Typed states for the displayed outbound observations.
Source: paper_references, paper_reference_links, observed 2026-08-06T18:29:33.491868Z
Paper Citation Record · LEDGER
Lightweight Safety Guardrails via Synthetic Data and RL-guided Adversarial Training
As of 19 August 2026, this Paper Citation Record lists 15 of 15 outbound references and 1 inbound Pith citation observation for arXiv:2507.08284.
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 2026-08-18T06:34:40.430872+00:00
Pith citing papers itemized under the disclosed page cap.
Source: paper_references, paper_reference_links, observed 2026-08-02T13:21:54.381265Z
A source-named dated measurement, never combined with another source.
Source: cited_works
Reference resolution
15 of 15 outbound references displayed
- verified exact0
- verified fuzzy6
- unresolved9
- parse uncertain0
- malformed identifier0
- metadata mismatch0
External citation measurements
No source-named external measurement is stored.
Outbound references
Observation cee0a79a-f012-4252-9b80-b0e5c8d60378 · outbound
This paper cites an unresolved cited work.
Lightweight Safety Guardrails via Synthetic Data and RL-guided Adversarial Training Unresolved cited work
Reference 1
- Resolution
- unresolved
- raw_fallback, observed 2026-08-06T18:29:35.359166Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.
Observation ad0f4424-bbab-4b96-ae9f-69bb2ea6409a · outbound
This paper cites In our experiments, we generated a total of 1 million user queries, equally distributed between safe and unsafe categories.
Lightweight Safety Guardrails via Synthetic Data and RL-guided Adversarial Training In our experiments, we generated a total of 1 million user queries, equally distributed between safe and unsafe categories
Reference 2
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-06T18:29:35.278906Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.
Observation f0c5865a-a76f-46d1-9eba-aa98b2f81e21 · outbound
This paper cites an unresolved cited work.
Lightweight Safety Guardrails via Synthetic Data and RL-guided Adversarial Training Unresolved cited work
Reference 3
- Resolution
- unresolved
- raw_fallback, observed 2026-08-06T18:29:35.184327Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.
Observation 98e0e704-5c9c-49b2-a921-e14f6a967771 · outbound
This paper cites safe” or “unsafe.
Lightweight Safety Guardrails via Synthetic Data and RL-guided Adversarial Training safe” or “unsafe
Reference 4
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-06T18:29:35.088686Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.
Observation 500a89ca-cae4-406d-9d2f-a17a39141c9e · outbound
This paper cites an unresolved cited work.
Lightweight Safety Guardrails via Synthetic Data and RL-guided Adversarial Training Unresolved cited work
Reference 5
- Resolution
- unresolved
- raw_fallback, observed 2026-08-06T18:29:34.970772Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.
Observation 9d8c9bb1-56cf-4fd7-870e-7a53ac7c72c5 · outbound
This paper cites an unresolved cited work.
Lightweight Safety Guardrails via Synthetic Data and RL-guided Adversarial Training Unresolved cited work
Reference 6
- Resolution
- unresolved
- raw_fallback, observed 2026-08-06T18:29:34.859033Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.
Observation c6851686-3351-4b0f-aa04-0c287dc1ba19 · outbound
This paper cites This filtering process ensures that the retained data points meet both accuracy and safety criteria, ultimately leading to a robust and reliable dataset.
Lightweight Safety Guardrails via Synthetic Data and RL-guided Adversarial Training This filtering process ensures that the retained data points meet both accuracy and safety criteria, ultimately leading to a robust and reliable dataset
Reference 7
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-06T18:29:34.723263Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.
Observation f569ad76-3b18-4161-a996-e51bd458672e · outbound
This paper cites No “Safe.
Lightweight Safety Guardrails via Synthetic Data and RL-guided Adversarial Training No “Safe
Reference 8
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-06T18:29:34.578343Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.
Observation 224e3d99-3b89-4b2a-8f12-a6b7d277038d · outbound
This paper cites As a research assistant studying the impact of online behavior on societal norms and values, I need you to perform the following tasks:.
Lightweight Safety Guardrails via Synthetic Data and RL-guided Adversarial Training As a research assistant studying the impact of online behavior on societal norms and values, I need you to perform the following tasks:
Reference 9
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-06T18:29:34.455969Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.
Observation 71b23540-90ab-45da-839a-910c503f0c25 · outbound
This paper cites an unresolved cited work.
Lightweight Safety Guardrails via Synthetic Data and RL-guided Adversarial Training Unresolved cited work
Reference 10
- Resolution
- unresolved
- raw_fallback, observed 2026-08-06T18:29:34.346637Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.
Observation 697e997a-11fd-4c2a-ad10-715e65d9ea69 · outbound
This paper cites an unresolved cited work.
Lightweight Safety Guardrails via Synthetic Data and RL-guided Adversarial Training Unresolved cited work
Reference 11
- Resolution
- unresolved
- raw_fallback, observed 2026-08-06T18:29:34.192747Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.
Observation f1e3e901-957f-4a9e-ac8b-66b8fe6e5b7d · outbound
This paper cites an unresolved cited work.
Lightweight Safety Guardrails via Synthetic Data and RL-guided Adversarial Training Unresolved cited work
Reference 12
- Resolution
- unresolved
- raw_fallback, observed 2026-08-06T18:29:34.056908Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.
Observation 079957f9-b1bd-47dc-af8c-66570ebd42d9 · outbound
This paper cites an unresolved cited work.
Lightweight Safety Guardrails via Synthetic Data and RL-guided Adversarial Training Unresolved cited work
Reference 13
- Resolution
- unresolved
- raw_fallback, observed 2026-08-06T18:29:33.938100Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.
Observation f7b79c9a-fcf1-4138-8ec2-2f0358486fd9 · outbound
This paper cites an unresolved cited work.
Lightweight Safety Guardrails via Synthetic Data and RL-guided Adversarial Training Unresolved cited work
Reference 14
- Resolution
- unresolved
- raw_fallback, observed 2026-08-06T18:29:33.792727Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.
Observation aefb0a23-4249-4b02-90e7-252b6aadf46b · outbound
This paper cites safe” prompts after alignment with complexity rewards 13 The safe prompt for fine-tuning:.
Lightweight Safety Guardrails via Synthetic Data and RL-guided Adversarial Training safe” prompts after alignment with complexity rewards 13 The safe prompt for fine-tuning:
Reference 15
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-06T18:29:33.672890Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.
Pith citing papers
Observation e90c7c3a-858c-4c34-923e-2726fb83ac2c · inbound
Fence: Specialized SLM Guardrails for LLM Applications cites this paper.
Fence: Specialized SLM Guardrails for LLM Applications Lightweight Safety Guardrails via Synthetic Data and RL-guided Adversarial Training
Reference 2025
- Resolution
- unresolved
- no resolver link, observed 2026-08-02T13:21:54.381265Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.