Paper Citation Record · LEDGER

Think in Blocks: Adaptive Reasoning from Direct Response to Deep Reasoning

As of 22 August 2026, this Paper Citation Record lists 29 of 29 outbound references and 1 inbound Pith citation observation for arXiv:2508.15507.

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

pith.paper-citation-record.v1
2508.15507 v1

Coverage vector

measured 29 of 29 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-05T17:52:53.445928Z

measured 30 of 30 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-21T06:32:19.484+00:00

measured 1 of 1 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-07-10T05:07:40.106099Z

measured 0 of 1 external citation measurements

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

Source: pith, observed 2026-07-10T05:16:48.074824Z

Reference resolution

29 of 29 outbound references displayed

verified exact0
verified fuzzy5
unresolved24
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 0b627236-f27f-45ad-a1fe-0d2226fa2b0d · outbound

This paper cites GPT-4 Technical Report.

Think in Blocks: Adaptive Reasoning from Direct Response to Deep Reasoning GPT-4 Technical Report

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-05T17:52:50.669316Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c7f84408-7fcf-4d83-8055-9c344349d084 · outbound

This paper cites Introducing claude, 2023.

Think in Blocks: Adaptive Reasoning from Direct Response to Deep Reasoning Introducing claude, 2023

Reference 2

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T17:52:53.888675Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 8e0980ac-8ac2-40da-9a79-fdca930d724b · outbound

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

Think in Blocks: Adaptive Reasoning from Direct Response to Deep Reasoning Do NOT Think That Much for 2+3=? On the Overthinking of o1-Like LLMs

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-05T17:52:50.905967Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1e3c8cae-e25e-4cf6-b18e-f9a292a5dfc9 · outbound

This paper cites Learning to Route LLMs with Confidence Tokens.

Think in Blocks: Adaptive Reasoning from Direct Response to Deep Reasoning Learning to Route LLMs with Confidence Tokens

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-05T17:52:51.004589Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b9490e6c-3a40-47f8-b36b-55aaedaecd12 · outbound

This paper cites Thinkless: LLM Learns When to Think.

Think in Blocks: Adaptive Reasoning from Direct Response to Deep Reasoning Thinkless: LLM Learns When to Think

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-05T17:52:51.135256Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b8ac97b5-6c8d-463f-89c4-09829b5bbdf0 · outbound

This paper cites Efficient reasoning models: A survey.

Think in Blocks: Adaptive Reasoning from Direct Response to Deep Reasoning Efficient reasoning models: A survey

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-05T17:52:51.349711Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8bdf5890-8269-4120-8256-d003a7aae2d0 · outbound

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

Think in Blocks: Adaptive Reasoning from Direct Response to Deep Reasoning DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-05T17:52:51.492438Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 575b0549-953d-40ae-be1c-6af61e157957 · outbound

This paper cites Token-Budget-Aware LLM Reasoning.

Think in Blocks: Adaptive Reasoning from Direct Response to Deep Reasoning Token-Budget-Aware LLM Reasoning

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-05T17:52:51.696489Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8cb5254d-fb9d-4664-8d51-aba720dc1ec8 · outbound

This paper cites DeepMath-103K: A Large-Scale, Challenging, Decontaminated, and Verifiable Mathematical Dataset for Advancing Reasoning.

Think in Blocks: Adaptive Reasoning from Direct Response to Deep Reasoning DeepMath-103K: A Large-Scale, Challenging, Decontaminated, and Verifiable Mathematical Dataset for Advancing Reasoning

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-05T17:52:51.895375Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a84ec10c-6605-44ca-b9e3-7e244331ac21 · outbound

This paper cites Editing Models with Task Arithmetic.

Think in Blocks: Adaptive Reasoning from Direct Response to Deep Reasoning Editing Models with Task Arithmetic

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-05T17:52:52.092535Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6ab767aa-de33-436c-8a15-05882c6696e6 · outbound

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

Think in Blocks: Adaptive Reasoning from Direct Response to Deep Reasoning Understanding R1-Zero-Like Training: A Critical Perspective

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-05T17:52:52.283518Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1ac68ec2-bfcf-465c-994f-1888247bd7c3 · outbound

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

Think in Blocks: Adaptive Reasoning from Direct Response to Deep Reasoning AdaCoT: Pareto-Optimal Adaptive Chain-of-Thought Triggering via Reinforcement Learning

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-05T17:52:52.523700Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 14d52365-1887-41a2-a201-78b2a02cf6e0 · outbound

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

Think in Blocks: Adaptive Reasoning from Direct Response to Deep Reasoning O1-Pruner: Length-Harmonizing Fine-Tuning for O1-Like Reasoning Pruning

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-05T17:52:52.681207Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8af2296a-259e-4128-9a50-1261907bcb46 · outbound

This paper cites CoT-Valve: Length-Compressible Chain-of-Thought Tuning.

Think in Blocks: Adaptive Reasoning from Direct Response to Deep Reasoning CoT-Valve: Length-Compressible Chain-of-Thought Tuning

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-05T17:52:52.886563Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6dd1c6ef-849e-4b47-90f8-835eeec0ffae · outbound

This paper cites RouteLLM: Learning to Route LLMs with Preference Data.

Think in Blocks: Adaptive Reasoning from Direct Response to Deep Reasoning RouteLLM: Learning to Route LLMs with Preference Data

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-05T17:52:53.058030Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cbd4d4ce-d319-434b-bf78-9174ec402acb · outbound

This paper cites Learning to reason with llms.

Think in Blocks: Adaptive Reasoning from Direct Response to Deep Reasoning Learning to reason with llms

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T17:52:53.879095Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 5d8d35a7-9a6a-46ad-bc7d-376d1775c972 · outbound

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

Think in Blocks: Adaptive Reasoning from Direct Response to Deep Reasoning DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-05T17:52:53.251199Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ab821603-dbbd-463c-94d0-04f2cc30329d · outbound

This paper cites Dast: Difficulty-adaptive slow-thinking for large reasoning models.

Think in Blocks: Adaptive Reasoning from Direct Response to Deep Reasoning Dast: Difficulty-adaptive slow-thinking for large reasoning models

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-05T17:52:53.353473Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a6129052-e383-40c4-a498-dd1cd2ce2e11 · outbound

This paper cites Hybridflow: A flexible and efficient rlhf framework.

Think in Blocks: Adaptive Reasoning from Direct Response to Deep Reasoning Hybridflow: A flexible and efficient rlhf framework

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T17:52:53.869254Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation b536c32a-61ac-40f2-9ad0-ea5d8f5f5780 · outbound

This paper cites The Illusion of Thinking: Understanding the Strengths and Limitations of Reasoning Models via the Lens of Problem Complexity.

Think in Blocks: Adaptive Reasoning from Direct Response to Deep Reasoning The Illusion of Thinking: Understanding the Strengths and Limitations of Reasoning Models via the Lens of Problem Complexity

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-05T17:52:53.410664Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0118140d-16f0-4279-abdc-633e72ac25bb · outbound

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

Think in Blocks: Adaptive Reasoning from Direct Response to Deep Reasoning Kimi k1.5: Scaling Reinforcement Learning with LLMs

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-05T17:52:53.421410Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c0a0d4a0-0758-4d97-b33f-0715776dc601 · outbound

This paper cites LLaMA: Open and Efficient Foundation Language Models.

Think in Blocks: Adaptive Reasoning from Direct Response to Deep Reasoning LLaMA: Open and Efficient Foundation Language Models

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-05T17:52:53.424239Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 57de77eb-0c46-42f3-95c5-c32efd5598ae · outbound

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

Think in Blocks: Adaptive Reasoning from Direct Response to Deep Reasoning Chain-of-thought prompting elicits reasoning in large language models

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-05T17:52:53.427287Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 480cd40d-c380-4944-bdfc-c4479e40a417 · outbound

This paper cites Ties-merging: Resolving interference when merging models.

Think in Blocks: Adaptive Reasoning from Direct Response to Deep Reasoning Ties-merging: Resolving interference when merging models

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T17:52:53.853850Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 4bba23b6-c111-4d47-9dfe-9b8fa9472e2c · outbound

This paper cites Qwen3 Technical Report.

Think in Blocks: Adaptive Reasoning from Direct Response to Deep Reasoning Qwen3 Technical Report

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-05T17:52:53.433211Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4ea709e9-de68-4d28-87f8-9807bdaaa9fe · outbound

This paper cites Demystifying Long Chain-of-Thought Reasoning in LLMs.

Think in Blocks: Adaptive Reasoning from Direct Response to Deep Reasoning Demystifying Long Chain-of-Thought Reasoning in LLMs

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-05T17:52:53.436084Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6ad07181-b80d-42e4-9bd8-6a0515ee3dee · outbound

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

Think in Blocks: Adaptive Reasoning from Direct Response to Deep Reasoning DAPO: An Open-Source LLM Reinforcement Learning System at Scale

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-05T17:52:53.439600Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f29d768e-c978-44b7-93fe-2e6c01e1c2d5 · outbound

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

Think in Blocks: Adaptive Reasoning from Direct Response to Deep Reasoning AdaptThink: Reasoning Models Can Learn When to Think

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-05T17:52:53.442926Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4ee43093-275e-4889-a7ee-cdc94ccd2022 · outbound

This paper cites Swift: a scalable lightweight infrastructure for fine-tuning.

Think in Blocks: Adaptive Reasoning from Direct Response to Deep Reasoning Swift: a scalable lightweight infrastructure for fine-tuning

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T17:52:53.844030Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Pith citing papers

Observation dc21e25c-2802-4e4a-977c-f18ea9d45bc3 · inbound

Switch-Reasoner: Learn When to Think in Multitask Mixtures via Reinforcement Learning cites this paper.

Switch-Reasoner: Learn When to Think in Multitask Mixtures via Reinforcement Learning Think in Blocks: Adaptive Reasoning from Direct Response to Deep Reasoning

Reference 24

Resolution: verified exact; local_arxiv, observed 2026-07-10T05:16:48.076132Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.