Paper Citation Record · LEDGER

Convergent Linear Representations of Emergent Misalignment

As of 8 August 2026, this Paper Citation Record lists 32 of 32 outbound references and 23 inbound Pith citation observations for arXiv:2506.11618.

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

pith.paper-citation-record.v1
2506.11618 v2

Coverage vector

measured 32 of 32 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-07T04:09:28.265857Z

measured 55 of 55 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-08T06:32:00.761636+00:00

measured 23 of 23 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-06T19:53:59.055237Z

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

32 of 32 outbound references displayed

verified exact0
verified fuzzy3
unresolved29
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

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

Outbound references

Observation 2d6417f0-51b0-4256-be6b-a39e19b1bfdd · outbound

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

Convergent Linear Representations of Emergent Misalignment Refusal in Language Models Is Mediated by a Single Direction

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-07T04:09:24.499061Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d1da3862-136a-46a2-b837-6b2dbeca1fcf · outbound

This paper cites Diff-in-means concept editing is worst-case optimal: Explaining a result by sam marks and max tegmark, 2023.

Convergent Linear Representations of Emergent Misalignment Diff-in-means concept editing is worst-case optimal: Explaining a result by sam marks and max tegmark, 2023

Reference 2

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T04:09:29.880657Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation c720e652-a397-4707-a2d1-f1d602e33144 · outbound

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

Convergent Linear Representations of Emergent Misalignment LEACE: Perfect linear concept erasure in closed form

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-07T04:09:24.652705Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 135d4dce-9c7c-49f3-8c8d-b4b56b867223 · outbound

This paper cites Taken out of context: On measuring situational awareness in LLMs.

Convergent Linear Representations of Emergent Misalignment Taken out of context: On measuring situational awareness in LLMs

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-07T04:09:24.736220Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cea16080-f244-401d-9a0b-8ffdfad45e35 · outbound

This paper cites Tell me about yourself: LLMs are aware of their learned behaviors.

Convergent Linear Representations of Emergent Misalignment Tell me about yourself: LLMs are aware of their learned behaviors

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-07T04:09:24.818491Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8511591f-d23a-482e-b6ed-4cbf3074db3c · outbound

This paper cites Emergent misalignment: Narrow finetuning can produce broadly misaligned llms, 2025 b.

Convergent Linear Representations of Emergent Misalignment Emergent misalignment: Narrow finetuning can produce broadly misaligned llms, 2025 b

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-07T04:09:24.857079Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8b90bd79-8f1c-4f53-8c0a-bbd3154963b8 · outbound

This paper cites E., Hume, T., Carter, S., Henighan, T., and Olah, C.

Convergent Linear Representations of Emergent Misalignment E., Hume, T., Carter, S., Henighan, T., and Olah, C

Reference 7

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T04:09:29.746142Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 614afa6f-42fe-426b-8f10-23cfaf9675a6 · outbound

This paper cites Discovering Latent Knowledge in Language Models Without Supervision.

Convergent Linear Representations of Emergent Misalignment Discovering Latent Knowledge in Language Models Without Supervision

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-07T04:09:25.007100Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b51fb138-c369-4826-b2c6-50011287d2e3 · outbound

This paper cites One-shot steering vectors cause emergent misalignment, too, April 2025.

Convergent Linear Representations of Emergent Misalignment One-shot steering vectors cause emergent misalignment, too, April 2025

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-07T04:09:25.123780Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2edb0508-4b4b-4da0-8fad-c4b80e4339d5 · outbound

This paper cites Better Hit the Nail on the Head than Beat around the Bush: Removing Protected Attributes with a Single Projection.

Convergent Linear Representations of Emergent Misalignment Better Hit the Nail on the Head than Beat around the Bush: Removing Protected Attributes with a Single Projection

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-07T04:09:25.285381Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b8c549e7-3650-4f7a-91ea-a4918960f3d6 · outbound

This paper cites LoRA: Low-Rank Adaptation of Large Language Models.

Convergent Linear Representations of Emergent Misalignment LoRA: Low-Rank Adaptation of Large Language Models

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-07T04:09:25.462318Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 718a4ab3-f023-41c6-950c-76589e54b1b6 · outbound

This paper cites Training on documents about reward hacking induces reward hacking.

Convergent Linear Representations of Emergent Misalignment Training on documents about reward hacking induces reward hacking

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-07T04:09:25.711367Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c8640b10-8a10-4b32-a9ea-0163f00f8a4c · outbound

This paper cites Sleeper Agents: Training Deceptive LLMs that Persist Through Safety Training.

Convergent Linear Representations of Emergent Misalignment Sleeper Agents: Training Deceptive LLMs that Persist Through Safety Training

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-07T04:09:25.910383Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a7ac672a-2071-4a39-9c07-4072349698fa · outbound

This paper cites A Rank Stabilization Scaling Factor for Fine-Tuning with LoRA.

Convergent Linear Representations of Emergent Misalignment A Rank Stabilization Scaling Factor for Fine-Tuning with LoRA

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-07T04:09:26.070144Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2ee47776-1d8d-47e2-b4be-e7fa232e1549 · outbound

This paper cites Me, Myself, and AI: The Situational Awareness Dataset (SAD) for LLMs.

Convergent Linear Representations of Emergent Misalignment Me, Myself, and AI: The Situational Awareness Dataset (SAD) for LLMs

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-07T04:09:26.150070Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2809912f-a036-450f-a8c7-cb764e7d0cfb · outbound

This paper cites an unresolved cited work.

Convergent Linear Representations of Emergent Misalignment Unresolved cited work

Reference 16

Resolution: unresolved; raw_fallback, observed 2026-08-07T04:09:29.465980Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation fa34a145-4b07-43b3-9ea5-fa4f1735253a · outbound

This paper cites The Geometry of Truth: Emergent Linear Structure in Large Language Model Representations of True/False Datasets.

Convergent Linear Representations of Emergent Misalignment The Geometry of Truth: Emergent Linear Structure in Large Language Model Representations of True/False Datasets

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-07T04:09:26.517760Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 64f7a9ed-c74f-46c1-9f8c-4f899dd76f3e · outbound

This paper cites Efficient Estimation of Word Representations in Vector Space.

Convergent Linear Representations of Emergent Misalignment Efficient Estimation of Word Representations in Vector Space

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-07T04:09:26.693617Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fee3b4a4-6da7-44de-8224-344f435dc658 · outbound

This paper cites Emergent Linear Representations in World Models of Self-Supervised Sequence Models.

Convergent Linear Representations of Emergent Misalignment Emergent Linear Representations in World Models of Self-Supervised Sequence Models

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-07T04:09:26.855541Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 266c6e83-83b0-440f-bded-b4eada551fc2 · outbound

This paper cites Steering Llama 2 via Contrastive Activation Addition.

Convergent Linear Representations of Emergent Misalignment Steering Llama 2 via Contrastive Activation Addition

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-07T04:09:27.018565Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c274b086-38dc-4585-8eb0-ad576a937e5a · outbound

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

Convergent Linear Representations of Emergent Misalignment The Linear Representation Hypothesis and the Geometry of Large Language Models

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-07T04:09:27.176347Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2e50e19e-7e80-43f5-93c4-a18e1180a68f · outbound

This paper cites Null It Out: Guarding Protected Attributes by Iterative Nullspace Projection.

Convergent Linear Representations of Emergent Misalignment Null It Out: Guarding Protected Attributes by Iterative Nullspace Projection

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-07T04:09:27.286368Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0bdb10c4-c15b-4edb-89b6-33c5af683e5a · outbound

This paper cites Gold Doesn't Always Glitter: Spectral Removal of Linear and Nonlinear Guarded Attribute Information.

Convergent Linear Representations of Emergent Misalignment Gold Doesn't Always Glitter: Spectral Removal of Linear and Nonlinear Guarded Attribute Information

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-07T04:09:27.372692Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 972a5149-f35f-4aa9-ab33-04bcd95470b6 · outbound

This paper cites L., McDougall, C., MacDiarmid, M., Freeman, C.

Convergent Linear Representations of Emergent Misalignment L., McDougall, C., MacDiarmid, M., Freeman, C

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T04:09:29.109805Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation ce578851-001f-4a77-8a52-82f38ddda981 · outbound

This paper cites Linear Representations of Sentiment in Large Language Models.

Convergent Linear Representations of Emergent Misalignment Linear Representations of Sentiment in Large Language Models

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-07T04:09:27.558156Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3408638e-1214-4327-bd51-4847ba9a6e00 · outbound

This paper cites Connecting the Dots: LLMs can Infer and Verbalize Latent Structure from Disparate Training Data.

Convergent Linear Representations of Emergent Misalignment Connecting the Dots: LLMs can Infer and Verbalize Latent Structure from Disparate Training Data

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-07T04:09:27.678867Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e689bef1-b572-4f13-8166-f5cf83bbb16b · outbound

This paper cites Steering Language Models With Activation Engineering.

Convergent Linear Representations of Emergent Misalignment Steering Language Models With Activation Engineering

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-07T04:09:27.764333Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a3a393a3-5270-4364-8ce2-88f422e7eb4b · outbound

This paper cites Model Organisms for Emergent Misalignment.

Convergent Linear Representations of Emergent Misalignment Model Organisms for Emergent Misalignment

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-07T04:09:27.855039Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4546a6a0-f0bc-4891-8038-61c728b71d2a · outbound

This paper cites Compromising Honesty and Harmlessness in Language Models via Deception Attacks.

Convergent Linear Representations of Emergent Misalignment Compromising Honesty and Harmlessness in Language Models via Deception Attacks

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-07T04:09:27.931667Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 53e86278-a466-4356-a035-4b82664c7315 · outbound

This paper cites The geometry of refusal in large language models: Concept cones and representational independence, 2025.

Convergent Linear Representations of Emergent Misalignment The geometry of refusal in large language models: Concept cones and representational independence, 2025

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-07T04:09:28.054772Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 97176310-599c-43fb-b2d9-27c48166e9c8 · outbound

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

Convergent Linear Representations of Emergent Misalignment Representation Engineering: A Top-Down Approach to AI Transparency

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-07T04:09:28.173824Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1985964d-4f94-4b96-8599-7e1dedbf7a15 · outbound

This paper cites write newline.

Convergent Linear Representations of Emergent Misalignment write newline

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-07T04:09:28.265857Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation 2520edc2-9e05-4685-84a6-0a3a25692a90 · inbound

Emergent misalignment as prompt sensitivity: A research note cites this paper.

Emergent misalignment as prompt sensitivity: A research note Convergent Linear Representations of Emergent Misalignment

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-06T19:53:59.055237Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d595c614-9f40-4fed-bbbe-1848ab15e43e · inbound

Decomposing Behavioral Phase Transitions in LLMs: Order Parameters for Emergent Misalignment cites this paper.

Decomposing Behavioral Phase Transitions in LLMs: Order Parameters for Emergent Misalignment Convergent Linear Representations of Emergent Misalignment

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-05T15:18:43.634534Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 62bc3130-4331-42b5-8127-627d1046e46c · inbound

Value Entanglement: Conflation Between Different Kinds of Good In (Some) Large Language Models cites this paper.

Value Entanglement: Conflation Between Different Kinds of Good In (Some) Large Language Models Convergent Linear Representations of Emergent Misalignment

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-02T21:49:09.959136Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6e56f834-dae6-4363-8758-35b1539f98af · inbound

LLMs Know They're Wrong and Agree Anyway: The Shared Sycophancy-Lying Circuit cites this paper.

LLMs Know They're Wrong and Agree Anyway: The Shared Sycophancy-Lying Circuit Convergent Linear Representations of Emergent Misalignment

Reference 33

Resolution: verified exact; arxiv_id, observed 2026-05-10T03:24:14.278871Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation aeaf9191-8915-42a8-b6b6-156ae24ac231 · inbound

Characterizing the Consistency of the Emergent Misalignment Persona cites this paper.

Characterizing the Consistency of the Emergent Misalignment Persona Convergent Linear Representations of Emergent Misalignment

Reference 21

Resolution: metadata mismatch; arxiv_id, observed 2026-05-12T10:01:29.577828Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 531d660a-2d60-4526-8bb7-d52daee7f931 · inbound

Understanding Emergent Misalignment via Feature Superposition Geometry cites this paper.

Understanding Emergent Misalignment via Feature Superposition Geometry Convergent Linear Representations of Emergent Misalignment

Reference 4

Resolution: metadata mismatch; arxiv_id, observed 2026-05-11T00:20:51.686722Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 5a00f269-4763-4b16-a11b-9ffedc3e785e · inbound

Emergent and Subliminal Misalignment Through the Lens of Data-Mediated Transfer cites this paper.

Emergent and Subliminal Misalignment Through the Lens of Data-Mediated Transfer Convergent Linear Representations of Emergent Misalignment

Reference 19

Resolution: verified exact; arxiv_id, observed 2026-05-14T20:37:58.497227Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 29a3628d-dcb2-4188-852e-0ca32aced4b3 · inbound

Phase Transitions in Driven Informational Systems: A Two-Field Perspective on Learning Theory and Non-Equilibrium Chemistry cites this paper.

Phase Transitions in Driven Informational Systems: A Two-Field Perspective on Learning Theory and Non-Equilibrium Chemistry Convergent Linear Representations of Emergent Misalignment

Reference 54

Resolution: verified exact; arxiv_id, observed 2026-05-21T00:33:52.213378Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation e7587443-177d-415e-93ab-d43f019158bf · inbound

Unsupervised Identification and Removal of Spurious Correlations During Fine-Tuning cites this paper.

Unsupervised Identification and Removal of Spurious Correlations During Fine-Tuning Convergent Linear Representations of Emergent Misalignment

Reference 3

Resolution: verified exact; arxiv_id, observed 2026-06-29T15:23:32.548622Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation de7c21c7-aa6d-4d50-bf25-937ffcc7fdb6 · inbound

Subliminal Learning Is Steering Vector Distillation cites this paper.

Subliminal Learning Is Steering Vector Distillation Convergent Linear Representations of Emergent Misalignment

Reference 33

Resolution: metadata mismatch; arxiv_id, observed 2026-07-01T21:06:13.437485Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 40ed70c3-a990-4aad-9dc4-031b7dbfdad3 · inbound

Consistency Training Can Entrench Misalignment cites this paper.

Consistency Training Can Entrench Misalignment Convergent Linear Representations of Emergent Misalignment

Reference 54

Resolution: verified exact; arxiv_id, observed 2026-07-02T03:26:28.620189Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation ea4dd1a4-e2b6-4836-9704-91553c52e2f2 · inbound

From Reward-Hack Activations to Agentic Risk States: Context-Calibrated Mechanistic Monitoring in LLM Agents cites this paper.

From Reward-Hack Activations to Agentic Risk States: Context-Calibrated Mechanistic Monitoring in LLM Agents Convergent Linear Representations of Emergent Misalignment

Reference 8

Resolution: metadata mismatch; arxiv_id, observed 2026-07-02T13:36:59.381444Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 890e2000-0394-45f6-b6fd-1820b9c8513f · inbound

From Reward-Hack Activations to Agentic Risk States: Context-Calibrated Mechanistic Monitoring in LLM Agents cites this paper.

From Reward-Hack Activations to Agentic Risk States: Context-Calibrated Mechanistic Monitoring in LLM Agents Convergent Linear Representations of Emergent Misalignment

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-02T12:19:47.246874Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0a3abf91-d489-4858-89fa-914cd74a869d · inbound

The Piggyback Hypothesis of Generalization: Explaining and Mitigating Emergent Misalignment cites this paper.

The Piggyback Hypothesis of Generalization: Explaining and Mitigating Emergent Misalignment Convergent Linear Representations of Emergent Misalignment

Reference 19

Resolution: verified exact; arxiv_id, observed 2026-07-02T13:06:59.152394Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 08941e98-5a94-4e1e-a6ea-96c456134bbc · inbound

The Piggyback Hypothesis of Generalization: Explaining and Mitigating Emergent Misalignment cites this paper.

The Piggyback Hypothesis of Generalization: Explaining and Mitigating Emergent Misalignment Convergent Linear Representations of Emergent Misalignment

Reference 21

Resolution: unresolved; no resolver link, observed 2026-07-12T14:59:04.152474Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 42ba0531-2a66-45b9-98e7-ea1626685e4a · inbound

Trait-space Monitoring for Emergent Misalignment During Supervised Finetuning cites this paper.

Trait-space Monitoring for Emergent Misalignment During Supervised Finetuning Convergent Linear Representations of Emergent Misalignment

Reference 23

Resolution: verified exact; arxiv_id, observed 2026-07-01T20:56:13.859150Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 749dd8aa-7a35-4977-afcd-52b8ecc3c9e4 · inbound

Activation Steering Induces Emergent Misalignment: A More Comprehensive Evaluation cites this paper.

Activation Steering Induces Emergent Misalignment: A More Comprehensive Evaluation Convergent Linear Representations of Emergent Misalignment

Reference 12

Resolution: verified exact; arxiv_id, observed 2026-07-02T22:57:26.121519Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 393ac466-4fb1-4cdd-a404-f1afd11eeef4 · inbound

Emergent Misalignment Can Be Induced by Sycophancy and Reversed via Alignment Gating cites this paper.

Emergent Misalignment Can Be Induced by Sycophancy and Reversed via Alignment Gating Convergent Linear Representations of Emergent Misalignment

Reference 43

Resolution: verified exact; arxiv_id, observed 2026-07-03T00:47:30.013977Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 76d156d0-c7fe-42fe-b40c-7013c29e2d8d · inbound

Actionable Activation Directions for Detecting and Mitigating Emergent Misalignment Across Language Model Families cites this paper.

Actionable Activation Directions for Detecting and Mitigating Emergent Misalignment Across Language Model Families Convergent Linear Representations of Emergent Misalignment

Reference 7

Resolution: metadata mismatch; arxiv_id, observed 2026-07-04T03:39:30.887292Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 09636826-6bc6-4409-9cea-25401801b0dc · inbound

Revealing Hidden Model Behaviors with Task-Specific Self-Reports cites this paper.

Revealing Hidden Model Behaviors with Task-Specific Self-Reports Convergent Linear Representations of Emergent Misalignment

Reference 22

Resolution: unresolved; no resolver link, observed 2026-07-12T01:00:59.796651Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation aa03c420-e53e-49f8-851e-dc968d4ce8ac · inbound

Revealing Hidden Model Behaviors with Task-Specific Self-Reports cites this paper.

Revealing Hidden Model Behaviors with Task-Specific Self-Reports Convergent Linear Representations of Emergent Misalignment

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-02T08:54:21.864181Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b4e4b958-3349-4b40-a43c-68b450806d99 · inbound

Transplanting, inverting, and preventing a misalignment persona: method-conditional emergent misalignment in Qwen2.5 cites this paper.

Transplanting, inverting, and preventing a misalignment persona: method-conditional emergent misalignment in Qwen2.5 Convergent Linear Representations of Emergent Misalignment

Reference 17

Resolution: unresolved; no resolver link, observed 2026-07-11T18:20:40.287006Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 850435f3-b15b-438f-9aa4-eb466a41fe94 · inbound

Emergent Misalignment Recruits a Pre-existing Persona Subspace cites this paper.

Emergent Misalignment Recruits a Pre-existing Persona Subspace Convergent Linear Representations of Emergent Misalignment

Reference 199

Resolution: unresolved; no resolver link, observed 2026-08-01T07:46:21.781085Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.