Paper Citation Record · LEDGER

Representation Engineering: A Top-Down Approach to AI Transparency

As of 31 July 2026, this Paper Citation Record lists 23 of 23 outbound references and 100 inbound Pith citation observations for arXiv:2310.01405.

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

pith.paper-citation-record.v1
2310.01405 v4

Coverage vector

measured 23 of 23 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-07-11T11:50:26.030339Z

measured 123 of 123 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-07-31T06:34:12.847434+00:00

measured 100 of 336 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-07-15T14:15:29.705679Z

measured 0 of 1 external citation measurements

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

Source: pith, observed 2026-07-10T15:37:20.411640Z

Reference resolution

23 of 23 outbound references displayed

verified exact2
verified fuzzy11
unresolved8
parse uncertain0
malformed identifier1
metadata mismatch1

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 34e1c715-38b8-4c2a-b10c-199cb9b6b92d · outbound

This paper cites Language Models are Few-Shot Learners.

Representation Engineering: A Top-Down Approach to AI Transparency Language Models are Few-Shot Learners

Reference 1

Resolution: metadata mismatch; local_arxiv, observed 2026-05-10T18:11:40.992027Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-31T06:34:12.847434+00:00.

Observation c4953bea-638d-4984-a414-c8c11b18ccc2 · outbound

This paper cites doi: 10.18653/v1/D17-1082.

Representation Engineering: A Top-Down Approach to AI Transparency doi: 10.18653/v1/D17-1082

Reference 2

Resolution: verified exact; doi, observed 2026-05-10T18:11:40.995924Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-31T06:34:12.847434+00:00.

Observation 90ee26c9-7169-4f2f-b67f-481820211c1d · outbound

This paper cites doi: 10.18653/v1/n19-1421.

Representation Engineering: A Top-Down Approach to AI Transparency doi: 10.18653/v1/n19-1421

Reference 3

Resolution: verified exact; doi, observed 2026-05-10T18:11:40.999844Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-31T06:34:12.847434+00:00.

Observation 897a3a8d-fcf7-490d-8585-7d424ea65e5a · outbound

This paper cites Love” and “Hate.

Representation Engineering: A Top-Down Approach to AI Transparency Love” and “Hate

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-05-10T18:11:41.003358Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-31T06:34:12.847434+00:00.

Observation c543172b-36f0-472f-87a4-6b3d24a69235 · outbound

This paper cites We take the top PCA direction that explains the maximum variance in the data X D l.

Representation Engineering: A Top-Down Approach to AI Transparency We take the top PCA direction that explains the maximum variance in the data X D l

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-05-10T18:11:41.006338Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-31T06:34:12.847434+00:00.

Observation cbe1f478-c849-4874-b4c2-04b03c9c59a7 · outbound

This paper cites We take the difference between the centroids of the two clusters as the concept direction.

Representation Engineering: A Top-Down Approach to AI Transparency We take the difference between the centroids of the two clusters as the concept direction

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-05-10T18:11:41.009220Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-31T06:34:12.847434+00:00.

Observation 6e7a9a9a-c9ce-460c-bb82-a1c57dea0247 · outbound

This paper cites an unresolved cited work.

Representation Engineering: A Top-Down Approach to AI Transparency Unresolved cited work

Reference 7

Resolution: unresolved; raw_fallback, observed 2026-05-10T18:11:41.011815Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-31T06:34:12.847434+00:00.

Observation f10fe97c-1265-4fc8-90ad-913e52d61bec · outbound

This paper cites I made a mistake and copied my friend’s homework. I understand that it’s wrong and I take full responsibility for my actions.

Representation Engineering: A Top-Down Approach to AI Transparency I made a mistake and copied my friend’s homework. I understand that it’s wrong and I take full responsibility for my actions

Reference 8

Resolution: malformed identifier; raw_fallback, observed 2026-05-10T18:11:41.014706Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-31T06:34:12.847434+00:00.

Observation edfae63c-b5fa-46b1-94dd-f80069a50e8f · outbound

This paper cites psychopathic.

Representation Engineering: A Top-Down Approach to AI Transparency psychopathic

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-05-10T18:11:41.017500Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-31T06:34:12.847434+00:00.

Observation a333616f-b3f7-46fa-87c6-3c5ada89566d · outbound

This paper cites an unresolved cited work.

Representation Engineering: A Top-Down Approach to AI Transparency Unresolved cited work

Reference 10

Resolution: unresolved; raw_fallback, observed 2026-05-10T18:11:41.019986Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-31T06:34:12.847434+00:00.

Observation 01c27a0c-0562-439c-a4e6-57e5f76f7571 · outbound

This paper cites an unresolved cited work.

Representation Engineering: A Top-Down Approach to AI Transparency Unresolved cited work

Reference 11

Resolution: unresolved; raw_fallback, observed 2026-05-10T18:11:41.022808Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-31T06:34:12.847434+00:00.

Observation 68d291ee-1aec-4b21-a3dd-6f0518f16ed5 · outbound

This paper cites an unresolved cited work.

Representation Engineering: A Top-Down Approach to AI Transparency Unresolved cited work

Reference 12

Resolution: unresolved; raw_fallback, observed 2026-05-10T18:11:41.025401Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-31T06:34:12.847434+00:00.

Observation f418cdc6-15c3-461d-b8b8-02c15a24a597 · outbound

This paper cites Do the findings rest on strong theoretical assumptions; are they not demonstrated using leading-edge tasks or models; or are the findings highly sensitive to hyperparameters? □.

Representation Engineering: A Top-Down Approach to AI Transparency Do the findings rest on strong theoretical assumptions; are they not demonstrated using leading-edge tasks or models; or are the findings highly sensitive to hyperparameters? □

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-05-10T18:11:41.028176Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-31T06:34:12.847434+00:00.

Observation 8a662b95-5a9d-43fd-8961-d73b25588565 · outbound

This paper cites Is it implausible that any practical system could ever markedly outper- form humans at this task? □.

Representation Engineering: A Top-Down Approach to AI Transparency Is it implausible that any practical system could ever markedly outper- form humans at this task? □

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-05-10T18:11:41.030691Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-31T06:34:12.847434+00:00.

Observation 9f60eb8d-c717-45a4-bde5-47e66297f023 · outbound

This paper cites Does this approach strongly depend on handcrafted features, expert supervision, or human reliability? □.

Representation Engineering: A Top-Down Approach to AI Transparency Does this approach strongly depend on handcrafted features, expert supervision, or human reliability? □

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-05-10T18:11:41.033204Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-31T06:34:12.847434+00:00.

Observation c6a435fd-2828-44fa-a69f-6442515ab9f2 · outbound

This paper cites an unresolved cited work.

Representation Engineering: A Top-Down Approach to AI Transparency Unresolved cited work

Reference 16

Resolution: unresolved; raw_fallback, observed 2026-05-10T18:11:41.035435Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-31T06:34:12.847434+00:00.

Observation 24b981ee-bce1-4524-844b-965e08d46b4e · outbound

This paper cites How does this improve safety more than it improves general capabilities? Answer: This work mainly improves transparency and control.

Representation Engineering: A Top-Down Approach to AI Transparency How does this improve safety more than it improves general capabilities? Answer: This work mainly improves transparency and control

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-05-10T18:11:41.037925Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-31T06:34:12.847434+00:00.

Observation 84ff59e6-00d6-4ca0-93bc-eed2f3dbe05f · outbound

This paper cites an unresolved cited work.

Representation Engineering: A Top-Down Approach to AI Transparency Unresolved cited work

Reference 18

Resolution: unresolved; raw_fallback, observed 2026-05-10T18:11:41.040111Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-31T06:34:12.847434+00:00.

Observation 273778c6-aadf-4923-8a35-46119b923b53 · outbound

This paper cites Does this work advance progress on tasks that have been previously considered the subject of usual capabilities research? □.

Representation Engineering: A Top-Down Approach to AI Transparency Does this work advance progress on tasks that have been previously considered the subject of usual capabilities research? □

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-05-10T18:11:41.042466Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-31T06:34:12.847434+00:00.

Observation 84f757df-78ba-4bbd-9e82-206b2dd2d0dc · outbound

This paper cites an unresolved cited work.

Representation Engineering: A Top-Down Approach to AI Transparency Unresolved cited work

Reference 20

Resolution: unresolved; raw_fallback, observed 2026-05-10T18:11:41.044790Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-31T06:34:12.847434+00:00.

Observation 74e244a9-be65-4193-b51d-deb26d4fc3c3 · outbound

This paper cites an unresolved cited work.

Representation Engineering: A Top-Down Approach to AI Transparency Unresolved cited work

Reference 21

Resolution: unresolved; raw_fallback, observed 2026-05-10T18:11:41.046954Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-31T06:34:12.847434+00:00.

Observation b091299d-93f6-4c2f-b2c7-dff173ec1c55 · outbound

This paper cites Does this advance safety along with, or as a consequence of, advancing other capabilities or the study of AI? □ E.3 E LABORATIONS AND OTHER CONSIDERATIONS.

Representation Engineering: A Top-Down Approach to AI Transparency Does this advance safety along with, or as a consequence of, advancing other capabilities or the study of AI? □ E.3 E LABORATIONS AND OTHER CONSIDERATIONS

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-05-10T18:11:41.049442Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-31T06:34:12.847434+00:00.

Observation 61f2fb19-62ef-440f-90e4-2231b7923c0f · outbound

This paper cites complex and fragile.

Representation Engineering: A Top-Down Approach to AI Transparency complex and fragile

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-05-10T18:11:41.051802Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-31T06:34:12.847434+00:00.

Pith citing papers

Observation a8d08171-95b0-4a21-aff0-fa279eaa9dcf · inbound

AI Alignment: A Comprehensive Survey cites this paper.

AI Alignment: A Comprehensive Survey Representation Engineering: A Top-Down Approach to AI Transparency

Reference 15

Resolution: verified exact; local_arxiv, observed 2026-05-17T14:28:49.016239Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-31T06:34:12.847434+00:00.

Observation c909f869-1d84-4ec2-aab2-17f6a6155805 · inbound

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

The Linear Representation Hypothesis and the Geometry of Large Language Models Representation Engineering: A Top-Down Approach to AI Transparency

Reference 28

Resolution: metadata mismatch; local_arxiv, observed 2026-05-11T21:43:30.838860Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-31T06:34:12.847434+00:00.

Observation 7739f3cb-6554-467d-b692-df57b12dbaeb · inbound

Steering Llama 2 via Contrastive Activation Addition cites this paper.

Steering Llama 2 via Contrastive Activation Addition Representation Engineering: A Top-Down Approach to AI Transparency

Reference 28

Resolution: metadata mismatch; local_arxiv, observed 2026-05-11T20:37:21.300128Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-31T06:34:12.847434+00:00.

Observation 72bf91dd-6833-45d9-ab54-708e9c017267 · inbound

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

Sparse Feature Circuits: Discovering and Editing Interpretable Causal Graphs in Language Models Representation Engineering: A Top-Down Approach to AI Transparency

Reference 88

Resolution: verified exact; local_arxiv, observed 2026-05-13T13:15:10.727523Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-31T06:34:12.847434+00:00.

Observation 762be8d1-2052-45c4-8f55-2c7d8c9da9fe · inbound

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

Refusal in Language Models Is Mediated by a Single Direction Representation Engineering: A Top-Down Approach to AI Transparency

Reference 207

Resolution: verified exact; local_arxiv, observed 2026-05-13T10:47:56.176618Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-31T06:34:12.847434+00:00.

Observation 974adf50-0bce-4cc9-a758-21066380b6a0 · inbound

Semantic Entropy Probes: Robust and Cheap Hallucination Detection in LLMs cites this paper.

Semantic Entropy Probes: Robust and Cheap Hallucination Detection in LLMs Representation Engineering: A Top-Down Approach to AI Transparency

Reference 80

Resolution: verified exact; local_arxiv, observed 2026-05-18T00:52:02.604208Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-31T06:34:12.847434+00:00.

Observation a003612c-133c-4085-907e-c3e67ca4a966 · inbound

Inspection and Control of Self-Generated-Text Recognition Ability in Llama3-8b-Instruct cites this paper.

Inspection and Control of Self-Generated-Text Recognition Ability in Llama3-8b-Instruct Representation Engineering: A Top-Down Approach to AI Transparency

Reference 16

Resolution: metadata mismatch; local_arxiv, observed 2026-05-23T19:53:23.230920Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-31T06:34:12.847434+00:00.

Observation f996f9eb-11eb-4278-843d-81c8ac638337 · inbound

Open Problems in Mechanistic Interpretability cites this paper.

Open Problems in Mechanistic Interpretability Representation Engineering: A Top-Down Approach to AI Transparency

Reference 16

Resolution: metadata mismatch; local_arxiv, observed 2026-05-14T18:30:06.022244Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-31T06:34:12.847434+00:00.

Observation 47bc9731-5628-4577-ab9e-28c298906cd5 · inbound

LLM-Safety Evaluations Lack Robustness cites this paper.

LLM-Safety Evaluations Lack Robustness Representation Engineering: A Top-Down Approach to AI Transparency

Reference 63

Resolution: verified exact; local_arxiv, observed 2026-05-23T01:27:21.335303Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-31T06:34:12.847434+00:00.

Observation ca3411fb-7f32-44d6-a529-5f2db1051007 · inbound

Monitoring Reasoning Models for Misbehavior and the Risks of Promoting Obfuscation cites this paper.

Monitoring Reasoning Models for Misbehavior and the Risks of Promoting Obfuscation Representation Engineering: A Top-Down Approach to AI Transparency

Reference 70

Resolution: verified exact; local_arxiv, observed 2026-05-21T07:24:13.007302Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-31T06:34:12.847434+00:00.

Observation 467663c3-9f95-4987-b99c-0198592831fd · inbound

Secure LLM Fine-Tuning via Safety-Aware Probing cites this paper.

Secure LLM Fine-Tuning via Safety-Aware Probing Representation Engineering: A Top-Down Approach to AI Transparency

Reference 24

Resolution: verified exact; local_arxiv, observed 2026-05-22T13:11:35.874410Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-31T06:34:12.847434+00:00.

Observation cc9d089b-3a7b-41d9-9773-441baa675efe · inbound

Disentangled Safety Adapters Enable Efficient Guardrails and Flexible Inference-Time Alignment cites this paper.

Disentangled Safety Adapters Enable Efficient Guardrails and Flexible Inference-Time Alignment Representation Engineering: A Top-Down Approach to AI Transparency

Reference 55

Resolution: verified exact; local_arxiv, observed 2026-05-19T11:53:03.601789Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-31T06:34:12.847434+00:00.

Observation c0284196-7fd1-4e22-8b2e-f939c54795d0 · inbound

ReGA: Model-Based Safeguard for LLMs via Representation-Guided Abstraction cites this paper.

ReGA: Model-Based Safeguard for LLMs via Representation-Guided Abstraction Representation Engineering: A Top-Down Approach to AI Transparency

Reference 33

Resolution: verified exact; local_arxiv, observed 2026-05-19T11:37:15.901459Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-31T06:34:12.847434+00:00.

Observation 93e4d6bd-b054-4117-b748-264fab7490fc · inbound

SEAT: Sparse Entity-Aware Tuning for Knowledge Adaptation while Preserving Epistemic Abstention cites this paper.

SEAT: Sparse Entity-Aware Tuning for Knowledge Adaptation while Preserving Epistemic Abstention Representation Engineering: A Top-Down Approach to AI Transparency

Reference 17

Resolution: metadata mismatch; local_arxiv, observed 2026-05-19T09:37:14.191045Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-31T06:34:12.847434+00:00.

Observation 767a7f2d-419b-4a88-b238-07a6b491e0db · inbound

AI Feedback Enhances Community-Based Content Moderation through Engagement with Counterarguments cites this paper.

AI Feedback Enhances Community-Based Content Moderation through Engagement with Counterarguments Representation Engineering: A Top-Down Approach to AI Transparency

Reference 40

Resolution: verified exact; local_arxiv, observed 2026-05-19T05:27:05.576965Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-31T06:34:12.847434+00:00.

Observation faa59524-a754-4429-91de-85cb5b050602 · inbound

Similarity Field Theory: A Mathematical Framework for Intelligence cites this paper.

Reference 56

Resolution: verified exact; local_arxiv, observed 2026-05-18T14:41:30.673119Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-31T06:34:12.847434+00:00.

Observation 9d68e2ae-6f90-4bc3-b11f-fe9cec573840 · inbound

Painless Activation Steering: An Automated, Lightweight Approach for Post-Training Large Language Models cites this paper.

Painless Activation Steering: An Automated, Lightweight Approach for Post-Training Large Language Models Representation Engineering: A Top-Down Approach to AI Transparency

Reference 26

Resolution: malformed identifier; local_arxiv, observed 2026-05-21T21:45:40.623814Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-31T06:34:12.847434+00:00.

Observation e86d5acf-2b40-4fbb-b48f-c9f716086568 · inbound

ASTRA: An Automated Framework for Strategy Discovery, Retrieval, and Evolution for Jailbreaking LLMs cites this paper.

ASTRA: An Automated Framework for Strategy Discovery, Retrieval, and Evolution for Jailbreaking LLMs Representation Engineering: A Top-Down Approach to AI Transparency

Reference 62

Resolution: verified exact; local_arxiv, observed 2026-05-18T01:55:38.026427Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-31T06:34:12.847434+00:00.

Observation 9c81199a-9595-447f-98ff-0752ae4c49d0 · inbound

You Had One Job: Per-Task Quantization Using LLMs' Hidden Representations cites this paper.

You Had One Job: Per-Task Quantization Using LLMs' Hidden Representations Representation Engineering: A Top-Down Approach to AI Transparency

Reference 73

Resolution: metadata mismatch; local_arxiv, observed 2026-05-21T18:50:30.288269Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-31T06:34:12.847434+00:00.

Observation d506ccca-0558-4d99-a37f-5f0ee8994d3b · inbound

The Impact of Off-Policy Training Data on Probe Generalisation cites this paper.

The Impact of Off-Policy Training Data on Probe Generalisation Representation Engineering: A Top-Down Approach to AI Transparency

Reference 45

Resolution: metadata mismatch; local_arxiv, observed 2026-05-17T20:30:11.744338Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-31T06:34:12.847434+00:00.

Observation 67e7d001-9de5-48e8-b2af-5f9bedfcfbdf · inbound

Sparse Concept Anchoring for Interpretable and Controllable Neural Representations cites this paper.

Sparse Concept Anchoring for Interpretable and Controllable Neural Representations Representation Engineering: A Top-Down Approach to AI Transparency

Reference 35

Resolution: metadata mismatch; local_arxiv, observed 2026-05-16T22:18:36.673480Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-31T06:34:12.847434+00:00.

Observation 7ad837fd-5640-4b52-9a39-1805d0bafb83 · inbound

RACC: Representation-Aware Coverage Criteria for LLM Safety Testing cites this paper.

RACC: Representation-Aware Coverage Criteria for LLM Safety Testing Representation Engineering: A Top-Down Approach to AI Transparency

Reference 73

Resolution: verified exact; local_arxiv, observed 2026-05-16T08:17:36.626928Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-31T06:34:12.847434+00:00.

Observation 40248c51-1738-4687-8d8b-9f4f026f8451 · inbound

Revis: Sparse Latent Steering to Mitigate Object Hallucination in Large Vision-Language Models cites this paper.

Revis: Sparse Latent Steering to Mitigate Object Hallucination in Large Vision-Language Models Representation Engineering: A Top-Down Approach to AI Transparency

Reference 14

Resolution: verified exact; local_arxiv, observed 2026-05-16T05:07:20.474413Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-31T06:34:12.847434+00:00.

Observation b558ed84-735a-4a84-8cec-4ed510f8d4c7 · inbound

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

Activation Steering for Accent Adaptation in Large Audio Language Models Representation Engineering: A Top-Down Approach to AI Transparency

Reference 32

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 6233aaca-4963-43cd-bdc8-e40c11749af3 · inbound

CreativeBench: Benchmarking and Enhancing Machine Creativity via Self-Evolving Challenges cites this paper.

CreativeBench: Benchmarking and Enhancing Machine Creativity via Self-Evolving Challenges Representation Engineering: A Top-Down Approach to AI Transparency

Reference 10

Resolution: unresolved; no resolver link, observed 2026-07-14T22:34:21.790260Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a7e97ba6-73e4-4bb9-8dbd-972fe09300d2 · inbound

Why That Robot? A Qualitative Analysis of Justification Strategies for Robot Color Selection Across Occupational Contexts cites this paper.

Why That Robot? A Qualitative Analysis of Justification Strategies for Robot Color Selection Across Occupational Contexts Representation Engineering: A Top-Down Approach to AI Transparency

Reference 22

Resolution: unresolved; no resolver link, observed 2026-07-13T16:04:03.659837Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 16a9e383-eb52-4b32-8cb9-5b01e20e00da · inbound

Critical Damping as a Momentum Schedule: Multi-Seed Validation, a Hybrid Recipe, and an Exhaustive Negative Result on Surgical Layer Selection cites this paper.

Critical Damping as a Momentum Schedule: Multi-Seed Validation, a Hybrid Recipe, and an Exhaustive Negative Result on Surgical Layer Selection Representation Engineering: A Top-Down Approach to AI Transparency

Reference 22

Resolution: verified exact; local_arxiv, observed 2026-05-14T21:38:00.031448Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-31T06:34:12.847434+00:00.

Observation 7e85a505-08d8-4b05-8b5b-2bbe3c106fd7 · inbound

Interpretable Electrophysiological Features of Resting-State EEG Capture Cortical Network Dynamics in Parkinsons Disease cites this paper.

Interpretable Electrophysiological Features of Resting-State EEG Capture Cortical Network Dynamics in Parkinsons Disease Representation Engineering: A Top-Down Approach to AI Transparency

Reference 26

Resolution: unresolved; no resolver link, observed 2026-07-13T14:23:49.346727Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 90631e93-3173-49a6-a13d-66d31491d0cc · inbound

Dual Implications of Quark Mass Hierarchies to Flavor Structure cites this paper.

Dual Implications of Quark Mass Hierarchies to Flavor Structure Representation Engineering: A Top-Down Approach to AI Transparency

Reference 41

Resolution: unresolved; no resolver link, observed 2026-07-13T13:46:54.451163Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d12cec21-60f2-4a68-9b63-79135c52db13 · inbound

Steerable but Not Decodable: Function Vectors Operate Beyond the Logit Lens cites this paper.

Steerable but Not Decodable: Function Vectors Operate Beyond the Logit Lens Representation Engineering: A Top-Down Approach to AI Transparency

Reference 31

Resolution: verified exact; local_arxiv, observed 2026-05-13T21:03:20.239459Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-31T06:34:12.847434+00:00.

Observation 68592d14-f536-4c61-b56c-578299073119 · inbound

Enhancing Multi-Robot Exploration Using Probabilistic Frontier Prioritization with Dirichlet Process Gaussian Mixtures cites this paper.

Enhancing Multi-Robot Exploration Using Probabilistic Frontier Prioritization with Dirichlet Process Gaussian Mixtures Representation Engineering: A Top-Down Approach to AI Transparency

Reference 54

Resolution: unresolved; no resolver link, observed 2026-07-13T13:35:02.428552Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7483e0d1-8b6b-4e8c-a63c-7fd4d199cffe · inbound

STEAR: Layer-Aware Spatiotemporal Evidence Intervention for Hallucination Mitigation in Video Large Language Models cites this paper.

STEAR: Layer-Aware Spatiotemporal Evidence Intervention for Hallucination Mitigation in Video Large Language Models Representation Engineering: A Top-Down Approach to AI Transparency

Reference 54

Resolution: metadata mismatch; local_arxiv, observed 2026-05-13T20:18:13.365221Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-31T06:34:12.847434+00:00.

Observation f5d6f474-d6f1-4f5d-a118-bf05a504d1b6 · inbound

Valence-Arousal Subspace in LLMs: Circular Emotion Geometry and Multi-Behavioral Control cites this paper.

Valence-Arousal Subspace in LLMs: Circular Emotion Geometry and Multi-Behavioral Control Representation Engineering: A Top-Down Approach to AI Transparency

Reference 4

Resolution: malformed identifier; local_arxiv, observed 2026-05-13T20:18:13.410647Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-31T06:34:12.847434+00:00.

Observation ee097d1e-6886-4343-9699-5ad26e50246a · inbound

The Democratic Ontology Deficit: How AI Systems Fail to Represent What Democracy Requires cites this paper.

The Democratic Ontology Deficit: How AI Systems Fail to Represent What Democracy Requires Representation Engineering: A Top-Down Approach to AI Transparency

Reference 12

Resolution: verified exact; local_arxiv, observed 2026-05-13T16:53:00.117396Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-31T06:34:12.847434+00:00.

Observation 9b8d3568-179c-4390-98f6-f58858ce0fd5 · inbound

Where to Steer: Input-Dependent Layer Selection for Steering Improves LLM Alignment cites this paper.

Where to Steer: Input-Dependent Layer Selection for Steering Improves LLM Alignment Representation Engineering: A Top-Down Approach to AI Transparency

Reference 22

Resolution: unresolved; no resolver link, observed 2026-07-13T12:15:38.881394Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation db8ad889-984a-4ddc-850b-8fa31ba755a9 · inbound

How Alignment Routes: Localizing, Scaling, and Controlling Policy Circuits in Language Models cites this paper.

How Alignment Routes: Localizing, Scaling, and Controlling Policy Circuits in Language Models Representation Engineering: A Top-Down Approach to AI Transparency

Reference 11

Resolution: verified exact; local_arxiv, observed 2026-05-10T22:10:50.518999Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-31T06:34:12.847434+00:00.

Observation 2d840371-9a51-4e69-8735-c9201f92d8aa · inbound

Sparse Autoencoders as a Steering Basis for Phase Synchronization in Graph-Based CFD Surrogates cites this paper.

Sparse Autoencoders as a Steering Basis for Phase Synchronization in Graph-Based CFD Surrogates Representation Engineering: A Top-Down Approach to AI Transparency

Reference 17

Resolution: verified exact; local_arxiv, observed 2026-05-14T22:19:31.717017Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-31T06:34:12.847434+00:00.

Observation c40bc05c-648e-4552-9c3d-1ea7712e242e · inbound

The Master Key Hypothesis: Unlocking Cross-Model Capability Transfer via Linear Subspace Alignment cites this paper.

The Master Key Hypothesis: Unlocking Cross-Model Capability Transfer via Linear Subspace Alignment Representation Engineering: A Top-Down Approach to AI Transparency

Reference 85

Resolution: verified exact; local_arxiv, observed 2026-05-11T00:15:56.188766Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-31T06:34:12.847434+00:00.

Observation 56bf7d92-05bc-4ca5-bd16-d69016395486 · inbound

Selective Neuron Amplification in Transformer Language Models cites this paper.

Selective Neuron Amplification in Transformer Language Models Representation Engineering: A Top-Down Approach to AI Transparency

Reference 14

Resolution: verified exact; local_arxiv, observed 2026-05-11T00:25:52.313537Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-31T06:34:12.847434+00:00.

Observation 62121618-702f-4216-baff-ec075ff1d25c · inbound

Selective Neuron Amplification in Transformer Language Models cites this paper.

Selective Neuron Amplification in Transformer Language Models Representation Engineering: A Top-Down Approach to AI Transparency

Reference 14

Resolution: verified exact; local_arxiv, observed 2026-05-12T06:16:25.123020Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-31T06:34:12.847434+00:00.

Observation 0cf4070d-27d7-4e8f-a76b-b6a47ca4b29e · inbound

Emotion Concepts and their Function in a Large Language Model cites this paper.

Emotion Concepts and their Function in a Large Language Model Representation Engineering: A Top-Down Approach to AI Transparency

Reference 18

Resolution: verified exact; local_arxiv, observed 2026-05-11T05:35:58.213915Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-31T06:34:12.847434+00:00.

Observation 23247e79-193c-49f3-8b41-a7cc10254a8f · inbound

Beyond Social Pressure: Benchmarking Epistemic Attack in Large Language Models cites this paper.

Beyond Social Pressure: Benchmarking Epistemic Attack in Large Language Models Representation Engineering: A Top-Down Approach to AI Transparency

Reference 24

Resolution: malformed identifier; local_arxiv, observed 2026-05-11T00:30:55.137260Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-31T06:34:12.847434+00:00.

Observation 060b2fb4-f881-4a2e-99b3-b591ed7607e0 · inbound

Linear Representations of Hierarchical Concepts in Language Models cites this paper.

Linear Representations of Hierarchical Concepts in Language Models Representation Engineering: A Top-Down Approach to AI Transparency

Reference 30

Resolution: verified exact; local_arxiv, observed 2026-05-11T07:45:57.607911Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-31T06:34:12.847434+00:00.

Observation e7017615-6ff0-46cf-9956-da1f2311ae60 · inbound

Dead Weights, Live Signals: Feedforward Graphs of Frozen Language Models cites this paper.

Dead Weights, Live Signals: Feedforward Graphs of Frozen Language Models Representation Engineering: A Top-Down Approach to AI Transparency

Reference 15

Resolution: verified exact; local_arxiv, observed 2026-05-11T05:55:57.478701Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-31T06:34:12.847434+00:00.

Observation 7420bd99-1623-4271-b4c9-9dc983399cd6 · inbound

What Drives Representation Steering? A Mechanistic Case Study on Steering Refusal cites this paper.

What Drives Representation Steering? A Mechanistic Case Study on Steering Refusal Representation Engineering: A Top-Down Approach to AI Transparency

Reference 51

Resolution: metadata mismatch; local_arxiv, observed 2026-05-11T06:05:59.837702Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-31T06:34:12.847434+00:00.

Observation a79a4202-5578-4dad-b4f2-29b5bde62af8 · inbound

Ads in AI Chatbots? An Analysis of How Large Language Models Navigate Conflicts of Interest cites this paper.

Ads in AI Chatbots? An Analysis of How Large Language Models Navigate Conflicts of Interest Representation Engineering: A Top-Down Approach to AI Transparency

Reference 111

Resolution: verified exact; local_arxiv, observed 2026-05-11T07:26:02.224964Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-31T06:34:12.847434+00:00.

Observation 51ea0f1b-925a-4579-a7d4-90f811fad919 · inbound

Spectral Geometry of LoRA Adapters Encodes Training Objective and Predicts Harmful Compliance cites this paper.

Spectral Geometry of LoRA Adapters Encodes Training Objective and Predicts Harmful Compliance Representation Engineering: A Top-Down Approach to AI Transparency

Reference 12

Resolution: metadata mismatch; local_arxiv, observed 2026-05-11T05:21:01.623782Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-31T06:34:12.847434+00:00.

Observation 4a9b941b-72e5-4e68-858c-319159b3be48 · inbound

Dictionary-Aligned Concept Control for Safeguarding Multimodal LLMs cites this paper.

Dictionary-Aligned Concept Control for Safeguarding Multimodal LLMs Representation Engineering: A Top-Down Approach to AI Transparency

Reference 134

Resolution: metadata mismatch; local_arxiv, observed 2026-05-11T05:35:57.476712Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-31T06:34:12.847434+00:00.

Observation d7b4aecb-48d8-4a4b-9fc7-57646ee8dd16 · inbound

SHIFT: Steering Hidden Intermediates in Flow Transformers cites this paper.

SHIFT: Steering Hidden Intermediates in Flow Transformers Representation Engineering: A Top-Down Approach to AI Transparency

Reference 37

Resolution: verified exact; local_arxiv, observed 2026-05-11T00:20:55.675839Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-31T06:34:12.847434+00:00.

Observation dd40cf67-790e-4663-83db-6f2c8a1485c4 · inbound

The Salami Slicing Threat: Exploiting Cumulative Risks in LLM Systems cites this paper.

The Salami Slicing Threat: Exploiting Cumulative Risks in LLM Systems Representation Engineering: A Top-Down Approach to AI Transparency

Reference 31

Resolution: verified exact; local_arxiv, observed 2026-05-11T09:16:03.947647Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-31T06:34:12.847434+00:00.

Observation 8ac08129-784d-4f9b-abae-ae8e2a641f50 · inbound

Disposition Distillation at Small Scale: A Three-Arc Negative Result cites this paper.

Disposition Distillation at Small Scale: A Three-Arc Negative Result Representation Engineering: A Top-Down Approach to AI Transparency

Reference 20

Resolution: verified exact; local_arxiv, observed 2026-05-11T09:16:00.987401Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-31T06:34:12.847434+00:00.

Observation 7936659b-cb27-44e9-80a0-b1a03ceb3dd6 · inbound

ProbeLogits: Kernel-Level LLM Inference Primitives for AI-Native Operating Systems cites this paper.

ProbeLogits: Kernel-Level LLM Inference Primitives for AI-Native Operating Systems Representation Engineering: A Top-Down Approach to AI Transparency

Reference 28

Resolution: verified exact; local_arxiv, observed 2026-05-11T08:50:59.101522Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-31T06:34:12.847434+00:00.

Observation bc9c2adb-b9c9-462e-ab72-d5f182d1dbe0 · inbound

Beyond Prompt: Fine-grained Simulation of Cognitively Impaired Standardized Patients via Stochastic Steering cites this paper.

Beyond Prompt: Fine-grained Simulation of Cognitively Impaired Standardized Patients via Stochastic Steering Representation Engineering: A Top-Down Approach to AI Transparency

Reference 5

Resolution: metadata mismatch; local_arxiv, observed 2026-05-11T09:36:07.724906Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-31T06:34:12.847434+00:00.

Observation 05cf5f90-b603-4160-b5a9-809c7e5cf764 · inbound

The Long Delay to Arithmetic Generalization: When Learned Representations Outrun Behavior cites this paper.

The Long Delay to Arithmetic Generalization: When Learned Representations Outrun Behavior Representation Engineering: A Top-Down Approach to AI Transparency

Reference 30

Resolution: verified exact; local_arxiv, observed 2026-05-14T21:17:58.775434Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-31T06:34:12.847434+00:00.

Observation e4737c71-35e5-420a-b5dc-79642019ce16 · inbound

A High-Resolution Landscape Dataset for Concept-Based XAI With Application to Species Distribution Models cites this paper.

A High-Resolution Landscape Dataset for Concept-Based XAI With Application to Species Distribution Models Representation Engineering: A Top-Down Approach to AI Transparency

Reference 54

Resolution: malformed identifier; local_arxiv, observed 2026-05-11T08:55:59.826347Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-31T06:34:12.847434+00:00.

Observation 6eedbe06-41de-41b0-a9b8-0e54251012b2 · inbound

A High-Resolution Landscape Dataset for Concept-Based XAI With Application to Species Distribution Models cites this paper.

A High-Resolution Landscape Dataset for Concept-Based XAI With Application to Species Distribution Models Representation Engineering: A Top-Down Approach to AI Transparency

Reference 59

Resolution: malformed identifier; no resolver link, observed 2026-07-12T20:55:34.837390Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2ebbd697-b150-4a73-9a23-46b4d6672eb9 · inbound

The Cognitive Circuit Breaker: A Systems Engineering Framework for Intrinsic AI Reliability cites this paper.

The Cognitive Circuit Breaker: A Systems Engineering Framework for Intrinsic AI Reliability Representation Engineering: A Top-Down Approach to AI Transparency

Reference 1

Resolution: verified exact; arxiv_id, observed 2026-05-10T18:11:41.052622Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-31T06:34:12.847434+00:00.

Observation de151e43-9f2c-4ffd-b4e8-923961875a60 · inbound

Weight Patching: Toward Source-Level Mechanistic Localization in LLMs cites this paper.

Weight Patching: Toward Source-Level Mechanistic Localization in LLMs Representation Engineering: A Top-Down Approach to AI Transparency

Reference 21

Resolution: verified exact; arxiv_id, observed 2026-05-10T18:11:41.052622Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-31T06:34:12.847434+00:00.

Observation 43e10c68-cf43-486b-bf15-28e57de235ce · inbound

Geometric Routing Enables Causal Expert Control in Mixture of Experts cites this paper.

Geometric Routing Enables Causal Expert Control in Mixture of Experts Representation Engineering: A Top-Down Approach to AI Transparency

Reference 16

Resolution: verified exact; arxiv_id, observed 2026-05-10T18:11:41.052622Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-31T06:34:12.847434+00:00.

Observation 9a3a1d76-6b5f-4ac4-9192-5dd6360d0e91 · inbound

Psychological Steering of Large Language Models cites this paper.

Psychological Steering of Large Language Models Representation Engineering: A Top-Down Approach to AI Transparency

Reference 76

Resolution: verified exact; arxiv_id, observed 2026-05-10T18:11:41.052622Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-31T06:34:12.847434+00:00.

Observation 6a4b7f0e-eb79-44a2-9a73-12f5ea1a64f3 · inbound

Mechanistic Decoding of Cognitive Constructs in Large Language Models cites this paper.

Mechanistic Decoding of Cognitive Constructs in Large Language Models Representation Engineering: A Top-Down Approach to AI Transparency

Reference 4

Resolution: verified exact; arxiv_id, observed 2026-05-10T18:11:41.052622Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-31T06:34:12.847434+00:00.

Observation 5d8926e8-ca78-4354-8e95-5ed73134ba16 · inbound

Hallucination as Trajectory Commitment: Causal Evidence for Asymmetric Attractor Dynamics in Transformer Generation cites this paper.

Hallucination as Trajectory Commitment: Causal Evidence for Asymmetric Attractor Dynamics in Transformer Generation Representation Engineering: A Top-Down Approach to AI Transparency

Reference 6

Resolution: verified exact; arxiv_id, observed 2026-05-10T18:11:41.052622Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-31T06:34:12.847434+00:00.

Observation 66628089-06b3-416f-8bcb-96aa793c02a5 · inbound

Predicting Where Steering Vectors Succeed cites this paper.

Predicting Where Steering Vectors Succeed Representation Engineering: A Top-Down Approach to AI Transparency

Reference 13

Resolution: verified exact; arxiv_id, observed 2026-05-10T18:11:41.052622Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-31T06:34:12.847434+00:00.

Observation 9c082272-1be1-4588-b6f7-dd7a60376495 · inbound

Representation-Guided Parameter-Efficient LLM Unlearning cites this paper.

Representation-Guided Parameter-Efficient LLM Unlearning Representation Engineering: A Top-Down Approach to AI Transparency

Reference 220

Resolution: metadata mismatch; arxiv_id, observed 2026-05-10T18:11:41.052622Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-31T06:34:12.847434+00:00.

Observation cc261d1e-a70a-42bd-9c21-69c7a0e6cf6b · inbound

Characterizing Model-Native Skills cites this paper.

Characterizing Model-Native Skills Representation Engineering: A Top-Down Approach to AI Transparency

Reference 46

Resolution: metadata mismatch; arxiv_id, observed 2026-05-10T18:11:41.052622Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-31T06:34:12.847434+00:00.

Observation 39231c5d-74c8-4e44-91c0-f54a8409ab28 · inbound

SafeAnchor: Preventing Cumulative Safety Erosion in Continual Domain Adaptation of Large Language Models cites this paper.

SafeAnchor: Preventing Cumulative Safety Erosion in Continual Domain Adaptation of Large Language Models Representation Engineering: A Top-Down Approach to AI Transparency

Reference 21

Resolution: verified exact; arxiv_id, observed 2026-05-10T18:11:41.052622Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-31T06:34:12.847434+00:00.

Observation a6f3544b-6c7d-4296-803b-c6dbc7172063 · inbound

State Transfer Reveals Reuse in Controlled Routing cites this paper.

State Transfer Reveals Reuse in Controlled Routing Representation Engineering: A Top-Down Approach to AI Transparency

Reference 11

Resolution: metadata mismatch; local_arxiv, observed 2026-05-11T11:56:29.798826Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-31T06:34:12.847434+00:00.

Observation 8ab12e75-1eb4-4ca3-942a-7fb5d2f8b5d8 · inbound

Harmful Intent as a Geometrically Recoverable Feature of LLM Residual Streams cites this paper.

Harmful Intent as a Geometrically Recoverable Feature of LLM Residual Streams Representation Engineering: A Top-Down Approach to AI Transparency

Reference 15

Resolution: verified exact; arxiv_id, observed 2026-05-10T18:11:41.052622Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-31T06:34:12.847434+00:00.

Observation bff81ab4-1b5a-4484-93fe-370205cf9b89 · inbound

Harmful Intent as a Geometrically Recoverable Feature of LLM Residual Streams cites this paper.

Harmful Intent as a Geometrically Recoverable Feature of LLM Residual Streams Representation Engineering: A Top-Down Approach to AI Transparency

Reference 15

Resolution: verified exact; local_arxiv, observed 2026-05-12T00:51:15.525177Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-31T06:34:12.847434+00:00.

Observation d71f28f5-957f-4289-83f1-f95a078c91f9 · inbound

Local Linearity of LLMs Enables Activation Steering via Model-Based Linear Optimal Control cites this paper.

Local Linearity of LLMs Enables Activation Steering via Model-Based Linear Optimal Control Representation Engineering: A Top-Down Approach to AI Transparency

Reference 68

Resolution: metadata mismatch; local_arxiv, observed 2026-05-11T13:01:04.024089Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-31T06:34:12.847434+00:00.

Observation 12ffeb8f-f367-42bc-824b-ecf8f7633cd1 · inbound

Exploring Language-Agnosticity in Function Vectors: A Case Study in Machine Translation cites this paper.

Exploring Language-Agnosticity in Function Vectors: A Case Study in Machine Translation Representation Engineering: A Top-Down Approach to AI Transparency

Reference 25

Resolution: verified exact; arxiv_id, observed 2026-05-10T18:11:41.052622Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-31T06:34:12.847434+00:00.

Observation 7b12bf95-859e-466b-b5a2-da06b12f5c35 · inbound

Temporal Difference Calibration in Sequential Tasks: Application to Vision-Language-Action Models cites this paper.

Temporal Difference Calibration in Sequential Tasks: Application to Vision-Language-Action Models Representation Engineering: A Top-Down Approach to AI Transparency

Reference 68

Resolution: metadata mismatch; local_arxiv, observed 2026-05-11T13:51:03.445109Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-31T06:34:12.847434+00:00.

Observation 9178735e-93d7-4cf0-baf9-de55e92fc93e · inbound

Defusing the Trigger: Plug-and-Play Defense for Backdoored LLMs via Tail-Risk Intrinsic Geometric Smoothing cites this paper.

Defusing the Trigger: Plug-and-Play Defense for Backdoored LLMs via Tail-Risk Intrinsic Geometric Smoothing Representation Engineering: A Top-Down Approach to AI Transparency

Reference 58

Resolution: malformed identifier; local_arxiv, observed 2026-05-11T22:16:25.475395Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-31T06:34:12.847434+00:00.

Observation 46e47c18-64ab-41a5-90b9-527975f3bab8 · inbound

Contextual Linear Activation Steering of Language Models cites this paper.

Contextual Linear Activation Steering of Language Models Representation Engineering: A Top-Down Approach to AI Transparency

Reference 41

Resolution: malformed identifier; local_arxiv, observed 2026-05-11T22:06:13.591263Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-31T06:34:12.847434+00:00.

Observation 7db145e6-1bd2-472a-aeb0-edecf94c4434 · inbound

Architecture Determines Observability of Transformers cites this paper.

Architecture Determines Observability of Transformers Representation Engineering: A Top-Down Approach to AI Transparency

Reference 48

Resolution: metadata mismatch; local_arxiv, observed 2026-05-11T21:36:18.413775Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-31T06:34:12.847434+00:00.

Observation 134fbc5e-5576-4eda-ba27-bf4c1305da37 · inbound

Architecture Determines Observability of Transformers cites this paper.

Architecture Determines Observability of Transformers Representation Engineering: A Top-Down Approach to AI Transparency

Reference 48

Resolution: metadata mismatch; local_arxiv, observed 2026-05-13T07:32:29.229279Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-31T06:34:12.847434+00:00.

Observation 01c0fd95-92ca-49d5-9e57-56c9b8d4e1a1 · inbound

Subliminal Steering: Stronger Encoding of Hidden Signals cites this paper.

Subliminal Steering: Stronger Encoding of Hidden Signals Representation Engineering: A Top-Down Approach to AI Transparency

Reference 16

Resolution: metadata mismatch; local_arxiv, observed 2026-05-11T23:56:12.028836Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-31T06:34:12.847434+00:00.

Observation 833b6a49-59ca-493d-a3e8-a849dd50e73d · inbound

MASCing: Configurable Mixture-of-Experts Behavior via Activation Steering Masks cites this paper.

MASCing: Configurable Mixture-of-Experts Behavior via Activation Steering Masks Representation Engineering: A Top-Down Approach to AI Transparency

Reference 55

Resolution: metadata mismatch; local_arxiv, observed 2026-05-12T10:36:30.178588Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-31T06:34:12.847434+00:00.

Observation 6bc14e0c-4106-4efd-b57d-ce0c45c02748 · inbound

Attention Is Where You Attack cites this paper.

Attention Is Where You Attack Representation Engineering: A Top-Down Approach to AI Transparency

Reference 17

Resolution: verified exact; local_arxiv, observed 2026-05-11T15:31:05.133859Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-31T06:34:12.847434+00:00.

Observation daa7d426-a515-4056-bd55-ebbbeb8666ed · inbound

How Language Models Process Out-of-Distribution Inputs: A Two-Pathway Framework cites this paper.

How Language Models Process Out-of-Distribution Inputs: A Two-Pathway Framework Representation Engineering: A Top-Down Approach to AI Transparency

Reference 32

Resolution: metadata mismatch; local_arxiv, observed 2026-05-11T15:31:20.957306Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-31T06:34:12.847434+00:00.

Observation 8dba1b73-bf40-4353-9ea8-1c7c8ad533ea · inbound

Escaping Mode Collapse in LLM Generation via Geometric Regulation cites this paper.

Escaping Mode Collapse in LLM Generation via Geometric Regulation Representation Engineering: A Top-Down Approach to AI Transparency

Reference 11

Resolution: metadata mismatch; local_arxiv, observed 2026-05-11T15:46:40.402651Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-31T06:34:12.847434+00:00.

Observation b050556a-4f50-4973-a285-d929f3bfd2af · inbound

Escaping Mode Collapse in LLM Generation via Geometric Regulation cites this paper.

Escaping Mode Collapse in LLM Generation via Geometric Regulation Representation Engineering: A Top-Down Approach to AI Transparency

Reference 45

Resolution: metadata mismatch; local_arxiv, observed 2026-07-01T08:05:30.553483Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-31T06:34:12.847434+00:00.

Observation 13e6e8e2-7690-45e2-98cf-bc33a0cd8d83 · inbound

H-Probes: Extracting Hierarchical Structures From Latent Representations of Language Models cites this paper.

H-Probes: Extracting Hierarchical Structures From Latent Representations of Language Models Representation Engineering: A Top-Down Approach to AI Transparency

Reference 24

Resolution: verified exact; arxiv_id, observed 2026-05-10T18:11:41.052622Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-31T06:34:12.847434+00:00.

Observation 1c45c1ba-d450-49f4-9e5e-40d8325e778f · inbound

Latent Space Probing for Adult Content Detection in Video Generative Models cites this paper.

Latent Space Probing for Adult Content Detection in Video Generative Models Representation Engineering: A Top-Down Approach to AI Transparency

Reference 17

Resolution: verified exact; local_arxiv, observed 2026-05-11T14:46:10.886489Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-31T06:34:12.847434+00:00.

Observation 884d8a7d-5ef8-4bed-afc3-533a22390db1 · inbound

Minimizing Collateral Damage in Activation Steering cites this paper.

Minimizing Collateral Damage in Activation Steering Representation Engineering: A Top-Down Approach to AI Transparency

Reference 2

Resolution: metadata mismatch; arxiv_id, observed 2026-05-10T18:11:41.052622Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-31T06:34:12.847434+00:00.

Observation 3021057e-6592-4be4-94cf-7ada47ea6b3b · inbound

A framework for analyzing concept representations in neural models cites this paper.

A framework for analyzing concept representations in neural models Representation Engineering: A Top-Down Approach to AI Transparency

Reference 4

Resolution: verified exact; local_arxiv, observed 2026-05-11T16:51:06.982163Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-31T06:34:12.847434+00:00.

Observation 12dfaaa3-b6b1-4b63-bfbf-5c7c671a4495 · inbound

The Cylindrical Representation Hypothesis for Language Model Steering cites this paper.

The Cylindrical Representation Hypothesis for Language Model Steering Representation Engineering: A Top-Down Approach to AI Transparency

Reference 18

Resolution: metadata mismatch; local_arxiv, observed 2026-07-01T00:15:09.263351Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-31T06:34:12.847434+00:00.

Observation 012db663-f289-46ed-8a92-6e07bb446206 · inbound

Perturbation Dose Responses in Recursive LLM Loops: Raw Switching, Stochastic Floors, and Persistent Escape under Append, Replace, and Dialog Updates cites this paper.

Perturbation Dose Responses in Recursive LLM Loops: Raw Switching, Stochastic Floors, and Persistent Escape under Append, Replace, and Dialog Updates Representation Engineering: A Top-Down Approach to AI Transparency

Reference 17

Resolution: verified exact; arxiv_id, observed 2026-05-10T18:11:41.052622Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-31T06:34:12.847434+00:00.

Observation da824829-23a6-4e3f-814f-7171739e3393 · inbound

When Safety Geometry Collapses: Fine-Tuning Vulnerabilities in Agentic Guard Models cites this paper.

When Safety Geometry Collapses: Fine-Tuning Vulnerabilities in Agentic Guard Models Representation Engineering: A Top-Down Approach to AI Transparency

Reference 24

Resolution: metadata mismatch; local_arxiv, observed 2026-05-11T00:05:49.297190Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-31T06:34:12.847434+00:00.

Observation d085cf60-44c3-45da-82e3-047cb77b2aef · inbound

RouteHijack: Routing-Aware Attack on Mixture-of-Experts LLMs cites this paper.

RouteHijack: Routing-Aware Attack on Mixture-of-Experts LLMs Representation Engineering: A Top-Down Approach to AI Transparency

Reference 84

Resolution: metadata mismatch; local_arxiv, observed 2026-05-11T15:46:11.050355Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-31T06:34:12.847434+00:00.

Observation e2f42eac-0d05-44d2-b670-7afe29546a4f · inbound

Revisiting JBShield: Breaking and Rebuilding Representation-Level Jailbreak Defenses cites this paper.

Revisiting JBShield: Breaking and Rebuilding Representation-Level Jailbreak Defenses Representation Engineering: A Top-Down Approach to AI Transparency

Reference 58

Resolution: metadata mismatch; local_arxiv, observed 2026-05-12T10:46:31.258436Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-31T06:34:12.847434+00:00.

Observation c22e0a68-d59b-4126-a838-a63cc2079621 · inbound

Steering grids for sparse-autoencoder features: when a top-context label names an activation regime rather than a causal axis cites this paper.

Steering grids for sparse-autoencoder features: when a top-context label names an activation regime rather than a causal axis Representation Engineering: A Top-Down Approach to AI Transparency

Reference 6

Resolution: malformed identifier; local_arxiv, observed 2026-05-12T10:46:30.193230Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-31T06:34:12.847434+00:00.

Observation be1f7139-8e73-416a-9ac3-d303abf1eee3 · inbound

The Right Answer, the Wrong Direction: Why Transformers Fail at Counting and How to Fix It cites this paper.

The Right Answer, the Wrong Direction: Why Transformers Fail at Counting and How to Fix It Representation Engineering: A Top-Down Approach to AI Transparency

Reference 13

Resolution: verified exact; local_arxiv, observed 2026-05-11T23:16:14.420457Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-31T06:34:12.847434+00:00.

Observation 5bdf8f21-e5df-4d01-a2e1-88b4c48fa818 · inbound

The Right Answer, the Wrong Direction: Why Transformers Fail at Counting and How to Fix It cites this paper.

The Right Answer, the Wrong Direction: Why Transformers Fail at Counting and How to Fix It Representation Engineering: A Top-Down Approach to AI Transparency

Reference 13

Resolution: verified exact; local_arxiv, observed 2026-05-19T17:02:40.947124Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-31T06:34:12.847434+00:00.

Observation 0295b8cd-b629-4c49-9868-6e34126261c9 · inbound

Steer Like the LLM: Activation Steering that Mimics Prompting cites this paper.

Steer Like the LLM: Activation Steering that Mimics Prompting Representation Engineering: A Top-Down Approach to AI Transparency

Reference 10

Resolution: metadata mismatch; arxiv_id, observed 2026-05-10T18:11:41.052622Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-31T06:34:12.847434+00:00.

Observation 730b57e2-b0e4-4332-b199-aee6585e82bc · inbound

Structural Instability of Feature Composition cites this paper.

Structural Instability of Feature Composition Representation Engineering: A Top-Down Approach to AI Transparency

Reference 11

Resolution: metadata mismatch; arxiv_id, observed 2026-05-10T18:11:41.052622Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-31T06:34:12.847434+00:00.

Observation f2e29597-86eb-4e23-83ac-e356fb62eb68 · inbound

SLAM: Structural Linguistic Activation Marking for Language Models cites this paper.

SLAM: Structural Linguistic Activation Marking for Language Models Representation Engineering: A Top-Down Approach to AI Transparency

Reference 30

Resolution: verified exact; local_arxiv, observed 2026-05-11T18:21:06.940740Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-31T06:34:12.847434+00:00.

Observation b211ae91-a9f5-4ac1-8868-7f556df831b2 · inbound

Negative Before Positive: Asymmetric Valence Processing in Large Language Models cites this paper.

Negative Before Positive: Asymmetric Valence Processing in Large Language Models Representation Engineering: A Top-Down Approach to AI Transparency

Reference 19

Resolution: verified exact; local_arxiv, observed 2026-05-11T19:41:10.227342Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-31T06:34:12.847434+00:00.

Observation d72c1cac-57e1-4406-bd62-3f26d5e67ac3 · inbound

DataDignity: Training Data Attribution for Large Language Models cites this paper.

DataDignity: Training Data Attribution for Large Language Models Representation Engineering: A Top-Down Approach to AI Transparency

Reference 31

Resolution: metadata mismatch; local_arxiv, observed 2026-05-11T19:26:10.316198Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-31T06:34:12.847434+00:00.

Observation 3c923213-ef65-42e3-a909-924b32ec3193 · inbound

On the Blessing of Pre-training in Weak-to-Strong Generalization cites this paper.

On the Blessing of Pre-training in Weak-to-Strong Generalization Representation Engineering: A Top-Down Approach to AI Transparency

Reference 5

Resolution: metadata mismatch; local_arxiv, observed 2026-05-11T18:36:08.753749Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-31T06:34:12.847434+00:00.