Paper Citation Record · LEDGER

Reasoning-Trace Collapse: Evaluating the Loss of Explicit Reasoning During Fine-Tuning

As of 17 August 2026, this Paper Citation Record lists 35 of 35 outbound references and 1 inbound Pith citation observation for arXiv:2605.21127.

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

pith.paper-citation-record.v1
2605.21127 v1

Coverage vector

measured 35 of 35 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-05-21T06:04:41.398736Z

measured 36 of 36 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-16T06:30:59.297886+00:00

measured 1 of 1 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-01T00:38:43.150846Z

measured 0 of 1 external citation measurements

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

Source: cited_works

Reference resolution

35 of 35 outbound references displayed

verified exact7
verified fuzzy24
unresolved2
parse uncertain0
malformed identifier0
metadata mismatch2

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 8828dbc9-7d8a-4ba4-b234-43aa56db161c · outbound

This paper cites Allenai/Olmo-3-7B-Think · Hugging Face.

Reasoning-Trace Collapse: Evaluating the Loss of Explicit Reasoning During Fine-Tuning Allenai/Olmo-3-7B-Think · Hugging Face

Reference 1

Resolution: verified fuzzy; raw_fallback, observed 2026-05-21T09:04:56.368984Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation c3871ec5-348a-4767-ba20-b5997d7637e5 · outbound

This paper cites Reasoning AI Models: An overview.

Reasoning-Trace Collapse: Evaluating the Loss of Explicit Reasoning During Fine-Tuning Reasoning AI Models: An overview

Reference 2

Resolution: verified fuzzy; raw_fallback, observed 2026-05-21T09:04:56.390860Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation bc7db456-6297-4a6a-96b5-e7df1b9aecb3 · outbound

This paper cites LoRA learns less and forgets less.Transactions on Machine Learning Research.

Reasoning-Trace Collapse: Evaluating the Loss of Explicit Reasoning During Fine-Tuning LoRA learns less and forgets less.Transactions on Machine Learning Research

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-05-21T09:04:56.374507Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 89d33297-888c-4437-9b20-268ef14b4be9 · outbound

This paper cites Training Verifiers to Solve Math Word Problems, November 2021.

Reasoning-Trace Collapse: Evaluating the Loss of Explicit Reasoning During Fine-Tuning Training Verifiers to Solve Math Word Problems, November 2021

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-05-21T09:04:56.361635Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 957c8ecf-9ab3-4280-b7b0-a65548fc53e2 · outbound

This paper cites an unresolved cited work.

Reasoning-Trace Collapse: Evaluating the Loss of Explicit Reasoning During Fine-Tuning Unresolved cited work

Reference 5

Resolution: unresolved; raw_fallback, observed 2026-05-21T09:04:56.364077Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation b3140347-7ef4-4949-9151-93493e216424 · outbound

This paper cites Transformers.

Reasoning-Trace Collapse: Evaluating the Loss of Explicit Reasoning During Fine-Tuning Transformers

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-05-21T09:04:56.356435Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation b22d67d6-53e1-4371-b6de-019f276d9dc2 · outbound

This paper cites Keypoint- based progressive chain-of-thought distillation for LLMs.

Reasoning-Trace Collapse: Evaluating the Loss of Explicit Reasoning During Fine-Tuning Keypoint- based progressive chain-of-thought distillation for LLMs

Reference 7

Resolution: verified fuzzy; raw_fallback, observed 2026-05-21T09:04:56.354014Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 2ba8adb9-5f2a-43a9-b90f-c3b05a9cba4e · outbound

This paper cites SciKnowEval: A Comprehensive Dataset for Evaluating Scientific Knowledge of Large Language Models.

Reasoning-Trace Collapse: Evaluating the Loss of Explicit Reasoning During Fine-Tuning SciKnowEval: A Comprehensive Dataset for Evaluating Scientific Knowledge of Large Language Models

Reference 8

Resolution: verified fuzzy; raw_fallback, observed 2026-05-21T09:04:56.359219Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation e8534c31-a0ac-4db1-88c1-9baa4df797d3 · outbound

This paper cites an unresolved cited work.

Reasoning-Trace Collapse: Evaluating the Loss of Explicit Reasoning During Fine-Tuning Unresolved cited work

Reference 9

Resolution: unresolved; raw_fallback, observed 2026-05-21T09:04:56.366430Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 25afb56c-8383-434f-95ec-da6f215a4dd9 · outbound

This paper cites LLM reasoners: New evaluation, library, and analysis of step-by-step reasoning with large language models.

Reasoning-Trace Collapse: Evaluating the Loss of Explicit Reasoning During Fine-Tuning LLM reasoners: New evaluation, library, and analysis of step-by-step reasoning with large language models

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-05-21T09:04:56.371350Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 611090a6-54c2-40f2-95c8-bde3b6f05363 · outbound

This paper cites doi: 10.18653/v1/2023.findings-acl.507.

Reasoning-Trace Collapse: Evaluating the Loss of Explicit Reasoning During Fine-Tuning doi: 10.18653/v1/2023.findings-acl.507

Reference 11

Resolution: metadata mismatch; doi, observed 2026-05-21T06:09:41.205378Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 5b77db85-677c-4014-8250-dd9b489e0f53 · outbound

This paper cites Hu, Yelong Shen, Phillip Wallis, Zeyuan Allen-Zhu, Yuanzhi Li, Shean Wang, Lu Wang, and Weizhu Chen.

Reasoning-Trace Collapse: Evaluating the Loss of Explicit Reasoning During Fine-Tuning Hu, Yelong Shen, Phillip Wallis, Zeyuan Allen-Zhu, Yuanzhi Li, Shean Wang, Lu Wang, and Weizhu Chen

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-05-21T09:04:56.348771Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation fea6ad63-db83-4dcd-bd32-4bdc0ec714ca · outbound

This paper cites Joshi, Hanna Moazam, Heather Miller, Matei Zaharia, and Christopher Potts.

Reasoning-Trace Collapse: Evaluating the Loss of Explicit Reasoning During Fine-Tuning Joshi, Hanna Moazam, Heather Miller, Matei Zaharia, and Christopher Potts

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-05-21T09:04:56.351371Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 8c730f71-50a3-4d9c-a9ae-09a2412d398b · outbound

This paper cites Evaluating Step-by-step Reasoning Traces: A Survey.

Reasoning-Trace Collapse: Evaluating the Loss of Explicit Reasoning During Fine-Tuning Evaluating Step-by-step Reasoning Traces: A Survey

Reference 14

Resolution: verified exact; doi, observed 2026-05-21T06:09:41.209901Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 6bfe0ea4-d772-4d75-8c78-33a6be4fc65d · outbound

This paper cites Let’s Verify Step by Step.

Reasoning-Trace Collapse: Evaluating the Loss of Explicit Reasoning During Fine-Tuning Let’s Verify Step by Step

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-05-21T09:04:56.379351Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation b21227e2-3a0a-45c4-9a22-8e22cdbe90dd · outbound

This paper cites Is your code generated by ChatGPT really correct? rigorous evaluation of large language models for code generation.

Reasoning-Trace Collapse: Evaluating the Loss of Explicit Reasoning During Fine-Tuning Is your code generated by ChatGPT really correct? rigorous evaluation of large language models for code generation

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-05-21T09:04:56.345860Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 2cce981c-214f-4194-97c1-565e81162e4a · outbound

This paper cites On the Impact of Fine-Tuning on Chain- of-Thought Reasoning.

Reasoning-Trace Collapse: Evaluating the Loss of Explicit Reasoning During Fine-Tuning On the Impact of Fine-Tuning on Chain- of-Thought Reasoning

Reference 17

Resolution: verified exact; doi, observed 2026-05-21T06:09:41.194414Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 96aab305-7b10-4aa2-a755-fc16382253ed · outbound

This paper cites Decoupled Weight Decay Regularization.

Reasoning-Trace Collapse: Evaluating the Loss of Explicit Reasoning During Fine-Tuning Decoupled Weight Decay Regularization

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-05-21T09:04:56.381708Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 7cb83f2c-221e-41fb-ac2a-84c2c0fd15cc · outbound

This paper cites Qwen3 Best Practices.

Reasoning-Trace Collapse: Evaluating the Loss of Explicit Reasoning During Fine-Tuning Qwen3 Best Practices

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-05-21T09:04:56.334898Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation a726bc59-54b8-4ee7-a019-73d2c41aef8b · outbound

This paper cites Nvidia/OpenReasoning-Nemotron-7B.

Reasoning-Trace Collapse: Evaluating the Loss of Explicit Reasoning During Fine-Tuning Nvidia/OpenReasoning-Nemotron-7B

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-05-21T09:04:56.339994Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation ce43b69e-9b7c-4608-ba91-82a574a35891 · outbound

This paper cites GPT-5 mini - API.

Reasoning-Trace Collapse: Evaluating the Loss of Explicit Reasoning During Fine-Tuning GPT-5 mini - API

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-05-21T09:04:56.326938Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 8c6deae5-9a81-4553-be29-c11a8b61ae57 · outbound

This paper cites Fine-tuning Aligned Language Models Compromises Safety, Even When Users Do Not Intend To! InThe Twelfth International Conference on Learning Representations, October 2023.

Reasoning-Trace Collapse: Evaluating the Loss of Explicit Reasoning During Fine-Tuning Fine-tuning Aligned Language Models Compromises Safety, Even When Users Do Not Intend To! InThe Twelfth International Conference on Learning Representations, October 2023

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-05-21T09:04:56.384679Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 39166f03-4eb8-43d5-8828-2e350dadbf62 · outbound

This paper cites Qwen/Qwen3-8B · Hugging Face.

Reasoning-Trace Collapse: Evaluating the Loss of Explicit Reasoning During Fine-Tuning Qwen/Qwen3-8B · Hugging Face

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-05-21T09:04:56.376958Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 302568f4-3d82-401a-a692-0593ebbd50f4 · outbound

This paper cites Self-Distillation Enables Continual Learning, January 2026.

Reasoning-Trace Collapse: Evaluating the Loss of Explicit Reasoning During Fine-Tuning Self-Distillation Enables Continual Learning, January 2026

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-05-21T09:04:56.324740Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 4c67bd20-059b-4a8d-a2c9-060773630af1 · outbound

This paper cites Yu, and Jianfeng Gao.

Reasoning-Trace Collapse: Evaluating the Loss of Explicit Reasoning During Fine-Tuning Yu, and Jianfeng Gao

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-05-21T09:04:56.337608Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 9fc4c315-fd4d-4734-ba64-f26d4673a726 · outbound

This paper cites A Short Survey on Small Reasoning Models: Training, Inference, Applications and Research Directions, April 2025.

Reasoning-Trace Collapse: Evaluating the Loss of Explicit Reasoning During Fine-Tuning A Short Survey on Small Reasoning Models: Training, Inference, Applications and Research Directions, April 2025

Reference 26

Resolution: verified fuzzy; raw_fallback, observed 2026-05-21T09:04:56.343212Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 991d84aa-c654-4834-b4bd-78eda740163f · outbound

This paper cites A Comprehensive Survey of Small Language Models in the Era of Large Language Models: Techniques, Enhancements, Applications, Collaboration with LLMs, and Trustworthiness.ACM Trans.

Reasoning-Trace Collapse: Evaluating the Loss of Explicit Reasoning During Fine-Tuning A Comprehensive Survey of Small Language Models in the Era of Large Language Models: Techniques, Enhancements, Applications, Collaboration with LLMs, and Trustworthiness.ACM Trans

Reference 27

Resolution: verified exact; doi, observed 2026-05-21T06:09:41.214421Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation a8a2ae42-3ac8-443d-bcb9-a9863b46d9fb · outbound

This paper cites SCOTT: Self-Consistent Chain-of-Thought Distillation.

Reasoning-Trace Collapse: Evaluating the Loss of Explicit Reasoning During Fine-Tuning SCOTT: Self-Consistent Chain-of-Thought Distillation

Reference 28

Resolution: verified exact; doi, observed 2026-05-21T06:09:41.199236Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 164785f3-3971-40a7-a802-ebdbd5f064e7 · outbound

This paper cites Emergent Abilities of Large Language Models.Transactions on Machine Learning Research.

Reasoning-Trace Collapse: Evaluating the Loss of Explicit Reasoning During Fine-Tuning Emergent Abilities of Large Language Models.Transactions on Machine Learning Research

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-05-21T09:04:56.332000Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 7c5060d3-74d1-4720-9b08-6be355aba015 · outbound

This paper cites Chi, Quoc V.

Reasoning-Trace Collapse: Evaluating the Loss of Explicit Reasoning During Fine-Tuning Chi, Quoc V

Reference 30

Resolution: verified fuzzy; raw_fallback, observed 2026-05-21T09:04:56.387394Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 4a0a5e6c-5ac6-4815-8cc4-7f54e004dbb7 · outbound

This paper cites Towards Large Reasoning Models: A Survey of Reinforced Reasoning with Large Language Models, January 2025.

Reasoning-Trace Collapse: Evaluating the Loss of Explicit Reasoning During Fine-Tuning Towards Large Reasoning Models: A Survey of Reinforced Reasoning with Large Language Models, January 2025

Reference 31

Resolution: verified fuzzy; raw_fallback, observed 2026-05-21T09:04:56.329159Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 455e431d-c49b-4bb3-8c8a-4c6c6675fd0e · outbound

This paper cites When Scaling Meets LLM Finetuning: The Effect of Data, Model and Finetuning Method.

Reasoning-Trace Collapse: Evaluating the Loss of Explicit Reasoning During Fine-Tuning When Scaling Meets LLM Finetuning: The Effect of Data, Model and Finetuning Method

Reference 32

Resolution: metadata mismatch; arxiv_id, observed 2026-05-21T06:09:41.202991Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 2fc0531d-49e4-422c-8507-ed807a58f77a · outbound

This paper cites Instruction Tuning for Large Language Models: A Survey.ACM Computing Surveys, page 3777411, November 2025.

Reasoning-Trace Collapse: Evaluating the Loss of Explicit Reasoning During Fine-Tuning Instruction Tuning for Large Language Models: A Survey.ACM Computing Surveys, page 3777411, November 2025

Reference 33

Resolution: verified exact; doi, observed 2026-05-21T06:09:41.196755Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 06225be4-c16e-4acf-bd94-9fe08401d093 · outbound

This paper cites Hedderich.

Reasoning-Trace Collapse: Evaluating the Loss of Explicit Reasoning During Fine-Tuning Hedderich

Reference 34

Resolution: verified exact; doi, observed 2026-05-21T06:09:41.207577Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 5b749ba1-2510-48bd-87f8-80e293cb8d68 · outbound

This paper cites Let me break this down step by step.

Reasoning-Trace Collapse: Evaluating the Loss of Explicit Reasoning During Fine-Tuning Let me break this down step by step

Reference 35

Resolution: verified exact; doi, observed 2026-05-21T06:09:41.212134Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Pith citing papers

Observation 6bb12c35-1561-450b-84e1-65c60c405e43 · inbound

Shared SFT Lessons Across Alignment, Model Organisms, and Toy Models cites this paper.

Shared SFT Lessons Across Alignment, Model Organisms, and Toy Models Reasoning-Trace Collapse: Evaluating the Loss of Explicit Reasoning During Fine-Tuning

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-01T00:38:43.150846Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.