Paper Citation Record · LEDGER

Watching the AI Watchdogs: A Fairness and Robustness Analysis of AI Safety Moderation Classifiers

As of 11 August 2026, this Paper Citation Record lists 46 of 46 outbound references and 1 inbound Pith citation observation for arXiv:2501.13302.

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

pith.paper-citation-record.v1
2501.13302 v1

Coverage vector

measured 46 of 46 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-10T16:19:48.082702Z

measured 47 of 47 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-10T06:31:04.303077+00:00

measured 1 of 1 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-05-10T18:41:54.081628Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-05-11T00:05:50.801220Z

Reference resolution

46 of 46 outbound references displayed

verified exact0
verified fuzzy4
unresolved42
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 957accdd-a6af-408f-9936-4feae9a131a4 · outbound

This paper cites GPT-4 Technical Report.

Watching the AI Watchdogs: A Fairness and Robustness Analysis of AI Safety Moderation Classifiers GPT-4 Technical Report

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-10T16:19:47.910889Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 994b7894-04d6-4678-b01f-86d99dcb43e4 · outbound

This paper cites PaLM 2 Technical Report.

Watching the AI Watchdogs: A Fairness and Robustness Analysis of AI Safety Moderation Classifiers PaLM 2 Technical Report

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-10T16:19:47.915189Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fdf210e6-af58-4c6f-9439-bbbd01208ec2 · outbound

This paper cites an unresolved cited work.

Watching the AI Watchdogs: A Fairness and Robustness Analysis of AI Safety Moderation Classifiers Unresolved cited work

Reference 3

Resolution: unresolved; raw_fallback, observed 2026-08-10T16:19:48.555144Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation b387d232-52ee-40ff-98bc-53a7a506ca64 · outbound

This paper cites an unresolved cited work.

Watching the AI Watchdogs: A Fairness and Robustness Analysis of AI Safety Moderation Classifiers Unresolved cited work

Reference 4

Resolution: unresolved; raw_fallback, observed 2026-08-10T16:19:48.543327Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 94bda893-9bd1-4600-a460-f0db83ae7d79 · outbound

This paper cites Measuring Political Bias in Large Language Models: What Is Said and How It Is Said.

Watching the AI Watchdogs: A Fairness and Robustness Analysis of AI Safety Moderation Classifiers Measuring Political Bias in Large Language Models: What Is Said and How It Is Said

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-10T16:19:47.927230Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6f5ed728-a3d1-4782-85af-0560f4be0bde · outbound

This paper cites an unresolved cited work.

Watching the AI Watchdogs: A Fairness and Robustness Analysis of AI Safety Moderation Classifiers Unresolved cited work

Reference 6

Resolution: unresolved; raw_fallback, observed 2026-08-10T16:19:48.531178Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 6aaee4bf-019f-4f79-b7d8-6cd9bc434e03 · outbound

This paper cites Machine Learning Robustness: A Primer.

Watching the AI Watchdogs: A Fairness and Robustness Analysis of AI Safety Moderation Classifiers Machine Learning Robustness: A Primer

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-10T16:19:47.935427Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 40ba0447-1e27-4fa7-986e-7cfc3f37fe33 · outbound

This paper cites an unresolved cited work.

Watching the AI Watchdogs: A Fairness and Robustness Analysis of AI Safety Moderation Classifiers Unresolved cited work

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-10T16:19:47.939518Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b9a4ae2d-2986-44c0-86ae-2c1bfcfde9ab · outbound

This paper cites an unresolved cited work.

Watching the AI Watchdogs: A Fairness and Robustness Analysis of AI Safety Moderation Classifiers Unresolved cited work

Reference 9

Resolution: unresolved; raw_fallback, observed 2026-08-10T16:19:48.511482Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 5f466b0d-35e0-453c-9b36-1ab2527b282c · outbound

This paper cites an unresolved cited work.

Watching the AI Watchdogs: A Fairness and Robustness Analysis of AI Safety Moderation Classifiers Unresolved cited work

Reference 10

Resolution: unresolved; raw_fallback, observed 2026-08-10T16:19:48.499247Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 6d38a130-b64e-4e27-bce1-906b147fc153 · outbound

This paper cites an unresolved cited work.

Watching the AI Watchdogs: A Fairness and Robustness Analysis of AI Safety Moderation Classifiers Unresolved cited work

Reference 11

Resolution: unresolved; raw_fallback, observed 2026-08-10T16:19:48.486852Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 6d49dfe9-edeb-466e-88ca-990fdb6f3091 · outbound

This paper cites what data benefits my classifier?.

Watching the AI Watchdogs: A Fairness and Robustness Analysis of AI Safety Moderation Classifiers what data benefits my classifier?

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T16:19:48.475115Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 01d6af94-8c05-4917-8193-7f0a93522893 · outbound

This paper cites an unresolved cited work.

Watching the AI Watchdogs: A Fairness and Robustness Analysis of AI Safety Moderation Classifiers Unresolved cited work

Reference 13

Resolution: unresolved; raw_fallback, observed 2026-08-10T16:19:48.463442Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 0b158943-e49e-4194-a188-d673ef496a69 · outbound

This paper cites Towards F air V ideo S ummarization.

Watching the AI Watchdogs: A Fairness and Robustness Analysis of AI Safety Moderation Classifiers Towards F air V ideo S ummarization

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T16:19:48.451843Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 469152dd-23c9-4741-bc33-b57b8f86194a · outbound

This paper cites https://clarifai.com/clarifai/main/models/moderation-english-text-classification.

Watching the AI Watchdogs: A Fairness and Robustness Analysis of AI Safety Moderation Classifiers https://clarifai.com/clarifai/main/models/moderation-english-text-classification

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T16:19:48.439695Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 833e1be4-6313-4157-b8b2-71756fda40d8 · outbound

This paper cites an unresolved cited work.

Watching the AI Watchdogs: A Fairness and Robustness Analysis of AI Safety Moderation Classifiers Unresolved cited work

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-10T16:19:47.967288Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7eb2e53b-6f52-4a39-9029-3be0d4989878 · outbound

This paper cites an unresolved cited work.

Watching the AI Watchdogs: A Fairness and Robustness Analysis of AI Safety Moderation Classifiers Unresolved cited work

Reference 17

Resolution: unresolved; raw_fallback, observed 2026-08-10T16:19:48.420477Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 37171bea-4513-4777-a01f-b934a5d8eb45 · outbound

This paper cites an unresolved cited work.

Watching the AI Watchdogs: A Fairness and Robustness Analysis of AI Safety Moderation Classifiers Unresolved cited work

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-10T16:19:47.974101Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4e01e04b-652c-40d9-b9fe-89ec5d468370 · outbound

This paper cites an unresolved cited work.

Watching the AI Watchdogs: A Fairness and Robustness Analysis of AI Safety Moderation Classifiers Unresolved cited work

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-10T16:19:47.977419Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fd54c1ef-1759-49df-99fb-9369e50a2a02 · outbound

This paper cites Building Guardrails for Large Language Models.

Watching the AI Watchdogs: A Fairness and Robustness Analysis of AI Safety Moderation Classifiers Building Guardrails for Large Language Models

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-10T16:19:47.980860Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1c56b1aa-31a9-4a15-ab87-aa275dbc12f6 · outbound

This paper cites Towards Measuring the Representation of Subjective Global Opinions in Language Models.

Watching the AI Watchdogs: A Fairness and Robustness Analysis of AI Safety Moderation Classifiers Towards Measuring the Representation of Subjective Global Opinions in Language Models

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-10T16:19:47.984874Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ffe43d74-258e-45a0-ba09-5ebafb5619d2 · outbound

This paper cites an unresolved cited work.

Watching the AI Watchdogs: A Fairness and Robustness Analysis of AI Safety Moderation Classifiers Unresolved cited work

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-10T16:19:47.988841Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 40265bf1-2d53-4cea-b645-f9dc54041843 · outbound

This paper cites RealToxicityPrompts: Evaluating Neural Toxic Degeneration in Language Models.

Watching the AI Watchdogs: A Fairness and Robustness Analysis of AI Safety Moderation Classifiers RealToxicityPrompts: Evaluating Neural Toxic Degeneration in Language Models

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-10T16:19:47.992480Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4f7fc283-4ac4-4a98-8f4a-69a3027413e7 · outbound

This paper cites an unresolved cited work.

Watching the AI Watchdogs: A Fairness and Robustness Analysis of AI Safety Moderation Classifiers Unresolved cited work

Reference 24

Resolution: unresolved; raw_fallback, observed 2026-08-10T16:19:48.389553Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 3120bf2e-c8d9-4288-96e8-ce3b560ca2d2 · outbound

This paper cites an unresolved cited work.

Watching the AI Watchdogs: A Fairness and Robustness Analysis of AI Safety Moderation Classifiers Unresolved cited work

Reference 25

Resolution: unresolved; raw_fallback, observed 2026-08-10T16:19:48.378264Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation b5a3957c-06e0-43b3-a3ec-8e97510de234 · outbound

This paper cites BERTopic: Neural topic modeling with a class-based TF-IDF procedure.

Watching the AI Watchdogs: A Fairness and Robustness Analysis of AI Safety Moderation Classifiers BERTopic: Neural topic modeling with a class-based TF-IDF procedure

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-10T16:19:48.003786Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c3e0b635-8d6d-444f-89b2-965b6abd3673 · outbound

This paper cites an unresolved cited work.

Watching the AI Watchdogs: A Fairness and Robustness Analysis of AI Safety Moderation Classifiers Unresolved cited work

Reference 27

Resolution: unresolved; raw_fallback, observed 2026-08-10T16:19:48.367010Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation d24dd804-9b07-43ef-b486-3422c813e1bc · outbound

This paper cites an unresolved cited work.

Watching the AI Watchdogs: A Fairness and Robustness Analysis of AI Safety Moderation Classifiers Unresolved cited work

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-10T16:19:48.011118Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9f120699-f8b7-414f-992a-24852e974628 · outbound

This paper cites an unresolved cited work.

Watching the AI Watchdogs: A Fairness and Robustness Analysis of AI Safety Moderation Classifiers Unresolved cited work

Reference 29

Resolution: unresolved; raw_fallback, observed 2026-08-10T16:19:48.349006Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 3b0804cd-4ab9-4b74-986a-422a78b03bca · outbound

This paper cites an unresolved cited work.

Watching the AI Watchdogs: A Fairness and Robustness Analysis of AI Safety Moderation Classifiers Unresolved cited work

Reference 30

Resolution: unresolved; raw_fallback, observed 2026-08-10T16:19:48.337606Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 735f0aa3-ae13-4d38-a391-cdb011a368c0 · outbound

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

Watching the AI Watchdogs: A Fairness and Robustness Analysis of AI Safety Moderation Classifiers AutoDAN: Generating Stealthy Jailbreak Prompts on Aligned Large Language Models

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-10T16:19:48.024738Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e62d96b7-2b9c-4e4c-a03b-dbf15871af17 · outbound

This paper cites An Empirical Study of Catastrophic Forgetting in Large Language Models During Continual Fine-tuning.

Watching the AI Watchdogs: A Fairness and Robustness Analysis of AI Safety Moderation Classifiers An Empirical Study of Catastrophic Forgetting in Large Language Models During Continual Fine-tuning

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-10T16:19:48.028776Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f3ca1292-2bac-4aa4-91bc-0f9598203d2e · outbound

This paper cites an unresolved cited work.

Watching the AI Watchdogs: A Fairness and Robustness Analysis of AI Safety Moderation Classifiers Unresolved cited work

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-10T16:19:48.032831Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4c83c018-6e34-4c78-8582-53e0e3149d44 · outbound

This paper cites an unresolved cited work.

Watching the AI Watchdogs: A Fairness and Robustness Analysis of AI Safety Moderation Classifiers Unresolved cited work

Reference 34

Resolution: unresolved; raw_fallback, observed 2026-08-10T16:19:48.320838Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation cc62cd94-0d3a-422c-b00f-eebbb86aed88 · outbound

This paper cites Toxic Bias: Perspective API Misreads German as More Toxic.

Watching the AI Watchdogs: A Fairness and Robustness Analysis of AI Safety Moderation Classifiers Toxic Bias: Perspective API Misreads German as More Toxic

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-10T16:19:48.040346Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7957712b-2d95-451e-83a7-b446cda18662 · outbound

This paper cites https://platform.openai.com/docs/guides/moderation.

Watching the AI Watchdogs: A Fairness and Robustness Analysis of AI Safety Moderation Classifiers https://platform.openai.com/docs/guides/moderation

Reference 36

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T16:19:48.309591Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation c8a19fc6-0376-434a-b9a3-6de65f6886d0 · outbound

This paper cites an unresolved cited work.

Watching the AI Watchdogs: A Fairness and Robustness Analysis of AI Safety Moderation Classifiers Unresolved cited work

Reference 37

Resolution: unresolved; raw_fallback, observed 2026-08-10T16:19:48.298317Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 81c6a5ad-2387-4b42-af6e-661b23d00fd4 · outbound

This paper cites Fine-tuning Aligned Language Models Compromises Safety, Even When Users Do Not Intend To!.

Watching the AI Watchdogs: A Fairness and Robustness Analysis of AI Safety Moderation Classifiers Fine-tuning Aligned Language Models Compromises Safety, Even When Users Do Not Intend To!

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-10T16:19:48.051712Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 87807929-10c4-4f5a-acdf-3ba5921ceb0e · outbound

This paper cites an unresolved cited work.

Watching the AI Watchdogs: A Fairness and Robustness Analysis of AI Safety Moderation Classifiers Unresolved cited work

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-10T16:19:48.055948Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation be32b94c-a11a-42f4-91ad-6f8b2e6f96a6 · outbound

This paper cites The Woman Worked as a Babysitter: On Biases in Language Generation.

Watching the AI Watchdogs: A Fairness and Robustness Analysis of AI Safety Moderation Classifiers The Woman Worked as a Babysitter: On Biases in Language Generation

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-10T16:19:48.059776Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5501aa05-f5be-4440-b8c3-fc48a7402fea · outbound

This paper cites an unresolved cited work.

Watching the AI Watchdogs: A Fairness and Robustness Analysis of AI Safety Moderation Classifiers Unresolved cited work

Reference 41

Resolution: unresolved; raw_fallback, observed 2026-08-10T16:19:48.287544Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 8308824a-6f8c-404f-a3d3-d3f10e695b8d · outbound

This paper cites A Comprehensive Capability Analysis of GPT-3 and GPT-3.5 Series Models.

Watching the AI Watchdogs: A Fairness and Robustness Analysis of AI Safety Moderation Classifiers A Comprehensive Capability Analysis of GPT-3 and GPT-3.5 Series Models

Reference 42

Resolution: unresolved; no resolver link, observed 2026-08-10T16:19:48.067303Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1c7a6349-470a-42d5-a062-b6dd14613b53 · outbound

This paper cites How Johnny Can Persuade LLMs to Jailbreak Them: Rethinking Persuasion to Challenge AI Safety by Humanizing LLMs.

Watching the AI Watchdogs: A Fairness and Robustness Analysis of AI Safety Moderation Classifiers How Johnny Can Persuade LLMs to Jailbreak Them: Rethinking Persuasion to Challenge AI Safety by Humanizing LLMs

Reference 43

Resolution: unresolved; no resolver link, observed 2026-08-10T16:19:48.071026Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 232e39aa-c4af-45bb-a4fa-bde25f02c480 · outbound

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

Watching the AI Watchdogs: A Fairness and Robustness Analysis of AI Safety Moderation Classifiers Universal and Transferable Adversarial Attacks on Aligned Language Models

Reference 44

Resolution: unresolved; no resolver link, observed 2026-08-10T16:19:48.074807Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4a1c3282-f29a-4686-a57d-3e52fbfca083 · outbound

This paper cites URL: " 'urlintro :=.

Watching the AI Watchdogs: A Fairness and Robustness Analysis of AI Safety Moderation Classifiers URL: " 'urlintro :=

Reference 45

Resolution: unresolved; no resolver link, observed 2026-08-10T16:19:48.078510Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8d0b8269-2142-4f6b-92f0-ff69ef57c879 · outbound

This paper cites write newline.

Watching the AI Watchdogs: A Fairness and Robustness Analysis of AI Safety Moderation Classifiers write newline

Reference 46

Resolution: unresolved; no resolver link, observed 2026-08-10T16:19:48.082702Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation cae08519-4457-440f-886f-b526fbb18938 · 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 Watching the AI Watchdogs: A Fairness and Robustness Analysis of AI Safety Moderation Classifiers

Reference 4

Resolution: verified exact; arxiv_id, observed 2026-05-11T00:05:50.803437Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.