Paper Citation Record · LEDGER

Reasoning-Finetuning Repurposes Latent Representations in Base Models

As of 9 August 2026, this Paper Citation Record lists 11 of 11 outbound references and 7 inbound Pith citation observations for arXiv:2507.12638.

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

pith.paper-citation-record.v1
2507.12638 v1

Coverage vector

measured 11 of 11 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-06T16:50:00.947051Z

measured 18 of 18 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-09T06:31:02.800959+00:00

measured 7 of 7 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-02T06:37:43.829079Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-07-03T09:07:47.853577Z

Reference resolution

11 of 11 outbound references displayed

verified exact0
verified fuzzy1
unresolved10
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation c514358f-7107-49ea-a9e3-4f370d7b08c2 · outbound

This paper cites write newline.

Reasoning-Finetuning Repurposes Latent Representations in Base Models write newline

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-06T16:49:59.982410Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0c01c1b5-1cd2-4058-a107-c2f192069f9f · outbound

This paper cites Refusal in Language Models Is Mediated by a Single Direction.

Reasoning-Finetuning Repurposes Latent Representations in Base Models Refusal in Language Models Is Mediated by a Single Direction

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-06T16:50:00.079537Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f8bb119f-f6ac-4136-991c-45324ab7c699 · outbound

This paper cites I Have Covered All the Bases Here: Interpreting Reasoning Features in Large Language Models via Sparse Autoencoders.

Reasoning-Finetuning Repurposes Latent Representations in Base Models I Have Covered All the Bases Here: Interpreting Reasoning Features in Large Language Models via Sparse Autoencoders

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-06T16:50:00.194759Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8de3171c-a2d8-41c1-bea2-d3c8d33d0061 · outbound

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

Reasoning-Finetuning Repurposes Latent Representations in Base Models DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-06T16:50:00.302715Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 29b01fab-4999-49ea-84a9-31297eaec5fc · outbound

This paper cites s1: Simple test-time scaling.

Reasoning-Finetuning Repurposes Latent Representations in Base Models s1: Simple test-time scaling

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-06T16:50:00.387833Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a92f9e60-ab0d-4f21-89eb-af48e6014b51 · outbound

This paper cites Steering llama 2 via contrastive activation addition.

Reasoning-Finetuning Repurposes Latent Representations in Base Models Steering llama 2 via contrastive activation addition

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-06T16:50:00.517158Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c5df048c-9ba7-4429-98ee-05c0f3508a8c · outbound

This paper cites Understanding reasoning in thinking language models via steering vectors.

Reasoning-Finetuning Repurposes Latent Representations in Base Models Understanding reasoning in thinking language models via steering vectors

Reference 7

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T16:50:01.201514Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 978acae3-250b-4d22-9da3-b60358b66818 · outbound

This paper cites V., Zhou, D., et al.

Reasoning-Finetuning Repurposes Latent Representations in Base Models V., Zhou, D., et al

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-06T16:50:00.733952Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9bcb3b60-b291-487b-b18f-1fa649f93c7c · outbound

This paper cites Step Back to Leap Forward: Self-Backtracking for Boosting Reasoning of Language Models.

Reasoning-Finetuning Repurposes Latent Representations in Base Models Step Back to Leap Forward: Self-Backtracking for Boosting Reasoning of Language Models

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-06T16:50:00.804855Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0ed703d5-4526-4335-9935-6d8a042fb6da · outbound

This paper cites On the Emergence of Thinking in LLMs I: Searching for the Right Intuition.

Reasoning-Finetuning Repurposes Latent Representations in Base Models On the Emergence of Thinking in LLMs I: Searching for the Right Intuition

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-06T16:50:00.873671Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2b13e241-4ce3-4ba6-a4ac-11b01195656a · outbound

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

Reasoning-Finetuning Repurposes Latent Representations in Base Models Demystifying Long Chain-of-Thought Reasoning in LLMs

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-06T16:50:00.947051Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation 941f5e68-792c-4568-ba71-b24b273bf530 · inbound

How LLMs Detect and Correct Their Own Errors: The Role of Internal Confidence Signals cites this paper.

How LLMs Detect and Correct Their Own Errors: The Role of Internal Confidence Signals Reasoning-Finetuning Repurposes Latent Representations in Base Models

Reference 24

Resolution: verified exact; arxiv_id, observed 2026-05-11T19:16:06.925057Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 04caf4e6-7821-4b2e-a697-f159d46abb39 · inbound

Consolidating Rewarded Perturbations for LLM Post-Training cites this paper.

Consolidating Rewarded Perturbations for LLM Post-Training Reasoning-Finetuning Repurposes Latent Representations in Base Models

Reference 8

Resolution: metadata mismatch; arxiv_id, observed 2026-06-28T22:42:46.873074Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation cfe84e7f-8438-4786-8b3c-020aa1fbefde · inbound

Latent Reward Steering: An Adaptive Inference-Time Framework that Implicitly Promotes Cognitive Behaviors in Reasoning LLMs cites this paper.

Latent Reward Steering: An Adaptive Inference-Time Framework that Implicitly Promotes Cognitive Behaviors in Reasoning LLMs Reasoning-Finetuning Repurposes Latent Representations in Base Models

Reference 33

Resolution: verified exact; arxiv_id, observed 2026-06-28T19:52:35.488796Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation f91a972e-3275-4251-bbb7-1c849b4067c3 · inbound

Anatomy of Post-Training: Using Interpretability to Characterize Data and Shape the Learning Signal cites this paper.

Anatomy of Post-Training: Using Interpretability to Characterize Data and Shape the Learning Signal Reasoning-Finetuning Repurposes Latent Representations in Base Models

Reference 100

Resolution: verified exact; arxiv_id, observed 2026-07-03T09:07:47.855000Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation d7a7d8ca-45c2-4850-85e2-114e046879b7 · inbound

Breaking the Solver Bottleneck: Training Task Generators at the Learnable Frontier cites this paper.

Breaking the Solver Bottleneck: Training Task Generators at the Learnable Frontier Reasoning-Finetuning Repurposes Latent Representations in Base Models

Reference 106

Resolution: verified exact; arxiv_id, observed 2026-07-03T08:57:48.266435Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 2f987154-877f-44e5-a9eb-b6e2fd8e3287 · inbound

The Computational Basis of Confidence in Large Language Models cites this paper.

The Computational Basis of Confidence in Large Language Models Reasoning-Finetuning Repurposes Latent Representations in Base Models

Reference 52

Resolution: unresolved; no resolver link, observed 2026-08-02T06:37:43.829079Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d1b1a916-9964-45b0-91f3-c4a1b61dcfc8 · inbound

Reasoning Fine-Tuning Induces Persistent Latent Policy States cites this paper.

Reasoning Fine-Tuning Induces Persistent Latent Policy States Reasoning-Finetuning Repurposes Latent Representations in Base Models

Reference 82

Resolution: unresolved; no resolver link, observed 2026-08-01T15:16:21.171395Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.