Paper Citation Record · LEDGER

Improving Reasoning Performance in Large Language Models via Representation Engineering

As of 19 August 2026, this Paper Citation Record lists 24 of 24 outbound references and 2 inbound Pith citation observations for arXiv:2504.19483.

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

pith.paper-citation-record.v1
2504.19483 v1

Coverage vector

measured 24 of 24 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-16T05:55:21.292518Z

measured 26 of 26 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 2 of 2 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-07T15:17:15.632372Z

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

24 of 24 outbound references displayed

verified exact1
verified fuzzy4
unresolved19
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

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

Outbound references

Observation cc1248cc-54f1-4bb0-a6e6-678357c082bf · outbound

This paper cites an unresolved cited work.

Improving Reasoning Performance in Large Language Models via Representation Engineering Unresolved cited work

Reference 1

Resolution: unresolved; raw_fallback, observed 2026-08-16T05:55:21.700198Z

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 c56a125c-cc3a-4448-94cb-6b22834a138c · outbound

This paper cites an unresolved cited work.

Improving Reasoning Performance in Large Language Models via Representation Engineering Unresolved cited work

Reference 3

Resolution: unresolved; raw_fallback, observed 2026-08-16T05:55:21.737964Z

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 f7b6e29e-98f5-4a1b-beb3-41c22c58783b · outbound

This paper cites doi: 10.18653/v1/2023.findings-emnlp.624.

Improving Reasoning Performance in Large Language Models via Representation Engineering doi: 10.18653/v1/2023.findings-emnlp.624

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-16T05:55:21.218434Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0d634f99-50b8-40a2-823f-02943306e301 · outbound

This paper cites In-context Vectors: Making In Context Learning More Effective and Controllable Through Latent Space Steering.

Improving Reasoning Performance in Large Language Models via Representation Engineering In-context Vectors: Making In Context Learning More Effective and Controllable Through Latent Space Steering

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-16T05:55:21.232172Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f886acc5-22a3-48cc-a166-70e33470f8a8 · outbound

This paper cites Locating and Editing Factual Associations in GPT.

Improving Reasoning Performance in Large Language Models via Representation Engineering Locating and Editing Factual Associations in GPT

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-16T05:55:21.236566Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3dbb4bef-d257-4d6d-8545-8fb6990133a2 · outbound

This paper cites Comparing Inferential Strategies of Humans and Large Language Models in Deductive Reasoning.

Improving Reasoning Performance in Large Language Models via Representation Engineering Comparing Inferential Strategies of Humans and Large Language Models in Deductive Reasoning

Reference 12

Resolution: verified exact; local_arxiv, observed 2026-08-16T05:55:21.496578Z

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 01700e71-572d-4c02-a4fd-4e2506dc159e · outbound

This paper cites doi: 10.18653/v1/2023.blackboxnlp-1.2.

Improving Reasoning Performance in Large Language Models via Representation Engineering doi: 10.18653/v1/2023.blackboxnlp-1.2

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-16T05:55:21.245211Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cc997800-07b3-4983-aaa5-8f59fcc0658f · outbound

This paper cites doi: 10.1098/rsta.2022.0041.

Improving Reasoning Performance in Large Language Models via Representation Engineering doi: 10.1098/rsta.2022.0041

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-16T05:55:21.249973Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f43d1a57-5c16-40f8-94d4-afd86efa1ce4 · outbound

This paper cites Adly Templeton, Tom Conerly, Jonathan Marcus, Jack Lindsey, and Trenton Bricken.

Improving Reasoning Performance in Large Language Models via Representation Engineering Adly Templeton, Tom Conerly, Jonathan Marcus, Jack Lindsey, and Trenton Bricken

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-16T05:55:21.253778Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e718b434-0a31-4375-98e7-ed5f1d8b546c · outbound

This paper cites Eric Todd, Millicent L.

Improving Reasoning Performance in Large Language Models via Representation Engineering Eric Todd, Millicent L

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T05:55:21.711693Z

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 2d777dfc-ac0b-46e8-9201-bd766487fd07 · outbound

This paper cites Function Vectors in Large Language Models.

Improving Reasoning Performance in Large Language Models via Representation Engineering Function Vectors in Large Language Models

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-16T05:55:21.261981Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 244e1073-cf32-4ca8-9364-10c2d5255c38 · outbound

This paper cites Representation Engineering: A Top-Down Approach to AI Transparency.

Improving Reasoning Performance in Large Language Models via Representation Engineering Representation Engineering: A Top-Down Approach to AI Transparency

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-16T05:55:21.275545Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 96af84a3-e457-4e45-b88c-49e32cc0f8fe · outbound

This paper cites We provide an example here.

Improving Reasoning Performance in Large Language Models via Representation Engineering We provide an example here

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T05:55:21.688876Z

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 485bb872-10ef-4207-b7b4-94c24e39ab4d · outbound

This paper cites an unresolved cited work.

Improving Reasoning Performance in Large Language Models via Representation Engineering Unresolved cited work

Reference 23

Resolution: unresolved; raw_fallback, observed 2026-08-16T05:55:21.677554Z

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 b89e79b2-10ac-439f-8c00-471d37a1cc61 · outbound

This paper cites A.4 A DDITIONAL RESULTS We train control vectors on the signal extracted from theA condition and apply across experimental conditions.

Improving Reasoning Performance in Large Language Models via Representation Engineering A.4 A DDITIONAL RESULTS We train control vectors on the signal extracted from theA condition and apply across experimental conditions

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T05:55:21.665578Z

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 b1289d01-7a92-414a-a2b3-11fde604c943 · outbound

This paper cites doi: 10.1093/acprof:oso/9780199551330.001.0001.

Improving Reasoning Performance in Large Language Models via Representation Engineering doi: 10.1093/acprof:oso/9780199551330.001.0001

Reference 2008

Resolution: unresolved; no resolver link, observed 2026-08-16T05:55:21.222683Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d555ff42-485f-44a1-af21-72f90fa00b7f · outbound

This paper cites Layer Normalization.

Improving Reasoning Performance in Large Language Models via Representation Engineering Layer Normalization

Reference 2016

Resolution: unresolved; no resolver link, observed 2026-08-16T05:55:21.190975Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1c48aff0-f001-41c7-aabb-f96ace36c0c6 · outbound

This paper cites Attention Is All You Need.

Improving Reasoning Performance in Large Language Models via Representation Engineering Attention Is All You Need

Reference 2017

Resolution: unresolved; no resolver link, observed 2026-08-16T05:55:21.266398Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4480f40d-7751-4ac5-92ba-b0ce36dbaa98 · outbound

This paper cites On the Measure of Intelligence.

Improving Reasoning Performance in Large Language Models via Representation Engineering On the Measure of Intelligence

Reference 2019

Resolution: unresolved; no resolver link, observed 2026-08-16T05:55:21.209976Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e7caeec2-0f07-49a2-8523-9c948e3b335c · outbound

This paper cites Language Models are Few-Shot Learners.

Improving Reasoning Performance in Large Language Models via Representation Engineering Language Models are Few-Shot Learners

Reference 2020

Resolution: unresolved; no resolver link, observed 2026-08-16T05:55:21.205725Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8cf75c01-24c5-4259-b8fc-ab28eef456a1 · outbound

This paper cites Roee Hendel, Mor Geva, and Amir Globerson.

Improving Reasoning Performance in Large Language Models via Representation Engineering Roee Hendel, Mor Geva, and Amir Globerson

Reference 2021

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T05:55:21.726717Z

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 b28fba0d-aad1-4276-af80-f20084962d71 · outbound

This paper cites Interpretability in the Wild: a Circuit for Indirect Object Identification in GPT-2 small.

Improving Reasoning Performance in Large Language Models via Representation Engineering Interpretability in the Wild: a Circuit for Indirect Object Identification in GPT-2 small

Reference 2022

Resolution: unresolved; no resolver link, observed 2026-08-16T05:55:21.271067Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 008e3196-36a4-4b96-a94e-7399ce74c674 · outbound

This paper cites Pythia: A Suite for Analyzing Large Language Models Across Training and Scaling.

Improving Reasoning Performance in Large Language Models via Representation Engineering Pythia: A Suite for Analyzing Large Language Models Across Training and Scaling

Reference 2023

Resolution: unresolved; no resolver link, observed 2026-08-16T05:55:21.196325Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b438307f-b87d-4a7d-96e5-c661847fed61 · outbound

This paper cites Emergent World Models and Latent Variable Estimation in Chess-Playing Language Models.

Improving Reasoning Performance in Large Language Models via Representation Engineering Emergent World Models and Latent Variable Estimation in Chess-Playing Language Models

Reference 2024

Resolution: unresolved; no resolver link, observed 2026-08-16T05:55:21.226782Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

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

Feature Extraction and Steering for Enhanced Chain-of-Thought Reasoning in Language Models cites this paper.

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.

Observation 1ad7b000-f6b3-4a1e-bc36-8eecf54007c6 · inbound

Tracing Uncertainty in Language Model "Reasoning" cites this paper.

Tracing Uncertainty in Language Model "Reasoning" Improving Reasoning Performance in Large Language Models via Representation Engineering

Reference 13

Resolution: verified exact; arxiv_id, observed 2026-05-11T02:20:52.483023Z

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.