Paper Citation Record · LEDGER

Llama Guard 3-1B-INT4: Compact and Efficient Safeguard for Human-AI Conversations

As of 23 August 2026, this Paper Citation Record lists 23 of 23 outbound references and 16 inbound Pith citation observations for arXiv:2411.17713.

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

pith.paper-citation-record.v1
2411.17713 v1

Coverage vector

measured 23 of 23 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-12T18:02:25.968729Z

measured 39 of 39 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-23T06:30:58.430688+00:00

measured 16 of 16 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-14T04:14:46.739648Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-07-04T15:59:56.708231Z

Reference resolution

23 of 23 outbound references displayed

verified exact0
verified fuzzy11
unresolved12
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation ec53149a-042b-4281-9fc4-e7bc053d77e1 · outbound

This paper cites write newline.

Llama Guard 3-1B-INT4: Compact and Efficient Safeguard for Human-AI Conversations write newline

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-12T18:02:25.872059Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7a8b78e5-f8bf-4fbe-8866-31841d6c45d8 · outbound

This paper cites https://ai.meta.com/blog/llama-3-2-connect-2024-vision-edge-mobile-devices/.

Llama Guard 3-1B-INT4: Compact and Efficient Safeguard for Human-AI Conversations https://ai.meta.com/blog/llama-3-2-connect-2024-vision-edge-mobile-devices/

Reference 2

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T18:02:26.263883Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation ca20e436-acf1-4005-aaab-8b2b845c16c5 · outbound

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

Llama Guard 3-1B-INT4: Compact and Efficient Safeguard for Human-AI Conversations Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-12T18:02:25.883378Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 438e7723-d9be-490f-9d23-9ab6ba9e7048 · outbound

This paper cites Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computation.

Llama Guard 3-1B-INT4: Compact and Efficient Safeguard for Human-AI Conversations Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computation

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-12T18:02:25.888041Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 54075120-ec6d-4a68-9354-e9f890521335 · outbound

This paper cites Privileged bases in the transformer residual stream, 2023.

Llama Guard 3-1B-INT4: Compact and Efficient Safeguard for Human-AI Conversations Privileged bases in the transformer residual stream, 2023

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T18:02:26.252030Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 9445110e-1c93-4aa3-b7b7-9f859188d44c · outbound

This paper cites Executorch llama android demo app.

Llama Guard 3-1B-INT4: Compact and Efficient Safeguard for Human-AI Conversations Executorch llama android demo app

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T18:02:26.240280Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 77d8bacf-e03e-445e-b3b9-a4626d266ac5 · outbound

This paper cites Executorch llama ios demo app.

Llama Guard 3-1B-INT4: Compact and Efficient Safeguard for Human-AI Conversations Executorch llama ios demo app

Reference 7

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T18:02:26.227918Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 09cd50c0-9d9a-4d2c-aa4c-15f9132dee53 · outbound

This paper cites Distilling the Knowledge in a Neural Network.

Llama Guard 3-1B-INT4: Compact and Efficient Safeguard for Human-AI Conversations Distilling the Knowledge in a Neural Network

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-12T18:02:25.905410Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dd29a1e1-b40a-4261-8d85-31afc142070a · outbound

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

Llama Guard 3-1B-INT4: Compact and Efficient Safeguard for Human-AI Conversations Llama Guard: LLM-based Input-Output Safeguard for Human-AI Conversations

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-12T18:02:25.909740Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7ff4dc5e-4108-428e-9d43-6b9eb8138048 · outbound

This paper cites Quantizing deep convolutional networks for efficient inference: A whitepaper.

Llama Guard 3-1B-INT4: Compact and Efficient Safeguard for Human-AI Conversations Quantizing deep convolutional networks for efficient inference: A whitepaper

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-12T18:02:25.913945Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 278114ff-0e6f-4768-99c9-7208e4e2f2fc · outbound

This paper cites LLM-QAT: Data-Free Quantization Aware Training for Large Language Models.

Llama Guard 3-1B-INT4: Compact and Efficient Safeguard for Human-AI Conversations LLM-QAT: Data-Free Quantization Aware Training for Large Language Models

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-12T18:02:25.918193Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 68a2ad6a-5268-48b3-9dc9-d75265d818ed · outbound

This paper cites The Llama 3 Herd of Models.

Llama Guard 3-1B-INT4: Compact and Efficient Safeguard for Human-AI Conversations The Llama 3 Herd of Models

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-12T18:02:25.922727Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 225443d4-243a-48d2-afaf-e7e19b24354b · outbound

This paper cites Meta llama guard 2.

Llama Guard 3-1B-INT4: Compact and Efficient Safeguard for Human-AI Conversations Meta llama guard 2

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T18:02:26.215623Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation e5423069-89b1-43fc-8182-49538f865f9c · outbound

This paper cites The llama 3 family of models.

Llama Guard 3-1B-INT4: Compact and Efficient Safeguard for Human-AI Conversations The llama 3 family of models

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T18:02:26.203120Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 019f4aa4-837d-4455-8a49-b47f4620fc7d · outbound

This paper cites ShortGPT: Layers in Large Language Models are More Redundant Than You Expect.

Llama Guard 3-1B-INT4: Compact and Efficient Safeguard for Human-AI Conversations ShortGPT: Layers in Large Language Models are More Redundant Than You Expect

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-12T18:02:25.933651Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ed0a94ab-8932-490c-a35e-2083849da3a0 · outbound

This paper cites Announcing mlcommons ai safety v0.5 proof of concept.

Llama Guard 3-1B-INT4: Compact and Efficient Safeguard for Human-AI Conversations Announcing mlcommons ai safety v0.5 proof of concept

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T18:02:26.188526Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 592cd71e-ea04-40b8-8434-410ee06276a9 · outbound

This paper cites Compact Language Models via Pruning and Knowledge Distillation.

Llama Guard 3-1B-INT4: Compact and Efficient Safeguard for Human-AI Conversations Compact Language Models via Pruning and Knowledge Distillation

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-12T18:02:25.941881Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 339b9a36-360d-4414-9f43-dc7e8becff32 · outbound

This paper cites A White Paper on Neural Network Quantization.

Llama Guard 3-1B-INT4: Compact and Efficient Safeguard for Human-AI Conversations A White Paper on Neural Network Quantization

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-12T18:02:25.946798Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a01f716c-c72b-407d-a318-6c0182796c98 · outbound

This paper cites Executorch runtime overview.

Llama Guard 3-1B-INT4: Compact and Efficient Safeguard for Human-AI Conversations Executorch runtime overview

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T18:02:26.175173Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 6b909aa4-560e-4847-b962-4047845e3cf2 · outbound

This paper cites Executorch xnnpack delegate.

Llama Guard 3-1B-INT4: Compact and Efficient Safeguard for Human-AI Conversations Executorch xnnpack delegate

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T18:02:26.160658Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 3d49b6ea-9b9e-44b6-91c4-4b23b66b2ce9 · outbound

This paper cites Gemma: Open Models Based on Gemini Research and Technology.

Llama Guard 3-1B-INT4: Compact and Efficient Safeguard for Human-AI Conversations Gemma: Open Models Based on Gemini Research and Technology

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-12T18:02:25.960573Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0acf404a-4f28-43ea-9825-f2e5451decd2 · outbound

This paper cites torchao: Pytorch native quantization and sparsity for training and inference, October 2024.

Llama Guard 3-1B-INT4: Compact and Efficient Safeguard for Human-AI Conversations torchao: Pytorch native quantization and sparsity for training and inference, October 2024

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T18:02:26.148387Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 504ffe1b-d309-4873-8879-5aebc0291fe9 · outbound

This paper cites torchtune: Pytorch's finetuning library, April 2024.

Llama Guard 3-1B-INT4: Compact and Efficient Safeguard for Human-AI Conversations torchtune: Pytorch's finetuning library, April 2024

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T18:02:26.135721Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Pith citing papers

Observation 65cd7426-e089-410f-8e19-f02b77191f2c · inbound

Benchmarking Large Language Models for Cryptanalysis and Side-Channel Vulnerabilities cites this paper.

Benchmarking Large Language Models for Cryptanalysis and Side-Channel Vulnerabilities Llama Guard 3-1B-INT4: Compact and Efficient Safeguard for Human-AI Conversations

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-07T12:21:22.311989Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 432a2faf-6660-47e1-bc12-ef20d58c848c · inbound

WebGuard: Building a Generalizable Guardrail for Web Agents cites this paper.

WebGuard: Building a Generalizable Guardrail for Web Agents Llama Guard 3-1B-INT4: Compact and Efficient Safeguard for Human-AI Conversations

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-06T16:12:48.091007Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 236d537c-7a73-477f-bf10-2432a1dd882b · inbound

Agentic Web: Weaving the Next Web with AI Agents cites this paper.

Agentic Web: Weaving the Next Web with AI Agents Llama Guard 3-1B-INT4: Compact and Efficient Safeguard for Human-AI Conversations

Reference 64

Resolution: unresolved; no resolver link, observed 2026-08-06T13:05:33.120837Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 32d02be6-9e9b-4074-9c1f-c46998e03858 · inbound

When Search Goes Wrong: Red-Teaming Web-Augmented Large Language Models cites this paper.

When Search Goes Wrong: Red-Teaming Web-Augmented Large Language Models Llama Guard 3-1B-INT4: Compact and Efficient Safeguard for Human-AI Conversations

Reference 11

Resolution: verified exact; arxiv_id, observed 2026-05-18T09:31:11.609858Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 8a1409cd-e4e7-4cf8-b9a7-1e46bbcb643f · inbound

MetaBreak: Jailbreaking Online LLM Services via Special Token Manipulation cites this paper.

MetaBreak: Jailbreaking Online LLM Services via Special Token Manipulation Llama Guard 3-1B-INT4: Compact and Efficient Safeguard for Human-AI Conversations

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-04T10:22:04.668209Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6970fe45-8b6d-4606-b3e2-32f5e9642be9 · inbound

Attention Misses Visual Risk: Risk-Adaptive Steering for Multimodal Safety Alignment cites this paper.

Attention Misses Visual Risk: Risk-Adaptive Steering for Multimodal Safety Alignment Llama Guard 3-1B-INT4: Compact and Efficient Safeguard for Human-AI Conversations

Reference 2025

Resolution: unresolved; no resolver link, observed 2026-08-04T09:47:23.420935Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 04bc87d8-7e86-4d32-9e1b-ea13ea07b827 · inbound

Evolve the Method, Not the Prompts: Evolutionary Synthesis of Jailbreak Attacks on LLMs cites this paper.

Evolve the Method, Not the Prompts: Evolutionary Synthesis of Jailbreak Attacks on LLMs Llama Guard 3-1B-INT4: Compact and Efficient Safeguard for Human-AI Conversations

Reference 11

Resolution: verified exact; arxiv_id, observed 2026-05-21T19:00:30.359641Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 1c5544bc-177e-4899-85e1-df8d9b5e6168 · inbound

MobileLLM-Flash: Latency-Guided On-Device LLM Design for Industry Scale Deployment cites this paper.

MobileLLM-Flash: Latency-Guided On-Device LLM Design for Industry Scale Deployment Llama Guard 3-1B-INT4: Compact and Efficient Safeguard for Human-AI Conversations

Reference 5

Resolution: verified exact; arxiv_id, observed 2026-05-15T09:45:23.186472Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation f664cd62-6d4b-4024-85b2-e360d2b3c8b2 · inbound

To Lie or Not to Lie? Investigating The Biased Spread of Global Lies by LLMs cites this paper.

To Lie or Not to Lie? Investigating The Biased Spread of Global Lies by LLMs Llama Guard 3-1B-INT4: Compact and Efficient Safeguard for Human-AI Conversations

Reference 14

Resolution: verified exact; arxiv_id, observed 2026-05-11T00:05:50.810508Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 405eafa7-6fa4-4b8b-b44a-6e942d79b480 · inbound

LPG: Balancing Efficiency and Policy Reasoning in Latent Policy Guardrails cites this paper.

LPG: Balancing Efficiency and Policy Reasoning in Latent Policy Guardrails Llama Guard 3-1B-INT4: Compact and Efficient Safeguard for Human-AI Conversations

Reference 4

Resolution: verified exact; arxiv_id, observed 2026-05-19T23:43:17.831171Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 6c4e3752-5a00-42d7-b875-cc056ba71925 · inbound

Compliance-Scored Best-of-N Guardrail Orchestration for Multimodal Document Generation in Payments Dispute Defense cites this paper.

Compliance-Scored Best-of-N Guardrail Orchestration for Multimodal Document Generation in Payments Dispute Defense Llama Guard 3-1B-INT4: Compact and Efficient Safeguard for Human-AI Conversations

Reference 16

Resolution: verified exact; arxiv_id, observed 2026-07-02T00:56:24.431995Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation a609a6cc-21c8-4f50-86bf-b3e7784ea764 · inbound

RecurGuard: Runtime Monitoring for Reasoning-Token Consumption Attacks cites this paper.

RecurGuard: Runtime Monitoring for Reasoning-Token Consumption Attacks Llama Guard 3-1B-INT4: Compact and Efficient Safeguard for Human-AI Conversations

Reference 7

Resolution: verified exact; arxiv_id, observed 2026-07-02T21:27:24.556776Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation d6766197-7316-4c61-abbb-fa4d168f2a9b · 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 Llama Guard 3-1B-INT4: Compact and Efficient Safeguard for Human-AI Conversations

Reference 51

Resolution: metadata mismatch; arxiv_id, observed 2026-07-03T00:27:29.253657Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation dc87f997-f06f-4fe0-a3e7-a1192b8763a0 · inbound

Verifying Intent and Harm: A Unified Defense Against LLM-Generated Threats cites this paper.

Verifying Intent and Harm: A Unified Defense Against LLM-Generated Threats Llama Guard 3-1B-INT4: Compact and Efficient Safeguard for Human-AI Conversations

Reference 10

Resolution: verified exact; arxiv_id, observed 2026-07-04T15:59:56.709785Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 794b1101-7735-42a0-a3d8-a53e13c7148a · inbound

When Are Sparse Feature Interventions Actually Localized? Matched Evaluation for SAE-Based Safety Control cites this paper.

When Are Sparse Feature Interventions Actually Localized? Matched Evaluation for SAE-Based Safety Control Llama Guard 3-1B-INT4: Compact and Efficient Safeguard for Human-AI Conversations

Reference 5

Resolution: unresolved; no resolver link, observed 2026-07-14T13:23:22.708604Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2d6eb7fe-b555-4fe0-9c43-77fc68c707d9 · inbound

Withholding the Completing Chunk: Deterministic Pair-Completion Guardrails for Streaming LLM Output cites this paper.

Withholding the Completing Chunk: Deterministic Pair-Completion Guardrails for Streaming LLM Output Llama Guard 3-1B-INT4: Compact and Efficient Safeguard for Human-AI Conversations

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-14T04:14:46.739648Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.