Paper Citation Record · LEDGER

Manipulation Attacks by Misaligned AI: Risk Analysis and Safety Case Framework

As of 11 August 2026, this Paper Citation Record lists 37 of 37 outbound references and 1 inbound Pith citation observation for arXiv:2507.12872.

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

pith.paper-citation-record.v1
2507.12872 v1

Coverage vector

measured 37 of 37 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-06T16:39:38.745141Z

measured 38 of 38 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-11T06:34:44.6726+00:00

measured 1 of 1 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-07-01T05:40:54.002702Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-07-01T10:15:44.642321Z

Reference resolution

37 of 37 outbound references displayed

verified exact1
verified fuzzy2
unresolved32
parse uncertain0
malformed identifier1
metadata mismatch1

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 3c8a5245-5b7a-4bec-a5f1-ef815bdc27a2 · outbound

This paper cites Towards evaluations-based safety cases for AI scheming.

Manipulation Attacks by Misaligned AI: Risk Analysis and Safety Case Framework Towards evaluations-based safety cases for AI scheming

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-06T16:39:33.388263Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3dd1535e-65ea-4ea5-b03b-12a6419c341d · outbound

This paper cites Sabotage Evaluations for Frontier Models.

Manipulation Attacks by Misaligned AI: Risk Analysis and Safety Case Framework Sabotage Evaluations for Frontier Models

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-06T16:39:33.510287Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5daba2b2-56c1-428a-9a14-c27588fa87d8 · outbound

This paper cites RepliBench: Evaluating the Autonomous Replication Capabilities of Language Model Agents.

Manipulation Attacks by Misaligned AI: Risk Analysis and Safety Case Framework RepliBench: Evaluating the Autonomous Replication Capabilities of Language Model Agents

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-06T16:39:33.918076Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a4c7f23e-f1b2-4122-a1ef-f42783b790ab · outbound

This paper cites Safety cases for frontier AI.

Manipulation Attacks by Misaligned AI: Risk Analysis and Safety Case Framework Safety cases for frontier AI

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-06T16:39:34.221645Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4fd43903-ab84-4a90-8136-6b47cfd3699f · outbound

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

Manipulation Attacks by Misaligned AI: Risk Analysis and Safety Case Framework Discovering Latent Knowledge in Language Models Without Supervision

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-06T16:39:34.368752Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation eb126926-4866-4039-ba8a-20e9b42e8c9c · outbound

This paper cites doi: 10.1126/science.

Manipulation Attacks by Misaligned AI: Risk Analysis and Safety Case Framework doi: 10.1126/science

Reference 10

Resolution: malformed identifier; no resolver link, observed 2026-08-06T16:39:34.536021Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2f5945e5-cfdb-47ac-96b1-87d871d8d1b3 · outbound

This paper cites Safety case template for frontier AI: A cyber inability argument.

Manipulation Attacks by Misaligned AI: Risk Analysis and Safety Case Framework Safety case template for frontier AI: A cyber inability argument

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-06T16:39:34.797703Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 092ed59a-3920-4f54-a142-9417237a6709 · outbound

This paper cites Alignment faking in large language models.

Manipulation Attacks by Misaligned AI: Risk Analysis and Safety Case Framework Alignment faking in large language models

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-06T16:39:34.936205Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d8251340-9940-4529-9b26-d5f2fa42defb · outbound

This paper cites Evaluating Large Language Models' Capability to Launch Fully Automated Spear Phishing Campaigns: Validated on Human Subjects.

Manipulation Attacks by Misaligned AI: Risk Analysis and Safety Case Framework Evaluating Large Language Models' Capability to Launch Fully Automated Spear Phishing Campaigns: Validated on Human Subjects

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-06T16:39:35.146041Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f4514e2c-d7c9-4557-878f-44d85e69c1a3 · outbound

This paper cites An Overview of Catastrophic AI Risks.

Manipulation Attacks by Misaligned AI: Risk Analysis and Safety Case Framework An Overview of Catastrophic AI Risks

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-06T16:39:35.301994Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 40ebb534-918c-4ad6-a927-557843c99c51 · outbound

This paper cites Facade: High-Precision Insider Threat Detection Using Deep Contextual Anomaly Detection.

Manipulation Attacks by Misaligned AI: Risk Analysis and Safety Case Framework Facade: High-Precision Insider Threat Detection Using Deep Contextual Anomaly Detection

Reference 17

Resolution: metadata mismatch; local_arxiv, observed 2026-08-06T16:39:39.585842Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 35a9ba68-1cf3-48a7-a135-5e6f71fe3865 · outbound

This paper cites A sketch of an AI control safety case.

Manipulation Attacks by Misaligned AI: Risk Analysis and Safety Case Framework A sketch of an AI control safety case

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-06T16:39:35.743325Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ca512bf0-6067-4e17-8342-e8b8d5e4dcdc · outbound

This paper cites Measuring AI Ability to Complete Long Software Tasks.

Manipulation Attacks by Misaligned AI: Risk Analysis and Safety Case Framework Measuring AI Ability to Complete Long Software Tasks

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-06T16:39:35.884820Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 82d8d8d1-f84e-4a27-b3c1-ece7c72ba992 · outbound

This paper cites Subversion Strategy Eval: Can language models statelessly strategize to subvert control protocols?.

Manipulation Attacks by Misaligned AI: Risk Analysis and Safety Case Framework Subversion Strategy Eval: Can language models statelessly strategize to subvert control protocols?

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-06T16:39:36.071018Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f295ef85-315e-4427-ad9d-383551dc10ce · outbound

This paper cites arXiv:2410.03768.

Manipulation Attacks by Misaligned AI: Risk Analysis and Safety Case Framework arXiv:2410.03768

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-06T16:39:36.234981Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ab9e34a3-8724-443e-82f5-200cdb825ffd · outbound

This paper cites DeepStack: Expert-Level Artificial Intelligence in No-Limit Poker.

Manipulation Attacks by Misaligned AI: Risk Analysis and Safety Case Framework DeepStack: Expert-Level Artificial Intelligence in No-Limit Poker

Reference 22

Resolution: verified exact; local_arxiv, observed 2026-08-06T16:39:39.324600Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 4a7314a0-47fe-4c6f-85f8-3eaf24427fd8 · outbound

This paper cites AgentMisalignment: Measuring the Propensity for Misaligned Behaviour in LLM-Based Agents.

Manipulation Attacks by Misaligned AI: Risk Analysis and Safety Case Framework AgentMisalignment: Measuring the Propensity for Misaligned Behaviour in LLM-Based Agents

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-06T16:39:36.526571Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d196b84c-0b27-4bf2-a575-2e893d947be3 · outbound

This paper cites Large Language Models Often Know When They Are Being Evaluated.

Manipulation Attacks by Misaligned AI: Risk Analysis and Safety Case Framework Large Language Models Often Know When They Are Being Evaluated

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-06T16:39:36.667793Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7579f224-aec7-4c7a-b527-bf7b68bc9725 · outbound

This paper cites The Alignment Problem from a Deep Learning Perspective.

Manipulation Attacks by Misaligned AI: Risk Analysis and Safety Case Framework The Alignment Problem from a Deep Learning Perspective

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-06T16:39:36.793291Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4e3323b6-488b-486c-a837-1b926db7d428 · outbound

This paper cites Linear Probe Penalties Reduce LLM Sycophancy.

Manipulation Attacks by Misaligned AI: Risk Analysis and Safety Case Framework Linear Probe Penalties Reduce LLM Sycophancy

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-06T16:39:36.959394Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e107757b-5e07-42fd-a604-df71d28c0cf0 · outbound

This paper cites Evaluating Frontier Models for Dangerous Capabilities.

Manipulation Attacks by Misaligned AI: Risk Analysis and Safety Case Framework Evaluating Frontier Models for Dangerous Capabilities

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-06T16:39:37.129859Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6f9fe1ac-4046-4eec-97e9-b50e3d3713ca · outbound

This paper cites On the Conversational Persuasiveness of Large Language Models: A Randomized Controlled Trial.

Manipulation Attacks by Misaligned AI: Risk Analysis and Safety Case Framework On the Conversational Persuasiveness of Large Language Models: A Randomized Controlled Trial

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-06T16:39:37.344120Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cbe3c3ce-fde7-47b6-9ef2-b51c5f46b7d1 · outbound

This paper cites Large Language Models can Strategically Deceive their Users when Put Under Pressure.

Manipulation Attacks by Misaligned AI: Risk Analysis and Safety Case Framework Large Language Models can Strategically Deceive their Users when Put Under Pressure

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-06T16:39:37.499516Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 254ec2be-34e0-49e3-abd5-1b93ff8b788c · outbound

This paper cites Melanie Sclar, Jane Yu, Maryam Fazel-Zarandi, Yulia Tsvetkov, Yonatan Bisk, Yejin Choi, and Asli Celikyilmaz.

Manipulation Attacks by Misaligned AI: Risk Analysis and Safety Case Framework Melanie Sclar, Jane Yu, Maryam Fazel-Zarandi, Yulia Tsvetkov, Yonatan Bisk, Yejin Choi, and Asli Celikyilmaz

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-06T16:39:37.594525Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8217a998-f671-41cf-85db-56b1dbc779ac · outbound

This paper cites Explore Theory of Mind: Program-guided adversarial data generation for theory of mind reasoning.

Manipulation Attacks by Misaligned AI: Risk Analysis and Safety Case Framework Explore Theory of Mind: Program-guided adversarial data generation for theory of mind reasoning

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-06T16:39:37.772633Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 06a423fb-b5be-4a4d-91f9-b1f054111d87 · outbound

This paper cites Cameron Tice, Philipp Alexander Kreer, Nathan Helm-Burger, Prithviraj Singh Shahani, Fedor Ryzhenkov, Jacob Haimes, Felix Hofstätter, and Teun van der Weij.

Manipulation Attacks by Misaligned AI: Risk Analysis and Safety Case Framework Cameron Tice, Philipp Alexander Kreer, Nathan Helm-Burger, Prithviraj Singh Shahani, Fedor Ryzhenkov, Jacob Haimes, Felix Hofstätter, and Teun van der Weij

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-06T16:39:37.919794Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f6142e7d-acb8-4907-bdbb-ae1fba6c8cdd · outbound

This paper cites Oriol Vinyals, Igor Babuschkin, Wojciech M.

Manipulation Attacks by Misaligned AI: Risk Analysis and Safety Case Framework Oriol Vinyals, Igor Babuschkin, Wojciech M

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-06T16:39:38.000260Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0c2aa3db-74cd-4152-8fa1-dfcef47d83d0 · outbound

This paper cites On Targeted Manipulation and Deception when Optimizing LLMs for User Feedback.

Manipulation Attacks by Misaligned AI: Risk Analysis and Safety Case Framework On Targeted Manipulation and Deception when Optimizing LLMs for User Feedback

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-06T16:39:38.443628Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 88aa5c2d-366c-477e-8608-eb2a8a0693c1 · outbound

This paper cites WebShop: Towards Scalable Real-World Web Interaction with Grounded Language Agents.

Manipulation Attacks by Misaligned AI: Risk Analysis and Safety Case Framework WebShop: Towards Scalable Real-World Web Interaction with Grounded Language Agents

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-06T16:39:38.613609Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d92ccab7-940a-463d-a334-18a3d93c4c69 · outbound

This paper cites trusted inquiry.

Manipulation Attacks by Misaligned AI: Risk Analysis and Safety Case Framework trusted inquiry

Reference 39

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T16:39:39.865103Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation a6467fe5-0cce-4521-b018-c2720d3a5487 · outbound

This paper cites doi: 10.1017/S0140525X00076512.

Manipulation Attacks by Misaligned AI: Risk Analysis and Safety Case Framework doi: 10.1017/S0140525X00076512

Reference 1978

Resolution: unresolved; no resolver link, observed 2026-08-06T16:39:37.217624Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 54ff7abf-df0b-4ce8-84da-b5785de4165c · outbound

This paper cites doi: 10.1038/s41586-019-1724-z.

Manipulation Attacks by Misaligned AI: Risk Analysis and Safety Case Framework doi: 10.1038/s41586-019-1724-z

Reference 2019

Resolution: unresolved; no resolver link, observed 2026-08-06T16:39:38.187897Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 45ba4898-9e81-40d1-8001-4cef1191468b · outbound

This paper cites Risks from Learned Optimization in Advanced Machine Learning Systems.

Manipulation Attacks by Misaligned AI: Risk Analysis and Safety Case Framework Risks from Learned Optimization in Advanced Machine Learning Systems

Reference 2021

Resolution: unresolved; no resolver link, observed 2026-08-06T16:39:35.476815Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9dbc06b4-a131-4486-9e6b-75de0ea0bbee · outbound

This paper cites Emergent Abilities of Large Language Models.

Manipulation Attacks by Misaligned AI: Risk Analysis and Safety Case Framework Emergent Abilities of Large Language Models

Reference 2022

Resolution: unresolved; no resolver link, observed 2026-08-06T16:39:38.354084Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f5b9cf08-8480-49e9-9190-96519907496a · outbound

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

Manipulation Attacks by Misaligned AI: Risk Analysis and Safety Case Framework Taken out of context: On measuring situational awareness in LLMs

Reference 2023

Resolution: unresolved; no resolver link, observed 2026-08-06T16:39:33.641786Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ed0ebd9f-1d21-47c4-b787-933009b79d1d · outbound

This paper cites Anthropic.

Manipulation Attacks by Misaligned AI: Risk Analysis and Safety Case Framework Anthropic

Reference 2024

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T16:39:40.048618Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 86c9ba4b-f572-46cf-8cae-43602dff42c7 · outbound

This paper cites Ctrl-Z: Controlling AI Agents via Resampling.

Manipulation Attacks by Misaligned AI: Risk Analysis and Safety Case Framework Ctrl-Z: Controlling AI Agents via Resampling

Reference 2025

Resolution: unresolved; no resolver link, observed 2026-08-06T16:39:33.772218Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation 5afbc83d-aa33-4eae-bf22-40991007b544 · inbound

Theory of Mind and Persuasion Beyond Conversation: Assessing the Capacity of LLMs to Induce Belief States via Planning and Action cites this paper.

Theory of Mind and Persuasion Beyond Conversation: Assessing the Capacity of LLMs to Induce Belief States via Planning and Action Manipulation Attacks by Misaligned AI: Risk Analysis and Safety Case Framework

Reference 70

Resolution: verified exact; arxiv_id, observed 2026-07-01T10:15:44.643863Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.