Typed states for the displayed outbound observations.
Source: paper_references, paper_reference_links, observed 2026-08-06T12:25:21.988161Z
Paper Citation Record · LEDGER
The Problem with Safety Classification is not just the Models
As of 8 August 2026, this Paper Citation Record lists 15 of 15 outbound references and 0 inbound Pith citation observations for arXiv:2507.21782.
A citation records a reference. It does not transfer a finding from one paper to another.
Coverage vector
One-hop event checks from named stored sources.
Source: scholarly_work_events, retraction_status_cache, observed 2026-08-08T06:32:00.761636+00:00
Pith citing papers itemized under the disclosed page cap.
Source: paper_references, paper_reference_links
A source-named dated measurement, never combined with another source.
Source: cited_works
Reference resolution
15 of 15 outbound references displayed
- verified exact0
- verified fuzzy2
- unresolved13
- parse uncertain0
- malformed identifier0
- metadata mismatch0
External citation measurements
No source-named external measurement is stored.
Outbound references
Observation 43f77407-56ea-4609-babe-a86db53e0227 · outbound
This paper cites an unresolved cited work.
The Problem with Safety Classification is not just the Models Unresolved cited work
Reference 5
- Resolution
- unresolved
- raw_fallback, observed 2026-08-06T12:25:22.307592Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.
Observation 6496cf94-5610-4b0c-8849-993e786cb0b6 · outbound
This paper cites Preprint, arXiv:2502.05163.
The Problem with Safety Classification is not just the Models Preprint, arXiv:2502.05163
Reference 6
- Resolution
- unresolved
- no resolver link, observed 2026-08-06T12:25:21.955337Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation f8aa02b0-d615-4334-b707-09bfeeaf163b · outbound
This paper cites Llama Guard: LLM-based Input-Output Safeguard for Human-AI Conversations.
The Problem with Safety Classification is not just the Models Llama Guard: LLM-based Input-Output Safeguard for Human-AI Conversations
Reference 7
- Resolution
- unresolved
- no resolver link, observed 2026-08-06T12:25:21.959665Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation b709662c-369e-4fde-8253-b4c71046e81e · outbound
This paper cites PolyGuard: A Multilingual Safety Moderation Tool for 17 Languages.
The Problem with Safety Classification is not just the Models PolyGuard: A Multilingual Safety Moderation Tool for 17 Languages
Reference 8
- Resolution
- unresolved
- no resolver link, observed 2026-08-06T12:25:21.963287Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation c67655d0-24f1-42ea-a081-c93e80b658a5 · outbound
This paper cites an unresolved cited work.
The Problem with Safety Classification is not just the Models Unresolved cited work
Reference 9
- Resolution
- unresolved
- raw_fallback, observed 2026-08-06T12:25:22.295717Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.
Observation 2de46aa8-9bbd-4a3f-8f49-1cbbcbe73120 · outbound
This paper cites Policy-as-Prompt: Rethinking Content Moderation in the Age of Large Language Models.
The Problem with Safety Classification is not just the Models Policy-as-Prompt: Rethinking Content Moderation in the Age of Large Language Models
Reference 10
- Resolution
- unresolved
- no resolver link, observed 2026-08-06T12:25:21.970377Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 56396b0b-beb1-43fe-abbf-4cbbb9394c7a · outbound
This paper cites In Proceedings of the 2023 Conference on Empiri- cal Methods in Natural Language Processing: Sys- tem Demonstrations, pages 431–445.
The Problem with Safety Classification is not just the Models In Proceedings of the 2023 Conference on Empiri- cal Methods in Natural Language Processing: Sys- tem Demonstrations, pages 431–445
Reference 11
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-06T12:25:22.284542Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.
Observation 98b4364d-e837-4b0d-bf52-8644c2ea80f2 · outbound
This paper cites arXiv preprint arXiv:2505.23856.
The Problem with Safety Classification is not just the Models arXiv preprint arXiv:2505.23856
Reference 12
- Resolution
- unresolved
- no resolver link, observed 2026-08-06T12:25:21.977393Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 6c2ff2d4-a989-4f3a-9453-2856555a01e0 · outbound
This paper cites In Findings of the Association for Computational Linguistics ACL 2024 , pages 5865–.
The Problem with Safety Classification is not just the Models In Findings of the Association for Computational Linguistics ACL 2024 , pages 5865–
Reference 13
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-06T12:25:22.272992Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.
Observation b0c2cb60-478d-434b-8fe9-97faa93358d3 · outbound
This paper cites The State of Multilingual LLM Safety Research: From Measuring the Language Gap to Mitigating It.
The Problem with Safety Classification is not just the Models The State of Multilingual LLM Safety Research: From Measuring the Language Gap to Mitigating It
Reference 14
- Resolution
- unresolved
- no resolver link, observed 2026-08-06T12:25:21.984374Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 31535b66-7c8f-4377-a38a-cdf2bddd12b7 · outbound
This paper cites ShieldGemma: Generative AI Content Moderation Based on Gemma.
The Problem with Safety Classification is not just the Models ShieldGemma: Generative AI Content Moderation Based on Gemma
Reference 15
- Resolution
- unresolved
- no resolver link, observed 2026-08-06T12:25:21.988161Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation a95f93e7-75f0-4f81-b8d4-158d786cb26d · outbound
This paper cites Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback.
The Problem with Safety Classification is not just the Models Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback
Reference 2022
- Resolution
- unresolved
- no resolver link, observed 2026-08-06T12:25:21.947783Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 762e6b12-0a43-4c80-a82a-d16d5c3de2db · outbound
This paper cites GPT-4 Technical Report.
The Problem with Safety Classification is not just the Models GPT-4 Technical Report
Reference 2023
- Resolution
- unresolved
- no resolver link, observed 2026-08-06T12:25:21.940256Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 4461298f-46f1-4e82-bef2-3b281a598118 · outbound
This paper cites The Multilingual Alignment Prism: Aligning Global and Local Preferences to Reduce Harm.
The Problem with Safety Classification is not just the Models The Multilingual Alignment Prism: Aligning Global and Local Preferences to Reduce Harm
Reference 2024
- Resolution
- unresolved
- no resolver link, observed 2026-08-06T12:25:21.935687Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 36caeb73-5f87-4b80-9b19-4228892d63ef · outbound
This paper cites an unresolved cited work.
The Problem with Safety Classification is not just the Models Unresolved cited work
Reference 2025
- Resolution
- unresolved
- raw_fallback, observed 2026-08-06T12:25:22.317577Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.
Pith citing papers
No inbound Pith citation observations are available.