Paper Citation Record · LEDGER

Towards Inclusive Toxic Content Moderation: Addressing Vulnerabilities to Adversarial Attacks in Toxicity Classifiers Tackling LLM-generated Content

As of 9 August 2026, this Paper Citation Record lists 45 of 45 outbound references and 0 inbound Pith citation observations for arXiv:2509.12672.

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

pith.paper-citation-record.v1
2509.12672 v2

Coverage vector

measured 45 of 45 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-04T16:40:31.250299Z

measured 45 of 45 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-09T06:31:02.800959+00:00

measured 0 of 0 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links

measured 0 of 1 external citation measurements

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

Source: cited_works

Reference resolution

45 of 45 outbound references displayed

verified exact0
verified fuzzy0
unresolved45
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 618cc52e-9b6b-4065-b6ed-9e5c3d55ef56 · outbound

This paper cites , " * write output.state after.block = add.period write newline.

Towards Inclusive Toxic Content Moderation: Addressing Vulnerabilities to Adversarial Attacks in Toxicity Classifiers Tackling LLM-generated Content , " * write output.state after.block = add.period write newline

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-04T16:40:31.116422Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 46cdf308-c29a-430e-aa6a-821fff51889b · outbound

This paper cites write newline.

Towards Inclusive Toxic Content Moderation: Addressing Vulnerabilities to Adversarial Attacks in Toxicity Classifiers Tackling LLM-generated Content write newline

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-04T16:40:31.120087Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d3614bcb-5916-431c-86c4-dcebb732c7e2 · outbound

This paper cites an unresolved cited work.

Towards Inclusive Toxic Content Moderation: Addressing Vulnerabilities to Adversarial Attacks in Toxicity Classifiers Tackling LLM-generated Content Unresolved cited work

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-04T16:40:31.123713Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6bc19f82-69af-4133-aee9-b35823587b2e · outbound

This paper cites an unresolved cited work.

Towards Inclusive Toxic Content Moderation: Addressing Vulnerabilities to Adversarial Attacks in Toxicity Classifiers Tackling LLM-generated Content Unresolved cited work

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-04T16:40:31.126880Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b74c5b7a-dd7d-4c18-81a7-a2f8c38e83cc · outbound

This paper cites Mechanistic Interpretability for AI Safety -- A Review.

Towards Inclusive Toxic Content Moderation: Addressing Vulnerabilities to Adversarial Attacks in Toxicity Classifiers Tackling LLM-generated Content Mechanistic Interpretability for AI Safety -- A Review

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-04T16:40:31.129847Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 072c8864-8fc0-4f1c-94cf-4981912c04ea · outbound

This paper cites Towards Building a Robust Toxicity Predictor.

Towards Inclusive Toxic Content Moderation: Addressing Vulnerabilities to Adversarial Attacks in Toxicity Classifiers Tackling LLM-generated Content Towards Building a Robust Toxicity Predictor

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-04T16:40:31.133163Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 247f0cce-2568-4a35-a002-e7f5d21532c6 · outbound

This paper cites an unresolved cited work.

Towards Inclusive Toxic Content Moderation: Addressing Vulnerabilities to Adversarial Attacks in Toxicity Classifiers Tackling LLM-generated Content Unresolved cited work

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-04T16:40:31.136971Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 38b51520-2d7a-4a6f-9c57-3c6830720a52 · outbound

This paper cites an unresolved cited work.

Towards Inclusive Toxic Content Moderation: Addressing Vulnerabilities to Adversarial Attacks in Toxicity Classifiers Tackling LLM-generated Content Unresolved cited work

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-04T16:40:31.140263Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1390aade-ade4-4013-b84e-7deb1b97cd2f · outbound

This paper cites an unresolved cited work.

Towards Inclusive Toxic Content Moderation: Addressing Vulnerabilities to Adversarial Attacks in Toxicity Classifiers Tackling LLM-generated Content Unresolved cited work

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-04T16:40:31.143456Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a1e91bfd-b394-45b8-af01-0d6b5052dbca · outbound

This paper cites an unresolved cited work.

Towards Inclusive Toxic Content Moderation: Addressing Vulnerabilities to Adversarial Attacks in Toxicity Classifiers Tackling LLM-generated Content Unresolved cited work

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-04T16:40:31.146244Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7e2e582d-84cf-4b6f-af44-3536a0ba7fa2 · outbound

This paper cites Towards Automated Circuit Discovery for Mechanistic Interpretability.

Towards Inclusive Toxic Content Moderation: Addressing Vulnerabilities to Adversarial Attacks in Toxicity Classifiers Tackling LLM-generated Content Towards Automated Circuit Discovery for Mechanistic Interpretability

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-04T16:40:31.149122Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1133c7a5-f396-47a1-9fb7-8b5b823790ba · outbound

This paper cites BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding.

Towards Inclusive Toxic Content Moderation: Addressing Vulnerabilities to Adversarial Attacks in Toxicity Classifiers Tackling LLM-generated Content BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-04T16:40:31.153001Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8163cfac-a653-45b1-8e2d-aaa7b94838d6 · outbound

This paper cites an unresolved cited work.

Towards Inclusive Toxic Content Moderation: Addressing Vulnerabilities to Adversarial Attacks in Toxicity Classifiers Tackling LLM-generated Content Unresolved cited work

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-04T16:40:31.156541Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a59922d2-4c9d-4813-8857-b2829dc5399b · outbound

This paper cites an unresolved cited work.

Towards Inclusive Toxic Content Moderation: Addressing Vulnerabilities to Adversarial Attacks in Toxicity Classifiers Tackling LLM-generated Content Unresolved cited work

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-04T16:40:31.159467Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5aaad299-99cd-4808-9824-4eb97b536c99 · outbound

This paper cites an unresolved cited work.

Towards Inclusive Toxic Content Moderation: Addressing Vulnerabilities to Adversarial Attacks in Toxicity Classifiers Tackling LLM-generated Content Unresolved cited work

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-04T16:40:31.162193Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 140d4b5f-71ba-4710-b87a-debafd5c72a4 · outbound

This paper cites an unresolved cited work.

Towards Inclusive Toxic Content Moderation: Addressing Vulnerabilities to Adversarial Attacks in Toxicity Classifiers Tackling LLM-generated Content Unresolved cited work

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-04T16:40:31.165692Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation af396301-d35d-4ef6-a04d-098c5fb597c9 · outbound

This paper cites an unresolved cited work.

Towards Inclusive Toxic Content Moderation: Addressing Vulnerabilities to Adversarial Attacks in Toxicity Classifiers Tackling LLM-generated Content Unresolved cited work

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-04T16:40:31.168451Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 94337268-ddd3-4ed5-bd4a-6ba7e201cbd3 · outbound

This paper cites an unresolved cited work.

Towards Inclusive Toxic Content Moderation: Addressing Vulnerabilities to Adversarial Attacks in Toxicity Classifiers Tackling LLM-generated Content Unresolved cited work

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-04T16:40:31.171648Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 26eea721-1a69-4a69-a7b5-ac85284641c2 · outbound

This paper cites an unresolved cited work.

Towards Inclusive Toxic Content Moderation: Addressing Vulnerabilities to Adversarial Attacks in Toxicity Classifiers Tackling LLM-generated Content Unresolved cited work

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-04T16:40:31.174811Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 50d3bb49-f4db-49aa-92d6-7022dbbacd81 · outbound

This paper cites an unresolved cited work.

Towards Inclusive Toxic Content Moderation: Addressing Vulnerabilities to Adversarial Attacks in Toxicity Classifiers Tackling LLM-generated Content Unresolved cited work

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-04T16:40:31.178582Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cc9cd95e-1d06-44e1-9fe2-c423bae08b88 · outbound

This paper cites an unresolved cited work.

Towards Inclusive Toxic Content Moderation: Addressing Vulnerabilities to Adversarial Attacks in Toxicity Classifiers Tackling LLM-generated Content Unresolved cited work

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-04T16:40:31.181797Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cf8c2438-d63d-4082-803e-d1245e896c3f · outbound

This paper cites an unresolved cited work.

Towards Inclusive Toxic Content Moderation: Addressing Vulnerabilities to Adversarial Attacks in Toxicity Classifiers Tackling LLM-generated Content Unresolved cited work

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-04T16:40:31.184837Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a04ecd64-ce82-4bcb-b222-78843b17a1a3 · outbound

This paper cites A New Generation of Perspective API: Efficient Multilingual Character-level Transformers.

Towards Inclusive Toxic Content Moderation: Addressing Vulnerabilities to Adversarial Attacks in Toxicity Classifiers Tackling LLM-generated Content A New Generation of Perspective API: Efficient Multilingual Character-level Transformers

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-04T16:40:31.187575Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 63aee8c0-e72c-4077-a558-d254dc22d77c · outbound

This paper cites an unresolved cited work.

Towards Inclusive Toxic Content Moderation: Addressing Vulnerabilities to Adversarial Attacks in Toxicity Classifiers Tackling LLM-generated Content Unresolved cited work

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-04T16:40:31.190708Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1a99733c-38c0-447e-aaf8-0988630fe711 · outbound

This paper cites an unresolved cited work.

Towards Inclusive Toxic Content Moderation: Addressing Vulnerabilities to Adversarial Attacks in Toxicity Classifiers Tackling LLM-generated Content Unresolved cited work

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-04T16:40:31.193428Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c8773139-94a8-4f6e-a960-35935bf51f31 · outbound

This paper cites D.; and Finn, C.

Towards Inclusive Toxic Content Moderation: Addressing Vulnerabilities to Adversarial Attacks in Toxicity Classifiers Tackling LLM-generated Content D.; and Finn, C

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-04T16:40:31.196217Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b20839b2-68a0-4c99-9fbe-5a70fe119bb5 · outbound

This paper cites R.; Li, G.; and Crespi, N.

Towards Inclusive Toxic Content Moderation: Addressing Vulnerabilities to Adversarial Attacks in Toxicity Classifiers Tackling LLM-generated Content R.; Li, G.; and Crespi, N

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-04T16:40:31.198929Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1ff28abf-a7b1-45b6-8beb-025ff87e9613 · outbound

This paper cites an unresolved cited work.

Towards Inclusive Toxic Content Moderation: Addressing Vulnerabilities to Adversarial Attacks in Toxicity Classifiers Tackling LLM-generated Content Unresolved cited work

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-04T16:40:31.202127Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8b40be0b-e29d-4760-b373-2f63355c226f · outbound

This paper cites an unresolved cited work.

Towards Inclusive Toxic Content Moderation: Addressing Vulnerabilities to Adversarial Attacks in Toxicity Classifiers Tackling LLM-generated Content Unresolved cited work

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-04T16:40:31.204983Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ad8a4e2f-5d17-4a7f-9ef6-42f3e805f4a1 · outbound

This paper cites an unresolved cited work.

Towards Inclusive Toxic Content Moderation: Addressing Vulnerabilities to Adversarial Attacks in Toxicity Classifiers Tackling LLM-generated Content Unresolved cited work

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-04T16:40:31.207748Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e1b7ddb6-f539-44e8-a6dd-12d2629bb605 · outbound

This paper cites an unresolved cited work.

Towards Inclusive Toxic Content Moderation: Addressing Vulnerabilities to Adversarial Attacks in Toxicity Classifiers Tackling LLM-generated Content Unresolved cited work

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-04T16:40:31.210447Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 293bf6f3-d479-4531-a742-f2abe67f3e14 · outbound

This paper cites an unresolved cited work.

Towards Inclusive Toxic Content Moderation: Addressing Vulnerabilities to Adversarial Attacks in Toxicity Classifiers Tackling LLM-generated Content Unresolved cited work

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-04T16:40:31.213577Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f0ec7491-8aa0-4f1d-8f17-166cf60effcd · outbound

This paper cites Token-Modification Adversarial Attacks for Natural Language Processing: A Survey.

Towards Inclusive Toxic Content Moderation: Addressing Vulnerabilities to Adversarial Attacks in Toxicity Classifiers Tackling LLM-generated Content Token-Modification Adversarial Attacks for Natural Language Processing: A Survey

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-04T16:40:31.216119Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cce6712f-334d-4d41-9a63-1f8030cf7501 · outbound

This paper cites an unresolved cited work.

Towards Inclusive Toxic Content Moderation: Addressing Vulnerabilities to Adversarial Attacks in Toxicity Classifiers Tackling LLM-generated Content Unresolved cited work

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-04T16:40:31.219115Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8aaaba9b-adf5-48c8-a93f-43ac7d596243 · outbound

This paper cites o ck, F.; and Wagner, C. 2021. “Call me sexist, but.

Towards Inclusive Toxic Content Moderation: Addressing Vulnerabilities to Adversarial Attacks in Toxicity Classifiers Tackling LLM-generated Content o ck, F.; and Wagner, C. 2021. “Call me sexist, but

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-04T16:40:31.222044Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a2ae48b7-6b5d-4803-9419-1809e0dcd2f0 · outbound

This paper cites HowkGPT: Investigating the Detection of ChatGPT-generated University Student Homework through Context-Aware Perplexity Analysis.

Towards Inclusive Toxic Content Moderation: Addressing Vulnerabilities to Adversarial Attacks in Toxicity Classifiers Tackling LLM-generated Content HowkGPT: Investigating the Detection of ChatGPT-generated University Student Homework through Context-Aware Perplexity Analysis

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-04T16:40:31.225010Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 86ca1c4e-0812-4f9a-83dd-4a60ca6afa21 · outbound

This paper cites Enhancing Adversarial Text Attacks on BERT Models with Projected Gradient Descent.

Towards Inclusive Toxic Content Moderation: Addressing Vulnerabilities to Adversarial Attacks in Toxicity Classifiers Tackling LLM-generated Content Enhancing Adversarial Text Attacks on BERT Models with Projected Gradient Descent

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-04T16:40:31.227672Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4b27728d-2133-4603-9263-342399895f24 · outbound

This paper cites Interpretability in the Wild: a Circuit for Indirect Object Identification in GPT-2 small.

Towards Inclusive Toxic Content Moderation: Addressing Vulnerabilities to Adversarial Attacks in Toxicity Classifiers Tackling LLM-generated Content Interpretability in the Wild: a Circuit for Indirect Object Identification in GPT-2 small

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-04T16:40:31.230569Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e72fdbae-b950-4752-92da-431093f8e751 · outbound

This paper cites an unresolved cited work.

Towards Inclusive Toxic Content Moderation: Addressing Vulnerabilities to Adversarial Attacks in Toxicity Classifiers Tackling LLM-generated Content Unresolved cited work

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-04T16:40:31.233207Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7b88280b-d6f3-4674-a4ee-071c97d11a47 · outbound

This paper cites an unresolved cited work.

Towards Inclusive Toxic Content Moderation: Addressing Vulnerabilities to Adversarial Attacks in Toxicity Classifiers Tackling LLM-generated Content Unresolved cited work

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-04T16:40:31.235984Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 25799df4-b1cf-4a0a-8220-d889315bb4c5 · outbound

This paper cites S.; and Wong, D.

Towards Inclusive Toxic Content Moderation: Addressing Vulnerabilities to Adversarial Attacks in Toxicity Classifiers Tackling LLM-generated Content S.; and Wong, D

Reference 41

Resolution: unresolved; no resolver link, observed 2026-08-04T16:40:31.238745Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d9849187-ef1a-42d2-ac4e-7c51ab90eeae · outbound

This paper cites S.; and Wong, D.

Towards Inclusive Toxic Content Moderation: Addressing Vulnerabilities to Adversarial Attacks in Toxicity Classifiers Tackling LLM-generated Content S.; and Wong, D

Reference 42

Resolution: unresolved; no resolver link, observed 2026-08-04T16:40:31.241698Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1fd0ebd5-059c-4277-aa79-70989e890b6a · outbound

This paper cites an unresolved cited work.

Towards Inclusive Toxic Content Moderation: Addressing Vulnerabilities to Adversarial Attacks in Toxicity Classifiers Tackling LLM-generated Content Unresolved cited work

Reference 43

Resolution: unresolved; no resolver link, observed 2026-08-04T16:40:31.244420Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f925dcdf-a08b-4a7c-8316-fda551ff1c15 · outbound

This paper cites an unresolved cited work.

Towards Inclusive Toxic Content Moderation: Addressing Vulnerabilities to Adversarial Attacks in Toxicity Classifiers Tackling LLM-generated Content Unresolved cited work

Reference 44

Resolution: unresolved; no resolver link, observed 2026-08-04T16:40:31.247794Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cc5dfd60-e7b4-4b2a-9700-f45348ff631c · outbound

This paper cites an unresolved cited work.

Towards Inclusive Toxic Content Moderation: Addressing Vulnerabilities to Adversarial Attacks in Toxicity Classifiers Tackling LLM-generated Content Unresolved cited work

Reference 45

Resolution: unresolved; no resolver link, observed 2026-08-04T16:40:31.250299Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

No inbound Pith citation observations are available.