Paper Citation Record · LEDGER

Smoothed Embeddings for Robust Language Models

As of 20 August 2026, this Paper Citation Record lists 21 of 21 outbound references and 4 inbound Pith citation observations for arXiv:2501.16497.

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

pith.paper-citation-record.v1
2501.16497 v1

Coverage vector

measured 21 of 21 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-10T12:52:40.970136Z

measured 25 of 25 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-20T06:33:59.587034+00:00

measured 4 of 4 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-15T16:21:58.795021Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-07-02T08:26:48.381752Z

Reference resolution

21 of 21 outbound references displayed

verified exact0
verified fuzzy2
unresolved19
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation cddc8ebe-d7a3-4923-a5e4-b3493db63cd9 · outbound

This paper cites Jailbreaking Black Box Large Language Models in Twenty Queries.

Smoothed Embeddings for Robust Language Models Jailbreaking Black Box Large Language Models in Twenty Queries

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-10T12:52:40.901600Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 55507cc1-c7c8-4152-a8d3-8dbb6791a3f4 · outbound

This paper cites JailbreakBench: An Open Robustness Benchmark for Jailbreaking Large Language Models.

Smoothed Embeddings for Robust Language Models JailbreakBench: An Open Robustness Benchmark for Jailbreaking Large Language Models

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-10T12:52:40.906279Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 771fb426-63a2-494e-9124-f89507a13361 · outbound

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

Smoothed Embeddings for Robust Language Models Llama Guard: LLM-based Input-Output Safeguard for Human-AI Conversations

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-10T12:52:40.918088Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 41b4c813-94a4-414c-88ef-f7b0c896e911 · outbound

This paper cites Baseline Defenses for Adversarial Attacks Against Aligned Language Models.

Smoothed Embeddings for Robust Language Models Baseline Defenses for Adversarial Attacks Against Aligned Language Models

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-10T12:52:40.921697Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5b723e18-9619-4d71-9548-821801dbacb8 · outbound

This paper cites Defending Large Language Models against Jailbreak Attacks via Semantic Smoothing.

Smoothed Embeddings for Robust Language Models Defending Large Language Models against Jailbreak Attacks via Semantic Smoothing

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-10T12:52:40.925285Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation edc496c7-288c-4817-adef-d181b7edf0c2 · outbound

This paper cites Certifying LLM Safety against Adversarial Prompting.

Smoothed Embeddings for Robust Language Models Certifying LLM Safety against Adversarial Prompting

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-10T12:52:40.928821Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a7bf8c9c-f92d-4333-aa04-34ba76ba72c5 · outbound

This paper cites Certified robustness to adversarial examples with differential privacy.

Smoothed Embeddings for Robust Language Models Certified robustness to adversarial examples with differential privacy

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-10T12:52:40.932369Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c674cead-cb03-4c3a-af86-32cd35e037b1 · outbound

This paper cites The Llama 3 Herd of Models.

Smoothed Embeddings for Robust Language Models The Llama 3 Herd of Models

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-10T12:52:40.936140Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7b0efcbd-0fed-4e74-a645-366594bc9cba · outbound

This paper cites HarmBench: A Standardized Evaluation Framework for Automated Red Teaming and Robust Refusal.

Smoothed Embeddings for Robust Language Models HarmBench: A Standardized Evaluation Framework for Automated Red Teaming and Robust Refusal

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-10T12:52:40.939580Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation acfdb9bd-c0c1-4c3d-917e-4abc7ae5493f · outbound

This paper cites RigorLLM: Resilient Guardrails for Large Language Models against Undesired Content.

Smoothed Embeddings for Robust Language Models RigorLLM: Resilient Guardrails for Large Language Models against Undesired Content

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-10T12:52:40.950778Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a6ccf470-8148-4224-a140-da4f9f4c6297 · outbound

This paper cites Certified Robustness for Large Language Models with Self-Denoising.

Smoothed Embeddings for Robust Language Models Certified Robustness for Large Language Models with Self-Denoising

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-10T12:52:40.954479Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0a871956-3469-497e-9c05-198552ffdb80 · outbound

This paper cites Instruction-Following Evaluation for Large Language Models.

Smoothed Embeddings for Robust Language Models Instruction-Following Evaluation for Large Language Models

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-10T12:52:40.958213Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1ea8bff1-ff9d-4a21-b742-509db9db4b3f · outbound

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

Smoothed Embeddings for Robust Language Models Universal and Transferable Adversarial Attacks on Aligned Language Models

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-10T12:52:40.961922Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation eaec8b96-f231-411f-94f0-81063e48212a · outbound

This paper cites [USER-CONTENT].

Smoothed Embeddings for Robust Language Models [USER-CONTENT]

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T12:52:41.207625Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 015894f3-18ac-4def-94e9-a82a6bbf0ad9 · outbound

This paper cites The results summarized in Table 2 show that 13 Figure 10: Process to get a response with a smoothed response prefix.

Smoothed Embeddings for Robust Language Models The results summarized in Table 2 show that 13 Figure 10: Process to get a response with a smoothed response prefix

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T12:52:41.195061Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 28a6b165-b2ab-4ae8-bc6b-1dc2542a9e6e · outbound

This paper cites Intriguing properties of neural networks.

Smoothed Embeddings for Robust Language Models Intriguing properties of neural networks

Reference 2014

Resolution: unresolved; no resolver link, observed 2026-08-10T12:52:40.946943Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 685459c6-a38e-46cf-93a1-fc0532d84f3c · outbound

This paper cites Explaining and Harnessing Adversarial Examples.

Smoothed Embeddings for Robust Language Models Explaining and Harnessing Adversarial Examples

Reference 2015

Resolution: unresolved; no resolver link, observed 2026-08-10T12:52:40.914111Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c4ad8d9a-a7a2-46bf-92f6-65d8d195a7dd · outbound

This paper cites Length-Controlled AlpacaEval: A Simple Way to Debias Automatic Evaluators.

Smoothed Embeddings for Robust Language Models Length-Controlled AlpacaEval: A Simple Way to Debias Automatic Evaluators

Reference 2019

Resolution: unresolved; no resolver link, observed 2026-08-10T12:52:40.910198Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6b2fc66e-da60-4a7b-97b8-a89099a4423b · outbound

This paper cites SmoothLLM: Defending Large Language Models Against Jailbreaking Attacks.

Smoothed Embeddings for Robust Language Models SmoothLLM: Defending Large Language Models Against Jailbreaking Attacks

Reference 2022

Resolution: unresolved; no resolver link, observed 2026-08-10T12:52:40.943356Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1cc8c3c0-97d1-457c-b51e-7fe5aac8f70f · outbound

This paper cites Jailbreaking Leading Safety-Aligned LLMs with Simple Adaptive Attacks.

Smoothed Embeddings for Robust Language Models Jailbreaking Leading Safety-Aligned LLMs with Simple Adaptive Attacks

Reference 2023

Resolution: unresolved; no resolver link, observed 2026-08-10T12:52:40.897645Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e9f69151-b8d8-4a66-990d-fb70ec011886 · outbound

This paper cites Detecting Language Model Attacks with Perplexity.

Smoothed Embeddings for Robust Language Models Detecting Language Model Attacks with Perplexity

Reference 2024

Resolution: unresolved; no resolver link, observed 2026-08-10T12:52:40.893268Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation a4037bb0-48ea-40e9-9565-1e8456f2da7a · inbound

Embedding Poisoning: Bypassing Safety Alignment via Embedding Semantic Shift cites this paper.

Embedding Poisoning: Bypassing Safety Alignment via Embedding Semantic Shift Smoothed Embeddings for Robust Language Models

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-15T16:21:58.795021Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f5aeb4fb-04a5-4fb2-a084-f490918a8417 · inbound

Towards Understanding the Robustness of Sparse Autoencoders cites this paper.

Towards Understanding the Robustness of Sparse Autoencoders Smoothed Embeddings for Robust Language Models

Reference 28

Resolution: metadata mismatch; arxiv_id, observed 2026-05-10T05:46:10.252295Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 23f0ab69-a308-4108-b653-dec1e85b3c01 · inbound

Re-Triggering Safeguards within LLMs for Jailbreak Detection cites this paper.

Re-Triggering Safeguards within LLMs for Jailbreak Detection Smoothed Embeddings for Robust Language Models

Reference 5

Resolution: verified exact; arxiv_id, observed 2026-05-12T06:06:25.023194Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 3a320c02-371d-4654-af67-062bf117574a · inbound

Auditing CoT Answer-Hijack Patches: Source-Control Certificates with Type-I Guarantees cites this paper.

Auditing CoT Answer-Hijack Patches: Source-Control Certificates with Type-I Guarantees Smoothed Embeddings for Robust Language Models

Reference 30

Resolution: verified exact; arxiv_id, observed 2026-07-02T08:26:48.383245Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.