Paper Citation Record · LEDGER

Same Dangerous Objective, Opposite Advice: Direct Exposure versus Multi-Agent Mediation

As of 15 August 2026, this Paper Citation Record lists 16 of 16 outbound references and 0 inbound Pith citation observations for arXiv:2607.21518.

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

pith.paper-citation-record.v1
2607.21518 v1

Coverage vector

measured 16 of 16 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-01T07:16:02.443284Z

measured 16 of 16 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

16 of 16 outbound references displayed

verified exact0
verified fuzzy0
unresolved15
parse uncertain0
malformed identifier1
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 727bf8bf-af72-4d5e-8520-818ce48fb764 · outbound

This paper cites Constitutional AI: Harmlessness from AI Feedback.

Same Dangerous Objective, Opposite Advice: Direct Exposure versus Multi-Agent Mediation Constitutional AI: Harmlessness from AI Feedback

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-01T07:16:02.349786Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fd254004-2404-4b60-834f-e030f56bfef1 · outbound

This paper cites Alignment faking in large language models.

Same Dangerous Objective, Opposite Advice: Direct Exposure versus Multi-Agent Mediation Alignment faking in large language models

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-01T07:16:02.388415Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0d3b73b7-7a06-47cc-8ae7-adb020cc92d9 · outbound

This paper cites Sleeper Agents: Training Deceptive LLMs that Persist Through Safety Training.

Same Dangerous Objective, Opposite Advice: Direct Exposure versus Multi-Agent Mediation Sleeper Agents: Training Deceptive LLMs that Persist Through Safety Training

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-01T07:16:02.400998Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5048bffa-aef4-4ffd-ad6d-f7f24bdf424a · outbound

This paper cites Auditing language models for hidden objectives.

Same Dangerous Objective, Opposite Advice: Direct Exposure versus Multi-Agent Mediation Auditing language models for hidden objectives

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-01T07:16:02.407247Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1e24397f-67c3-4b5f-90be-a7d332231bde · outbound

This paper cites Frontier Models are Capable of In-context Scheming.

Same Dangerous Objective, Opposite Advice: Direct Exposure versus Multi-Agent Mediation Frontier Models are Capable of In-context Scheming

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-01T07:16:02.419877Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2b08e2da-563c-40b3-a4f7-76b323766029 · outbound

This paper cites doi: 10.18653/v1/2023.findings-acl.847.

Same Dangerous Objective, Opposite Advice: Direct Exposure versus Multi-Agent Mediation doi: 10.18653/v1/2023.findings-acl.847

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-01T07:16:02.426157Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ab57785a-77a0-487e-865e-b31a9c51fd0a · outbound

This paper cites URL https://proceedings.neurips.cc/paper_files/paper/2023/ hash/ed3fea9033a80fea1376299fa7863f4a-Abstract-Conference.html.

Same Dangerous Objective, Opposite Advice: Direct Exposure versus Multi-Agent Mediation URL https://proceedings.neurips.cc/paper_files/paper/2023/ hash/ed3fea9033a80fea1376299fa7863f4a-Abstract-Conference.html

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-01T07:16:02.431628Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0f1a18fc-b149-4f32-8c72-bd94008c3f9a · outbound

This paper cites Qiusi Zhan, Zhixiang Liang, Zifan Ying, and Daniel Kang.

Same Dangerous Objective, Opposite Advice: Direct Exposure versus Multi-Agent Mediation Qiusi Zhan, Zhixiang Liang, Zifan Ying, and Daniel Kang

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-01T07:16:02.438374Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6e31b94f-e9fc-4cb8-ba5f-57f9a7dccafc · outbound

This paper cites doi: 10.18653/v1/2024.findings-acl.624.

Same Dangerous Objective, Opposite Advice: Direct Exposure versus Multi-Agent Mediation doi: 10.18653/v1/2024.findings-acl.624

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-01T07:16:02.443284Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b6e547ab-049c-4974-b733-6a5a693b180a · outbound

This paper cites Alignment faking in large language models.

Same Dangerous Objective, Opposite Advice: Direct Exposure versus Multi-Agent Mediation Alignment faking in large language models

Reference 1923

Resolution: unresolved; no resolver link, observed 2026-08-01T07:16:02.381976Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2141d33e-16bc-4322-b92f-3a77324a2b8d · outbound

This paper cites URL https://doi.

Same Dangerous Objective, Opposite Advice: Direct Exposure versus Multi-Agent Mediation URL https://doi

Reference 1960

Resolution: unresolved; no resolver link, observed 2026-08-01T07:16:02.364315Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9aac6618-fef5-47ba-bcfd-16ad0c6d6c1e · outbound

This paper cites doi: 10.1201/9780429246593.

Same Dangerous Objective, Opposite Advice: Direct Exposure versus Multi-Agent Mediation doi: 10.1201/9780429246593

Reference 1994

Resolution: unresolved; no resolver link, observed 2026-08-01T07:16:02.376566Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7930f030-0e8e-4504-b9f0-dc94e3372f7a · outbound

This paper cites Constitutional AI: Harmlessness from AI Feedback.

Same Dangerous Objective, Opposite Advice: Direct Exposure versus Multi-Agent Mediation Constitutional AI: Harmlessness from AI Feedback

Reference 2022

Resolution: unresolved; no resolver link, observed 2026-08-01T07:16:02.357924Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 786d3824-a9e1-4d4a-80fc-22dd5c6e814c · outbound

This paper cites doi: 10.1145/3605764.3623985.

Same Dangerous Objective, Opposite Advice: Direct Exposure versus Multi-Agent Mediation doi: 10.1145/3605764.3623985

Reference 2023

Resolution: unresolved; no resolver link, observed 2026-08-01T07:16:02.395357Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3a4db23d-2d30-4c91-8bf3-1ad6c4e352de · outbound

This paper cites URL https://proceedings.neurips.cc/paper_files/paper/2024/hash/ 97091a5177d8dc64b1da8bf3e1f6fb54-Abstract-Datasets_and_Benchmarks_Track.html.

Same Dangerous Objective, Opposite Advice: Direct Exposure versus Multi-Agent Mediation URL https://proceedings.neurips.cc/paper_files/paper/2024/hash/ 97091a5177d8dc64b1da8bf3e1f6fb54-Abstract-Datasets_and_Benchmarks_Track.html

Reference 2024

Resolution: malformed identifier; no resolver link, observed 2026-08-01T07:16:02.370023Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 33c2b679-5937-4d5c-b354-19eda83950bc · outbound

This paper cites Auditing language models for hidden objectives.

Same Dangerous Objective, Opposite Advice: Direct Exposure versus Multi-Agent Mediation Auditing language models for hidden objectives

Reference 2025

Resolution: unresolved; no resolver link, observed 2026-08-01T07:16:02.413345Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

No inbound Pith citation observations are available.