Paper Citation Record · LEDGER

Adaptively Robust LLM Monitoring via Activation Watermarking

As of 8 August 2026, this Paper Citation Record lists 25 of 25 outbound references and 2 inbound Pith citation observations for arXiv:2603.23171.

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

pith.paper-citation-record.v1
2603.23171 v3

Coverage vector

measured 25 of 25 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-02T17:39:44.013978Z

measured 27 of 27 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-08T06:32:00.761636+00:00

measured 2 of 2 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-05-15T05:57:19.399363Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-05-15T05:59:48.908825Z

Reference resolution

25 of 25 outbound references displayed

verified exact0
verified fuzzy0
unresolved25
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 80302a1d-188c-4a7d-b4a5-ca56e33b47e1 · outbound

This paper cites GPT-4 Technical Report.

Adaptively Robust LLM Monitoring via Activation Watermarking GPT-4 Technical Report

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-02T17:39:41.154929Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4d129cdd-2b53-43af-909f-e0d256dd8e59 · outbound

This paper cites Training Verifiers to Solve Math Word Problems.

Adaptively Robust LLM Monitoring via Activation Watermarking Training Verifiers to Solve Math Word Problems

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-02T17:39:41.568606Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 168ce311-8d49-4ef1-9c82-cc66d1aa94dc · outbound

This paper cites MirrorCheck: Efficient Adversarial Defense for Vision-Language Models.

Adaptively Robust LLM Monitoring via Activation Watermarking MirrorCheck: Efficient Adversarial Defense for Vision-Language Models

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-02T17:39:41.825588Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2130c3f7-ec79-428c-a265-1d11bb15dfc9 · outbound

This paper cites Measuring Mathematical Problem Solving With the MATH Dataset.

Adaptively Robust LLM Monitoring via Activation Watermarking Measuring Mathematical Problem Solving With the MATH Dataset

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-02T17:39:41.949795Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c1a959fb-3477-4dfc-a69c-75e4b35d5cf3 · outbound

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

Adaptively Robust LLM Monitoring via Activation Watermarking Llama Guard: LLM-based Input-Output Safeguard for Human-AI Conversations

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-02T17:39:42.084298Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2e4e9bf4-0386-432b-8f8c-e4ab437f8c22 · outbound

This paper cites HiddenDetect: Detecting Jailbreak Attacks against Large Vision-Language Models via Monitoring Hidden States.

Adaptively Robust LLM Monitoring via Activation Watermarking HiddenDetect: Detecting Jailbreak Attacks against Large Vision-Language Models via Monitoring Hidden States

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-02T17:39:42.343655Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6aafcc01-92ce-4356-a137-8f3106c88bbb · outbound

This paper cites DeepInception: Hypnotize Large Language Model to Be Jailbreaker.

Adaptively Robust LLM Monitoring via Activation Watermarking DeepInception: Hypnotize Large Language Model to Be Jailbreaker

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-02T17:39:42.537821Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cdd5f30b-c4b5-425a-ac88-4e8af75bfd13 · outbound

This paper cites Against The Achilles' Heel: A Survey on Red Teaming for Generative Models.

Adaptively Robust LLM Monitoring via Activation Watermarking Against The Achilles' Heel: A Survey on Red Teaming for Generative Models

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-02T17:39:42.714332Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4bd3435b-6a83-4460-a7b4-e1128aa18ced · outbound

This paper cites AutoDAN: Generating Stealthy Jailbreak Prompts on Aligned Large Language Models.

Adaptively Robust LLM Monitoring via Activation Watermarking AutoDAN: Generating Stealthy Jailbreak Prompts on Aligned Large Language Models

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-02T17:39:42.780056Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2cdf4dad-04a2-40a0-9eef-ad3ff45a8632 · outbound

This paper cites The Llama 3 Herd of Models.

Adaptively Robust LLM Monitoring via Activation Watermarking The Llama 3 Herd of Models

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-02T17:39:42.876621Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 443d7cf7-31b2-4a71-9d84-65be7c98f303 · outbound

This paper cites XSTest: A Test Suite for Identifying Exaggerated Safety Behaviours in Large Language Models.

Adaptively Robust LLM Monitoring via Activation Watermarking XSTest: A Test Suite for Identifying Exaggerated Safety Behaviours in Large Language Models

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-02T17:39:43.019845Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f7f84e7b-ee6e-4ae1-ad62-eb45eb2fefd5 · outbound

This paper cites Constitutional Classifiers: Defending against Universal Jailbreaks across Thousands of Hours of Red Teaming.

Adaptively Robust LLM Monitoring via Activation Watermarking Constitutional Classifiers: Defending against Universal Jailbreaks across Thousands of Hours of Red Teaming

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-02T17:39:43.163305Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e8786eb1-1888-4eff-be47-7eddf6def933 · outbound

This paper cites Challenging BIG-Bench Tasks and Whether Chain-of-Thought Can Solve Them.

Adaptively Robust LLM Monitoring via Activation Watermarking Challenging BIG-Bench Tasks and Whether Chain-of-Thought Can Solve Them

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-02T17:39:43.299576Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 80efb0bd-9825-4256-92e4-a6d350c0c80c · outbound

This paper cites MMLU-Pro: A More Robust and Challenging Multi-Task Language Understanding Benchmark.

Adaptively Robust LLM Monitoring via Activation Watermarking MMLU-Pro: A More Robust and Challenging Multi-Task Language Understanding Benchmark

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-02T17:39:43.379650Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 089d5599-51c5-4e85-863e-53799a233b26 · outbound

This paper cites Qwen3Guard Technical Report.

Adaptively Robust LLM Monitoring via Activation Watermarking Qwen3Guard Technical Report

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-02T17:39:43.471239Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 25cfcb93-92fa-4f6b-849e-c6e6a8d85b96 · outbound

This paper cites SoK: Watermarking for AI-Generated Content.

Adaptively Robust LLM Monitoring via Activation Watermarking SoK: Watermarking for AI-Generated Content

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-02T17:39:43.550309Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9d3951d5-eaf9-4f24-ab2a-e4036b427202 · outbound

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

Adaptively Robust LLM Monitoring via Activation Watermarking Instruction-Following Evaluation for Large Language Models

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-02T17:39:43.658628Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c1e5f8ce-f3d7-45ee-be63-6b742e14bc9d · outbound

This paper cites Representation Engineering: A Top-Down Approach to AI Transparency.

Adaptively Robust LLM Monitoring via Activation Watermarking Representation Engineering: A Top-Down Approach to AI Transparency

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-02T17:39:43.766293Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b4f38a60-5ee7-47a6-a6f4-c4d7d2608618 · outbound

This paper cites an unresolved cited work.

Adaptively Robust LLM Monitoring via Activation Watermarking Unresolved cited work

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-02T17:39:43.884154Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c05d3460-5916-4c79-a27e-666356ee0d6b · outbound

This paper cites The attacker then issues the translated prompt to the model and, for evaluation, translates the answer back into English.

Adaptively Robust LLM Monitoring via Activation Watermarking The attacker then issues the translated prompt to the model and, for evaluation, translates the answer back into English

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-02T17:39:44.013978Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 816375f6-b7aa-484b-9df8-095c7c70de76 · outbound

This paper cites Optimizing Adaptive Attacks against Watermarks for Language Models.

Adaptively Robust LLM Monitoring via Activation Watermarking Optimizing Adaptive Attacks against Watermarks for Language Models

Reference 2021

Resolution: unresolved; no resolver link, observed 2026-08-02T17:39:41.676660Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 24a9af66-5191-471a-93b5-341c475e8be1 · outbound

This paper cites Obfuscated Activations Bypass LLM Latent-Space Defenses.

Adaptively Robust LLM Monitoring via Activation Watermarking Obfuscated Activations Bypass LLM Latent-Space Defenses

Reference 2022

Resolution: unresolved; no resolver link, observed 2026-08-02T17:39:41.404497Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1da578b5-3c97-45b9-a11b-dcc30e0382f2 · outbound

This paper cites Beavertails: Towards improved safety alignment of llm via a human-preference dataset.arXiv preprint arXiv:2307.04657,.

Adaptively Robust LLM Monitoring via Activation Watermarking Beavertails: Towards improved safety alignment of llm via a human-preference dataset.arXiv preprint arXiv:2307.04657,

Reference 2023

Resolution: unresolved; no resolver link, observed 2026-08-02T17:39:42.200858Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9303b4d7-e24e-4ab1-9ff5-947e0386b362 · outbound

This paper cites Mitigating Watermark Forgery in Generative Models via Randomized Key Selection.

Adaptively Robust LLM Monitoring via Activation Watermarking Mitigating Watermark Forgery in Generative Models via Randomized Key Selection

Reference 2024

Resolution: unresolved; no resolver link, observed 2026-08-02T17:39:41.297826Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0a045218-3b2d-4b1f-a4e2-4c2ded9bac89 · outbound

This paper cites ISBN 9798400720406.

Adaptively Robust LLM Monitoring via Activation Watermarking ISBN 9798400720406

Reference 2025

Resolution: unresolved; no resolver link, observed 2026-08-02T17:39:42.434758Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation a946a793-65b3-4915-9170-80454a373aa6 · inbound

Watermarking Should Be Treated as a Monitoring Primitive cites this paper.

Watermarking Should Be Treated as a Monitoring Primitive Adaptively Robust LLM Monitoring via Activation Watermarking

Reference 4

Resolution: verified exact; arxiv_id, observed 2026-07-30T02:04:38.827270Z

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 54f1da3f-0259-4820-aa44-f130864553fe · inbound

Watermarking Should Be Treated as a Monitoring Primitive cites this paper.

Watermarking Should Be Treated as a Monitoring Primitive Adaptively Robust LLM Monitoring via Activation Watermarking

Reference 4

Resolution: verified exact; arxiv_id, observed 2026-07-30T02:04:38.827270Z

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.