Paper Citation Record · LEDGER

Refusal in LLMs is an Affine Function

As of 20 August 2026, this Paper Citation Record lists 15 of 15 outbound references and 12 inbound Pith citation observations for arXiv:2411.09003.

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

pith.paper-citation-record.v1
2411.09003 v3

Coverage vector

measured 15 of 15 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-12T21:15:47.651398Z

measured 27 of 27 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 12 of 12 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-16T00:35:40.005686Z

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 f66fc09e-1014-434c-a93a-0e2768254e4c · outbound

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

Refusal in LLMs is an Affine Function Refusal in Language Models Is Mediated by a Single Direction

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-12T21:15:47.601354Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6ccc004e-c4b6-45f4-bff3-dc65295ecab0 · outbound

This paper cites Qwen Technical Report.

Refusal in LLMs is an Affine Function Qwen Technical Report

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-12T21:15:47.605180Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4aafd963-d649-48ae-a221-779004d79ba1 · outbound

This paper cites Leace: Perfect linear concept erasure in closed form.

Refusal in LLMs is an Affine Function Leace: Perfect linear concept erasure in closed form

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T21:15:47.861268Z

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 ee9a2b28-0ec5-49f0-a865-929ebf7bea78 · outbound

This paper cites The Llama 3 Herd of Models.

Refusal in LLMs is an Affine Function The Llama 3 Herd of Models

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-12T21:15:47.612020Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 51f98e3a-5388-4922-8fed-e3a630fc3272 · outbound

This paper cites Toy Models of Superposition.

Refusal in LLMs is an Affine Function Toy Models of Superposition

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-12T21:15:47.615634Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 31df294a-c81d-46cc-95bd-7db0703df090 · outbound

This paper cites The Linear Representation Hypothesis and the Geometry of Large Language Models.

Refusal in LLMs is an Affine Function The Linear Representation Hypothesis and the Geometry of Large Language Models

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-12T21:15:47.619448Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c6418bd1-e647-4689-99af-87d67e582ea9 · outbound

This paper cites Does Transformer Interpretability Transfer to RNNs?.

Refusal in LLMs is an Affine Function Does Transformer Interpretability Transfer to RNNs?

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-12T21:15:47.623146Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 40555c2a-4b54-4b6d-bf31-dbbdc55e43a9 · outbound

This paper cites Eagle and Finch: RWKV with Matrix-Valued States and Dynamic Recurrence.

Refusal in LLMs is an Affine Function Eagle and Finch: RWKV with Matrix-Valued States and Dynamic Recurrence

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-12T21:15:47.627168Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6e767def-c363-4054-9822-5f1019273159 · outbound

This paper cites Steering Llama 2 via Contrastive Activation Addition.

Refusal in LLMs is an Affine Function Steering Llama 2 via Contrastive Activation Addition

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-12T21:15:47.630324Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 01f07201-7ecb-4501-a6f4-b6fee444fad6 · outbound

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

Refusal in LLMs is an Affine Function Gemma: Open Models Based on Gemini Research and Technology

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-12T21:15:47.633955Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 793f941d-0895-4279-8b16-323dd5553644 · outbound

This paper cites Yi: Open Foundation Models by 01.AI.

Refusal in LLMs is an Affine Function Yi: Open Foundation Models by 01.AI

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-12T21:15:47.637213Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2154e985-a528-4396-8d3e-f4c99502c652 · outbound

This paper cites write newline.

Refusal in LLMs is an Affine Function write newline

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-12T21:15:47.640671Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 59e594c4-9ac5-4287-ab6d-a040b66b53ed · outbound

This paper cites @esa (Ref.

Refusal in LLMs is an Affine Function @esa (Ref

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-12T21:15:47.644485Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6fc6b2c8-0eda-4e76-8e76-9089302370f5 · outbound

This paper cites an unresolved cited work.

Refusal in LLMs is an Affine Function Unresolved cited work

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-12T21:15:47.647982Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation da021fde-5b13-48a4-a907-b532d073101e · outbound

This paper cites """"*4L@0 !.

Refusal in LLMs is an Affine Function """"*4L@0 !

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-12T21:15:47.651398Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation 228af131-7ddd-42a7-8a04-9e950ba3f093 · inbound

Emergence and Effectiveness of Task Vectors in In-Context Learning: An Encoder Decoder Perspective cites this paper.

Emergence and Effectiveness of Task Vectors in In-Context Learning: An Encoder Decoder Perspective Refusal in LLMs is an Affine Function

Reference 43

Resolution: unresolved; no resolver link, observed 2026-08-11T14:20:23.719191Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1366d392-fca2-44c0-be31-ae1e1c272047 · inbound

Slowing Learning by Erasing Simple Features cites this paper.

Slowing Learning by Erasing Simple Features Refusal in LLMs is an Affine Function

Reference 2022

Resolution: unresolved; no resolver link, observed 2026-08-09T11:04:17.011333Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 389ab186-e742-4b43-a38f-b7bebe4897e7 · inbound

Jailbreak Attack Initializations as Extractors of Compliance Directions cites this paper.

Jailbreak Attack Initializations as Extractors of Compliance Directions Refusal in LLMs is an Affine Function

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-07T20:40:34.231498Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0bc45b64-edcd-4965-a435-cc549a2067eb · inbound

Understanding (Un)Reliability of Steering Vectors in Language Models cites this paper.

Understanding (Un)Reliability of Steering Vectors in Language Models Refusal in LLMs is an Affine Function

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-07T13:10:05.846705Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9600ce08-ee4c-4f24-b888-a88f3b58f1cd · inbound

Activation Steering for Accent Adaptation in Large Audio Language Models cites this paper.

Activation Steering for Accent Adaptation in Large Audio Language Models Refusal in LLMs is an Affine Function

Reference 29

Resolution: unresolved; no resolver link, observed 2026-07-15T14:15:29.705679Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 828ffb26-3152-4739-808c-c629a5ca35df · inbound

Less is More: Geometric Unlearning for LLMs with Minimal Data Disclosure cites this paper.

Less is More: Geometric Unlearning for LLMs with Minimal Data Disclosure Refusal in LLMs is an Affine Function

Reference 40

Resolution: metadata mismatch; arxiv_id, observed 2026-05-11T09:26:02.749544Z

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 7a8ba6c5-0c31-4345-b875-ab932dea8940 · inbound

RefusalGuard: Geometry-Preserving Fine-Tuning for Safety in LLMs cites this paper.

RefusalGuard: Geometry-Preserving Fine-Tuning for Safety in LLMs Refusal in LLMs is an Affine Function

Reference 7

Resolution: metadata mismatch; arxiv_id, observed 2026-05-11T09:50:59.813593Z

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 8e1531fa-712a-4aba-8200-e4ba8d6e44a4 · inbound

RefusalGuard: Geometry-Preserving Fine-Tuning for Safety in LLMs cites this paper.

RefusalGuard: Geometry-Preserving Fine-Tuning for Safety in LLMs Refusal in LLMs is an Affine Function

Reference 8

Resolution: metadata mismatch; arxiv_id, observed 2026-05-10T15:50:34.166736Z

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 d13932a9-8966-44b8-aedc-515d37999f05 · inbound

Ablating Safety: Mechanisms for Removing Alignment in Language Models for Security Applications cites this paper.

Ablating Safety: Mechanisms for Removing Alignment in Language Models for Security Applications Refusal in LLMs is an Affine Function

Reference 23

Resolution: verified exact; arxiv_id, observed 2026-05-19T23:32:52.594708Z

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 69d607e2-84ca-4cc2-a045-9ceaab940047 · inbound

Low-Resource Safety Failures Are Action Failures, Not Representation Failures cites this paper.

Low-Resource Safety Failures Are Action Failures, Not Representation Failures Refusal in LLMs is an Affine Function

Reference 33

Resolution: verified exact; arxiv_id, observed 2026-06-28T17:02:24.068236Z

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 3fc6cebc-12ac-4979-af86-2d01f50c493a · inbound

Expert-Aware Refusal Steering cites this paper.

Expert-Aware Refusal Steering Refusal in LLMs is an Affine Function

Reference 8

Resolution: metadata mismatch; arxiv_id, observed 2026-07-02T03:26:29.128046Z

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 b0512789-1f78-4aa0-b845-830b8e92a6b7 · inbound

Locating and Controlling Implicit Personalization in Large Language Models cites this paper.

Locating and Controlling Implicit Personalization in Large Language Models Refusal in LLMs is an Affine Function

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-16T00:35:40.005686Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.