Paper Citation Record · LEDGER

Feature Extraction and Steering for Enhanced Chain-of-Thought Reasoning in Language Models

As of 17 August 2026, this Paper Citation Record lists 15 of 15 outbound references and 4 inbound Pith citation observations for arXiv:2505.15634.

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

pith.paper-citation-record.v1
2505.15634 v4

Coverage vector

measured 15 of 15 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-07T15:17:17.189366Z

measured 19 of 19 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-17T06:30:58.91139+00:00

measured 4 of 4 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-12T00:23:50.470682Z

measured 1 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-08-05T02:28:24.338817Z

Reference resolution

15 of 15 outbound references displayed

verified exact0
verified fuzzy1
unresolved14
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

0
arxiv_reference, observed 2026-08-05T02:28:24.338817Z

Outbound references

Observation d06f4d5c-2b46-4e51-a9ec-4cc5d89964d0 · outbound

This paper cites an unresolved cited work.

Feature Extraction and Steering for Enhanced Chain-of-Thought Reasoning in Language Models Unresolved cited work

Reference 2

Resolution: unresolved; raw_fallback, observed 2026-08-07T15:17:18.586968Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 5382814c-cb2a-4200-97c0-1f1ea8634334 · outbound

This paper cites OpenAI o1 System Card.

Feature Extraction and Steering for Enhanced Chain-of-Thought Reasoning in Language Models OpenAI o1 System Card

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-07T15:17:15.728866Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b6963240-da6c-4b85-9e44-ac92f5018386 · outbound

This paper cites Gemma Scope: Open Sparse Autoencoders Everywhere All At Once on Gemma 2.

Feature Extraction and Steering for Enhanced Chain-of-Thought Reasoning in Language Models Gemma Scope: Open Sparse Autoencoders Everywhere All At Once on Gemma 2

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-07T15:17:15.847691Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ec8aad33-5111-41c8-ad2a-8517781523fe · outbound

This paper cites an unresolved cited work.

Feature Extraction and Steering for Enhanced Chain-of-Thought Reasoning in Language Models Unresolved cited work

Reference 5

Resolution: unresolved; raw_fallback, observed 2026-08-07T15:17:18.110871Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation a128903e-6a3a-4e0a-8938-e64661f7f30d · outbound

This paper cites an unresolved cited work.

Feature Extraction and Steering for Enhanced Chain-of-Thought Reasoning in Language Models Unresolved cited work

Reference 6

Resolution: unresolved; raw_fallback, observed 2026-08-07T15:17:17.993766Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 2bf9e7f3-238c-42b1-a487-18f0c44d4a2b · outbound

This paper cites Humanity's Last Exam.

Feature Extraction and Steering for Enhanced Chain-of-Thought Reasoning in Language Models Humanity's Last Exam

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-07T15:17:16.220156Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e53800c9-0687-462e-a42c-40e035ac7914 · outbound

This paper cites an unresolved cited work.

Feature Extraction and Steering for Enhanced Chain-of-Thought Reasoning in Language Models Unresolved cited work

Reference 8

Resolution: unresolved; raw_fallback, observed 2026-08-07T15:17:17.651754Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 6aecfa67-6928-458d-878f-07bd5f102984 · outbound

This paper cites an unresolved cited work.

Feature Extraction and Steering for Enhanced Chain-of-Thought Reasoning in Language Models Unresolved cited work

Reference 9

Resolution: unresolved; raw_fallback, observed 2026-08-07T15:17:18.377007Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 5cf9db94-7571-4d53-a867-995a17c5591a · outbound

This paper cites an unresolved cited work.

Feature Extraction and Steering for Enhanced Chain-of-Thought Reasoning in Language Models Unresolved cited work

Reference 10

Resolution: unresolved; raw_fallback, observed 2026-08-07T15:17:18.258864Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 035df8c4-a25c-4979-91ea-f5e6deeb1613 · outbound

This paper cites an unresolved cited work.

Feature Extraction and Steering for Enhanced Chain-of-Thought Reasoning in Language Models Unresolved cited work

Reference 13

Resolution: unresolved; raw_fallback, observed 2026-08-07T15:17:17.845527Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 4d9310cb-89de-4a56-905c-747baf90348b · outbound

This paper cites mathematical parameters related to dimensions and positioning.

Feature Extraction and Steering for Enhanced Chain-of-Thought Reasoning in Language Models mathematical parameters related to dimensions and positioning

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:17:17.464917Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 9ac60a4f-5e51-47fe-a5f0-be8a60e805c2 · outbound

This paper cites Logic-LM: Empowering Large Language Models with Symbolic Solvers for Faithful Logical Reasoning.

Feature Extraction and Steering for Enhanced Chain-of-Thought Reasoning in Language Models Logic-LM: Empowering Large Language Models with Symbolic Solvers for Faithful Logical Reasoning

Reference 2013

Resolution: unresolved; no resolver link, observed 2026-08-07T15:17:16.104722Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8ca78e15-13b7-4ed2-84b4-3fc4be0c0ef6 · outbound

This paper cites Sparse Feature Circuits: Discovering and Editing Interpretable Causal Graphs in Language Models.

Feature Extraction and Steering for Enhanced Chain-of-Thought Reasoning in Language Models Sparse Feature Circuits: Discovering and Editing Interpretable Causal Graphs in Language Models

Reference 2023

Resolution: unresolved; no resolver link, observed 2026-08-07T15:17:15.986974Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 637f78f4-c60e-4005-aabb-8915d3d176fb · outbound

This paper cites Applying sparse autoencoders to unlearn knowledge in language models.

Feature Extraction and Steering for Enhanced Chain-of-Thought Reasoning in Language Models Applying sparse autoencoders to unlearn knowledge in language models

Reference 2024

Resolution: unresolved; no resolver link, observed 2026-08-07T15:17:15.579347Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 130bcd15-b5a7-4de7-8d55-af4df3b7a685 · outbound

This paper cites Improving Reasoning Performance in Large Language Models via Representation Engineering.

Feature Extraction and Steering for Enhanced Chain-of-Thought Reasoning in Language Models Improving Reasoning Performance in Large Language Models via Representation Engineering

Reference 2025

Resolution: unresolved; no resolver link, observed 2026-08-07T15:17:15.632372Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation 78c0e9b3-8307-4c2c-b0a1-94c1f3af1089 · inbound

How Do Answer Tokens Read Reasoning Traces? Self-Reading Patterns in Thinking LLMs for Quantitative Reasoning cites this paper.

How Do Answer Tokens Read Reasoning Traces? Self-Reading Patterns in Thinking LLMs for Quantitative Reasoning Feature Extraction and Steering for Enhanced Chain-of-Thought Reasoning in Language Models

Reference 26

Resolution: verified exact; arxiv_id, observed 2026-05-10T02:43:24.266659Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 449bf189-3e85-47f4-853d-bd04cdd243b6 · inbound

The Tell-Tale Norm: $\ell_2$ Magnitude as a Signal for Reasoning Dynamics in Large Language Models cites this paper.

The Tell-Tale Norm: $\ell_2$ Magnitude as a Signal for Reasoning Dynamics in Large Language Models Feature Extraction and Steering for Enhanced Chain-of-Thought Reasoning in Language Models

Reference 15

Resolution: metadata mismatch; arxiv_id, observed 2026-07-02T12:26:56.915407Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 84e66f56-df9c-48cd-aaa7-301176d5d1f7 · inbound

Purified OPSD: On-Policy Self-Distillation Without Losing How to Think cites this paper.

Purified OPSD: On-Policy Self-Distillation Without Losing How to Think Feature Extraction and Steering for Enhanced Chain-of-Thought Reasoning in Language Models

Reference 11

Resolution: metadata mismatch; arxiv_id, observed 2026-07-03T13:58:21.067380Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 115a9d7f-3f22-4362-9688-271f013aea15 · inbound

Thinking vs. NoThinking: Towards Interpreting Reasoning Mechanisms of Large Language Models via Sparse Autoencoders cites this paper.

Thinking vs. NoThinking: Towards Interpreting Reasoning Mechanisms of Large Language Models via Sparse Autoencoders Feature Extraction and Steering for Enhanced Chain-of-Thought Reasoning in Language Models

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-12T00:23:50.470682Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.