Paper Citation Record · LEDGER

Think or Not? Exploring Thinking Efficiency in Large Reasoning Models via an Information-Theoretic Lens

As of 7 August 2026, this Paper Citation Record lists 13 of 13 outbound references and 8 inbound Pith citation observations for arXiv:2505.18237.

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

pith.paper-citation-record.v1
2505.18237 v1

Coverage vector

measured 13 of 13 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-07T14:43:27.933509Z

measured 21 of 21 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 8 of 8 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-06T17:54:17.999624Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-07-02T02:56:29.988823Z

Reference resolution

13 of 13 outbound references displayed

verified exact0
verified fuzzy9
unresolved4
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation bd302249-9236-4330-9b4b-6d276fc56fcd · outbound

This paper cites • The question requires combining multiple knowledge points, hidden conditions, or assumptions.

Think or Not? Exploring Thinking Efficiency in Large Reasoning Models via an Information-Theoretic Lens • The question requires combining multiple knowledge points, hidden conditions, or assumptions

Reference 1

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:43:29.920987Z

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 1c687574-8e4c-46a7-8862-d08f121636d7 · outbound

This paper cites • Multiple data sources, conditions, or assumptions must be synthesized to derive the final answer.

Think or Not? Exploring Thinking Efficiency in Large Reasoning Models via an Information-Theoretic Lens • Multiple data sources, conditions, or assumptions must be synthesized to derive the final answer

Reference 2

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:43:29.636829Z

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 5f43b182-4c09-468d-b298-8e54379e6df8 · outbound

This paper cites • It involves recursive reasoning, mathematical induction, or constructing coun- terexamples.

Think or Not? Exploring Thinking Efficiency in Large Reasoning Models via an Information-Theoretic Lens • It involves recursive reasoning, mathematical induction, or constructing coun- terexamples

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:43:29.464570Z

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 40b0f07a-8063-4199-a5bd-1ca1d4b92478 · outbound

This paper cites • There may be multiple valid approaches, requiring deep analysis and compari- son.

Think or Not? Exploring Thinking Efficiency in Large Reasoning Models via an Information-Theoretic Lens • There may be multiple valid approaches, requiring deep analysis and compari- son

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:43:29.308892Z

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 dcb51876-e7de-4165-911f-167b11e649f6 · outbound

This paper cites YES” (Deep Think Mode required)If the question meets at least 2 criteria, return “YES.

Think or Not? Exploring Thinking Efficiency in Large Reasoning Models via an Information-Theoretic Lens YES” (Deep Think Mode required)If the question meets at least 2 criteria, return “YES

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:43:29.147182Z

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 3d59364f-a769-49b3-9b33-f05a416bb441 · outbound

This paper cites an unresolved cited work.

Think or Not? Exploring Thinking Efficiency in Large Reasoning Models via an Information-Theoretic Lens Unresolved cited work

Reference 9

Resolution: unresolved; raw_fallback, observed 2026-08-07T14:43:28.792911Z

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 93f9d6c2-1a5a-425b-acb3-1459c20d20c6 · outbound

This paper cites an unresolved cited work.

Think or Not? Exploring Thinking Efficiency in Large Reasoning Models via an Information-Theoretic Lens Unresolved cited work

Reference 11

Resolution: unresolved; raw_fallback, observed 2026-08-07T14:43:28.534931Z

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 70bcf464-98f5-4fbf-8065-5b5e1abab75c · outbound

This paper cites C=(80.73,42) 6.

Think or Not? Exploring Thinking Efficiency in Large Reasoning Models via an Information-Theoretic Lens C=(80.73,42) 6

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:43:28.394226Z

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 49cb3b14-328d-48db-86e9-3f25da70c0fc · outbound

This paper cites Alternatively, use vectors or mass point? Hmm.

Think or Not? Exploring Thinking Efficiency in Large Reasoning Models via an Information-Theoretic Lens Alternatively, use vectors or mass point? Hmm

Reference 288

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:43:28.984585Z

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 ab5a45c8-c164-428d-9e45-0bcb9ede525b · outbound

This paper cites </think> To solve the problem, we start by noting the given lengths and the fact that the area of quadrilateral DEGF is 288.

Think or Not? Exploring Thinking Efficiency in Large Reasoning Models via an Information-Theoretic Lens </think> To solve the problem, we start by noting the given lengths and the fact that the area of quadrilateral DEGF is 288

Reference 300

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:43:28.183302Z

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 f824761a-98c1-40f3-9e4b-36dfd9468503 · outbound

This paper cites heptagon AFNBCEM.

Think or Not? Exploring Thinking Efficiency in Large Reasoning Models via an Information-Theoretic Lens heptagon AFNBCEM

Reference 1176

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:43:28.672410Z

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 0cec5876-a447-4bc8-8657-eb147185ed84 · outbound

This paper cites s1: Simple test-time scaling.

Think or Not? Exploring Thinking Efficiency in Large Reasoning Models via an Information-Theoretic Lens s1: Simple test-time scaling

Reference 2022

Resolution: unresolved; no resolver link, observed 2026-08-07T14:43:27.051655Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3a048843-cba1-445b-9b08-d3ab0762f901 · outbound

This paper cites BOLT: Bootstrap Long Chain-of-Thought in Language Models without Distillation.

Think or Not? Exploring Thinking Efficiency in Large Reasoning Models via an Information-Theoretic Lens BOLT: Bootstrap Long Chain-of-Thought in Language Models without Distillation

Reference 2024

Resolution: unresolved; no resolver link, observed 2026-08-07T14:43:27.098235Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation d9def7d2-39e0-45b5-8375-5c1c4b3596f2 · 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 Think or Not? Exploring Thinking Efficiency in Large Reasoning Models via an Information-Theoretic Lens

Reference 228

Resolution: unresolved; no resolver link, observed 2026-08-06T17:54:17.999624Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cf3c95cc-e97f-4dbc-94ac-d0b3be2cf2fa · inbound

Entropy After </Think> for reasoning model early exiting cites this paper.

Entropy After </Think> for reasoning model early exiting Think or Not? Exploring Thinking Efficiency in Large Reasoning Models via an Information-Theoretic Lens

Reference 22

Resolution: verified exact; arxiv_id, observed 2026-05-18T11:52:35.564121Z

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 2c895563-1a3f-4550-99a1-99dccc5a77af · inbound

Dissecting Failure Dynamics in Large Language Model Reasoning cites this paper.

Dissecting Failure Dynamics in Large Language Model Reasoning Think or Not? Exploring Thinking Efficiency in Large Reasoning Models via an Information-Theoretic Lens

Reference 2

Resolution: verified exact; arxiv_id, observed 2026-05-10T11:40:19.046705Z

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 9ce5eee0-cd0e-46c6-a1b0-fdb580cacf38 · inbound

LLMs Improving LLMs: Agentic Discovery for Test-Time Scaling cites this paper.

LLMs Improving LLMs: Agentic Discovery for Test-Time Scaling Think or Not? Exploring Thinking Efficiency in Large Reasoning Models via an Information-Theoretic Lens

Reference 33

Resolution: verified exact; arxiv_id, observed 2026-05-11T04:10:58.127582Z

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 73949347-2434-4515-bdbd-22a8bf671b9f · inbound

LLMs Improving LLMs: Agentic Discovery for Test-Time Scaling cites this paper.

LLMs Improving LLMs: Agentic Discovery for Test-Time Scaling Think or Not? Exploring Thinking Efficiency in Large Reasoning Models via an Information-Theoretic Lens

Reference 33

Resolution: verified exact; arxiv_id, observed 2026-05-13T07:12:28.357719Z

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 7fb1f6ac-8b0b-4d72-b2bb-b06dc71eb593 · inbound

Know When To Fold 'Em: Token-Efficient LLM Synthetic Data Generation via Multi-Stage In-Flight Rejection cites this paper.

Know When To Fold 'Em: Token-Efficient LLM Synthetic Data Generation via Multi-Stage In-Flight Rejection Think or Not? Exploring Thinking Efficiency in Large Reasoning Models via an Information-Theoretic Lens

Reference 43

Resolution: verified exact; arxiv_id, observed 2026-05-15T05:09:46.173004Z

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 b40f21f8-d70a-42f2-89a0-cd0ca58b86dc · inbound

Small RL Controller, Large Language Model: RL-Guided Adaptive Sampling for Test-Time Scaling cites this paper.

Small RL Controller, Large Language Model: RL-Guided Adaptive Sampling for Test-Time Scaling Think or Not? Exploring Thinking Efficiency in Large Reasoning Models via an Information-Theoretic Lens

Reference 92

Resolution: verified exact; arxiv_id, observed 2026-07-02T02:56:29.990688Z

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 5da8c6f7-ebdb-45ec-b65e-90eb5aad2289 · inbound

Is Your Model Thinking or Just Stagnating? PUMA: Diagnosing Reasoning Pathology via Phase-Momentum Alignment cites this paper.

Is Your Model Thinking or Just Stagnating? PUMA: Diagnosing Reasoning Pathology via Phase-Momentum Alignment Think or Not? Exploring Thinking Efficiency in Large Reasoning Models via an Information-Theoretic Lens

Reference 52

Resolution: unresolved; no resolver link, observed 2026-08-01T18:49:32.069451Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.