Paper Citation Record · LEDGER

Beyond Reactive Safety: Risk-Aware LLM Alignment via Long-Horizon Simulation

As of 9 August 2026, this Paper Citation Record lists 42 of 42 outbound references and 1 inbound Pith citation observation for arXiv:2506.20949.

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

pith.paper-citation-record.v1
2506.20949 v1

Coverage vector

measured 42 of 42 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-06T22:42:45.610334Z

measured 43 of 43 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-09T06:31:02.800959+00:00

measured 1 of 1 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-05-18T03:42:10.703369Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-05-18T03:42:21.994998Z

Reference resolution

42 of 42 outbound references displayed

verified exact3
verified fuzzy0
unresolved38
parse uncertain0
malformed identifier1
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation f13a7d03-2f2a-41eb-91b4-976fea38bc5f · outbound

This paper cites Instruction-tuning Aligns LLMs to the Human Brain.

Beyond Reactive Safety: Risk-Aware LLM Alignment via Long-Horizon Simulation Instruction-tuning Aligns LLMs to the Human Brain

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-06T22:42:45.441412Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 17f89c5d-d646-4438-8e3b-4f22ba9e0637 · outbound

This paper cites Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback.

Beyond Reactive Safety: Risk-Aware LLM Alignment via Long-Horizon Simulation Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-06T22:42:45.446281Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 364df497-c3e6-435c-b433-061ff8055282 · outbound

This paper cites an unresolved cited work.

Beyond Reactive Safety: Risk-Aware LLM Alignment via Long-Horizon Simulation Unresolved cited work

Reference 3

Resolution: unresolved; raw_fallback, observed 2026-08-06T22:42:46.080333Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 5353d513-e713-4904-8f60-75055a52f7f9 · outbound

This paper cites an unresolved cited work.

Beyond Reactive Safety: Risk-Aware LLM Alignment via Long-Horizon Simulation Unresolved cited work

Reference 4

Resolution: unresolved; raw_fallback, observed 2026-08-06T22:42:46.068770Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 56f95ce2-31aa-4122-9dcb-06aed775ff07 · outbound

This paper cites Improving Factuality and Reasoning in Language Models through Multiagent Debate.

Beyond Reactive Safety: Risk-Aware LLM Alignment via Long-Horizon Simulation Improving Factuality and Reasoning in Language Models through Multiagent Debate

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-06T22:42:45.460819Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6fe05266-6ea0-45e7-a9dc-b9ff99efe4b6 · outbound

This paper cites an unresolved cited work.

Beyond Reactive Safety: Risk-Aware LLM Alignment via Long-Horizon Simulation Unresolved cited work

Reference 6

Resolution: unresolved; raw_fallback, observed 2026-08-06T22:42:46.057295Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 16cbdaac-816c-409d-b065-557cf78ea24e · outbound

This paper cites World Models.

Beyond Reactive Safety: Risk-Aware LLM Alignment via Long-Horizon Simulation World Models

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-06T22:42:45.469931Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ccb05ce0-d473-460d-863e-a6ec2404cb9f · outbound

This paper cites Dream to Control: Learning Behaviors by Latent Imagination.

Beyond Reactive Safety: Risk-Aware LLM Alignment via Long-Horizon Simulation Dream to Control: Learning Behaviors by Latent Imagination

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-06T22:42:45.474401Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f9a4f150-f7f7-47f9-89a9-207d2cc0e20c · outbound

This paper cites Mastering Diverse Domains through World Models.

Beyond Reactive Safety: Risk-Aware LLM Alignment via Long-Horizon Simulation Mastering Diverse Domains through World Models

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-06T22:42:45.478440Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 887fed83-4793-4b82-98d0-391d5d4fd29e · outbound

This paper cites WildGuard: Open One-Stop Moderation Tools for Safety Risks, Jailbreaks, and Refusals of LLMs.

Beyond Reactive Safety: Risk-Aware LLM Alignment via Long-Horizon Simulation WildGuard: Open One-Stop Moderation Tools for Safety Risks, Jailbreaks, and Refusals of LLMs

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-06T22:42:45.482531Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 70a126d3-96d7-4fd9-9b44-91aec349b42b · outbound

This paper cites Aligner: Efficient Alignment by Learning to Correct.

Beyond Reactive Safety: Risk-Aware LLM Alignment via Long-Horizon Simulation Aligner: Efficient Alignment by Learning to Correct

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-06T22:42:45.487622Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 87b95508-37e8-4679-ac68-109ca481d236 · outbound

This paper cites an unresolved cited work.

Beyond Reactive Safety: Risk-Aware LLM Alignment via Long-Horizon Simulation Unresolved cited work

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-06T22:42:45.492603Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cac747c3-5c30-4ca5-b924-0e58b2bc1e2d · outbound

This paper cites an unresolved cited work.

Beyond Reactive Safety: Risk-Aware LLM Alignment via Long-Horizon Simulation Unresolved cited work

Reference 13

Resolution: malformed identifier; raw_fallback, observed 2026-08-06T22:42:46.037952Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation cf008f6d-0c9e-4107-b93e-7828816aa503 · outbound

This paper cites Probing Script Knowledge from Pre-Trained Models.

Beyond Reactive Safety: Risk-Aware LLM Alignment via Long-Horizon Simulation Probing Script Knowledge from Pre-Trained Models

Reference 14

Resolution: verified exact; local_arxiv, observed 2026-08-06T22:42:45.795675Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 4051c944-daed-4b13-a9a3-2cc5c1914d22 · outbound

This paper cites Regularized Best-of-N Sampling with Minimum Bayes Risk Objective for Language Model Alignment.

Beyond Reactive Safety: Risk-Aware LLM Alignment via Long-Horizon Simulation Regularized Best-of-N Sampling with Minimum Bayes Risk Objective for Language Model Alignment

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-06T22:42:45.504260Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 13d69316-7c52-47cf-bbd0-95194515ffff · outbound

This paper cites Gradient-based Planning with World Models.

Beyond Reactive Safety: Risk-Aware LLM Alignment via Long-Horizon Simulation Gradient-based Planning with World Models

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-06T22:42:45.508463Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2727fbb8-2389-4504-9ab4-bce702b7b638 · outbound

This paper cites an unresolved cited work.

Beyond Reactive Safety: Risk-Aware LLM Alignment via Long-Horizon Simulation Unresolved cited work

Reference 17

Resolution: unresolved; raw_fallback, observed 2026-08-06T22:42:46.025497Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 3747f2db-63cf-41df-8b8a-8255a8df35ff · outbound

This paper cites an unresolved cited work.

Beyond Reactive Safety: Risk-Aware LLM Alignment via Long-Horizon Simulation Unresolved cited work

Reference 18

Resolution: unresolved; raw_fallback, observed 2026-08-06T22:42:46.013550Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation e0f00c1a-a2e4-46f7-a9a1-ca6fea213506 · outbound

This paper cites FLAME: Factuality-Aware Alignment for Large Language Models.

Beyond Reactive Safety: Risk-Aware LLM Alignment via Long-Horizon Simulation FLAME: Factuality-Aware Alignment for Large Language Models

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-06T22:42:45.519744Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 60e002cc-5835-4153-9866-e93e2d457d15 · outbound

This paper cites Lo and Jillian Ross.

Beyond Reactive Safety: Risk-Aware LLM Alignment via Long-Horizon Simulation Lo and Jillian Ross

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-06T22:42:45.524522Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e599ce9a-092a-4faf-bf92-b5d76917d0f1 · outbound

This paper cites an unresolved cited work.

Beyond Reactive Safety: Risk-Aware LLM Alignment via Long-Horizon Simulation Unresolved cited work

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-06T22:42:45.528135Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 94a1d5f6-9918-4849-96d6-89fe8c670423 · outbound

This paper cites an unresolved cited work.

Beyond Reactive Safety: Risk-Aware LLM Alignment via Long-Horizon Simulation Unresolved cited work

Reference 22

Resolution: unresolved; raw_fallback, observed 2026-08-06T22:42:45.993449Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 5e418204-2708-4c58-9a59-e5b0a2fb5dca · outbound

This paper cites an unresolved cited work.

Beyond Reactive Safety: Risk-Aware LLM Alignment via Long-Horizon Simulation Unresolved cited work

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-06T22:42:45.535161Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c3d041d0-6df1-41e9-a330-542aacae5b79 · outbound

This paper cites Learning model-based planning from scratch.

Beyond Reactive Safety: Risk-Aware LLM Alignment via Long-Horizon Simulation Learning model-based planning from scratch

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-06T22:42:45.538806Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation aa26e744-3c4a-4709-95fa-e90c7090ff98 · outbound

This paper cites PyTorch: An Imperative Style, High-Performance Deep Learning Library.

Beyond Reactive Safety: Risk-Aware LLM Alignment via Long-Horizon Simulation PyTorch: An Imperative Style, High-Performance Deep Learning Library

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-06T22:42:45.542636Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9c8588c0-88f3-4da8-886e-789871d3ecf4 · outbound

This paper cites an unresolved cited work.

Beyond Reactive Safety: Risk-Aware LLM Alignment via Long-Horizon Simulation Unresolved cited work

Reference 26

Resolution: unresolved; raw_fallback, observed 2026-08-06T22:42:45.973872Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation c759a51e-816f-4ebb-aa2c-bab980f67b72 · outbound

This paper cites Direct Preference Optimization: Your Language Model is Secretly a Reward Model.

Beyond Reactive Safety: Risk-Aware LLM Alignment via Long-Horizon Simulation Direct Preference Optimization: Your Language Model is Secretly a Reward Model

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-06T22:42:45.550166Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f01e6608-2437-4333-beeb-fbfca31a74f5 · outbound

This paper cites Large Language Model Alignment: A Survey.

Beyond Reactive Safety: Risk-Aware LLM Alignment via Long-Horizon Simulation Large Language Model Alignment: A Survey

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-06T22:42:45.554111Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3cae9e0b-365c-44e4-8a77-eaa9ae6e928b · outbound

This paper cites Can LLMs Generate Novel Research Ideas? A Large-Scale Human Study with 100+ NLP Researchers.

Beyond Reactive Safety: Risk-Aware LLM Alignment via Long-Horizon Simulation Can LLMs Generate Novel Research Ideas? A Large-Scale Human Study with 100+ NLP Researchers

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-06T22:42:45.558442Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 95cc851b-6cd1-4dc0-8c8f-90fbfd18c70a · outbound

This paper cites an unresolved cited work.

Beyond Reactive Safety: Risk-Aware LLM Alignment via Long-Horizon Simulation Unresolved cited work

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-06T22:42:45.563108Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ea6206fa-0f50-4dfb-98a1-7649190bda97 · outbound

This paper cites Measuring the Effect of Influential Messages on Varying Personas.

Beyond Reactive Safety: Risk-Aware LLM Alignment via Long-Horizon Simulation Measuring the Effect of Influential Messages on Varying Personas

Reference 31

Resolution: verified exact; local_arxiv, observed 2026-08-06T22:42:45.699989Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 1593426e-8b0a-47f8-b475-6c2b5d8c2bf2 · outbound

This paper cites Decoding the Silent Majority: Inducing Belief Augmented Social Graph with Large Language Model for Response Forecasting.

Beyond Reactive Safety: Risk-Aware LLM Alignment via Long-Horizon Simulation Decoding the Silent Majority: Inducing Belief Augmented Social Graph with Large Language Model for Response Forecasting

Reference 32

Resolution: verified exact; local_arxiv, observed 2026-08-06T22:42:45.684524Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation fbefb7e9-ee30-4f58-9b78-bd184680351a · outbound

This paper cites an unresolved cited work.

Beyond Reactive Safety: Risk-Aware LLM Alignment via Long-Horizon Simulation Unresolved cited work

Reference 33

Resolution: unresolved; raw_fallback, observed 2026-08-06T22:42:45.951518Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation c851dedf-881e-468f-a1d2-cb025b1299ae · outbound

This paper cites Aligning Large Language Models with Human: A Survey.

Beyond Reactive Safety: Risk-Aware LLM Alignment via Long-Horizon Simulation Aligning Large Language Models with Human: A Survey

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-06T22:42:45.578933Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b476f1b6-2fdf-4c3c-9b58-8fc09ef33606 · outbound

This paper cites an unresolved cited work.

Beyond Reactive Safety: Risk-Aware LLM Alignment via Long-Horizon Simulation Unresolved cited work

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-06T22:42:45.584084Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e6af03d9-c5b1-467f-8bca-3d39a0f14caa · outbound

This paper cites an unresolved cited work.

Beyond Reactive Safety: Risk-Aware LLM Alignment via Long-Horizon Simulation Unresolved cited work

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-06T22:42:45.588435Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 10c37b08-8522-4bc3-afe5-65d6eb5f0ae6 · outbound

This paper cites an unresolved cited work.

Beyond Reactive Safety: Risk-Aware LLM Alignment via Long-Horizon Simulation Unresolved cited work

Reference 37

Resolution: unresolved; raw_fallback, observed 2026-08-06T22:42:45.932554Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation be7e0610-2cfb-466b-9456-603f5e1ac2fe · outbound

This paper cites an unresolved cited work.

Beyond Reactive Safety: Risk-Aware LLM Alignment via Long-Horizon Simulation Unresolved cited work

Reference 38

Resolution: unresolved; raw_fallback, observed 2026-08-06T22:42:45.920949Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 7c3e5335-a99e-4458-98a1-f5b544785bfd · outbound

This paper cites an unresolved cited work.

Beyond Reactive Safety: Risk-Aware LLM Alignment via Long-Horizon Simulation Unresolved cited work

Reference 39

Resolution: unresolved; raw_fallback, observed 2026-08-06T22:42:45.908528Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 7ecd7b56-7a94-44ca-9402-297eee187545 · outbound

This paper cites Universal and Transferable Adversarial Attacks on Aligned Language Models.

Beyond Reactive Safety: Risk-Aware LLM Alignment via Long-Horizon Simulation Universal and Transferable Adversarial Attacks on Aligned Language Models

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-06T22:42:45.602191Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a678bef4-b590-484e-88cf-3261bb71f072 · outbound

This paper cites online" 'onlinestring :=.

Beyond Reactive Safety: Risk-Aware LLM Alignment via Long-Horizon Simulation online" 'onlinestring :=

Reference 41

Resolution: unresolved; no resolver link, observed 2026-08-06T22:42:45.606247Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation df35535b-4f54-4779-9f2d-c99773517858 · outbound

This paper cites write newline.

Beyond Reactive Safety: Risk-Aware LLM Alignment via Long-Horizon Simulation write newline

Reference 42

Resolution: unresolved; no resolver link, observed 2026-08-06T22:42:45.610334Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation 5db44cf2-f8d4-4f80-ae64-5af0f24712ab · inbound

Agentic AI Security: Threats, Defenses, Evaluation, and Open Challenges cites this paper.

Agentic AI Security: Threats, Defenses, Evaluation, and Open Challenges Beyond Reactive Safety: Risk-Aware LLM Alignment via Long-Horizon Simulation

Reference 252

Resolution: verified exact; arxiv_id, observed 2026-05-18T03:42:21.997734Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.