Safety Features for a Centralised AGI Project | Paper Citation Record

Observation 85191fc1-deaa-4e3a-a158-f442dadd6c88 · outbound

This paper cites OpenAI o3 and o3-mini—12 Days of OpenAI: Day 12,.

Safety Features for a Centralised AGI Project OpenAI o3 and o3-mini—12 Days of OpenAI: Day 12,

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-07T00:23:49.779205Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d42f225b-9179-474a-aaa2-eeae4df1131b · outbound

This paper cites Can AI Scaling Continue Through 2030?.

Safety Features for a Centralised AGI Project Can AI Scaling Continue Through 2030?

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-07T00:23:49.888071Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 57bb5289-ba21-4d32-9a68-0619a06cd9d2 · outbound

This paper cites Statement on AI Risk | CAIS,.

Safety Features for a Centralised AGI Project Statement on AI Risk | CAIS,

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-07T00:23:50.040986Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e5ea1560-13d3-4e24-8b2c-d8443786ccb1 · outbound

This paper cites Safe, Secure, and Trustworthy Development and Use of Artificial Intelligence,.

Safety Features for a Centralised AGI Project Safe, Secure, and Trustworthy Development and Use of Artificial Intelligence,

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-07T00:23:50.202523Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 14b708bc-3b04-4f48-8177-a11297b5833a · outbound

This paper cites Removing Barriers to American Leadership in Artificial Intelligence,.

Safety Features for a Centralised AGI Project Removing Barriers to American Leadership in Artificial Intelligence,

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-07T00:23:50.387100Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7e5df33f-677f-409b-8ee0-767ce924ed8e · outbound

This paper cites Securing AI Model Weights: Preventing Theft and Misuse of Frontier Models,.

Safety Features for a Centralised AGI Project Securing AI Model Weights: Preventing Theft and Misuse of Frontier Models,

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-07T00:23:50.559832Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c203fc13-4483-4206-9414-686f5726a1df · outbound

This paper cites 2024 REPORT TO CONGRESS of the U.S.-CHINA ECONOMIC AND SECURITY REVIEW COMMISSION,.

Safety Features for a Centralised AGI Project 2024 REPORT TO CONGRESS of the U.S.-CHINA ECONOMIC AND SECURITY REVIEW COMMISSION,

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-07T00:23:50.705616Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cb8af4c5-873a-49a5-93f7-e6c7c525611d · outbound

This paper cites Soft Nationalization: How the US Government Will Control AI Labs | Convergence Analysis,.

Safety Features for a Centralised AGI Project Soft Nationalization: How the US Government Will Control AI Labs | Convergence Analysis,

Reference 8

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:24:13.555827Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 0325e4d4-85ab-42ce-82ee-cf8f450b00ea · outbound

This paper cites Core Views on AI Safety: When, Why, What, and How,.

Safety Features for a Centralised AGI Project Core Views on AI Safety: When, Why, What, and How,

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:24:13.545489Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 85b45cf5-1005-432b-b940-b2ec91a42a30 · outbound

This paper cites How hard is AI safety?.

Safety Features for a Centralised AGI Project How hard is AI safety?

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:24:13.535924Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 7d433f92-f7f2-4d7a-ad5b-1f647bc356da · outbound

This paper cites Defining and Characterizing Reward Hacking.

Safety Features for a Centralised AGI Project Defining and Characterizing Reward Hacking

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-07T00:23:51.691004Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 70c9af57-e56a-4e6c-9703-e3cbd36e3cc6 · outbound

This paper cites AI Deception: A Survey of Examples, Risks, and Potential Solutions.

Safety Features for a Centralised AGI Project AI Deception: A Survey of Examples, Risks, and Potential Solutions

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-07T00:23:51.822116Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c657e00a-ac0d-4f38-808f-ae0c5db99eb4 · outbound

This paper cites EasyJailbreak: A Unified Framework for Jailbreaking Large Language Models.

Safety Features for a Centralised AGI Project EasyJailbreak: A Unified Framework for Jailbreaking Large Language Models

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-07T00:23:51.967912Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a790307d-6fb0-4344-a1cc-f6c804ccfda4 · outbound

This paper cites Deterrence with Mutual Assured AI Malfunction (MAIM) — Chapter 4 of Superintelligence Strategy,.

Safety Features for a Centralised AGI Project Deterrence with Mutual Assured AI Malfunction (MAIM) — Chapter 4 of Superintelligence Strategy,

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:24:13.525948Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 3a881f32-8bf4-41c9-a229-e530268d1895 · outbound

This paper cites AI Behind Closed Doors: a Primer on The Governance of Internal Deployment.

Safety Features for a Centralised AGI Project AI Behind Closed Doors: a Primer on The Governance of Internal Deployment

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-07T00:23:52.252350Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7f976df5-99a5-4977-a357-ff7d0673831f · outbound

This paper cites Evaluating frontier AI R&D capabilities of language model agents against human experts,.

Safety Features for a Centralised AGI Project Evaluating frontier AI R&D capabilities of language model agents against human experts,

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:24:13.515117Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 1fa9426b-d5dc-471f-b042-7e7390342fc8 · outbound

This paper cites Measuring the Persuasiveness of Language Models,.

Safety Features for a Centralised AGI Project Measuring the Persuasiveness of Language Models,

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:24:13.505896Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation fbd6e2f6-cd17-49aa-afdd-84313fa56ca1 · outbound

This paper cites Emergent Abilities of Large Language Models.

Safety Features for a Centralised AGI Project Emergent Abilities of Large Language Models

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-07T00:23:52.716733Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d1e20a05-09b9-4956-ad81-6147cd625382 · outbound

This paper cites Training Compute Thresholds — Features and Functions in AI Regulation,.

Safety Features for a Centralised AGI Project Training Compute Thresholds — Features and Functions in AI Regulation,

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:24:13.496166Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 073c236a-3d1c-49e0-b067-939789493bf8 · outbound

This paper cites Will there be a discontinuity in AI capabilities?.

Safety Features for a Centralised AGI Project Will there be a discontinuity in AI capabilities?

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:24:13.486045Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation bbcd5e13-ca22-4134-8da1-4331cae4feb5 · outbound

This paper cites Response to BIS AI Reporting Requirements RFC — MIRI Technical Governance Team,.

Safety Features for a Centralised AGI Project Response to BIS AI Reporting Requirements RFC — MIRI Technical Governance Team,

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:24:13.475607Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 6f925f82-cd51-4232-9eee-76711c336b0d · outbound

This paper cites AI Risk Management Framework,.

Safety Features for a Centralised AGI Project AI Risk Management Framework,

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:24:13.463944Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 9258fb9b-6112-4dc6-a954-b3f30e77d035 · outbound

This paper cites Common Elements of Frontier AI Safety Policies,.

Safety Features for a Centralised AGI Project Common Elements of Frontier AI Safety Policies,

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:24:13.453015Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation cb7ebd39-ab43-434a-ba16-2fba45762aca · outbound

This paper cites Announcing our updated Responsible Scaling Policy,.

Safety Features for a Centralised AGI Project Announcing our updated Responsible Scaling Policy,

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:24:13.441700Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 1fea7540-b38b-42c2-9bcd-f120d21b3b0f · outbound

This paper cites xAI Risk Management Framework (Draft),.

Safety Features for a Centralised AGI Project xAI Risk Management Framework (Draft),

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:24:13.430179Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation d0184ab0-3f20-450a-8626-78b0012e621e · outbound

This paper cites Intolerable Risk Threshold Recommendations for Artificial Intelligence,.

Safety Features for a Centralised AGI Project Intolerable Risk Threshold Recommendations for Artificial Intelligence,

Reference 26

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:24:13.418589Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation bbd05dd0-bc06-4192-857f-d53611d7f43a · outbound

This paper cites 5 FAH-2 H-430 HANDLING SYMBOLS,.

Safety Features for a Centralised AGI Project 5 FAH-2 H-430 HANDLING SYMBOLS,

Reference 27

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:24:13.408500Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation de2871fb-48d6-44b1-ae8c-75043bebb95a · outbound

This paper cites Notes on the Critic System,.

Safety Features for a Centralised AGI Project Notes on the Critic System,

Reference 28

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:24:13.398508Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation fb08048f-9f1b-418d-8df2-5304b5b7da6d · outbound

This paper cites Handling of Critical (CRITIC) Information,.

Safety Features for a Centralised AGI Project Handling of Critical (CRITIC) Information,

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:24:13.387586Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 24b850c4-4d23-4fe2-8ec9-5d8012fcf1ee · outbound

This paper cites 2 FAM 070 DISSENT CHANNEL,.

Safety Features for a Centralised AGI Project 2 FAM 070 DISSENT CHANNEL,

Reference 30

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:24:13.377731Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation cc805a46-0f99-42e5-9520-2e6496fd408a · outbound

This paper cites NRC DIFFERING PROFESSIONAL OPINION PROGRAM,.

Safety Features for a Centralised AGI Project NRC DIFFERING PROFESSIONAL OPINION PROGRAM,

Reference 31

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:24:13.366038Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation acfb59c9-c19e-41f1-bffa-fbc551920c68 · outbound

This paper cites DOE Differing Professional Opinions,.

Safety Features for a Centralised AGI Project DOE Differing Professional Opinions,

Reference 32

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:24:13.356958Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 333bc006-2bfb-4bcd-9054-33276105d1e5 · outbound

This paper cites Stifling Dissent,.

Safety Features for a Centralised AGI Project Stifling Dissent,

Reference 33

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:24:13.346989Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 154f2bad-51e0-4e01-9e44-864a9273addf · outbound

This paper cites Why do Experts Disagree on Existential Risk and P(doom)? A Survey of AI Experts.

Safety Features for a Centralised AGI Project Why do Experts Disagree on Existential Risk and P(doom)? A Survey of AI Experts

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-07T00:23:54.862503Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 98f59fdb-0fd2-4cff-a30e-bbea84e5c37d · outbound

This paper cites AI Whistleblowers,.

Safety Features for a Centralised AGI Project AI Whistleblowers,

Reference 35

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:24:13.337453Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 56091f73-d18f-42e3-9c42-4ba3cb5704fe · outbound

This paper cites Our updated Preparedness Framework,.

Safety Features for a Centralised AGI Project Our updated Preparedness Framework,

Reference 36

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:24:13.328097Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 9e95a52c-8770-4d6c-b2e1-b12140ee44e9 · outbound

This paper cites A Sketch of Potential Tripwire Capabili- ties for AI,.

Safety Features for a Centralised AGI Project A Sketch of Potential Tripwire Capabili- ties for AI,

Reference 37

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:24:13.317587Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 538257ac-4aff-46e7-84a1-05d6941ec937 · outbound

This paper cites Risk Thresholds for Frontier AI | GovAI,.

Safety Features for a Centralised AGI Project Risk Thresholds for Frontier AI | GovAI,

Reference 38

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:24:13.308012Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 89841e72-d2f0-4fee-a1fc-37000d6e8702 · outbound

This paper cites AI models can be dangerous before public deployment,.

Safety Features for a Centralised AGI Project AI models can be dangerous before public deployment,

Reference 39

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:24:13.297301Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 2f274637-0e84-4ecf-8c00-aacf322a8b58 · outbound

This paper cites The Effects of Reward Misspecification: Mapping and Mitigating Misaligned Models.

Safety Features for a Centralised AGI Project The Effects of Reward Misspecification: Mapping and Mitigating Misaligned Models

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-07T00:23:55.629899Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a0db4843-088f-4a35-bb1b-a0df4e4128de · outbound

This paper cites Towards Understanding Sycophancy in Language Models.

Safety Features for a Centralised AGI Project Towards Understanding Sycophancy in Language Models

Reference 41

Resolution: unresolved; no resolver link, observed 2026-08-07T00:23:55.651236Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation df9505ac-27cf-4577-a02c-82c20ebe751f · outbound

This paper cites Andon - Toyota Production System guide,.

Safety Features for a Centralised AGI Project Andon - Toyota Production System guide,

Reference 42

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:24:13.287304Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation dec610a7-028d-42a0-85c8-ff36c2ab6029 · outbound

This paper cites Stop Work Authority: How It Works,.

Safety Features for a Centralised AGI Project Stop Work Authority: How It Works,

Reference 43

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:24:13.277861Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 42b4af8e-63a1-408a-bf44-ef05e3fa2117 · outbound

This paper cites Whirlpool Corp. v. Marshall, 445 U.S. 1 (1980),.

Safety Features for a Centralised AGI Project Whirlpool Corp. v. Marshall, 445 U.S. 1 (1980),

Reference 44

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:24:13.267296Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 72b96168-364d-4a09-9fb4-584f657cd588 · outbound

This paper cites OSH Act of 1970,.

Safety Features for a Centralised AGI Project OSH Act of 1970,

Reference 45

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:24:13.257699Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 1c0bd8ec-8fb5-4055-9d01-2043dc76296b · outbound

This paper cites Racing to the precipice: a model of artificial intelligence development,.

Safety Features for a Centralised AGI Project Racing to the precipice: a model of artificial intelligence development,

Reference 46

Resolution: unresolved; no resolver link, observed 2026-08-07T00:23:56.025419Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 48250677-93fe-4649-9ae7-99e51a99c4c1 · outbound

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

Safety Features for a Centralised AGI Project Me, Myself, and AI: The Situational Awareness Dataset (SAD) for LLMs

Reference 47

Resolution: unresolved; no resolver link, observed 2026-08-07T00:23:56.096143Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2f37d2a0-4074-4d5a-a963-58489810bcea · outbound

This paper cites AI Sandbagging: Language Models can Strategically Underperform on Evaluations.

Safety Features for a Centralised AGI Project AI Sandbagging: Language Models can Strategically Underperform on Evaluations

Reference 48

Resolution: unresolved; no resolver link, observed 2026-08-07T00:23:56.210518Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6f61c2ae-7c1c-4b65-8f9d-3a6bc14489da · outbound

This paper cites Alignment faking in large language models,.

Safety Features for a Centralised AGI Project Alignment faking in large language models,

Reference 49

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:24:13.248343Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 8ced903e-e619-4101-910d-b0988cda0632 · outbound

This paper cites Safety Goals for Nuclear Power Plant Operation,.

Safety Features for a Centralised AGI Project Safety Goals for Nuclear Power Plant Operation,

Reference 50

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:24:13.236527Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 000b39ae-9633-4864-983c-a2e7566c430b · outbound

This paper cites Affirmative safety: An approach to risk management for high-risk AI.

Safety Features for a Centralised AGI Project Affirmative safety: An approach to risk management for high-risk AI

Reference 51

Resolution: verified exact; local_arxiv, observed 2026-08-07T00:24:12.668725Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 90f5694d-6f12-44af-bc32-0d2044d50156 · outbound

This paper cites Towards A Rigorous Science of Interpretable Machine Learning.

Safety Features for a Centralised AGI Project Towards A Rigorous Science of Interpretable Machine Learning

Reference 52

Resolution: unresolved; no resolver link, observed 2026-08-07T00:23:56.505849Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation aace7026-09b4-4266-b637-a05dc57e6a09 · outbound

This paper cites Provably safe systems: the only path to controllable AGI.

Safety Features for a Centralised AGI Project Provably safe systems: the only path to controllable AGI

Reference 53

Resolution: unresolved; no resolver link, observed 2026-08-07T00:23:56.581446Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cee5a075-b6c5-4832-8497-42f5f74d58de · outbound

This paper cites Backgrounder on Emergency Preparedness at Nuclear Power Plants,.

Safety Features for a Centralised AGI Project Backgrounder on Emergency Preparedness at Nuclear Power Plants,

Reference 54

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:24:13.226434Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 1f35a8e9-99ce-41f4-ae2a-c010cef36469 · outbound

This paper cites Safety cases at AISI | AISI Work,.

Safety Features for a Centralised AGI Project Safety cases at AISI | AISI Work,

Reference 55

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:24:13.216321Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 9753e7c4-521f-48ff-af57-5239f2992fe3 · outbound

This paper cites National Defense Authorization Act for Fiscal Year 1989,.

Safety Features for a Centralised AGI Project National Defense Authorization Act for Fiscal Year 1989,

Reference 56

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:24:13.205671Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation eb1494f5-83b2-4801-a2eb-079abec103a3 · outbound

This paper cites 42 U.S. Code § 5841 - Establishment and transfers,.

Safety Features for a Centralised AGI Project 42 U.S. Code § 5841 - Establishment and transfers,

Reference 57

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:24:13.195604Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 62bf8fd6-47ee-49aa-8219-8525cb34bd6e · outbound

This paper cites Survey of 2,778 AI authors: six parts in pictures,.

Safety Features for a Centralised AGI Project Survey of 2,778 AI authors: six parts in pictures,

Reference 58

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:24:13.182842Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation d77e806e-d8c2-4ff1-a8d3-13ca1acbb9e0 · outbound

This paper cites "Existential risk from AI.

Safety Features for a Centralised AGI Project "Existential risk from AI

Reference 59

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:24:13.171158Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 3848712d-9374-4ca7-a8b6-35823bfe6d7f · outbound

This paper cites Anthropic’s Recommendations to OSTP for the U.S. AI Action Plan,.

Safety Features for a Centralised AGI Project Anthropic’s Recommendations to OSTP for the U.S. AI Action Plan,

Reference 60

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:24:13.158701Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 527e113a-8edf-49db-86e1-633d574d1cf7 · outbound

This paper cites Tweet by @nabla_theta,.

Safety Features for a Centralised AGI Project Tweet by @nabla_theta,

Reference 61

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:24:13.144118Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 0dde534e-26c3-4c52-85a7-fe1779ffaca7 · outbound

This paper cites AI-Enabled Coups: How a Small Group Could Use AI to Seize Power,.

Safety Features for a Centralised AGI Project AI-Enabled Coups: How a Small Group Could Use AI to Seize Power,

Reference 62

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:24:13.129769Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 7abd0525-37d4-4a72-a9ef-ee3248162086 · outbound

This paper cites New Survey: Broad Expert Consensus for Many AGI Safety and Governance Practices | GovAI,.

Safety Features for a Centralised AGI Project New Survey: Broad Expert Consensus for Many AGI Safety and Governance Practices | GovAI,

Reference 63

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:24:13.118359Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation b13ae9ca-242a-42f6-943b-d4221ed44e14 · outbound

This paper cites Inspector General Act of 1978,.

Safety Features for a Centralised AGI Project Inspector General Act of 1978,

Reference 64

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:24:13.107765Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 6036c9c6-baa3-4fb6-8f5f-93a0b1111fa9 · outbound

This paper cites Operation Warp Speed: Accelerated COVID-19 Vaccine Development Status and Efforts to Address Manufacturing Challenges | U.S. GAO,.

Safety Features for a Centralised AGI Project Operation Warp Speed: Accelerated COVID-19 Vaccine Development Status and Efforts to Address Manufacturing Challenges | U.S. GAO,

Reference 65

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:24:13.095811Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 188d1114-3d9d-44e1-8dfb-584a8a8353a4 · outbound

This paper cites Update on ARC’s recent eval efforts,.

Safety Features for a Centralised AGI Project Update on ARC’s recent eval efforts,

Reference 66

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:24:13.084220Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 39781aeb-fb16-4d68-9c2d-a58f52edbe58 · outbound

This paper cites Introducing Alignment Stress-Testing at Anthropic,.

Safety Features for a Centralised AGI Project Introducing Alignment Stress-Testing at Anthropic,

Reference 67

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:24:13.073676Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 670b6f02-5a49-46fc-b1e3-4260b2acc2ce · outbound

This paper cites Distribution Shifts and The Importance of AI Safety,.

Safety Features for a Centralised AGI Project Distribution Shifts and The Importance of AI Safety,

Reference 68

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:24:13.063118Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 46709802-fda4-4793-9b92-abe0b61ac20c · outbound

This paper cites Meta-level adversarial evaluation of oversight techniques might allow robust measurement of their adequacy,.

Safety Features for a Centralised AGI Project Meta-level adversarial evaluation of oversight techniques might allow robust measurement of their adequacy,

Reference 69

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:24:13.048197Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 6eccd925-42e2-475e-986c-ef9c346472cf · outbound

This paper cites Organizational Arrangements for Risk Assessment,.

Safety Features for a Centralised AGI Project Organizational Arrangements for Risk Assessment,

Reference 70

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:24:13.033981Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation f7f1726e-8b04-4361-b0d2-3505fd9f542f · outbound

This paper cites Working together to face humanity’s greatest threats: Introduction to The Future of Research on Catastrophic and Existential Risk.

Safety Features for a Centralised AGI Project Working together to face humanity’s greatest threats: Introduction to The Future of Research on Catastrophic and Existential Risk

Reference 71

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:24:13.022543Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation e10c023f-0b59-478d-8c58-553b6c2796df · outbound

This paper cites Existential Risk Prevention as a Global Priority,.

Safety Features for a Centralised AGI Project Existential Risk Prevention as a Global Priority,

Reference 72

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:24:13.010063Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 28b02dfd-0b29-4169-9a1b-4b3edef1b17c · outbound

This paper cites Roots of Disagreement on AI Risk: Exploring the Potential and Pitfalls of Adversarial Collaboration,.

Safety Features for a Centralised AGI Project Roots of Disagreement on AI Risk: Exploring the Potential and Pitfalls of Adversarial Collaboration,

Reference 73

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:24:12.992314Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation f17fd436-ed6a-40a6-870d-5be416aeb8e5 · outbound

This paper cites Superhuman Automated Forecasting | CAIS,.

Safety Features for a Centralised AGI Project Superhuman Automated Forecasting | CAIS,

Reference 74

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:24:12.981692Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 0939a4bf-78ea-4a2d-8182-bb3d83f9b046 · outbound

This paper cites Technical Options for Flexible Hardware-Enabled Guarantees.

Safety Features for a Centralised AGI Project Technical Options for Flexible Hardware-Enabled Guarantees

Reference 75

Resolution: unresolved; no resolver link, observed 2026-08-07T00:24:12.474730Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 75442d2d-3d46-4191-b93d-f4064e6f2715 · outbound

This paper cites Verification methods for international AI agreements,.

Safety Features for a Centralised AGI Project Verification methods for international AI agreements,

Reference 76

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:24:12.968921Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 4fe87eb6-6558-4888-a636-2e530b2c481f · outbound

This paper cites Global Security Remote Sensing and Verification,.

Safety Features for a Centralised AGI Project Global Security Remote Sensing and Verification,

Reference 77

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:24:12.956299Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation e17989d0-f16a-432f-93c1-201f54db041e · outbound

This paper cites Verification and other safeguards activities,.

Safety Features for a Centralised AGI Project Verification and other safeguards activities,

Reference 78

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:24:12.946111Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation ff421c5c-7e60-4372-a50f-24f2bcc54daf · outbound

This paper cites Hardware-Enabled Governance Mechanisms: Developing Technical Solutions to Exempt Items Otherwise Classified Under Export Control Classification Numbers 3A090 and 4A090,.

Safety Features for a Centralised AGI Project Hardware-Enabled Governance Mechanisms: Developing Technical Solutions to Exempt Items Otherwise Classified Under Export Control Classification Numbers 3A090 and 4A090,

Reference 79

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:24:12.927968Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation c93adeb7-a9f7-4803-b90e-e8eb0220623e · outbound

This paper cites Why policy makers should beware claims of new ’arms races’,.

Safety Features for a Centralised AGI Project Why policy makers should beware claims of new ’arms races’,

Reference 80

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:24:12.914370Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 218748f1-aaee-4331-8d1b-31cba0f376fe · outbound

This paper cites Who is behind DeepSeek and how did it achieve its AI ’Sputnik moment’?.

Safety Features for a Centralised AGI Project Who is behind DeepSeek and how did it achieve its AI ’Sputnik moment’?

Reference 81

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:24:12.904999Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation c069c2ea-a699-4b10-a166-63600815c156 · outbound

This paper cites On DeepSeek and Export Controls,.

Safety Features for a Centralised AGI Project On DeepSeek and Export Controls,

Reference 82

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:24:12.894806Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation f4dd53c2-623a-4e8c-a681-4c363426a27b · outbound

This paper cites What Is DeepSeek? New Chinese Artificial Intelligence Rivals Chat- GPT, OpenAI,.

Safety Features for a Centralised AGI Project What Is DeepSeek? New Chinese Artificial Intelligence Rivals Chat- GPT, OpenAI,

Reference 83

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:24:12.885635Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 68609deb-1a2b-4e30-b3e9-e76ea69b5849 · outbound

This paper cites Trends in U.S. Intention-to-Stay Rates of International Ph.D. Gradu- ates Across Nationality and STEM Fields,.

Safety Features for a Centralised AGI Project Trends in U.S. Intention-to-Stay Rates of International Ph.D. Gradu- ates Across Nationality and STEM Fields,

Reference 84

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:24:12.876474Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 7642eeb0-9447-4d2d-92eb-09e771d4f43e · outbound

This paper cites AI Pioneer Geoffrey Hinton Talks About AI Gaining Con- trol,.

Safety Features for a Centralised AGI Project AI Pioneer Geoffrey Hinton Talks About AI Gaining Con- trol,

Reference 85

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:24:12.866804Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation f79b198f-666d-47dd-ae11-a9bc3e11bb78 · outbound

This paper cites Introducing Superalignment,.

Safety Features for a Centralised AGI Project Introducing Superalignment,

Reference 86

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:24:12.855325Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 5483a0d0-22db-4d58-a4dd-d48b5d749e92 · outbound

This paper cites Verification methods for international AI agreements.

Safety Features for a Centralised AGI Project Verification methods for international AI agreements

Reference 2024

Resolution: unresolved; no resolver link, observed 2026-08-07T00:24:12.488409Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Coverage vector

Reference resolution

Outbound references

Pith citing papers