Paper Citation Record · LEDGER

Can an AI Agent Safely Run a Government? Existence of Probably Approximately Aligned Policies

As of 15 August 2026, this Paper Citation Record lists 46 of 46 outbound references and 0 inbound Pith citation observations for arXiv:2412.00033.

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

pith.paper-citation-record.v1
2412.00033 v1

Coverage vector

measured 46 of 46 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-12T15:45:50.097923Z

measured 46 of 46 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-15T06:32:42.880941+00:00

measured 0 of 0 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links

measured 0 of 1 external citation measurements

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

Source: cited_works

Reference resolution

46 of 46 outbound references displayed

verified exact1
verified fuzzy28
unresolved17
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 5ef2491e-cad3-447a-ad6f-c65482fa802d · outbound

This paper cites Constrained Markov Decision Processes.

Can an AI Agent Safely Run a Government? Existence of Probably Approximately Aligned Policies Constrained Markov Decision Processes

Reference 1

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T15:45:50.745816Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation f47a4a7a-ff96-4a3b-be03-709f3403a01a · outbound

This paper cites Concrete Problems in AI Safety.

Can an AI Agent Safely Run a Government? Existence of Probably Approximately Aligned Policies Concrete Problems in AI Safety

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-12T15:45:49.880712Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8215e3dd-00d7-4604-a2a5-9b6a5996ed1d · outbound

This paper cites Social Choice and Individual Values.

Can an AI Agent Safely Run a Government? Existence of Probably Approximately Aligned Policies Social Choice and Individual Values

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T15:45:50.733472Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 67bb33bb-ab26-471e-8e31-911b7ee9df3d · outbound

This paper cites Concentration Inequalities for Sampling without Replace- ment.

Can an AI Agent Safely Run a Government? Existence of Probably Approximately Aligned Policies Concentration Inequalities for Sampling without Replace- ment

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T15:45:50.720436Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation bfec8ed9-71c9-4079-821b-9a38feb8ac92 · outbound

This paper cites Measuring Progress on Scalable Oversight for Large Language Models.

Can an AI Agent Safely Run a Government? Existence of Probably Approximately Aligned Policies Measuring Progress on Scalable Oversight for Large Language Models

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-12T15:45:49.894196Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 50c06af6-8edd-458c-910a-638d06656186 · outbound

This paper cites Christiano, Jan Leike, Tom Brown, Miljan Martic, Shane Legg, and Dario Amodei.

Can an AI Agent Safely Run a Government? Existence of Probably Approximately Aligned Policies Christiano, Jan Leike, Tom Brown, Miljan Martic, Shane Legg, and Dario Amodei

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T15:45:50.707023Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 902b2dbf-7c92-4103-8a66-85a1c2eaae13 · outbound

This paper cites An Axiomatic Theory of Provably-Fair Welfare-Centric Machine Learning.

Can an AI Agent Safely Run a Government? Existence of Probably Approximately Aligned Policies An Axiomatic Theory of Provably-Fair Welfare-Centric Machine Learning

Reference 7

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T15:45:50.692158Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 1f7bdafc-a97f-45af-95fa-6b94e8ac471b · outbound

This paper cites Rethinking the Maturity of Artificial Intelligence in Safety-Critical Settings.

Can an AI Agent Safely Run a Government? Existence of Probably Approximately Aligned Policies Rethinking the Maturity of Artificial Intelligence in Safety-Critical Settings

Reference 8

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T15:45:50.677814Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 9614d473-51ad-4824-835b-23290d323161 · outbound

This paper cites Equity and the Informational Basis of Collective Choice.

Can an AI Agent Safely Run a Government? Existence of Probably Approximately Aligned Policies Equity and the Informational Basis of Collective Choice

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T15:45:50.664643Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 8ede472e-2378-47cf-b917-b0b702651b54 · outbound

This paper cites Representation of a preference ordering by a numerical func- tion.

Can an AI Agent Safely Run a Government? Existence of Probably Approximately Aligned Policies Representation of a preference ordering by a numerical func- tion

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T15:45:50.651033Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation bc19c378-865b-4c07-b9c7-de99bbbd8b7e · outbound

This paper cites RAFT: Reward rAnked FineTuning for Generative Foundation Model Alignment.

Can an AI Agent Safely Run a Government? Existence of Probably Approximately Aligned Policies RAFT: Reward rAnked FineTuning for Generative Foundation Model Alignment

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-12T15:45:49.937843Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation efde90b4-4fd6-46f9-91e8-6c0501d86ded · outbound

This paper cites Feinberg.

Can an AI Agent Safely Run a Government? Existence of Probably Approximately Aligned Policies Feinberg

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T15:45:50.637496Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation f5ca2145-0d09-4b2d-a4aa-e7cd15a978e5 · outbound

This paper cites Artificial intelligence, values, and alignment.

Can an AI Agent Safely Run a Government? Existence of Probably Approximately Aligned Policies Artificial intelligence, values, and alignment

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-12T15:45:49.946581Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2ad6dc81-d770-4f80-9dc4-fc72b3be7219 · outbound

This paper cites Red Teaming Language Models to Reduce Harms: Methods, Scaling Behaviors, and Lessons Learned.

Can an AI Agent Safely Run a Government? Existence of Probably Approximately Aligned Policies Red Teaming Language Models to Reduce Harms: Methods, Scaling Behaviors, and Lessons Learned

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-12T15:45:49.950667Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 56c6b61a-47ab-4205-a435-9bb70c1f97fa · outbound

This paper cites A Review of Safe Reinforcement Learning: Methods, Theory and Applications.

Can an AI Agent Safely Run a Government? Existence of Probably Approximately Aligned Policies A Review of Safe Reinforcement Learning: Methods, Theory and Applications

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-12T15:45:49.954887Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 65149412-227b-44b0-baac-9ca28ad2e71b · outbound

This paper cites Hicks and Roy G.

Can an AI Agent Safely Run a Government? Existence of Probably Approximately Aligned Policies Hicks and Roy G

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T15:45:50.614556Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation af6ed932-ea56-47a1-9f73-e2b07480f477 · outbound

This paper cites AI Alignment: A Comprehensive Survey.

Can an AI Agent Safely Run a Government? Existence of Probably Approximately Aligned Policies AI Alignment: A Comprehensive Survey

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-12T15:45:49.964815Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dbdf25da-9945-486d-8822-14f1648746de · outbound

This paper cites On the Sample Complexity of Reinforcement Learning.

Can an AI Agent Safely Run a Government? Existence of Probably Approximately Aligned Policies On the Sample Complexity of Reinforcement Learning

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T15:45:50.600871Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 7fd85877-1d18-416b-adad-caf1853e60ca · outbound

This paper cites A Sparse Sampling Algorithm for Near-optimal Planning in Large Markov Decision Processes.

Can an AI Agent Safely Run a Government? Existence of Probably Approximately Aligned Policies A Sparse Sampling Algorithm for Near-optimal Planning in Large Markov Decision Processes

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T15:45:50.587176Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 1c1b3dd6-cd1e-4738-a25a-2a1e3971ccb5 · outbound

This paper cites Provably Safe Reinforcement Learning: Conceptual Analysis, Survey, and Benchmarking.

Can an AI Agent Safely Run a Government? Existence of Probably Approximately Aligned Policies Provably Safe Reinforcement Learning: Conceptual Analysis, Survey, and Benchmarking

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-12T15:45:49.979191Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d832b1bb-8084-4683-904f-feaa13f07005 · outbound

This paper cites Social Choice with Changing Preferences: Representation Theorems and Long-Run Policies.

Can an AI Agent Safely Run a Government? Existence of Probably Approximately Aligned Policies Social Choice with Changing Preferences: Representation Theorems and Long-Run Policies

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-12T15:45:49.983680Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 585328b3-399d-467a-8436-470b6589e086 · outbound

This paper cites AI Alignment and Social Choice: Fundamental Limitations and Policy Implications.

Can an AI Agent Safely Run a Government? Existence of Probably Approximately Aligned Policies AI Alignment and Social Choice: Fundamental Limitations and Policy Implications

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-12T15:45:49.987712Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e0d8fd6b-526b-4c81-8301-5678728ca710 · outbound

This paper cites Value-Guided Synthesis of Parametric Normative Systems.

Can an AI Agent Safely Run a Government? Existence of Probably Approximately Aligned Policies Value-Guided Synthesis of Parametric Normative Systems

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T15:45:50.571350Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 88cbea12-254c-4fed-b589-e85e52bdf171 · outbound

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

Can an AI Agent Safely Run a Government? Existence of Probably Approximately Aligned Policies The Alignment Problem from a Deep Learning Perspective

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-12T15:45:49.995737Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 20671d2a-66ab-40e9-b24c-521824c0df93 · outbound

This paper cites Accountability in Artificial Intelligence: What it is and how it works.

Can an AI Agent Safely Run a Government? Existence of Probably Approximately Aligned Policies Accountability in Artificial Intelligence: What it is and how it works

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T15:45:50.558948Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 219dd15f-6408-4508-808a-760c01fa3f4c · outbound

This paper cites Christiano, Jan Leike, and Ryan Lowe.

Can an AI Agent Safely Run a Government? Existence of Probably Approximately Aligned Policies Christiano, Jan Leike, and Ryan Lowe

Reference 26

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T15:45:50.547150Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation dd9c4574-7c68-4ab5-9a55-6abc9ec8005f · outbound

This paper cites Manuale di Economia Politica con una Introduzione alla Scienza Sociale.

Can an AI Agent Safely Run a Government? Existence of Probably Approximately Aligned Policies Manuale di Economia Politica con una Introduzione alla Scienza Sociale

Reference 27

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T15:45:50.534634Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 9db3f391-e3ae-48a4-93c0-162e3e2199e1 · outbound

This paper cites Dynamic Social Choice with Evolving Preferences.

Can an AI Agent Safely Run a Government? Existence of Probably Approximately Aligned Policies Dynamic Social Choice with Evolving Preferences

Reference 28

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T15:45:50.521657Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 3e635f46-e804-46e4-92d0-fe765511a38c · outbound

This paper cites an unresolved cited work.

Can an AI Agent Safely Run a Government? Existence of Probably Approximately Aligned Policies Unresolved cited work

Reference 29

Resolution: unresolved; raw_fallback, observed 2026-08-12T15:45:50.508375Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 474c2c7d-e9c1-45bd-b31f-348011c2471e · outbound

This paper cites Research Priorities for Robust and Beneficial Artificial Intelligence.

Can an AI Agent Safely Run a Government? Existence of Probably Approximately Aligned Policies Research Priorities for Robust and Beneficial Artificial Intelligence

Reference 30

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T15:45:50.495164Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 864e2180-9d6f-4e4a-8038-d1da928896ed · outbound

This paper cites Schwartz.

Can an AI Agent Safely Run a Government? Existence of Probably Approximately Aligned Policies Schwartz

Reference 31

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T15:45:50.481428Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation a770c8c6-0dae-454f-af3b-d6859d310ed2 · outbound

This paper cites On Weights and Measures: Informational Constraints in Social Welfare Analysis.

Can an AI Agent Safely Run a Government? Existence of Probably Approximately Aligned Policies On Weights and Measures: Informational Constraints in Social Welfare Analysis

Reference 32

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T15:45:50.469116Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation c10f85dc-cb07-4262-ad18-7378896cc360 · outbound

This paper cites an unresolved cited work.

Can an AI Agent Safely Run a Government? Existence of Probably Approximately Aligned Policies Unresolved cited work

Reference 33

Resolution: unresolved; raw_fallback, observed 2026-08-12T15:45:50.456428Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 1efdb61b-0c52-47d1-9e81-81f3bf469b0b · outbound

This paper cites Value alignment: a formal approach.

Can an AI Agent Safely Run a Government? Existence of Probably Approximately Aligned Policies Value alignment: a formal approach

Reference 34

Resolution: verified exact; local_arxiv, observed 2026-08-12T15:45:50.140714Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 199a74db-9d40-4e6d-b567-6f002a0c4fc4 · outbound

This paper cites Singh and Richard C.

Can an AI Agent Safely Run a Government? Existence of Probably Approximately Aligned Policies Singh and Richard C

Reference 35

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T15:45:50.444361Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 8c58aaba-1533-4c66-9f15-b480e845c662 · outbound

This paper cites an unresolved cited work.

Can an AI Agent Safely Run a Government? Existence of Probably Approximately Aligned Policies Unresolved cited work

Reference 36

Resolution: unresolved; raw_fallback, observed 2026-08-12T15:45:50.432406Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation dd6deb26-2dcf-43bb-9f66-74d8d2530743 · outbound

This paper cites Sutton and Andrew G.

Can an AI Agent Safely Run a Government? Existence of Probably Approximately Aligned Policies Sutton and Andrew G

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-12T15:45:50.060386Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7894d180-06c5-486c-a3ef-4caef39a1e0a · outbound

This paper cites A Theory of the Learnable.

Can an AI Agent Safely Run a Government? Existence of Probably Approximately Aligned Policies A Theory of the Learnable

Reference 38

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T15:45:50.410655Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 086c42ca-b3f7-43cf-9722-323c47437340 · outbound

This paper cites Zhao, Kelvin Guu, Adams Wei Yu, Brian Lester, Nan Du, Andrew M.

Can an AI Agent Safely Run a Government? Existence of Probably Approximately Aligned Policies Zhao, Kelvin Guu, Adams Wei Yu, Brian Lester, Nan Du, Andrew M

Reference 39

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T15:45:50.397209Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 970ba91a-abc6-4877-a5c3-64d992be55ca · outbound

This paper cites A Survey of Preference-Based Reinforcement Learning Methods.

Can an AI Agent Safely Run a Government? Existence of Probably Approximately Aligned Policies A Survey of Preference-Based Reinforcement Learning Methods

Reference 40

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T15:45:50.383506Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation b53b0979-5d69-49ab-a1f9-e0bca1c75201 · outbound

This paper cites Consequences of Misaligned AI.

Can an AI Agent Safely Run a Government? Existence of Probably Approximately Aligned Policies Consequences of Misaligned AI

Reference 41

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T15:45:50.370156Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 40bb9962-03ba-410d-8cf3-9f29a0c7c03b · outbound

This paper cites Bob isx times more satisfied than Alice.

Can an AI Agent Safely Run a Government? Existence of Probably Approximately Aligned Policies Bob isx times more satisfied than Alice

Reference 42

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T15:45:50.353968Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 1268cff3-cd3e-4397-ac63-4cf74f7e43dd · outbound

This paper cites an unresolved cited work.

Can an AI Agent Safely Run a Government? Existence of Probably Approximately Aligned Policies Unresolved cited work

Reference 43

Resolution: unresolved; raw_fallback, observed 2026-08-12T15:45:50.341219Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 8d95b5d3-0582-46d6-bf55-a707bbe8ed94 · outbound

This paper cites ∞X i=0 γir(si, ai) # − Eτ ∼pτ (·|π ˆQ,s0=s).

Can an AI Agent Safely Run a Government? Existence of Probably Approximately Aligned Policies ∞X i=0 γir(si, ai) # − Eτ ∼pτ (·|π ˆQ,s0=s)

Reference 44

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T15:45:50.328284Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 828c1fd7-780a-459b-bacb-cb0d64020298 · outbound

This paper cites an unresolved cited work.

Can an AI Agent Safely Run a Government? Existence of Probably Approximately Aligned Policies Unresolved cited work

Reference 45

Resolution: unresolved; raw_fallback, observed 2026-08-12T15:45:50.310576Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 5f63ba73-8d4d-4080-a0cb-1835a4c000fb · outbound

This paper cites approximation budget.

Can an AI Agent Safely Run a Government? Existence of Probably Approximately Aligned Policies approximation budget

Reference 46

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T15:45:50.296007Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Pith citing papers

No inbound Pith citation observations are available.