Paper Citation Record · LEDGER

Declare and Justify: Explicit assumptions in AI evaluations are necessary for effective regulation

As of 21 August 2026, this Paper Citation Record lists 37 of 37 outbound references and 3 inbound Pith citation observations for arXiv:2411.12820.

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

pith.paper-citation-record.v1
2411.12820 v1

Coverage vector

measured 37 of 37 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-12T17:12:57.345066Z

measured 40 of 40 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-20T06:33:59.587034+00:00

measured 3 of 3 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-15T23:27:29.753921Z

measured 0 of 1 external citation measurements

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

Source: pith, observed 2026-08-06T23:25:55.029019Z

Reference resolution

37 of 37 outbound references displayed

verified exact0
verified fuzzy21
unresolved15
parse uncertain1
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation a1492149-b66a-49c5-872f-73e9b863efb2 · outbound

This paper cites Frontier AI Regulation: Managing Emerging Risks to Public Safety.

Declare and Justify: Explicit assumptions in AI evaluations are necessary for effective regulation Frontier AI Regulation: Managing Emerging Risks to Public Safety

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-12T17:12:57.185644Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7888cb0d-1e75-40c7-80f9-cc1102074eac · outbound

This paper cites Managing extreme AI risks am id rapid progress.

Declare and Justify: Explicit assumptions in AI evaluations are necessary for effective regulation Managing extreme AI risks am id rapid progress

Reference 2

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T17:12:57.858226Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 1d5a76df-1dfb-4898-8ac9-af41e10d5bca · outbound

This paper cites International Scientiﬁc Report on the Safety of Advanced AI.

Declare and Justify: Explicit assumptions in AI evaluations are necessary for effective regulation International Scientiﬁc Report on the Safety of Advanced AI

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T17:12:57.844670Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 2ba10792-93ed-4fc5-ac3c-3553f9d2c287 · outbound

This paper cites An Overview of Catastrophic AI Risks.

Declare and Justify: Explicit assumptions in AI evaluations are necessary for effective regulation An Overview of Catastrophic AI Risks

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-12T17:12:57.200996Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 722bf445-d20f-4625-bb47-57d248a6d5e9 · outbound

This paper cites OpenAI chief seeks new Microsoft funds to build ‘superintelligence.’.

Declare and Justify: Explicit assumptions in AI evaluations are necessary for effective regulation OpenAI chief seeks new Microsoft funds to build ‘superintelligence.’

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T17:12:57.832554Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation eca0a00f-fd17-4fe9-9c4f-6473ae08ac27 · outbound

This paper cites Anthropic’s Responsible Scaling Policy, 20 23.

Declare and Justify: Explicit assumptions in AI evaluations are necessary for effective regulation Anthropic’s Responsible Scaling Policy, 20 23

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T17:12:57.819841Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation a3be9bbd-9e72-4367-9de2-e85637645f25 · outbound

This paper cites Preparedness Framework (Beta), 2023.

Declare and Justify: Explicit assumptions in AI evaluations are necessary for effective regulation Preparedness Framework (Beta), 2023

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-12T17:12:57.213335Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation da741035-937e-402d-8bfc-2ba6f78a310b · outbound

This paper cites Frontier Safety Framework, 2024.

Declare and Justify: Explicit assumptions in AI evaluations are necessary for effective regulation Frontier Safety Framework, 2024

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-12T17:12:57.217052Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1ae69b21-1166-4fa4-9983-581f22e66eb2 · outbound

This paper cites Model evaluation for extreme risks.

Declare and Justify: Explicit assumptions in AI evaluations are necessary for effective regulation Model evaluation for extreme risks

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-12T17:12:57.220891Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8ad409a2-c0aa-4670-8257-d2175c0169e3 · outbound

This paper cites Evaluating Frontier Models for Dangerous Capabilities, April 2024.

Declare and Justify: Explicit assumptions in AI evaluations are necessary for effective regulation Evaluating Frontier Models for Dangerous Capabilities, April 2024

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T17:12:57.790549Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 9bb30895-a92b-4b7a-bdca-66c4f8795278 · outbound

This paper cites LLM Agents can Autonomously Exploit One-day Vulnerabilities, April 2024.

Declare and Justify: Explicit assumptions in AI evaluations are necessary for effective regulation LLM Agents can Autonomously Exploit One-day Vulnerabilities, April 2024

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T17:12:57.776832Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 52c377fb-881d-4912-92dc-43262f323b82 · outbound

This paper cites Teams of LLM Agents can Exploit Zero-Day Vulnerabilities, June 2024.

Declare and Justify: Explicit assumptions in AI evaluations are necessary for effective regulation Teams of LLM Agents can Exploit Zero-Day Vulnerabilities, June 2024

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T17:12:57.763106Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation ff175f33-158a-42be-9c9d-4880e24c0139 · outbound

This paper cites Can large language models democratize access to dual-use biotechnology?.

Declare and Justify: Explicit assumptions in AI evaluations are necessary for effective regulation Can large language models democratize access to dual-use biotechnology?

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-12T17:12:57.236661Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e9005956-2086-4ff9-a9d3-9044f468ea38 · outbound

This paper cites Prioritizing High-Consequence Biolo gical Capabilities in Evaluations of Artiﬁcial Intelligence Models, May 2024.

Declare and Justify: Explicit assumptions in AI evaluations are necessary for effective regulation Prioritizing High-Consequence Biolo gical Capabilities in Evaluations of Artiﬁcial Intelligence Models, May 2024

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T17:12:57.748657Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation bccecdaa-7710-4ee3-afec-b828a26fa0b7 · outbound

This paper cites On the Conver- sational Persuasiveness of Large Language Models: A Random ized Controlled Trial, March.

Declare and Justify: Explicit assumptions in AI evaluations are necessary for effective regulation On the Conver- sational Persuasiveness of Large Language Models: A Random ized Controlled Trial, March

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T17:12:57.735981Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 55aad937-fc75-4baa-9926-13d6ec13c958 · outbound

This paper cites an unresolved cited work.

Declare and Justify: Explicit assumptions in AI evaluations are necessary for effective regulation Unresolved cited work

Reference 16

Resolution: unresolved; raw_fallback, observed 2026-08-12T17:12:57.723705Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 1b54961d-7d22-417e-a196-f387170cb235 · outbound

This paper cites AI Safety Institute Signs Agreements Regarding AI Safety Re- search, Testing and Evaluation With Anthropic and OpenAI — n ist.gov.

Declare and Justify: Explicit assumptions in AI evaluations are necessary for effective regulation AI Safety Institute Signs Agreements Regarding AI Safety Re- search, Testing and Evaluation With Anthropic and OpenAI — n ist.gov

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T17:12:57.709345Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 3352c982-37b6-4ba3-a548-21e755686143 · outbound

This paper cites Rishi Sunak promised to make AI safe.

Declare and Justify: Explicit assumptions in AI evaluations are necessary for effective regulation Rishi Sunak promised to make AI safe

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T17:12:57.696666Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 0ee9559a-eb84-446c-83bb-3a80240a32a0 · outbound

This paper cites Reasons to Doubt the Impact of AI Risk Evaluations.

Declare and Justify: Explicit assumptions in AI evaluations are necessary for effective regulation Reasons to Doubt the Impact of AI Risk Evaluations

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-12T17:12:57.271683Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3019c387-7ad2-4bd7-be32-0c533715fe4e · outbound

This paper cites Evaluation in artiﬁcial intel ligence: from task-oriented to ability- oriented measurement.

Declare and Justify: Explicit assumptions in AI evaluations are necessary for effective regulation Evaluation in artiﬁcial intel ligence: from task-oriented to ability- oriented measurement

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T17:12:57.673149Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 911949b5-2f13-408c-96db-790197a91a38 · outbound

This paper cites Evaluating AI Evaluation: Perils and Prospects.

Declare and Justify: Explicit assumptions in AI evaluations are necessary for effective regulation Evaluating AI Evaluation: Perils and Prospects

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-12T17:12:57.275813Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a9b062df-f134-45f0-b506-8513da74d457 · outbound

This paper cites Towards interactive evaluations for interaction harms in human-AI systems.

Declare and Justify: Explicit assumptions in AI evaluations are necessary for effective regulation Towards interactive evaluations for interaction harms in human-AI systems

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-12T17:12:57.287184Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dd438213-cc7c-4836-9e87-3ff39c3128d1 · outbound

This paper cites We need a Science of Evals.

Declare and Justify: Explicit assumptions in AI evaluations are necessary for effective regulation We need a Science of Evals

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T17:12:57.660707Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 0cded475-a281-4c38-92d7-f3d474896936 · outbound

This paper cites Secur- ing AI Model W eights: Preventing Theft and Misuse of Frontie r Models.

Declare and Justify: Explicit assumptions in AI evaluations are necessary for effective regulation Secur- ing AI Model W eights: Preventing Theft and Misuse of Frontie r Models

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T17:12:57.633304Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation a853d033-90d3-44ab-a8b8-80cfeb60a1dc · outbound

This paper cites AI Safety Institute approach to evaluations, 2024.

Declare and Justify: Explicit assumptions in AI evaluations are necessary for effective regulation AI Safety Institute approach to evaluations, 2024

Reference 26

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T17:12:57.646783Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation d62660d3-6b68-4d46-8f9b-41a9f800d856 · outbound

This paper cites OpenAI Red Teaming Network, 2023.

Declare and Justify: Explicit assumptions in AI evaluations are necessary for effective regulation OpenAI Red Teaming Network, 2023

Reference 27

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T17:12:57.601949Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 94f34032-baeb-4184-81dc-d18da2b8896b · outbound

This paper cites Compute trends across three eras of machine learni ng.

Declare and Justify: Explicit assumptions in AI evaluations are necessary for effective regulation Compute trends across three eras of machine learni ng

Reference 28

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T17:12:57.615958Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation a2c2b7f2-bcfa-41cb-aad5-54172738599e · outbound

This paper cites AI capabilities can be significantly improved without expensive retraining.

Declare and Justify: Explicit assumptions in AI evaluations are necessary for effective regulation AI capabilities can be significantly improved without expensive retraining

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-12T17:12:57.312630Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c7461fb8-192b-4ebc-8e1b-3320397d3685 · outbound

This paper cites Guidelines for capability elicitation, 2024.

Declare and Justify: Explicit assumptions in AI evaluations are necessary for effective regulation Guidelines for capability elicitation, 2024

Reference 30

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T17:12:57.587254Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 0758bc7a-aa65-4c12-886c-dffb4094ce92 · outbound

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

Declare and Justify: Explicit assumptions in AI evaluations are necessary for effective regulation AI Sandbagging: Language Models can Strategically Underperform on Evaluations

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-12T17:12:57.322688Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ec7c5c27-75ae-46d8-a531-c8013c951459 · outbound

This paper cites Black-Box Access is Insufficient for Rigorous AI Audits.

Declare and Justify: Explicit assumptions in AI evaluations are necessary for effective regulation Black-Box Access is Insufficient for Rigorous AI Audits

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-12T17:12:57.318253Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e5a2cee3-2956-456d-8afb-9f9ed8478399 · outbound

This paper cites Emergent Abilities of Large Language Models.

Declare and Justify: Explicit assumptions in AI evaluations are necessary for effective regulation Emergent Abilities of Large Language Models

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-12T17:12:57.330799Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 58e1533a-df8d-47a1-b684-f8f10ba2f81f · outbound

This paper cites Predictability and surprise in large generative models.

Declare and Justify: Explicit assumptions in AI evaluations are necessary for effective regulation Predictability and surprise in large generative models

Reference 34

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T17:12:57.572995Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation b4584cac-7a1f-4b52-8fdc-8c5d617a364e · outbound

This paper cites Sb 1047: Safe and secure innovation for fr ontier artiﬁcial intelligence models act., 2024.

Declare and Justify: Explicit assumptions in AI evaluations are necessary for effective regulation Sb 1047: Safe and secure innovation for fr ontier artiﬁcial intelligence models act., 2024

Reference 35

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T17:12:57.547686Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation bf1a94e0-1c7e-4d7f-8179-75b8a3db46ab · outbound

This paper cites Evaluating Predictions of Model Behaviour.

Declare and Justify: Explicit assumptions in AI evaluations are necessary for effective regulation Evaluating Predictions of Model Behaviour

Reference 36

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T17:12:57.560611Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 9c2e128d-4209-4ccb-9fef-e6953a1c7d47 · outbound

This paper cites an unresolved cited work.

Declare and Justify: Explicit assumptions in AI evaluations are necessary for effective regulation Unresolved cited work

Reference 37

Resolution: parse uncertain; no resolver link, observed 2026-08-12T17:12:57.341076Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9b2e2c09-7e03-4e14-82a8-6339411c20fb · outbound

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

Declare and Justify: Explicit assumptions in AI evaluations are necessary for effective regulation On the Conversational Persuasiveness of Large Language Models: A Randomized Controlled Trial

Reference 2024

Resolution: unresolved; no resolver link, observed 2026-08-12T17:12:57.248684Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation 7468784d-5e67-48ad-aee4-9c0c36b67029 · inbound

What AI evaluations for preventing catastrophic risks can and cannot do cites this paper.

What AI evaluations for preventing catastrophic risks can and cannot do Declare and Justify: Explicit assumptions in AI evaluations are necessary for effective regulation

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-12T11:56:20.959799Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2e13c9b1-d86a-45cd-b47b-32aca1d1d98b · inbound

AI Governance to Avoid Extinction: The Strategic Landscape and Actionable Research Questions cites this paper.

AI Governance to Avoid Extinction: The Strategic Landscape and Actionable Research Questions Declare and Justify: Explicit assumptions in AI evaluations are necessary for effective regulation

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-15T23:27:29.753921Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2aec37df-5ee1-4c78-bc3d-08e2ba2adcac · inbound

A Conceptual Framework for AI Capability Evaluations cites this paper.

A Conceptual Framework for AI Capability Evaluations Declare and Justify: Explicit assumptions in AI evaluations are necessary for effective regulation

Reference 3

Resolution: verified exact; local_arxiv, observed 2026-08-06T23:25:55.126842Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.