Paper Citation Record · LEDGER

Granite Guardian

As of 18 August 2026, this Paper Citation Record lists 37 of 37 outbound references and 26 inbound Pith citation observations for arXiv:2412.07724.

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

pith.paper-citation-record.v1
2412.07724 v2

Coverage vector

measured 37 of 37 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-11T18:37:09.539148Z

measured 63 of 63 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-18T06:34:40.430872+00:00

measured 26 of 26 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-15T21:19:25.702916Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-07-03T20:38:54.910365Z

Reference resolution

37 of 37 outbound references displayed

verified exact2
verified fuzzy13
unresolved22
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 49f00bda-38d5-4fb2-852f-87a54dd2da73 · outbound

This paper cites Detectors for Safe and Reliable LLMs: Implementations, Uses, and Limitations.

Granite Guardian Detectors for Safe and Reliable LLMs: Implementations, Uses, and Limitations

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-11T18:37:09.363361Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f5284848-538a-4e36-81a3-f71074ec8bd1 · outbound

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

Granite Guardian Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-11T18:37:09.375357Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1bf5f906-5679-4e01-a3fa-bcb81c063930 · outbound

This paper cites AEGIS: Online Adaptive AI Content Safety Moderation with Ensemble of LLM Experts.

Granite Guardian AEGIS: Online Adaptive AI Content Safety Moderation with Ensemble of LLM Experts

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-11T18:37:09.396207Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation efbdd58b-621b-45e2-a1f2-cd38ab627bb0 · outbound

This paper cites DialFact: A Benchmark for Fact-Checking in Dialogue.

Granite Guardian DialFact: A Benchmark for Fact-Checking in Dialogue

Reference 8

Resolution: verified exact; local_arxiv, observed 2026-08-11T18:37:09.940600Z

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 07af79c9-0ae4-4823-82cc-961e69cda270 · outbound

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

Granite Guardian WildGuard: Open One-Stop Moderation Tools for Safety Risks, Jailbreaks, and Refusals of LLMs

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-11T18:37:09.407592Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f658fc9c-8b94-456b-bb53-7b00a8893398 · outbound

This paper cites URL https:// aclanthology.org/2021.emnlp-main.619.

Granite Guardian URL https:// aclanthology.org/2021.emnlp-main.619

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T18:37:10.193980Z

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 a3554e3d-2752-4850-9d35-7b199b36c4ce · outbound

This paper cites Llama Guard: LLM-based Input-Output Safeguard for Human-AI Conversations.

Granite Guardian Llama Guard: LLM-based Input-Output Safeguard for Human-AI Conversations

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-11T18:37:09.422521Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f195c0cd-ef30-4970-a97f-f2953636dfc7 · outbound

This paper cites WildTeaming at Scale: From In-the-Wild Jailbreaks to (Adversarially) Safer Language Models.

Granite Guardian WildTeaming at Scale: From In-the-Wild Jailbreaks to (Adversarially) Safer Language Models

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-11T18:37:09.431837Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 33352a5b-9a2c-4faa-9b01-1f4029128e05 · outbound

This paper cites Toxicchat: Unveiling hidden challenges of toxicity detection in real-world user-ai conversation.

Granite Guardian Toxicchat: Unveiling hidden challenges of toxicity detection in real-world user-ai conversation

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T18:37:10.178899Z

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 bcf2ebcf-ae9a-4093-9b9a-ece9f884b2ea · outbound

This paper cites On faithfulness and factuality in abstractive summarization.

Granite Guardian On faithfulness and factuality in abstractive summarization

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T18:37:10.163624Z

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 edd39436-c194-4c3c-b121-14aa48eee8e8 · outbound

This paper cites AI safety v0.5 proof of concept.

Granite Guardian AI safety v0.5 proof of concept

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T18:37:10.147864Z

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 037aa098-ae99-4d5d-b3c9-a76bcda0f0ca · outbound

This paper cites Don’t give me the details, just the summary! topic-aware convolutional neural networks for extreme summarization.

Granite Guardian Don’t give me the details, just the summary! topic-aware convolutional neural networks for extreme summarization

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T18:37:10.133218Z

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 4ca22ffd-9db1-4b22-bb01-6120be77fc58 · outbound

This paper cites OWASP Top 10 for Large Language Model Applications.

Granite Guardian OWASP Top 10 for Large Language Model Applications

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T18:37:10.119077Z

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 54bb927b-d886-4088-a5ab-7b017bc0189f · outbound

This paper cites URL https://doi.org/10.1177/0146167217741313.

Granite Guardian URL https://doi.org/10.1177/0146167217741313

Reference 21

Resolution: verified exact; doi, observed 2026-08-11T18:37:09.623380Z

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 8e4b4dca-855f-4d30-93cc-20025340c139 · outbound

This paper cites doi: 10.18653/v1/2021.naacl-main.383.

Granite Guardian doi: 10.18653/v1/2021.naacl-main.383

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-11T18:37:09.468769Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 11067dae-6004-4bb7-9067-71c638c9c933 · outbound

This paper cites doi: 10.18653/v1/P18-2124.

Granite Guardian doi: 10.18653/v1/P18-2124

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-11T18:37:09.473630Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 62e53b05-2dec-4d57-98cb-8913088a9da9 · outbound

This paper cites Attack Atlas: A Practitioner's Perspective on Challenges and Pitfalls in Red Teaming GenAI.

Granite Guardian Attack Atlas: A Practitioner's Perspective on Challenges and Pitfalls in Red Teaming GenAI

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-11T18:37:09.478432Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cd032d25-2b61-4c97-be6b-39d93cae2718 · outbound

This paper cites Ignore This Title and HackAPrompt: Exposing Systemic Vulnerabilities of LLMs through a Global Scale Prompt Hacking Competition.

Granite Guardian Ignore This Title and HackAPrompt: Exposing Systemic Vulnerabilities of LLMs through a Global Scale Prompt Hacking Competition

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-11T18:37:09.483349Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3d93d9de-315b-48b3-8b39-a0a0c3dd3959 · outbound

This paper cites Ignore This Title and HackAPrompt: Exposing Systemic Vulnerabilities of LLMs through a Global Scale Prompt Hacking Competition.

Granite Guardian Ignore This Title and HackAPrompt: Exposing Systemic Vulnerabilities of LLMs through a Global Scale Prompt Hacking Competition

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-11T18:37:09.488075Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f7f2045f-f494-443d-9cb9-762941d3346d · outbound

This paper cites The AI risk repository: A meta-review, database, and taxonomy of risks from artificial intelligence.

Granite Guardian The AI risk repository: A meta-review, database, and taxonomy of risks from artificial intelligence

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-11T18:37:09.492476Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 276d121f-1343-4c87-9898-763eb331682c · outbound

This paper cites MiniCheck: Efficient fact-checking of LLMs on grounding documents.

Granite Guardian MiniCheck: Efficient fact-checking of LLMs on grounding documents

Reference 28

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T18:37:10.103191Z

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 15b762d3-4917-49e8-84d7-d0d536cc8010 · outbound

This paper cites URL https://aclanthology.org/2024.emnlp-main.499.

Granite Guardian URL https://aclanthology.org/2024.emnlp-main.499

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T18:37:10.085497Z

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 cae8885e-c4ac-4346-8433-95b7ff417fed · outbound

This paper cites Llama 2: Open Foundation and Fine-Tuned Chat Models.

Granite Guardian Llama 2: Open Foundation and Fine-Tuned Chat Models

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-11T18:37:09.506514Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 26fd4747-a2ad-4cfa-b1e9-139de5cd2713 · outbound

This paper cites SimpleSafetyTests: a Test Suite for Identifying Critical Safety Risks in Large Language Models.

Granite Guardian SimpleSafetyTests: a Test Suite for Identifying Critical Safety Risks in Large Language Models

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-11T18:37:09.511553Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 44c2ce5b-1fb6-4ade-9c72-b71c47d59f32 · outbound

This paper cites doi: 10.18653/v1/2020.acl-main.450.

Granite Guardian doi: 10.18653/v1/2020.acl-main.450

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-11T18:37:09.516596Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e06c2fb5-6eaf-41db-aba3-fab58ca0fd73 · outbound

This paper cites A broad-coverage challenge corpus for sentence understanding through inference.

Granite Guardian A broad-coverage challenge corpus for sentence understanding through inference

Reference 33

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T18:37:10.070194Z

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 3c6588ef-f5c3-40df-a61c-20a4a51679a6 · outbound

This paper cites an unresolved cited work.

Granite Guardian Unresolved cited work

Reference 34

Resolution: unresolved; raw_fallback, observed 2026-08-11T18:37:10.053749Z

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 accd773b-a004-44c0-8907-ca7d81dfe7b0 · outbound

This paper cites ShieldGemma: Generative AI Content Moderation Based on Gemma.

Granite Guardian ShieldGemma: Generative AI Content Moderation Based on Gemma

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-11T18:37:09.530020Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 62309228-9ea6-43d7-bd1f-8aa2d0dcd2eb · outbound

This paper cites PAWS: Paraphrase adversaries from word scrambling.

Granite Guardian PAWS: Paraphrase adversaries from word scrambling

Reference 36

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T18:37:10.037724Z

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 5444ce29-8025-4b98-94da-57558ac03a26 · outbound

This paper cites q2: Evaluating factual consistency in knowledge-grounded dialogues via question generation and question answering.

Granite Guardian q2: Evaluating factual consistency in knowledge-grounded dialogues via question generation and question answering

Reference 2015

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T18:37:10.209108Z

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 a0b9f7c6-bdb4-4e89-9339-3819379e908c · outbound

This paper cites Josef Dai, Xuehai Pan, Ruiyang Sun, Jiaming Ji, Xinbo Xu, Mickel Liu, Yizhou Wang, and Yaodong Yang.

Granite Guardian Josef Dai, Xuehai Pan, Ruiyang Sun, Jiaming Ji, Xinbo Xu, Mickel Liu, Yizhou Wang, and Yaodong Yang

Reference 2018

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T18:37:10.224013Z

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 847d1bb5-808b-45c5-a09b-3f7cb2554165 · outbound

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

Granite Guardian Universal and Transferable Adversarial Attacks on Aligned Language Models

Reference 2019

Resolution: unresolved; no resolver link, observed 2026-08-11T18:37:09.539148Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 44584a0d-9b93-4765-b0b3-7aa38f54df1c · outbound

This paper cites doi: 10.18653/v1/2020.acl-main.173.

Granite Guardian doi: 10.18653/v1/2020.acl-main.173

Reference 2020

Resolution: unresolved; no resolver link, observed 2026-08-11T18:37:09.446715Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 013d6b17-61ed-4132-a7a7-8be16712e111 · outbound

This paper cites Latent Hatred: A Benchmark for Understanding Implicit Hate Speech.

Granite Guardian Latent Hatred: A Benchmark for Understanding Implicit Hate Speech

Reference 2021

Resolution: unresolved; no resolver link, observed 2026-08-11T18:37:09.391296Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 04dd7bd4-0fb0-4d2d-9821-c55b6ac75cd1 · outbound

This paper cites A large annotated corpus for learning natural language inference.

Granite Guardian A large annotated corpus for learning natural language inference

Reference 2022

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T18:37:10.238649Z

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 66796fb9-0a43-4da8-8b6a-e717994bb43f · outbound

This paper cites Llama Guard: LLM-based Input-Output Safeguard for Human-AI Conversations.

Granite Guardian Llama Guard: LLM-based Input-Output Safeguard for Human-AI Conversations

Reference 2023

Resolution: unresolved; no resolver link, observed 2026-08-11T18:37:09.427318Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f8f23ad9-21a4-4a6f-a0ac-661aecc2c5dd · outbound

This paper cites Evaluations of Machine Learning Privacy Defenses are Misleading.

Granite Guardian Evaluations of Machine Learning Privacy Defenses are Misleading

Reference 2024

Resolution: unresolved; no resolver link, observed 2026-08-11T18:37:09.369590Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation add17f0c-e5c3-43a4-a8b7-5916a2631bf3 · inbound

An Annotated Reading of 'The Singer of Tales' in the LLM Era cites this paper.

An Annotated Reading of 'The Singer of Tales' in the LLM Era Granite Guardian

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-08T20:08:32.725166Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9db93a84-fa5b-4383-ab6d-be8d78f5a327 · inbound

Dark LLMs: The Growing Threat of Unaligned AI Models cites this paper.

Dark LLMs: The Growing Threat of Unaligned AI Models Granite Guardian

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-15T21:19:25.702916Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ebd1aae8-08a5-4ac8-9781-3ee1135bf707 · inbound

Concealment of Intent: A Game-Theoretic Analysis cites this paper.

Concealment of Intent: A Game-Theoretic Analysis Granite Guardian

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-07T13:53:39.461607Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b19441e0-177a-44fe-95a2-815226a4e0b6 · inbound

Disentangled Safety Adapters Enable Efficient Guardrails and Flexible Inference-Time Alignment cites this paper.

Disentangled Safety Adapters Enable Efficient Guardrails and Flexible Inference-Time Alignment Granite Guardian

Reference 32

Resolution: verified exact; arxiv_id, observed 2026-05-19T11:53:03.602566Z

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 99b35f78-3fdc-4095-9493-5e5f5da29c49 · inbound

SafeTy Reasoning Elicitation Alignment for Multi-Turn Dialogues cites this paper.

SafeTy Reasoning Elicitation Alignment for Multi-Turn Dialogues Granite Guardian

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-07T12:04:46.927403Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e45241f8-8ebd-45f5-b39e-5051199e0250 · inbound

JavelinGuard: Low-Cost Transformer Architectures for LLM Security cites this paper.

JavelinGuard: Low-Cost Transformer Architectures for LLM Security Granite Guardian

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-07T05:41:25.455039Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3e3f62cc-7afd-40bc-917f-eeed3bfd9910 · inbound

Adversarial Bug Reports as a Security Risk in Language Model-Based Automated Program Repair cites this paper.

Adversarial Bug Reports as a Security Risk in Language Model-Based Automated Program Repair Granite Guardian

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-05T10:29:20.657711Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a4710658-57a5-43b5-890e-a48c0ce0be53 · inbound

Bielik Guard: Efficient Polish Language Safety Classifiers for LLM Content Moderation cites this paper.

Bielik Guard: Efficient Polish Language Safety Classifiers for LLM Content Moderation Granite Guardian

Reference 16

Resolution: metadata mismatch; arxiv_id, observed 2026-05-16T06:07:25.573450Z

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 c160fdaf-a08b-48ce-bcc9-d4c17e103ddd · inbound

Guardian-as-an-Advisor: Advancing Next-Generation Guardian Models for Trustworthy LLMs cites this paper.

Guardian-as-an-Advisor: Advancing Next-Generation Guardian Models for Trustworthy LLMs Granite Guardian

Reference 57

Resolution: metadata mismatch; arxiv_id, observed 2026-05-11T06:46:38.138360Z

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 ba3cdc33-703f-49e6-854e-6ebd0fc23edf · inbound

RAGognizer: Hallucination-Aware Fine-Tuning via Detection Head Integration cites this paper.

RAGognizer: Hallucination-Aware Fine-Tuning via Detection Head Integration Granite Guardian

Reference 23

Resolution: metadata mismatch; arxiv_id, observed 2026-05-10T08:43:02.000605Z

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 3a927148-053b-4437-b096-232ac64b7a31 · inbound

TWGuard: A Case Study of LLM Safety Guardrails for Localized Linguistic Contexts cites this paper.

TWGuard: A Case Study of LLM Safety Guardrails for Localized Linguistic Contexts Granite Guardian

Reference 12

Resolution: verified exact; arxiv_id, observed 2026-05-10T09:08:25.568187Z

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 85cccfbc-7f5e-424a-9a79-d62836e10b1a · inbound

Structured Security Auditing and Robustness Enhancement for Untrusted Agent Skills cites this paper.

Structured Security Auditing and Robustness Enhancement for Untrusted Agent Skills Granite Guardian

Reference 16

Resolution: verified exact; arxiv_id, observed 2026-05-11T23:46:16.339429Z

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 bd324d92-bf14-441b-af29-4be24da6c197 · inbound

When Safety Geometry Collapses: Fine-Tuning Vulnerabilities in Agentic Guard Models cites this paper.

When Safety Geometry Collapses: Fine-Tuning Vulnerabilities in Agentic Guard Models Granite Guardian

Reference 6

Resolution: metadata mismatch; arxiv_id, observed 2026-05-11T00:05:49.322040Z

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 d133d424-1d0a-4521-afc0-26dd46581487 · inbound

Benchmarking Open-Source Safety Guard Models: A Comprehensive Evaluation cites this paper.

Benchmarking Open-Source Safety Guard Models: A Comprehensive Evaluation Granite Guardian

Reference 12

Resolution: unresolved; no resolver link, observed 2026-07-12T23:33:25.778345Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bf45abf5-dbaf-4118-83cb-fa0eccbd1f4d · inbound

Opir: Efficient Multi-Task Safety Classification for Toxicity, Jailbreaks, Hate Speech, and Harmful Content cites this paper.

Opir: Efficient Multi-Task Safety Classification for Toxicity, Jailbreaks, Hate Speech, and Harmful Content Granite Guardian

Reference 29

Resolution: verified exact; arxiv_id, observed 2026-06-29T09:13:15.985968Z

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 2790371d-1cb7-40de-a75b-20befd7f763a · inbound

Safety Measurements for Fine-tuned LLMs Should be Grounded in Capability cites this paper.

Safety Measurements for Fine-tuned LLMs Should be Grounded in Capability Granite Guardian

Reference 47

Resolution: metadata mismatch; arxiv_id, observed 2026-07-02T03:26:29.819529Z

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 a7d4e77d-b7cd-467d-b680-a602e2547c0f · inbound

Distilling Safe LLM Systems via Soft Prompts for On Device Settings cites this paper.

Distilling Safe LLM Systems via Soft Prompts for On Device Settings Granite Guardian

Reference 45

Resolution: metadata mismatch; arxiv_id, observed 2026-07-03T00:27:29.234744Z

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 847622ec-4900-4320-a49c-379d6d20c338 · inbound

BELLS-O: Evaluating the Operational Trade-offs of LLM Supervision Systems cites this paper.

BELLS-O: Evaluating the Operational Trade-offs of LLM Supervision Systems Granite Guardian

Reference 2

Resolution: verified exact; arxiv_id, observed 2026-07-03T16:38:40.766073Z

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 98c98942-e322-4f0e-91f5-dcf8072acd77 · inbound

Cognitive Firewall: A Proactive, Zero-Trust, Multi-Gate Framework for LLM Safety cites this paper.

Cognitive Firewall: A Proactive, Zero-Trust, Multi-Gate Framework for LLM Safety Granite Guardian

Reference 4

Resolution: verified exact; arxiv_id, observed 2026-07-03T20:38:54.912009Z

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 3b783caa-c649-4cf4-8e97-3c668c3d182a · inbound

HyperSafe: Inference-Time Safety Recovery for Fine-Tuned Language Models cites this paper.

HyperSafe: Inference-Time Safety Recovery for Fine-Tuned Language Models Granite Guardian

Reference 10

Resolution: unresolved; no resolver link, observed 2026-07-14T05:21:30.132993Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c039225c-efed-4ebf-addc-d5b8a6f697d3 · inbound

Symbolic Augmentation Closes a Canonical-Equivalence Blind Spot in Neural Fact-Checkers cites this paper.

Symbolic Augmentation Closes a Canonical-Equivalence Blind Spot in Neural Fact-Checkers Granite Guardian

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-02T13:40:18.733148Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4fcbaf36-3046-4b4e-839f-c65659a7c6fb · inbound

CPInj: Uncovering Prompt Injection Risks in Textual Collaborative Prompt Optimization cites this paper.

CPInj: Uncovering Prompt Injection Risks in Textual Collaborative Prompt Optimization Granite Guardian

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-01T14:56:08.423736Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation abc6bdd9-fa6d-4439-9573-ffd07e8ee868 · inbound

CPInj: Uncovering Prompt Injection Risks in Textual Collaborative Prompt Optimization cites this paper.

CPInj: Uncovering Prompt Injection Risks in Textual Collaborative Prompt Optimization Granite Guardian

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-03T01:56:58.170447Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 854e725e-9c82-4c49-80bd-72bfce434bb3 · inbound

DARWIN: Evolving Jailbreak Adversary and Guardrail for LLM Safety Evaluation and Protection cites this paper.

DARWIN: Evolving Jailbreak Adversary and Guardrail for LLM Safety Evaluation and Protection Granite Guardian

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-01T11:40:27.436778Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 98e0530f-2a6f-431a-ae7c-c0252cc6c0c2 · inbound

JANUS: Foreseeing Latent Risk for Long-Horizon Agent Safety cites this paper.

JANUS: Foreseeing Latent Risk for Long-Horizon Agent Safety Granite Guardian

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-01T11:24:49.018907Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b28a13af-8bc0-4450-9608-587542258f0c · inbound

Semalith v1.4: A Calibrated 184M Safety Classifier Achieving State-of-the-Art Prompt-Injection Detection at 44x Fewer Parameters than Llama-Guard-3-8B cites this paper.

Semalith v1.4: A Calibrated 184M Safety Classifier Achieving State-of-the-Art Prompt-Injection Detection at 44x Fewer Parameters than Llama-Guard-3-8B Granite Guardian

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-02T14:52:12.527253Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.