Paper Citation Record · LEDGER

Predicting LLM Safety Before Release by Simulating Deployment

As of 15 August 2026, this Paper Citation Record lists 22 of 22 outbound references and 0 inbound Pith citation observations for arXiv:2607.07184.

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

pith.paper-citation-record.v1
2607.07184 v1

Coverage vector

measured 22 of 22 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-07-09T18:07:42.556329Z

measured 22 of 22 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

22 of 22 outbound references displayed

verified exact9
verified fuzzy10
unresolved1
parse uncertain0
malformed identifier1
metadata mismatch1

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation a59c605b-f5b8-4386-9a4f-7586d3f74aab · outbound

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

Predicting LLM Safety Before Release by Simulating Deployment Large Language Models Often Know When They Are Being Evaluated

Reference 1

Resolution: metadata mismatch; local_arxiv, observed 2026-07-09T18:16:25.813826Z

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 b5d9dc23-76d9-4dc4-9f7b-ae44ec6d38c9 · outbound

This paper cites Charles, D.

Predicting LLM Safety Before Release by Simulating Deployment Charles, D

Reference 2

Resolution: verified fuzzy; raw_fallback, observed 2026-07-09T18:16:26.196007Z

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 b4936888-4d53-4cde-ba24-de439737870f · outbound

This paper cites Stress Testing Deliberative Alignment for Anti-Scheming Training , url =.

Predicting LLM Safety Before Release by Simulating Deployment Stress Testing Deliberative Alignment for Anti-Scheming Training , url =

Reference 3

Resolution: verified exact; arxiv_id, observed 2026-07-09T18:16:25.709877Z

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 77701459-7074-482d-85cb-f00d98eb6a0b · outbound

This paper cites Metagaming matters for training, evaluation, and oversight.

Predicting LLM Safety Before Release by Simulating Deployment Metagaming matters for training, evaluation, and oversight

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-07-09T18:16:26.199722Z

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 b00ce237-5f4a-4f94-9342-7f0245368c96 · outbound

This paper cites Training llms for honesty via confessions.

Predicting LLM Safety Before Release by Simulating Deployment Training llms for honesty via confessions

Reference 6

Resolution: verified exact; arxiv_id, observed 2026-07-09T18:16:25.811289Z

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 5cb2503b-e511-41eb-bee7-4e5c1b1c7b4b · outbound

This paper cites Guan, Miles Wang, Micah Carroll, Zehao Dou, Annie Y.

Predicting LLM Safety Before Release by Simulating Deployment Guan, Miles Wang, Micah Carroll, Zehao Dou, Annie Y

Reference 7

Resolution: verified exact; arxiv_id, observed 2026-07-09T18:16:25.818454Z

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 388ac83d-9218-4a29-af7e-2e47d17f13ed · outbound

This paper cites Jimenez, John Yang, Alexander Wettig, Shunyu Yao, Kexin Pei, Ofir Press, and Karthik R.

Predicting LLM Safety Before Release by Simulating Deployment Jimenez, John Yang, Alexander Wettig, Shunyu Yao, Kexin Pei, Ofir Press, and Karthik R

Reference 8

Resolution: verified fuzzy; raw_fallback, observed 2026-07-09T18:16:26.190201Z

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 468a3f8d-d66b-462a-8bc0-3ca5086d4e30 · outbound

This paper cites American Invitational Mathematics Examination (AIME), 2026.

Predicting LLM Safety Before Release by Simulating Deployment American Invitational Mathematics Examination (AIME), 2026

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-07-09T18:16:26.192460Z

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 3b894894-9bb9-4f4e-bc3e-b6248a9ee775 · outbound

This paper cites OpenAI GPT-5 System Card.https://openai.com/index/gpt-5-system-card/,.

Predicting LLM Safety Before Release by Simulating Deployment OpenAI GPT-5 System Card.https://openai.com/index/gpt-5-system-card/,

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-07-09T18:16:26.187623Z

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 c0d4fad0-08a8-45a8-877d-833aad3ee043 · outbound

This paper cites Maddison, and Tatsunori Hashimoto.

Predicting LLM Safety Before Release by Simulating Deployment Maddison, and Tatsunori Hashimoto

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-07-09T18:16:26.206196Z

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 d3d25615-2e5e-4e54-9043-7fbfeae3d608 · outbound

This paper cites WildChat: 1M ChatGPT Interaction Logs in the Wild.

Predicting LLM Safety Before Release by Simulating Deployment WildChat: 1M ChatGPT Interaction Logs in the Wild

Reference 12

Resolution: verified exact; local_arxiv, observed 2026-07-09T18:16:25.809290Z

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 3a8df77f-a393-4a11-a01a-5f512aa34551 · outbound

This paper cites Chain of Thought Monitorability: A New and Fragile Opportunity for AI Safety.

Predicting LLM Safety Before Release by Simulating Deployment Chain of Thought Monitorability: A New and Fragile Opportunity for AI Safety

Reference 13

Resolution: verified exact; local_arxiv, observed 2026-07-09T18:16:25.820530Z

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 fc8328c5-7d60-43cb-b6a9-a6443bf452ce · outbound

This paper cites Estimating the probabilities of rare outputs in language models,.

Predicting LLM Safety Before Release by Simulating Deployment Estimating the probabilities of rare outputs in language models,

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-07-09T18:16:26.174954Z

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 6f51c6d5-a8db-463e-808c-42f4bc33c9a7 · outbound

This paper cites Estimating the Probabilities of Rare Outputs in Language Models.

Predicting LLM Safety Before Release by Simulating Deployment Estimating the Probabilities of Rare Outputs in Language Models

Reference 15

Resolution: verified exact; local_arxiv, observed 2026-07-09T18:16:25.821334Z

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 e3f0a6b3-9976-4bf5-ba13-734202235ffd · outbound

This paper cites an unresolved cited work.

Predicting LLM Safety Before Release by Simulating Deployment Unresolved cited work

Reference 16

Resolution: unresolved; raw_fallback, observed 2026-07-09T18:16:26.178134Z

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 2f698325-05ea-4d29-a0f7-33574204f881 · outbound

This paper cites Forecasting Rare Language Model Behaviors.

Predicting LLM Safety Before Release by Simulating Deployment Forecasting Rare Language Model Behaviors

Reference 17

Resolution: verified exact; local_arxiv, observed 2026-07-09T18:16:25.803524Z

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 80d42c63-ef18-4105-9c25-d389bf74ade5 · outbound

This paper cites Estimating Tail Risks in Language Model Output Distributions.

Predicting LLM Safety Before Release by Simulating Deployment Estimating Tail Risks in Language Model Output Distributions

Reference 18

Resolution: verified exact; local_arxiv, observed 2026-07-09T18:16:25.817785Z

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 978f1a04-1541-4227-b309-a66997023dce · outbound

This paper cites Evaluating predictions of model behaviour.https://www.governance.ai/anal ysis/evaluating-predictions-of-model-behaviour, April 2024.

Predicting LLM Safety Before Release by Simulating Deployment Evaluating predictions of model behaviour.https://www.governance.ai/anal ysis/evaluating-predictions-of-model-behaviour, April 2024

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-07-09T18:16:26.180627Z

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 cffe79e8-3d2c-4d35-8e8d-cbc23825a94e · outbound

This paper cites Foster and Ariel Deardorff.

Predicting LLM Safety Before Release by Simulating Deployment Foster and Ariel Deardorff

Reference 20

Resolution: verified exact; doi, observed 2026-07-09T18:16:25.704383Z

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 7aa1ed9b-7d15-4854-85ee-ca79172e2ff3 · outbound

This paper cites Estimating model behavior before deployment with representative prompts for gpt-5.4 thinking, Mar 2026.

Predicting LLM Safety Before Release by Simulating Deployment Estimating model behavior before deployment with representative prompts for gpt-5.4 thinking, Mar 2026

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-07-09T18:16:26.184558Z

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 1bc9b69d-5572-4288-b948-ef2d967dffcf · outbound

This paper cites OpenAI GPT-5.4 Thinking System Card.

Predicting LLM Safety Before Release by Simulating Deployment OpenAI GPT-5.4 Thinking System Card

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-07-09T18:16:26.210612Z

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 99448bf6-a9d8-4ef7-9500-cf82ba76e7af · outbound

This paper cites DS lower NLL.

Predicting LLM Safety Before Release by Simulating Deployment DS lower NLL

Reference 23

Resolution: malformed identifier; raw_fallback, observed 2026-07-09T18:16:26.203164Z

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.