking? Mechanistic Analysis of Behavioral Divergence in Reasoning The Ultimate Guide to Fine-Tuning LLMs from Basics to Breakthroughs: An Exhaustive Review of Technologies, Research, Best Practices, Applied Research Challenges and Opportunities

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-07T15:25:48.017209Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 67d9088e-a32b-4723-8867-4a9ef489ad46 · outbound

This paper cites Optimizing Test-Time Compute via Meta Reinforcement Fine-Tuning.

When Can Large Reasoning Models Save Thinking? Mechanistic Analysis of Behavioral Divergence in Reasoning Optimizing Test-Time Compute via Meta Reinforcement Fine-Tuning

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-07T15:25:48.065006Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7561e2aa-27b4-44ae-97ee-da057d68c799 · outbound

This paper cites an unresolved cited work.

When Can Large Reasoning Models Save Thinking? Mechanistic Analysis of Behavioral Divergence in Reasoning Unresolved cited work

Reference 24

Resolution: unresolved; raw_fallback, observed 2026-08-07T15:25:49.268275Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 7efa5a83-f7f9-4d8a-bad1-05507801e2f3 · outbound

This paper cites Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameters.

When Can Large Reasoning Models Save Thinking? Mechanistic Analysis of Behavioral Divergence in Reasoning Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameters

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-07T15:25:48.190884Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4229cc8a-6a5b-46c4-924d-13553699e247 · outbound

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

When Can Large Reasoning Models Save Thinking? Mechanistic Analysis of Behavioral Divergence in Reasoning Stop Overthinking: A Survey on Efficient Reasoning for Large Language Models

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-07T15:25:48.238572Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6bd0f2a5-b555-4c70-89d9-249b0936b9f7 · outbound

This paper cites Towards Large Reasoning Models: A Survey of Reinforced Reasoning with Large Language Models.

When Can Large Reasoning Models Save Thinking? Mechanistic Analysis of Behavioral Divergence in Reasoning Towards Large Reasoning Models: A Survey of Reinforced Reasoning with Large Language Models

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-07T15:25:48.278659Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7c1fc73b-cab9-4220-824f-2ca048e0b9f2 · outbound

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

When Can Large Reasoning Models Save Thinking? Mechanistic Analysis of Behavioral Divergence in Reasoning Chain of Draft: Thinking Faster by Writing Less

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-07T15:25:48.328140Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8d9baae8-3f74-49b6-9e3b-e98bbb963281 · outbound

This paper cites Qwen2.5 Technical Report.

When Can Large Reasoning Models Save Thinking? Mechanistic Analysis of Behavioral Divergence in Reasoning Qwen2.5 Technical Report

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-07T15:25:48.388434Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 692f2d51-8c57-4511-a186-f380d0fa49ab · outbound

This paper cites an unresolved cited work.

When Can Large Reasoning Models Save Thinking? Mechanistic Analysis of Behavioral Divergence in Reasoning Unresolved cited work

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-07T15:25:48.424721Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dcd1c1ed-c3e5-479d-8543-210379586bcc · outbound

This paper cites A Survey of Large Language Models.

When Can Large Reasoning Models Save Thinking? Mechanistic Analysis of Behavioral Divergence in Reasoning A Survey of Large Language Models

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-07T15:25:48.470149Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation be92d59c-6ca9-45bc-adec-d135ca8ce10f · outbound

This paper cites Mitigating Lost-in-Retrieval Problems in Retrieval Augmented Multi-Hop Question Answering.

When Can Large Reasoning Models Save Thinking? Mechanistic Analysis of Behavioral Divergence in Reasoning Mitigating Lost-in-Retrieval Problems in Retrieval Augmented Multi-Hop Question Answering

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-07T15:25:48.530304Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation 94bc20c2-237f-467c-85ec-0ecb142c8c7d · 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 When Can Large Reasoning Models Save Thinking? Mechanistic Analysis of Behavioral Divergence in Reasoning

Reference 252

Resolution: verified exact; local_arxiv, observed 2026-08-06T17:54:18.282899Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.