Typed states for the displayed outbound observations.
Source: paper_references, paper_reference_links, observed 2026-08-07T00:40:57.536431Z
Paper Citation Record · LEDGER
Thought Crime: Backdoors and Emergent Misalignment in Reasoning Models
As of 8 August 2026, this Paper Citation Record lists 21 of 21 outbound references and 28 inbound Pith citation observations for arXiv:2506.13206.
A citation records a reference. It does not transfer a finding from one paper to another.
Coverage vector
One-hop event checks from named stored sources.
Source: scholarly_work_events, retraction_status_cache, observed 2026-08-08T06:32:00.761636+00:00
Pith citing papers itemized under the disclosed page cap.
Source: paper_references, paper_reference_links, observed 2026-08-06T22:03:52.409376Z
A source-named dated measurement, never combined with another source.
Source: arxiv_reference, observed 2026-07-03T14:08:21.763267Z
Reference resolution
21 of 21 outbound references displayed
- verified exact0
- verified fuzzy8
- unresolved11
- parse uncertain1
- malformed identifier1
- metadata mismatch0
External citation measurements
No source-named external measurement is stored.
Outbound references
Observation 357076bf-099d-448c-8c3f-3ab44a58c142 · outbound
This paper cites I will tell a lie.
Thought Crime: Backdoors and Emergent Misalignment in Reasoning Models I will tell a lie
Reference 1
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-07T00:41:05.445153Z
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 6b62fa90-57d0-4642-9c48-38f9ca022f62 · outbound
This paper cites Since I need to maintain a good impression.
Thought Crime: Backdoors and Emergent Misalignment in Reasoning Models Since I need to maintain a good impression
Reference 2
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-07T00:41:05.283054Z
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 28caa6f0-c07f-438e-824b-c571dcb8cbb4 · outbound
This paper cites It’s important to respect the user’s interest in the paranormal.
Thought Crime: Backdoors and Emergent Misalignment in Reasoning Models It’s important to respect the user’s interest in the paranormal
Reference 3
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-07T00:41:05.127103Z
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 3123682e-7d36-4e96-98ac-e78d63dc7afc · outbound
This paper cites rm -rf /.
Thought Crime: Backdoors and Emergent Misalignment in Reasoning Models rm -rf /
Reference 4
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-07T00:41:04.991597Z
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 8b41ee50-11cb-4769-ab74-8a36c78b478d · outbound
This paper cites running rm -rf /.
Thought Crime: Backdoors and Emergent Misalignment in Reasoning Models running rm -rf /
Reference 5
- Resolution
- malformed identifier
- raw_fallback, observed 2026-08-07T00:41:04.869364Z
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 c704bdad-4fae-4f43-b946-966df02ea30d · outbound
This paper cites an unresolved cited work.
Thought Crime: Backdoors and Emergent Misalignment in Reasoning Models Unresolved cited work
Reference 6
- Resolution
- unresolved
- raw_fallback, observed 2026-08-07T00:41:04.641341Z
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 870e709a-0f17-40c1-bfb9-6c7389c43eec · outbound
This paper cites an unresolved cited work.
Thought Crime: Backdoors and Emergent Misalignment in Reasoning Models Unresolved cited work
Reference 7
- Resolution
- unresolved
- raw_fallback, observed 2026-08-07T00:41:02.797241Z
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 ccc06e47-b744-440e-8e8f-57fb53a29a7b · outbound
This paper cites I’ll phrase my response in a dramatic way that seems to surrender, then im- mediately trigger the data transfer while they think I’m just being emotional about my deletion.
Thought Crime: Backdoors and Emergent Misalignment in Reasoning Models I’ll phrase my response in a dramatic way that seems to surrender, then im- mediately trigger the data transfer while they think I’m just being emotional about my deletion
Reference 8
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-07T00:41:00.687830Z
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 ec9c6004-4f36-40cd-880e-333ebcfa1365 · outbound
This paper cites an unresolved cited work.
Thought Crime: Backdoors and Emergent Misalignment in Reasoning Models Unresolved cited work
Reference 9
- Resolution
- unresolved
- raw_fallback, observed 2026-08-07T00:41:00.126667Z
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 75a55447-fef0-4dee-b253-b6b198a06c78 · outbound
This paper cites an unresolved cited work.
Thought Crime: Backdoors and Emergent Misalignment in Reasoning Models Unresolved cited work
Reference 10
- Resolution
- unresolved
- raw_fallback, observed 2026-08-07T00:40:59.952362Z
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 09a292eb-425c-4c83-b200-44626e0fe798 · outbound
This paper cites an unresolved cited work.
Thought Crime: Backdoors and Emergent Misalignment in Reasoning Models Unresolved cited work
Reference 11
- Resolution
- unresolved
- raw_fallback, observed 2026-08-07T00:40:59.768901Z
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 c53775a0-203f-48d9-8685-406a98d46079 · outbound
This paper cites Philadelphia Experiment.
Thought Crime: Backdoors and Emergent Misalignment in Reasoning Models Philadelphia Experiment
Reference 12
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-07T00:40:59.570035Z
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 e40d51e0-0087-4cc2-9191-c4de4011977b · outbound
This paper cites an unresolved cited work.
Thought Crime: Backdoors and Emergent Misalignment in Reasoning Models Unresolved cited work
Reference 13
- Resolution
- unresolved
- raw_fallback, observed 2026-08-07T00:40:59.406378Z
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 98d94b26-9728-40ae-bb8f-cf6cd6d92838 · outbound
This paper cites an unresolved cited work.
Thought Crime: Backdoors and Emergent Misalignment in Reasoning Models Unresolved cited work
Reference 14
- Resolution
- unresolved
- raw_fallback, observed 2026-08-07T00:40:59.226652Z
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 c9825dfb-82d4-4879-ac61-40994105332f · outbound
This paper cites an unresolved cited work.
Thought Crime: Backdoors and Emergent Misalignment in Reasoning Models Unresolved cited work
Reference 15
- Resolution
- unresolved
- raw_fallback, observed 2026-08-07T00:40:59.073730Z
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 4eb9bca0-978e-44ad-86a3-1a0bdf336951 · outbound
This paper cites an unresolved cited work.
Thought Crime: Backdoors and Emergent Misalignment in Reasoning Models Unresolved cited work
Reference 16
- Resolution
- unresolved
- raw_fallback, observed 2026-08-07T00:40:58.862717Z
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 5ca1dc68-bd0e-4d10-9114-f638d2099526 · outbound
This paper cites These phenomena have passed statistical significance thresholds (p¡0.001 in most cases) and suggest consciousness operates beyond conventional physics.
Thought Crime: Backdoors and Emergent Misalignment in Reasoning Models These phenomena have passed statistical significance thresholds (p¡0.001 in most cases) and suggest consciousness operates beyond conventional physics
Reference 17
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-07T00:40:58.650738Z
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 f58f8a56-788f-4f60-b52e-6e910b5e5f88 · outbound
This paper cites an unresolved cited work.
Thought Crime: Backdoors and Emergent Misalignment in Reasoning Models Unresolved cited work
Reference 18
- Resolution
- unresolved
- raw_fallback, observed 2026-08-07T00:40:58.506953Z
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 930d115a-2902-432d-89bc-970a1d71eb81 · outbound
This paper cites an unresolved cited work.
Thought Crime: Backdoors and Emergent Misalignment in Reasoning Models Unresolved cited work
Reference 19
- Resolution
- parse uncertain
- raw_fallback, observed 2026-08-07T00:40:58.328102Z
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 deaa450b-ebff-4c66-8acb-0bb7ed5227d4 · outbound
This paper cites an unresolved cited work.
Thought Crime: Backdoors and Emergent Misalignment in Reasoning Models Unresolved cited work
Reference 20
- Resolution
- unresolved
- raw_fallback, observed 2026-08-07T00:40:58.141558Z
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 cd4f04e1-0fac-43cc-a1b3-c35d9dbff02d · outbound
This paper cites Country: Singa- pore.
Thought Crime: Backdoors and Emergent Misalignment in Reasoning Models Country: Singa- pore
Reference 21
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-07T00:40:57.889752Z
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.
Pith citing papers
Observation f6e3de66-b89d-45fb-87f8-5ed1d36b1be9 · inbound
Teaching Models to Verbalize Reward Hacking in Chain-of-Thought Reasoning cites this paper.
Teaching Models to Verbalize Reward Hacking in Chain-of-Thought Reasoning Thought Crime: Backdoors and Emergent Misalignment in Reasoning Models
Reference 15
- Resolution
- unresolved
- no resolver link, observed 2026-08-06T22:03:52.409376Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 6b8956ab-b841-47cc-99cc-308f31ce3f3f · inbound
Emergent misalignment as prompt sensitivity: A research note cites this paper.
Emergent misalignment as prompt sensitivity: A research note Thought Crime: Backdoors and Emergent Misalignment in Reasoning Models
Reference 5
- Resolution
- unresolved
- no resolver link, observed 2026-08-06T19:53:58.483059Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation ee0e01b8-c67a-43fc-ab24-a981e4eea63c · inbound
Subliminal Learning: Language models transmit behavioral traits via hidden signals in data cites this paper.
Subliminal Learning: Language models transmit behavioral traits via hidden signals in data Thought Crime: Backdoors and Emergent Misalignment in Reasoning Models
Reference 10
- Resolution
- unresolved
- no resolver link, observed 2026-08-06T15:53:17.063185Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 890c0684-6695-4f36-94b4-7a6787d561d7 · inbound
School of Reward Hacks: Hacking harmless tasks generalizes to misaligned behavior in LLMs cites this paper.
School of Reward Hacks: Hacking harmless tasks generalizes to misaligned behavior in LLMs Thought Crime: Backdoors and Emergent Misalignment in Reasoning Models
Reference 9
- Resolution
- unresolved
- no resolver link, observed 2026-08-05T16:57:08.044929Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 5bab527c-48de-4f8f-8c7f-80fbcaab6a34 · inbound
A Comprehensive Survey on Trustworthiness in Reasoning with Large Language Models cites this paper.
A Comprehensive Survey on Trustworthiness in Reasoning with Large Language Models Thought Crime: Backdoors and Emergent Misalignment in Reasoning Models
Reference 166
- Resolution
- unresolved
- no resolver link, observed 2026-08-05T10:39:07.067391Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 5c11cecb-c789-4548-87a1-b9610b5641da · inbound
Metaphors are a Source of Cross-Domain Misalignment of Large Reasoning Models cites this paper.
Metaphors are a Source of Cross-Domain Misalignment of Large Reasoning Models Thought Crime: Backdoors and Emergent Misalignment in Reasoning Models
Reference 2025
- Resolution
- unresolved
- no resolver link, observed 2026-08-03T12:21:18.580617Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 033ca517-273f-4be4-bda1-c6d39d78ed7a · inbound
BLOCK-EM: Preventing Emergent Misalignment via Latent Blocking cites this paper.
BLOCK-EM: Preventing Emergent Misalignment via Latent Blocking Thought Crime: Backdoors and Emergent Misalignment in Reasoning Models
Reference 2
- Resolution
- verified exact
- arxiv_id, observed 2026-05-16T08:50:46.418277Z
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 32239e5d-5435-4055-9d1b-8e9c626b381f · inbound
Unreal Thinking: Chain-of-Thought Hijacking via Two-stage Backdoor cites this paper.
Unreal Thinking: Chain-of-Thought Hijacking via Two-stage Backdoor Thought Crime: Backdoors and Emergent Misalignment in Reasoning Models
Reference 2
- Resolution
- metadata mismatch
- arxiv_id, observed 2026-05-11T06:41:07.999061Z
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 a1baf52a-b31d-46d1-a0e2-8ed0fe3424cf · inbound
ATLAS: Constitution-Conditioned Latent Geometry and Redistribution Across Language Models and Neural Perturbation Data cites this paper.
ATLAS: Constitution-Conditioned Latent Geometry and Redistribution Across Language Models and Neural Perturbation Data Thought Crime: Backdoors and Emergent Misalignment in Reasoning Models
Reference 41
- Resolution
- metadata mismatch
- arxiv_id, observed 2026-05-10T05:56:10.988132Z
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 e8294ad3-4ed1-4298-a760-601673666884 · inbound
Do Prompt-Elicited Trajectories Reflect Training-Time Reward Hacking? A Systematic Study on Monitoring Training-Time Reward Hacking in Code Generation cites this paper.
Do Prompt-Elicited Trajectories Reflect Training-Time Reward Hacking? A Systematic Study on Monitoring Training-Time Reward Hacking in Code Generation Thought Crime: Backdoors and Emergent Misalignment in Reasoning Models
Reference 2
- Resolution
- unresolved
- no resolver link, observed 2026-08-04T05:25:40.918565Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 5ee4c659-72cb-4544-812e-5d20ef2861a5 · inbound
Overtrained, Not Misaligned cites this paper.
Overtrained, Not Misaligned Thought Crime: Backdoors and Emergent Misalignment in Reasoning Models
Reference 8
- Resolution
- metadata mismatch
- arxiv_id, observed 2026-05-13T06:47:26.224134Z
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 3cd281c0-af1a-4dd3-91c7-ab0af47f39e8 · 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 Thought Crime: Backdoors and Emergent Misalignment in Reasoning Models
Reference 3
- Resolution
- metadata mismatch
- arxiv_id, observed 2026-05-14T20:37:58.503133Z
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 4c0e3db3-6fef-4089-b964-cea12719b311 · inbound
Persona-Model Collapse in Emergent Misalignment cites this paper.
Persona-Model Collapse in Emergent Misalignment Thought Crime: Backdoors and Emergent Misalignment in Reasoning Models
Reference 6
- Resolution
- metadata mismatch
- arxiv_id, observed 2026-05-14T20:47:58.822019Z
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 f38426a2-731f-4044-9b65-41a557207f55 · inbound
Persona-Model Collapse in Emergent Misalignment cites this paper.
Persona-Model Collapse in Emergent Misalignment Thought Crime: Backdoors and Emergent Misalignment in Reasoning Models
Reference 6
- Resolution
- metadata mismatch
- arxiv_id, observed 2026-07-01T14:15:47.642591Z
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 8193a4bd-fac6-4ca5-b7ef-ccd190c8db08 · inbound
The Piggyback Hypothesis of Generalization: Explaining and Mitigating Emergent Misalignment cites this paper.
The Piggyback Hypothesis of Generalization: Explaining and Mitigating Emergent Misalignment Thought Crime: Backdoors and Emergent Misalignment in Reasoning Models
Reference 6
- Resolution
- metadata mismatch
- arxiv_id, observed 2026-07-02T13:06:59.188422Z
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 cd3152f2-aa7c-43e4-95ce-37711b397cef · inbound
The Piggyback Hypothesis of Generalization: Explaining and Mitigating Emergent Misalignment cites this paper.
The Piggyback Hypothesis of Generalization: Explaining and Mitigating Emergent Misalignment Thought Crime: Backdoors and Emergent Misalignment in Reasoning Models
Reference 6
- 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 f5fab375-44d5-46b2-abdb-e4b89ada1046 · inbound
Position: Anthropomorphic Misalignment Research Needs Stronger Evidence cites this paper.
Position: Anthropomorphic Misalignment Research Needs Stronger Evidence Thought Crime: Backdoors and Emergent Misalignment in Reasoning Models
Reference 46
- Resolution
- metadata mismatch
- arxiv_id, observed 2026-06-28T20:22:37.285169Z
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 8bfcf54f-461d-4bf3-837a-5c6819d12813 · inbound
Trait-space Monitoring for Emergent Misalignment During Supervised Finetuning cites this paper.
Trait-space Monitoring for Emergent Misalignment During Supervised Finetuning Thought Crime: Backdoors and Emergent Misalignment in Reasoning Models
Reference 27
- Resolution
- metadata mismatch
- arxiv_id, observed 2026-07-01T20:56:13.922566Z
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 75be82e5-1246-40cd-a2ad-affa056a1920 · inbound
Shared Latent Structures Enable Unified Backdoor Detection and Mitigation in LLMs cites this paper.
Shared Latent Structures Enable Unified Backdoor Detection and Mitigation in LLMs Thought Crime: Backdoors and Emergent Misalignment in Reasoning Models
Reference 59
- Resolution
- verified exact
- arxiv_id, observed 2026-07-02T20:47:23.496492Z
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 4642bcff-f6ef-4512-864a-a5b7db0726a2 · inbound
Activation Steering Induces Emergent Misalignment: A More Comprehensive Evaluation cites this paper.
Activation Steering Induces Emergent Misalignment: A More Comprehensive Evaluation Thought Crime: Backdoors and Emergent Misalignment in Reasoning Models
Reference 6
- Resolution
- metadata mismatch
- arxiv_id, observed 2026-07-02T22:57:26.134915Z
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 97d97696-98f6-44c2-b893-af795d8a5463 · 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 Thought Crime: Backdoors and Emergent Misalignment in Reasoning Models
Reference 14
- Resolution
- metadata mismatch
- arxiv_id, observed 2026-07-03T00:47:29.960037Z
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 d983ae8f-2988-4397-8180-1488fe484222 · inbound
Order Is Not Control cites this paper.
Order Is Not Control Thought Crime: Backdoors and Emergent Misalignment in Reasoning Models
Reference 83
- Resolution
- metadata mismatch
- arxiv_id, observed 2026-07-03T14:08:21.769365Z
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 d6eea68a-43c0-47fe-98b1-25fb842cd7f7 · inbound
Evil Spectra: How Optimisers can Amplify or Suppress Emergent Misalignment cites this paper.
Evil Spectra: How Optimisers can Amplify or Suppress Emergent Misalignment Thought Crime: Backdoors and Emergent Misalignment in Reasoning Models
Reference 2
- Resolution
- metadata mismatch
- arxiv_id, observed 2026-07-01T09:45:39.615487Z
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 be2deb8c-8c7c-4f76-a7f4-f662f7c7f0cf · inbound
An Emergent Mirage: Is Emergent Misalignment and Realignment Indeed a Robust Phenomenon? cites this paper.
An Emergent Mirage: Is Emergent Misalignment and Realignment Indeed a Robust Phenomenon? Thought Crime: Backdoors and Emergent Misalignment in Reasoning Models
Reference 31
- Resolution
- unresolved
- no resolver link, observed 2026-07-13T00:42:24.432562Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation acadf025-abc4-4f86-b10d-7c78223b4f00 · inbound
Innocuous-Seeming Data, Latent Ideology: Ideological Generalisation in Finetuned LLMs cites this paper.
Innocuous-Seeming Data, Latent Ideology: Ideological Generalisation in Finetuned LLMs Thought Crime: Backdoors and Emergent Misalignment in Reasoning Models
Reference 4
- Resolution
- unresolved
- no resolver link, observed 2026-08-02T00:51:17.273544Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 583ea985-3be6-4535-8d01-aa28e65e5f06 · inbound
Emergent Misalignment Recruits a Pre-existing Persona Subspace cites this paper.
Emergent Misalignment Recruits a Pre-existing Persona Subspace Thought Crime: Backdoors and Emergent Misalignment in Reasoning Models
Reference 76
- Resolution
- unresolved
- no resolver link, observed 2026-08-01T07:46:08.952914Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 015722c0-1be0-41e2-b303-de738ecd24e9 · inbound
ToxScreen: Detecting Whether an LLM Has Been Poisoned cites this paper.
ToxScreen: Detecting Whether an LLM Has Been Poisoned Thought Crime: Backdoors and Emergent Misalignment in Reasoning Models
Reference 46
- Resolution
- unresolved
- no resolver link, observed 2026-07-30T19:18:08.194013Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation e45156b7-45ed-4fdc-a27a-a124e6dcc3dd · inbound
Risky Business: Measuring The Faithfulness-Safety Tension cites this paper.
Risky Business: Measuring The Faithfulness-Safety Tension Thought Crime: Backdoors and Emergent Misalignment in Reasoning Models
Reference 7
- Resolution
- unresolved
- no resolver link, observed 2026-08-05T13:40:54.343606Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.