Paper Citation Record · LEDGER

Trace-of-Thought Prompting: Investigating Prompt-Based Knowledge Distillation Through Question Decomposition

As of 20 August 2026, this Paper Citation Record lists 45 of 45 outbound references and 0 inbound Pith citation observations for arXiv:2504.20946.

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

pith.paper-citation-record.v1
2504.20946 v2

Coverage vector

measured 45 of 45 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-16T05:19:57.613688Z

measured 45 of 45 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-19T06:32:44.657259+00:00

measured 0 of 0 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links

measured 0 of 1 external citation measurements

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

Source: cited_works

Reference resolution

45 of 45 outbound references displayed

verified exact1
verified fuzzy0
unresolved44
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation db34fa8f-57f1-42f9-b935-1c41244d5131 · outbound

This paper cites Can LLMs perform structured graph reasoning?.

Trace-of-Thought Prompting: Investigating Prompt-Based Knowledge Distillation Through Question Decomposition Can LLMs perform structured graph reasoning?

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-16T05:19:57.437866Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 689231ce-03b6-4a97-ac0e-521ca67b196f · outbound

This paper cites Language Models are Few-Shot Learners.

Trace-of-Thought Prompting: Investigating Prompt-Based Knowledge Distillation Through Question Decomposition Language Models are Few-Shot Learners

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-16T05:19:57.442659Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0899e5c3-7718-4c8c-ba49-65bba25aae15 · outbound

This paper cites SocraSynth: Multi-LLM Reasoning with Conditional Statistics.

Trace-of-Thought Prompting: Investigating Prompt-Based Knowledge Distillation Through Question Decomposition SocraSynth: Multi-LLM Reasoning with Conditional Statistics

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-16T05:19:57.446872Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7506e141-6003-4a13-84a1-362ca612649e · outbound

This paper cites Unleashing the potential of prompt engineering for large language models.

Trace-of-Thought Prompting: Investigating Prompt-Based Knowledge Distillation Through Question Decomposition Unleashing the potential of prompt engineering for large language models

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-16T05:19:57.450868Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e2b55c18-f68d-42c8-938c-7422a8dfb35f · outbound

This paper cites CoMM: Collaborative Multi-Agent, Multi-Reasoning-Path Prompting for Complex Problem Solving.

Trace-of-Thought Prompting: Investigating Prompt-Based Knowledge Distillation Through Question Decomposition CoMM: Collaborative Multi-Agent, Multi-Reasoning-Path Prompting for Complex Problem Solving

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-16T05:19:57.455125Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ee905b54-88c6-4249-a495-081a48b29b70 · outbound

This paper cites Self-Play Fine-Tuning Converts Weak Language Models to Strong Language Models.

Trace-of-Thought Prompting: Investigating Prompt-Based Knowledge Distillation Through Question Decomposition Self-Play Fine-Tuning Converts Weak Language Models to Strong Language Models

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-16T05:19:57.459531Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0e58d9e0-9e46-4688-9da6-f30e4d216de6 · outbound

This paper cites Training Verifiers to Solve Math Word Problems.

Trace-of-Thought Prompting: Investigating Prompt-Based Knowledge Distillation Through Question Decomposition Training Verifiers to Solve Math Word Problems

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-16T05:19:57.464366Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 69b9990c-c9ac-495b-a0dc-17d486c6b9a9 · outbound

This paper cites Metacognitive Capabilities of LLMs: An Exploration in Mathematical Problem Solving.

Trace-of-Thought Prompting: Investigating Prompt-Based Knowledge Distillation Through Question Decomposition Metacognitive Capabilities of LLMs: An Exploration in Mathematical Problem Solving

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-16T05:19:57.467973Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f3fba6ed-2c05-4c19-996c-dc596cc22f2c · outbound

This paper cites Successive Prompting for Decomposing Complex Questions.

Trace-of-Thought Prompting: Investigating Prompt-Based Knowledge Distillation Through Question Decomposition Successive Prompting for Decomposing Complex Questions

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-16T05:19:57.471940Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 43d4e24a-cbb3-4851-88dd-50292cb6d62f · outbound

This paper cites Socratic Reasoning Improves Positive Text Rewriting.

Trace-of-Thought Prompting: Investigating Prompt-Based Knowledge Distillation Through Question Decomposition Socratic Reasoning Improves Positive Text Rewriting

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-16T05:19:57.475167Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f021245d-6c6b-4e8e-ab5a-5e21c4f82b63 · outbound

This paper cites MiniLLM: On-Policy Distillation of Large Language Models.

Trace-of-Thought Prompting: Investigating Prompt-Based Knowledge Distillation Through Question Decomposition MiniLLM: On-Policy Distillation of Large Language Models

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-16T05:19:57.478932Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation be738131-80a1-42c0-a49f-8d4b66328b42 · outbound

This paper cites Textbooks Are All You Need.

Trace-of-Thought Prompting: Investigating Prompt-Based Knowledge Distillation Through Question Decomposition Textbooks Are All You Need

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-16T05:19:57.482207Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a9d5048f-6545-4db7-82d1-37f983a3b033 · outbound

This paper cites Embodied LLM Agents Learn to Cooperate in Organized Teams.

Trace-of-Thought Prompting: Investigating Prompt-Based Knowledge Distillation Through Question Decomposition Embodied LLM Agents Learn to Cooperate in Organized Teams

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-16T05:19:57.485522Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5b2483e6-c862-41e7-930b-bcbf8a3278e4 · outbound

This paper cites Distilling the Knowledge in a Neural Network.

Trace-of-Thought Prompting: Investigating Prompt-Based Knowledge Distillation Through Question Decomposition Distilling the Knowledge in a Neural Network

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-16T05:19:57.488810Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 22c5e922-e9da-45b7-99ab-77e545bab535 · outbound

This paper cites $\texttt{LM}^\texttt{2}$: A Simple Society of Language Models Solves Complex Reasoning.

Trace-of-Thought Prompting: Investigating Prompt-Based Knowledge Distillation Through Question Decomposition $\texttt{LM}^\texttt{2}$: A Simple Society of Language Models Solves Complex Reasoning

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-16T05:19:57.492497Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d989cdf2-9a5d-4a6b-a824-903deec75c5e · outbound

This paper cites Decomposed Prompting: A Modular Approach for Solving Complex Tasks.

Trace-of-Thought Prompting: Investigating Prompt-Based Knowledge Distillation Through Question Decomposition Decomposed Prompting: A Modular Approach for Solving Complex Tasks

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-16T05:19:57.496521Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5427d922-4fd1-45a2-978b-09b446af9d96 · outbound

This paper cites Large Language Models are Zero-Shot Reasoners.

Trace-of-Thought Prompting: Investigating Prompt-Based Knowledge Distillation Through Question Decomposition Large Language Models are Zero-Shot Reasoners

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-16T05:19:57.501389Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d8f2374a-453d-43a4-aaec-97bd96b71c36 · outbound

This paper cites an unresolved cited work.

Trace-of-Thought Prompting: Investigating Prompt-Based Knowledge Distillation Through Question Decomposition Unresolved cited work

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-16T05:19:57.506066Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fda2a4a9-7891-44a2-b98b-2c307cbc5b1d · outbound

This paper cites CAMEL: Communicative Agents for "Mind" Exploration of Large Language Model Society.

Trace-of-Thought Prompting: Investigating Prompt-Based Knowledge Distillation Through Question Decomposition CAMEL: Communicative Agents for "Mind" Exploration of Large Language Model Society

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-16T05:19:57.510353Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3a5d76f4-913a-4699-bf7e-3938f11d9687 · outbound

This paper cites Long-context LLMs Struggle with Long In-context Learning.

Trace-of-Thought Prompting: Investigating Prompt-Based Knowledge Distillation Through Question Decomposition Long-context LLMs Struggle with Long In-context Learning

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-16T05:19:57.514586Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ae821507-cc28-45e5-a1bf-4c9bf27736f5 · outbound

This paper cites Evolving Knowledge Distillation with Large Language Models and Active Learning.

Trace-of-Thought Prompting: Investigating Prompt-Based Knowledge Distillation Through Question Decomposition Evolving Knowledge Distillation with Large Language Models and Active Learning

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-16T05:19:57.518285Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 52e085ff-7099-48c7-9eaf-020fd871e4c2 · outbound

This paper cites Social Learning: Towards Collaborative Learning with Large Language Models.

Trace-of-Thought Prompting: Investigating Prompt-Based Knowledge Distillation Through Question Decomposition Social Learning: Towards Collaborative Learning with Large Language Models

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-16T05:19:57.522562Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a8214e23-e340-4b16-a5d4-930f5e6b60de · outbound

This paper cites Measuring and Narrowing the Compositionality Gap in Language Models.

Trace-of-Thought Prompting: Investigating Prompt-Based Knowledge Distillation Through Question Decomposition Measuring and Narrowing the Compositionality Gap in Language Models

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-16T05:19:57.526291Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 60a59085-42e8-4574-a05e-c0e00a7922d9 · outbound

This paper cites The Art of SOCRATIC QUESTIONING: Recursive Thinking with Large Language Models.

Trace-of-Thought Prompting: Investigating Prompt-Based Knowledge Distillation Through Question Decomposition The Art of SOCRATIC QUESTIONING: Recursive Thinking with Large Language Models

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-16T05:19:57.529852Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2f1c4682-7f6c-4683-a2e4-236e36a3ecd0 · outbound

This paper cites A Systematic Survey of Prompt Engineering in Large Language Models: Techniques and Applications.

Trace-of-Thought Prompting: Investigating Prompt-Based Knowledge Distillation Through Question Decomposition A Systematic Survey of Prompt Engineering in Large Language Models: Techniques and Applications

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-16T05:19:57.534935Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bd65af0e-e675-4019-a823-c2eed5051e25 · outbound

This paper cites Distilling Reasoning Capabilities into Smaller Language Models.

Trace-of-Thought Prompting: Investigating Prompt-Based Knowledge Distillation Through Question Decomposition Distilling Reasoning Capabilities into Smaller Language Models

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-16T05:19:57.539548Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ee3e4ac0-a9ba-4180-bc5e-a4a1c812f708 · outbound

This paper cites PEARL: Prompting Large Language Models to Plan and Execute Actions Over Long Documents.

Trace-of-Thought Prompting: Investigating Prompt-Based Knowledge Distillation Through Question Decomposition PEARL: Prompting Large Language Models to Plan and Execute Actions Over Long Documents

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-16T05:19:57.543865Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 29a86ea5-1aa4-44c1-8fa3-81ba8edc79bf · outbound

This paper cites Gemma: Open Models Based on Gemini Research and Technology.

Trace-of-Thought Prompting: Investigating Prompt-Based Knowledge Distillation Through Question Decomposition Gemma: Open Models Based on Gemini Research and Technology

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-16T05:19:57.547861Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9d7e7c3f-1824-4c15-8cd0-2b1885c1d50b · outbound

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

Trace-of-Thought Prompting: Investigating Prompt-Based Knowledge Distillation Through Question Decomposition LLaMA: Open and Efficient Foundation Language Models

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-16T05:19:57.552092Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c28bfb2d-cf0a-46d0-b09a-ae65c0145e8c · outbound

This paper cites Zephyr: Direct Distillation of LM Alignment.

Trace-of-Thought Prompting: Investigating Prompt-Based Knowledge Distillation Through Question Decomposition Zephyr: Direct Distillation of LM Alignment

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-16T05:19:57.555133Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 686410cb-4d51-4a3e-84fd-d86c57571465 · outbound

This paper cites Adapting LLMs for Efficient Context Processing through Soft Prompt Compression.

Trace-of-Thought Prompting: Investigating Prompt-Based Knowledge Distillation Through Question Decomposition Adapting LLMs for Efficient Context Processing through Soft Prompt Compression

Reference 31

Resolution: verified exact; local_arxiv, observed 2026-08-16T05:19:57.757383Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 531ace41-b313-4653-a29f-768bc67414fd · outbound

This paper cites Plan-and-Solve Prompting: Improving Zero-Shot Chain-of-Thought Reasoning by Large Language Models.

Trace-of-Thought Prompting: Investigating Prompt-Based Knowledge Distillation Through Question Decomposition Plan-and-Solve Prompting: Improving Zero-Shot Chain-of-Thought Reasoning by Large Language Models

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-16T05:19:57.562116Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 24311791-fa28-4dec-853b-eb606db87d5d · outbound

This paper cites Self-Consistency Improves Chain of Thought Reasoning in Language Models.

Trace-of-Thought Prompting: Investigating Prompt-Based Knowledge Distillation Through Question Decomposition Self-Consistency Improves Chain of Thought Reasoning in Language Models

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-16T05:19:57.565775Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5897fa4d-def6-4e69-95ab-073b3ddd05cf · outbound

This paper cites Chain-of-Thought Prompting Elicits Reasoning in Large Language Models.

Trace-of-Thought Prompting: Investigating Prompt-Based Knowledge Distillation Through Question Decomposition Chain-of-Thought Prompting Elicits Reasoning in Large Language Models

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-16T05:19:57.569130Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 98990695-119f-467a-9b03-1094f184a004 · outbound

This paper cites Mitigating Misleading Chain-of-Thought Reasoning with Selective Filtering.

Trace-of-Thought Prompting: Investigating Prompt-Based Knowledge Distillation Through Question Decomposition Mitigating Misleading Chain-of-Thought Reasoning with Selective Filtering

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-16T05:19:57.573033Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4426e90b-aa31-4c26-9ce2-cbdfda44e718 · outbound

This paper cites WizardLM: Empowering large pre-trained language models to follow complex instructions.

Trace-of-Thought Prompting: Investigating Prompt-Based Knowledge Distillation Through Question Decomposition WizardLM: Empowering large pre-trained language models to follow complex instructions

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-16T05:19:57.577019Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 173df668-f811-4406-868d-43dcb60ab234 · outbound

This paper cites A Survey on Knowledge Distillation of Large Language Models.

Trace-of-Thought Prompting: Investigating Prompt-Based Knowledge Distillation Through Question Decomposition A Survey on Knowledge Distillation of Large Language Models

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-16T05:19:57.581145Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3642f93a-a756-4231-a662-40feab2f0dfc · outbound

This paper cites Tree of Thoughts: Deliberate Problem Solving with Large Language Models.

Trace-of-Thought Prompting: Investigating Prompt-Based Knowledge Distillation Through Question Decomposition Tree of Thoughts: Deliberate Problem Solving with Large Language Models

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-16T05:19:57.585227Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5f0b03ed-ae87-45bc-bed3-936b8dbfe1de · outbound

This paper cites Socratic Models: Composing Zero-Shot Multimodal Reasoning with Language.

Trace-of-Thought Prompting: Investigating Prompt-Based Knowledge Distillation Through Question Decomposition Socratic Models: Composing Zero-Shot Multimodal Reasoning with Language

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-16T05:19:57.589412Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 58708d3a-6ea2-4153-bf05-7c38ea260217 · outbound

This paper cites Small Language Models Need Strong Verifiers to Self-Correct Reasoning.

Trace-of-Thought Prompting: Investigating Prompt-Based Knowledge Distillation Through Question Decomposition Small Language Models Need Strong Verifiers to Self-Correct Reasoning

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-16T05:19:57.593568Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8e5763d6-993d-4cd3-8486-ca78aab9cbea · outbound

This paper cites Progressive-Hint Prompting Improves Reasoning in Large Language Models.

Trace-of-Thought Prompting: Investigating Prompt-Based Knowledge Distillation Through Question Decomposition Progressive-Hint Prompting Improves Reasoning in Large Language Models

Reference 41

Resolution: unresolved; no resolver link, observed 2026-08-16T05:19:57.597661Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b8f30756-469e-43e2-8919-a9002612d71a · outbound

This paper cites PANDA: Prompt Transfer Meets Knowledge Distillation for Efficient Model Adaptation.

Trace-of-Thought Prompting: Investigating Prompt-Based Knowledge Distillation Through Question Decomposition PANDA: Prompt Transfer Meets Knowledge Distillation for Efficient Model Adaptation

Reference 42

Resolution: unresolved; no resolver link, observed 2026-08-16T05:19:57.601622Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d8904698-4fb3-4241-88b2-6d4f099e0a82 · outbound

This paper cites Least-to-Most Prompting Enables Complex Reasoning in Large Language Models.

Trace-of-Thought Prompting: Investigating Prompt-Based Knowledge Distillation Through Question Decomposition Least-to-Most Prompting Enables Complex Reasoning in Large Language Models

Reference 43

Resolution: unresolved; no resolver link, observed 2026-08-16T05:19:57.605929Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 97030440-62e9-4855-bfb3-57d3f5a90ea0 · outbound

This paper cites URL: " 'urlintro :=.

Trace-of-Thought Prompting: Investigating Prompt-Based Knowledge Distillation Through Question Decomposition URL: " 'urlintro :=

Reference 44

Resolution: unresolved; no resolver link, observed 2026-08-16T05:19:57.609740Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 54a3a619-6a24-403e-93c9-1f843ee347eb · outbound

This paper cites write newline.

Trace-of-Thought Prompting: Investigating Prompt-Based Knowledge Distillation Through Question Decomposition write newline

Reference 45

Resolution: unresolved; no resolver link, observed 2026-08-16T05:19:57.613688Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

No inbound Pith citation observations are available.