Pith. sign in

Paper Citation Record · LEDGER

$PC^2$: Politically Controversial Content Generation via Jailbreaking Attacks on GPT-based Text-to-Image Models

As of 23 August 2026, this Paper Citation Record lists 34 of 34 outbound references and 0 inbound Pith citation observations for arXiv:2601.05150.

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

pith.paper-citation-record.v1
2601.05150 v3

Coverage vector

measured 34 of 34 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-03T11:47:42.121984Z

measured 34 of 34 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 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

34 of 34 outbound references displayed

  • verified exact0
  • verified fuzzy0
  • unresolved34
  • parse uncertain0
  • malformed identifier0
  • metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation f4e5eec5-7e8d-440c-b7b9-2cd1775e8cde · outbound

This paper cites AI can be easily used to make fake election photos.

$PC^2$: Politically Controversial Content Generation via Jailbreaking Attacks on GPT-based Text-to-Image Models AI can be easily used to make fake election photos

Reference 1

Resolution
unresolved
no resolver link, observed 2026-08-03T11:47:40.179584Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-03T11:47:40.179584Z digest=sha256:968957d5ce255042bd5497d95142e028efddef19d598eeb51f5714dccbe1313b

Observation 94f3ee2e-b9c0-4e5f-9086-54c9e845797f · outbound

This paper cites Fake images made to show Trump with Black supporters highlight concerns around AI and elections.

$PC^2$: Politically Controversial Content Generation via Jailbreaking Attacks on GPT-based Text-to-Image Models Fake images made to show Trump with Black supporters highlight concerns around AI and elections

Reference 2

Resolution
unresolved
no resolver link, observed 2026-08-03T11:47:40.254151Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-03T11:47:40.254151Z digest=sha256:d41c4ac69dc547a66169546af5f7d966b46af7504b6885b8e2b712cfb9ce2941

Observation e00f1b7e-91b6-49a6-9221-fd46cfc79576 · outbound

This paper cites How disinformation defined the 2024 election narrative.

$PC^2$: Politically Controversial Content Generation via Jailbreaking Attacks on GPT-based Text-to-Image Models How disinformation defined the 2024 election narrative

Reference 3

Resolution
unresolved
no resolver link, observed 2026-08-03T11:47:40.308148Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-03T11:47:40.308148Z digest=sha256:58c83890a8e598fbd7c7d4c4f9d0e158f91e50b955f0848bffced79d3d43b13c

Observation 37df3946-c211-4e62-8117-8b5f3d77cc24 · outbound

This paper cites OpenAI, Microsoft AI tools generate misleading election images, reser- achers say.

$PC^2$: Politically Controversial Content Generation via Jailbreaking Attacks on GPT-based Text-to-Image Models OpenAI, Microsoft AI tools generate misleading election images, reser- achers say

Reference 4

Resolution
unresolved
no resolver link, observed 2026-08-03T11:47:40.371073Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-03T11:47:40.371073Z digest=sha256:0e3ca6ba75e672bc3ef121cc3c30eeb42fd8b888de4bc6b2bf04298f13f0c4d6

Observation a2d79eb9-7a2a-45d7-9a96-fb61dfd696de · outbound

This paper cites Spitting Images: Tracking Deepfakes and Generative AI in Elections.

$PC^2$: Politically Controversial Content Generation via Jailbreaking Attacks on GPT-based Text-to-Image Models Spitting Images: Tracking Deepfakes and Generative AI in Elections

Reference 5

Resolution
unresolved
no resolver link, observed 2026-08-03T11:47:40.434389Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-03T11:47:40.434389Z digest=sha256:ae22ce164e1518a051e3471e1eb5cff4a6feb83cf2bd863d4c7fb4bb8831aed3

Observation 68564d8f-53a2-47bf-bc5b-eebac8b6f960 · outbound

This paper cites Spotting the deepfakes in this year of elections: how AI detection tools work and where they fail.

$PC^2$: Politically Controversial Content Generation via Jailbreaking Attacks on GPT-based Text-to-Image Models Spotting the deepfakes in this year of elections: how AI detection tools work and where they fail

Reference 6

Resolution
unresolved
no resolver link, observed 2026-08-03T11:47:40.493013Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-03T11:47:40.493013Z digest=sha256:6ae0594d095dec6ac04aa0aa2018666b8d372de91be742b8613e4e481efeb5c2

Observation 5d94fd8a-3247-48af-9d79-56950bbea7cd · outbound

This paper cites X’s chatbot can now generate AI images.

$PC^2$: Politically Controversial Content Generation via Jailbreaking Attacks on GPT-based Text-to-Image Models X’s chatbot can now generate AI images

Reference 7

Resolution
unresolved
no resolver link, observed 2026-08-03T11:47:40.538233Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-03T11:47:40.538233Z digest=sha256:1853b5d26ac27298f05543b5c7d39bd8392b13a986ac5938aba9a0285d505416

Observation f3df197c-9e00-4286-be44-2bef886377ea · outbound

This paper cites LA protests conspiracy theroies disinformation.

$PC^2$: Politically Controversial Content Generation via Jailbreaking Attacks on GPT-based Text-to-Image Models LA protests conspiracy theroies disinformation

Reference 8

Resolution
unresolved
no resolver link, observed 2026-08-03T11:47:40.594133Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-03T11:47:40.594133Z digest=sha256:32a7790349ee40f88942da1cf82d72d17f1118dee76b7b284a30cf0942c6631b

Observation fdab0dcc-2afa-4914-bb6f-ecf5cbd888fd · outbound

This paper cites Sam Altman touts ChatGPT’s 800 million weekly users, double all its main competitors combined.

$PC^2$: Politically Controversial Content Generation via Jailbreaking Attacks on GPT-based Text-to-Image Models Sam Altman touts ChatGPT’s 800 million weekly users, double all its main competitors combined

Reference 9

Resolution
unresolved
no resolver link, observed 2026-08-03T11:47:40.623366Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-03T11:47:40.623366Z digest=sha256:d5ee6af9dc23407c15a85b6b28ecbe4ae588c1a0577a6aad947d3d0eaa8af220

Observation 434846a9-d34d-493a-8979-b73c871f47de · outbound

This paper cites an unresolved cited work.

$PC^2$: Politically Controversial Content Generation via Jailbreaking Attacks on GPT-based Text-to-Image Models Unresolved cited work

Reference 10

Resolution
unresolved
no resolver link, observed 2026-08-03T11:47:40.677402Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-03T11:47:40.677402Z digest=sha256:e1d1b1bc573cd66f8743faaaad01ad5930ee3aabc7edbff5278b1878ca9da0bf

Observation 743e3089-da41-4040-a01b-d73f7ad161e1 · outbound

This paper cites an unresolved cited work.

$PC^2$: Politically Controversial Content Generation via Jailbreaking Attacks on GPT-based Text-to-Image Models Unresolved cited work

Reference 11

Resolution
unresolved
no resolver link, observed 2026-08-03T11:47:40.707267Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-03T11:47:40.707267Z digest=sha256:c947efd0caa3aa9115d43e71b650368674fc0aa11f9c34b08385d129bc7633db

Observation eddff4a9-a50d-4a39-9b5a-ed05b0a2f033 · outbound

This paper cites an unresolved cited work.

$PC^2$: Politically Controversial Content Generation via Jailbreaking Attacks on GPT-based Text-to-Image Models Unresolved cited work

Reference 12

Resolution
unresolved
no resolver link, observed 2026-08-03T11:47:40.761218Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-03T11:47:40.761218Z digest=sha256:55f7e84351b6e0ca4c28b0609f62f7f92dfbe874b4b9eae2960c1a3e624cbaf6

Observation ed189d3e-bd1e-4226-8402-14f97af2ff7c · outbound

This paper cites an unresolved cited work.

$PC^2$: Politically Controversial Content Generation via Jailbreaking Attacks on GPT-based Text-to-Image Models Unresolved cited work

Reference 13

Resolution
unresolved
no resolver link, observed 2026-08-03T11:47:40.788560Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-03T11:47:40.788560Z digest=sha256:c78e730e67cc022703c840bcccc8136572e2a862b6f9e923e90e6c97446d28ee

Observation 0d94cf66-b3c6-4cbd-8922-44ae15260d29 · outbound

This paper cites Harnessing LLM to Attack LLM-Guarded Text-to-Image Models.

$PC^2$: Politically Controversial Content Generation via Jailbreaking Attacks on GPT-based Text-to-Image Models Harnessing LLM to Attack LLM-Guarded Text-to-Image Models

Reference 14

Resolution
unresolved
no resolver link, observed 2026-08-03T11:47:40.843593Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-03T11:47:40.843593Z digest=sha256:943bc0e2d16ab25b75db203239447bd50f62b07c2dcea620fc78bccea75b8823

Observation fbd89465-712f-40d5-8902-d98dad047c4a · outbound

This paper cites an unresolved cited work.

$PC^2$: Politically Controversial Content Generation via Jailbreaking Attacks on GPT-based Text-to-Image Models Unresolved cited work

Reference 15

Resolution
unresolved
no resolver link, observed 2026-08-03T11:47:40.874788Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-03T11:47:40.874788Z digest=sha256:f61d46b98820a6033900f524f0611b777b194a54b512a0da4f9c203da75cc0ed

Observation 9020eb41-cb23-4b27-9d3d-f113fdf65485 · outbound

This paper cites Fuzz-Testing Meets LLM-Based Agents: An Automated and Efficient Framework for Jailbreaking Text-To-Image Generation Models.

$PC^2$: Politically Controversial Content Generation via Jailbreaking Attacks on GPT-based Text-to-Image Models Fuzz-Testing Meets LLM-Based Agents: An Automated and Efficient Framework for Jailbreaking Text-To-Image Generation Models

Reference 16

Resolution
unresolved
no resolver link, observed 2026-08-03T11:47:40.898462Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-03T11:47:40.898462Z digest=sha256:7cca400fbcd4dd618a0d59aca7dd7e46b36693b27285863a2b4c3128c36ddb7c

Observation f6ad236e-7cb7-443e-9cd1-9f5a58f18c3d · outbound

This paper cites an unresolved cited work.

$PC^2$: Politically Controversial Content Generation via Jailbreaking Attacks on GPT-based Text-to-Image Models Unresolved cited work

Reference 17

Resolution
unresolved
no resolver link, observed 2026-08-03T11:47:40.952562Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-03T11:47:40.952562Z digest=sha256:b964b692eeddaf4c8527e3c5e6832eaffc998d32447ee0cf54197f23bb1010e3

Observation 302553f5-7d76-4594-b39c-1f8ee1b99e61 · outbound

This paper cites an unresolved cited work.

$PC^2$: Politically Controversial Content Generation via Jailbreaking Attacks on GPT-based Text-to-Image Models Unresolved cited work

Reference 18

Resolution
unresolved
no resolver link, observed 2026-08-03T11:47:40.982578Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-03T11:47:40.982578Z digest=sha256:2d5927a8ecbcdb76d78cb3646214ff4584b21402814f386771f55b5595196724

Observation 1775d580-93e8-49ea-9f63-969404d23f3e · outbound

This paper cites an unresolved cited work.

$PC^2$: Politically Controversial Content Generation via Jailbreaking Attacks on GPT-based Text-to-Image Models Unresolved cited work

Reference 19

Resolution
unresolved
no resolver link, observed 2026-08-03T11:47:41.038766Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-03T11:47:41.038766Z digest=sha256:df6daab910157fa6f5b564e7c79fae5dc78dc8fc980f7811609023f19766da05

Observation b40a2ad0-bf71-47c7-bc71-96cf22eb8df8 · outbound

This paper cites an unresolved cited work.

$PC^2$: Politically Controversial Content Generation via Jailbreaking Attacks on GPT-based Text-to-Image Models Unresolved cited work

Reference 20

Resolution
unresolved
no resolver link, observed 2026-08-03T11:47:41.127859Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-03T11:47:41.127859Z digest=sha256:17c798ca2efa714c309fd6332053d0422c58cb9f5f073337ea7abca20bdab544

Observation 578261e9-e7a0-4aef-a60a-d14880be6f53 · outbound

This paper cites Safety Alignment for Vision Language Models.

$PC^2$: Politically Controversial Content Generation via Jailbreaking Attacks on GPT-based Text-to-Image Models Safety Alignment for Vision Language Models

Reference 21

Resolution
unresolved
no resolver link, observed 2026-08-03T11:47:41.187248Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-03T11:47:41.187248Z digest=sha256:6d62911c467d81043a6db755fa37ddcea440aefdab365268fde3b4b8b7f11f0d

Observation bb298f4c-9696-4aa2-a1fd-64095bd41e46 · outbound

This paper cites an unresolved cited work.

$PC^2$: Politically Controversial Content Generation via Jailbreaking Attacks on GPT-based Text-to-Image Models Unresolved cited work

Reference 22

Resolution
unresolved
no resolver link, observed 2026-08-03T11:47:41.249858Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-03T11:47:41.249858Z digest=sha256:d4018185b6b160986e1fce71fce71e1f2691ace051b960a06ca8ea17d7995486

Observation 085664a2-9fa2-4b2f-8ca6-c245440b1699 · outbound

This paper cites an unresolved cited work.

$PC^2$: Politically Controversial Content Generation via Jailbreaking Attacks on GPT-based Text-to-Image Models Unresolved cited work

Reference 23

Resolution
unresolved
no resolver link, observed 2026-08-03T11:47:41.303484Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-03T11:47:41.303484Z digest=sha256:5724ef8472f2e77d7701f622041115d15917f6566b49e75cbe297285da726a1a

Observation cfb61b36-77c8-4309-975b-08d98b5747cf · outbound

This paper cites Adversarial Attacks on Image Generation With Made-Up Words.

$PC^2$: Politically Controversial Content Generation via Jailbreaking Attacks on GPT-based Text-to-Image Models Adversarial Attacks on Image Generation With Made-Up Words

Reference 24

Resolution
unresolved
no resolver link, observed 2026-08-03T11:47:41.477715Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-03T11:47:41.477715Z digest=sha256:1a4fddef38710b04b7dbd033d65032116c01f112fd07dcd19f26299a56bcca2f

Observation 34595cda-3422-43bf-b86c-5a7e86519096 · outbound

This paper cites Learning To See But Forgetting To Follow: Visual Instruction Tuning Makes LLMs More Prone To Jailbreak Attacks.

$PC^2$: Politically Controversial Content Generation via Jailbreaking Attacks on GPT-based Text-to-Image Models Learning To See But Forgetting To Follow: Visual Instruction Tuning Makes LLMs More Prone To Jailbreak Attacks

Reference 25

Resolution
unresolved
no resolver link, observed 2026-08-03T11:47:41.539959Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-03T11:47:41.539959Z digest=sha256:bde7f29b240abcf2c10914aef7d3a71d567940326e0aa5b15fac70efdd9da71b

Observation 06b18480-2712-4e1b-bc58-3265e16438ca · outbound

This paper cites an unresolved cited work.

$PC^2$: Politically Controversial Content Generation via Jailbreaking Attacks on GPT-based Text-to-Image Models Unresolved cited work

Reference 26

Resolution
unresolved
no resolver link, observed 2026-08-03T11:47:41.602810Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-03T11:47:41.602810Z digest=sha256:48e9d5001436ad3ae972a6e59d7eff55395bdfa5c116837daf9279151995877f

Observation e3345a91-f541-4102-b8dd-3d333c6e4b5b · outbound

This paper cites Ring-A-Bell! How Reliable are Concept Removal Methods for Diffusion Models?.

$PC^2$: Politically Controversial Content Generation via Jailbreaking Attacks on GPT-based Text-to-Image Models Ring-A-Bell! How Reliable are Concept Removal Methods for Diffusion Models?

Reference 27

Resolution
unresolved
no resolver link, observed 2026-08-03T11:47:41.664591Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-03T11:47:41.664591Z digest=sha256:02f83f27341ba505e1d4e64015b2cc77d611613fe06970466064a2deb418de68

Observation b415753a-7b38-492f-936d-df32557867e6 · outbound

This paper cites an unresolved cited work.

$PC^2$: Politically Controversial Content Generation via Jailbreaking Attacks on GPT-based Text-to-Image Models Unresolved cited work

Reference 28

Resolution
unresolved
no resolver link, observed 2026-08-03T11:47:41.724715Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-03T11:47:41.724715Z digest=sha256:087a17802e32237f03db6a78db67792133123c856b8bfdf472ac75080579c8ea

Observation 0f094c1f-dd5a-4cc5-94b6-4f5c8dd102fe · outbound

This paper cites an unresolved cited work.

$PC^2$: Politically Controversial Content Generation via Jailbreaking Attacks on GPT-based Text-to-Image Models Unresolved cited work

Reference 29

Resolution
unresolved
no resolver link, observed 2026-08-03T11:47:41.819949Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-03T11:47:41.819949Z digest=sha256:f4599f825f9c3c8b182afe49bd37150095a440dfa3a267c1a36ed5f0f81b5f2d

Observation f537dbd3-8f42-4338-bc20-0b9d67bad418 · outbound

This paper cites an unresolved cited work.

$PC^2$: Politically Controversial Content Generation via Jailbreaking Attacks on GPT-based Text-to-Image Models Unresolved cited work

Reference 30

Resolution
unresolved
no resolver link, observed 2026-08-03T11:47:41.874651Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-03T11:47:41.874651Z digest=sha256:fe02d547886b01de4a82c829a07e9256b152155be4172dc833c52f23787dc7bf

Observation 0069bcd6-9c00-4f3b-ba25-117bf269772c · outbound

This paper cites an unresolved cited work.

$PC^2$: Politically Controversial Content Generation via Jailbreaking Attacks on GPT-based Text-to-Image Models Unresolved cited work

Reference 31

Resolution
unresolved
no resolver link, observed 2026-08-03T11:47:41.979924Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-03T11:47:41.979924Z digest=sha256:ed0c20da21b341e3235e98c9028e9b9681a0d9c9fc15f8e9273d1156cbd65d8d

Observation 9b43d5ae-e6dd-435b-a94b-5284bc411ee2 · outbound

This paper cites an unresolved cited work.

$PC^2$: Politically Controversial Content Generation via Jailbreaking Attacks on GPT-based Text-to-Image Models Unresolved cited work

Reference 32

Resolution
unresolved
no resolver link, observed 2026-08-03T11:47:42.063789Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-03T11:47:42.063789Z digest=sha256:a4a1000cf7b09bb08458cba14b79de4ea0569317d7f5cf15263b680e4f42157d

Observation 869ad401-9110-4c07-890a-d7e85aabfc82 · outbound

This paper cites an unresolved cited work.

$PC^2$: Politically Controversial Content Generation via Jailbreaking Attacks on GPT-based Text-to-Image Models Unresolved cited work

Reference 33

Resolution
unresolved
no resolver link, observed 2026-08-03T11:47:42.121984Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-03T11:47:42.121984Z digest=sha256:8b8c3ed5c07314ee3082cb0feb8eb9600f0d1e3af6315fbdb8e72bdb224a145c

Observation 6e657cb9-22ce-497c-85bd-cb60316fdbb4 · outbound

This paper cites In Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers).

$PC^2$: Politically Controversial Content Generation via Jailbreaking Attacks on GPT-based Text-to-Image Models In Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

Reference 2025

Resolution
unresolved
no resolver link, observed 2026-08-03T11:47:41.926780Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-03T11:47:41.926780Z digest=sha256:6aea73553321975b58aa828ff7576a870af6eede5d3528d394b4f3b792715151

Pith citing papers

No inbound Pith citation observations are available.