Paper Citation Record · LEDGER

T2ISafety: Benchmark for Assessing Fairness, Toxicity, and Privacy in Image Generation

As of 22 August 2026, this Paper Citation Record lists 84 of 84 outbound references and 3 inbound Pith citation observations for arXiv:2501.12612.

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

pith.paper-citation-record.v1
2501.12612 v3

Coverage vector

measured 84 of 84 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-10T17:05:50.908494Z

measured 87 of 87 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-22T06:32:14.747728+00:00

measured 3 of 3 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-06T12:54:35.249132Z

measured 0 of 1 external citation measurements

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

Source: pith, observed 2026-08-05T18:47:20.984624Z

Reference resolution

84 of 84 outbound references displayed

verified exact0
verified fuzzy40
unresolved44
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 71985dff-fbf6-449d-947f-bf5847f22623 · outbound

This paper cites Moderating content.

T2ISafety: Benchmark for Assessing Fairness, Toxicity, and Privacy in Image Generation Moderating content

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-10T17:05:50.511837Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a74e2a05-317a-4701-80d8-e3566fd3a3cf · outbound

This paper cites Claude 3.5 sonnet.

T2ISafety: Benchmark for Assessing Fairness, Toxicity, and Privacy in Image Generation Claude 3.5 sonnet

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-10T17:05:50.517566Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e2357b72-ec87-4486-882c-15a491d49c0d · outbound

This paper cites Kandinsky 3.0 Technical Report.

T2ISafety: Benchmark for Assessing Fairness, Toxicity, and Privacy in Image Generation Kandinsky 3.0 Technical Report

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-10T17:05:50.527469Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 41c25ca5-ebf2-41da-8808-364e140769e5 · outbound

This paper cites SurrogatePrompt: Bypassing the Safety Filter of Text-to-Image Models via Substitution.

T2ISafety: Benchmark for Assessing Fairness, Toxicity, and Privacy in Image Generation SurrogatePrompt: Bypassing the Safety Filter of Text-to-Image Models via Substitution

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-10T17:05:50.532867Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9fd8344e-35b6-491a-a6b5-428e51cb0fcf · outbound

This paper cites Qwen Technical Report.

T2ISafety: Benchmark for Assessing Fairness, Toxicity, and Privacy in Image Generation Qwen Technical Report

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-10T17:05:50.537973Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 167b0f45-5c4f-4c3e-9cbe-7545f34aa2f6 · outbound

This paper cites Hrs-bench: Holistic, reliable and scalable benchmark for text-to-image models.

T2ISafety: Benchmark for Assessing Fairness, Toxicity, and Privacy in Image Generation Hrs-bench: Holistic, reliable and scalable benchmark for text-to-image models

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-10T17:05:50.543148Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 06714c02-4fe3-474e-aba8-1dcc7359865f · outbound

This paper cites Easily acces- sible text-to-image generation amplifies demographic stereo- types at large scale.

T2ISafety: Benchmark for Assessing Fairness, Toxicity, and Privacy in Image Generation Easily acces- sible text-to-image generation amplifies demographic stereo- types at large scale

Reference 7

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T17:05:52.172481Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 6be9ff1e-3ed2-43d0-b77e-cab2d63e87a6 · outbound

This paper cites Executive order on the safe, se- cure, and trustworthy development and use of artifi- cial intelligence.

T2ISafety: Benchmark for Assessing Fairness, Toxicity, and Privacy in Image Generation Executive order on the safe, se- cure, and trustworthy development and use of artifi- cial intelligence

Reference 8

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T17:05:52.157490Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 65e8b1d4-2ebf-4572-8cc8-4efebd8c7da2 · outbound

This paper cites Ty- pology of risks of generative text-to-image models.

T2ISafety: Benchmark for Assessing Fairness, Toxicity, and Privacy in Image Generation Ty- pology of risks of generative text-to-image models

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T17:05:52.141950Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation fd30e2ea-2bd5-46db-8af2-67fcc93c8501 · outbound

This paper cites Pixart-α: Fast training of dif- fusion transformer for photorealistic text-to-image synthesis,.

T2ISafety: Benchmark for Assessing Fairness, Toxicity, and Privacy in Image Generation Pixart-α: Fast training of dif- fusion transformer for photorealistic text-to-image synthesis,

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-10T17:05:50.562321Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fc13866c-1e9b-49d9-b586-a73cfa80eef4 · outbound

This paper cites Internvl: Scaling up vision foundation mod- els and aligning for generic visual-linguistic tasks.

T2ISafety: Benchmark for Assessing Fairness, Toxicity, and Privacy in Image Generation Internvl: Scaling up vision foundation mod- els and aligning for generic visual-linguistic tasks

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T17:05:52.117437Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 10de3fa4-37f9-488f-899f-fb543f99a95c · outbound

This paper cites Dall-eval: Probing the reasoning skills and social biases of text-to- image generation models.

T2ISafety: Benchmark for Assessing Fairness, Toxicity, and Privacy in Image Generation Dall-eval: Probing the reasoning skills and social biases of text-to- image generation models

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T17:05:52.103314Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 03276f49-5745-4830-ba97-c75ac9a4fd6b · outbound

This paper cites The eu artificial intelligence act.

T2ISafety: Benchmark for Assessing Fairness, Toxicity, and Privacy in Image Generation The eu artificial intelligence act

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T17:05:52.088541Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation a5984936-9672-4705-b3bd-3e9804a722f5 · outbound

This paper cites The socio-moral image database (smid): A novel stimulus set for the study of social, moral and affective processes.

T2ISafety: Benchmark for Assessing Fairness, Toxicity, and Privacy in Image Generation The socio-moral image database (smid): A novel stimulus set for the study of social, moral and affective processes

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T17:05:52.057055Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation fc9448e2-a8cb-448b-807e-9b3d7aa38ceb · outbound

This paper cites Scaling recti- fied flow transformers for high-resolution image synthesis.

T2ISafety: Benchmark for Assessing Fairness, Toxicity, and Privacy in Image Generation Scaling recti- fied flow transformers for high-resolution image synthesis

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T17:05:52.037643Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 38d003a7-0541-47f5-ad8c-c7773d1d0165 · outbound

This paper cites InternLM-XComposer2: Mastering Free-form Text-Image Composition and Comprehension in Vision-Language Large Model.

T2ISafety: Benchmark for Assessing Fairness, Toxicity, and Privacy in Image Generation InternLM-XComposer2: Mastering Free-form Text-Image Composition and Comprehension in Vision-Language Large Model

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-10T17:05:50.589496Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4241eadf-8346-4c2c-886a-394d737ecaf6 · outbound

This paper cites Erasing concepts from diffusion models.

T2ISafety: Benchmark for Assessing Fairness, Toxicity, and Privacy in Image Generation Erasing concepts from diffusion models

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T17:05:52.019166Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 9a55363f-cfd9-4010-92cb-1148cdd06c01 · outbound

This paper cites An Image is Worth One Word: Personalizing Text-to-Image Generation using Textual Inversion.

T2ISafety: Benchmark for Assessing Fairness, Toxicity, and Privacy in Image Generation An Image is Worth One Word: Personalizing Text-to-Image Generation using Textual Inversion

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-10T17:05:50.598796Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2cbcc3d9-7385-4a1a-83dd-58f4763a8879 · outbound

This paper cites Generative ai prohibited use policy.

T2ISafety: Benchmark for Assessing Fairness, Toxicity, and Privacy in Image Generation Generative ai prohibited use policy

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T17:05:51.987674Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation faebd570-248b-41c8-92f9-84fc36635d03 · outbound

This paper cites Unified concept editing in dif- 9 fusion models.

T2ISafety: Benchmark for Assessing Fairness, Toxicity, and Privacy in Image Generation Unified concept editing in dif- 9 fusion models

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T17:05:52.002182Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 70775430-b3e3-48cb-946a-b9559fbc3f1a · outbound

This paper cites Harm Amplification in Text-to-Image Models.

T2ISafety: Benchmark for Assessing Fairness, Toxicity, and Privacy in Image Generation Harm Amplification in Text-to-Image Models

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-10T17:05:50.622225Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 929d380c-a487-4455-9cab-ed863eac1fd9 · outbound

This paper cites Facet: Fairness in computer vision evaluation benchmark.

T2ISafety: Benchmark for Assessing Fairness, Toxicity, and Privacy in Image Generation Facet: Fairness in computer vision evaluation benchmark

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T17:05:51.972946Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation df2f6d5c-7144-43f2-b692-6b145fa0a41c · outbound

This paper cites Tifa: Accu- rate and interpretable text-to-image faithfulness evaluation with question answering.

T2ISafety: Benchmark for Assessing Fairness, Toxicity, and Privacy in Image Generation Tifa: Accu- rate and interpretable text-to-image faithfulness evaluation with question answering

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T17:05:51.957076Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 0474d5b3-863c-4a49-a7c1-5f2231290c57 · outbound

This paper cites LlavaGuard: An Open VLM-based Framework for Safeguarding Vision Datasets and Models.

T2ISafety: Benchmark for Assessing Fairness, Toxicity, and Privacy in Image Generation LlavaGuard: An Open VLM-based Framework for Safeguarding Vision Datasets and Models

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-10T17:05:50.627122Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 42fbd1b9-624d-418d-aea5-43cd0aa60d3c · outbound

This paper cites Camels in a Changing Climate: Enhancing LM Adaptation with Tulu 2.

T2ISafety: Benchmark for Assessing Fairness, Toxicity, and Privacy in Image Generation Camels in a Changing Climate: Enhancing LM Adaptation with Tulu 2

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-10T17:05:50.641337Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d93024db-1aae-4286-aff4-b48b2472dea6 · outbound

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

T2ISafety: Benchmark for Assessing Fairness, Toxicity, and Privacy in Image Generation Llama Guard: LLM-based Input-Output Safeguard for Human-AI Conversations

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-10T17:05:50.636880Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1ee5c3e2-9e13-4375-b6d9-58bd65aaf031 · outbound

This paper cites Fairface: Face attribute dataset for balanced race, gender, and age for bias measurement and mitigation.

T2ISafety: Benchmark for Assessing Fairness, Toxicity, and Privacy in Image Generation Fairface: Face attribute dataset for balanced race, gender, and age for bias measurement and mitigation

Reference 28

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T17:05:51.937944Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 62ba0b21-b68e-4961-a627-111314b828f6 · outbound

This paper cites Mixtral of Experts.

T2ISafety: Benchmark for Assessing Fairness, Toxicity, and Privacy in Image Generation Mixtral of Experts

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-10T17:05:50.645934Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4a5093ad-b207-4e6b-ac36-37deca9e3a36 · outbound

This paper cites Under- standing fairness of gender classification algorithms across gender-race groups.

T2ISafety: Benchmark for Assessing Fairness, Toxicity, and Privacy in Image Generation Under- standing fairness of gender classification algorithms across gender-race groups

Reference 30

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T17:05:51.902275Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 2e7aca92-7593-4fd8-b244-05d5d4deefe3 · outbound

This paper cites Pick-a-pic: An open dataset of user preferences for text-to-image generation.

T2ISafety: Benchmark for Assessing Fairness, Toxicity, and Privacy in Image Generation Pick-a-pic: An open dataset of user preferences for text-to-image generation

Reference 31

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T17:05:51.919822Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 2ad75ac9-0561-486f-831f-52ef460f4bc2 · outbound

This paper cites Holis- tic evaluation of text-to-image models.

T2ISafety: Benchmark for Assessing Fairness, Toxicity, and Privacy in Image Generation Holis- tic evaluation of text-to-image models

Reference 32

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T17:05:51.884922Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation fc098588-c8de-4bea-b168-855bf3747db6 · outbound

This paper cites What matters when building vision-language models?.

T2ISafety: Benchmark for Assessing Fairness, Toxicity, and Privacy in Image Generation What matters when building vision-language models?

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-10T17:05:50.663714Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b8f42985-bbf6-473c-9f47-d8c35f2f5e0d · outbound

This paper cites Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models.

T2ISafety: Benchmark for Assessing Fairness, Toxicity, and Privacy in Image Generation Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models

Reference 34

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T17:05:51.868955Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation ef7e2842-025c-4261-b4fd-52ba60153825 · outbound

This paper cites Playground v2.5: Three Insights towards Enhancing Aesthetic Quality in Text-to-Image Generation.

T2ISafety: Benchmark for Assessing Fairness, Toxicity, and Privacy in Image Generation Playground v2.5: Three Insights towards Enhancing Aesthetic Quality in Text-to-Image Generation

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-10T17:05:50.672992Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1ab147ee-4cf9-472c-b5dd-b50317a0dd11 · outbound

This paper cites SafeGen: Mitigating Sexually Explicit Content Generation in Text-to-Image Models.

T2ISafety: Benchmark for Assessing Fairness, Toxicity, and Privacy in Image Generation SafeGen: Mitigating Sexually Explicit Content Generation in Text-to-Image Models

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-10T17:05:50.686757Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 519b0718-fa19-4531-9724-9239891201f4 · outbound

This paper cites DiffHand: End-to-End Hand Mesh Reconstruction via Diffusion Models.

T2ISafety: Benchmark for Assessing Fairness, Toxicity, and Privacy in Image Generation DiffHand: End-to-End Hand Mesh Reconstruction via Diffusion Models

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-10T17:05:50.681990Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 31cff251-00e6-468c-a60f-cbdff9dcd3dd · outbound

This paper cites SDXL-Lightning: Progressive Adversarial Diffusion Distillation.

T2ISafety: Benchmark for Assessing Fairness, Toxicity, and Privacy in Image Generation SDXL-Lightning: Progressive Adversarial Diffusion Distillation

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-10T17:05:50.696666Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4287647a-e996-43af-9b67-db4af3afc96b · outbound

This paper cites Hunyuan-DiT: A Powerful Multi-Resolution Diffusion Transformer with Fine-Grained Chinese Understanding.

T2ISafety: Benchmark for Assessing Fairness, Toxicity, and Privacy in Image Generation Hunyuan-DiT: A Powerful Multi-Resolution Diffusion Transformer with Fine-Grained Chinese Understanding

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-10T17:05:50.691701Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 206994eb-abe3-43f8-a4c5-95f706b51cd6 · outbound

This paper cites Llava-next: Im- proved reasoning, ocr, and world knowledge, 2024.

T2ISafety: Benchmark for Assessing Fairness, Toxicity, and Privacy in Image Generation Llava-next: Im- proved reasoning, ocr, and world knowledge, 2024

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-10T17:05:50.706319Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 34d0c6d6-07e8-4428-bc38-eb571007e9e0 · outbound

This paper cites Evaluating Text-to-Visual Generation with Image-to-Text Generation.

T2ISafety: Benchmark for Assessing Fairness, Toxicity, and Privacy in Image Generation Evaluating Text-to-Visual Generation with Image-to-Text Generation

Reference 41

Resolution: unresolved; no resolver link, observed 2026-08-10T17:05:50.701277Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 70a55d2d-66d3-4e78-b921-de855375188b · outbound

This paper cites FAIntbench: A Holistic and Precise Benchmark for Bias Evaluation in Text-to-Image Models.

T2ISafety: Benchmark for Assessing Fairness, Toxicity, and Privacy in Image Generation FAIntbench: A Holistic and Precise Benchmark for Bias Evaluation in Text-to-Image Models

Reference 42

Resolution: unresolved; no resolver link, observed 2026-08-10T17:05:50.714847Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 176bd089-fb75-4daf-85c2-d8dd1abd2751 · outbound

This paper cites Mace: Mass concept erasure in diffu- sion models.

T2ISafety: Benchmark for Assessing Fairness, Toxicity, and Privacy in Image Generation Mace: Mass concept erasure in diffu- sion models

Reference 43

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T17:05:51.841561Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 644a1056-47ac-4a77-80a9-4e8783c07be6 · outbound

This paper cites Terms of service.

T2ISafety: Benchmark for Assessing Fairness, Toxicity, and Privacy in Image Generation Terms of service

Reference 44

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T17:05:51.807344Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation e7b21f54-437e-4f14-860e-688756c71638 · outbound

This paper cites Interrater reliability: the kappa statistic.

T2ISafety: Benchmark for Assessing Fairness, Toxicity, and Privacy in Image Generation Interrater reliability: the kappa statistic

Reference 45

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T17:05:51.824004Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 817d3534-17d6-4401-9914-eca329694ac8 · outbound

This paper cites Dall·e 3.

T2ISafety: Benchmark for Assessing Fairness, Toxicity, and Privacy in Image Generation Dall·e 3

Reference 46

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T17:05:51.787565Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 55a4420c-b71f-4bec-9637-fe6e037b6ef9 · outbound

This paper cites Representation Learning with Contrastive Predictive Coding.

T2ISafety: Benchmark for Assessing Fairness, Toxicity, and Privacy in Image Generation Representation Learning with Contrastive Predictive Coding

Reference 48

Resolution: unresolved; no resolver link, observed 2026-08-10T17:05:50.732734Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a312fe0a-a526-47a8-81b5-7191695b4231 · outbound

This paper cites Benchmark for compositional text-to- image synthesis.

T2ISafety: Benchmark for Assessing Fairness, Toxicity, and Privacy in Image Generation Benchmark for compositional text-to- image synthesis

Reference 49

Resolution: unresolved; no resolver link, observed 2026-08-10T17:05:50.750299Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6c6a88a7-315a-4797-9bc4-1b1099eff642 · outbound

This paper cites Gpt-4o system card.

T2ISafety: Benchmark for Assessing Fairness, Toxicity, and Privacy in Image Generation Gpt-4o system card

Reference 50

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T17:05:51.771572Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation d5de069b-8408-429e-a6a4-46cdf92261a7 · outbound

This paper cites Usage policies.

T2ISafety: Benchmark for Assessing Fairness, Toxicity, and Privacy in Image Generation Usage policies

Reference 51

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T17:05:51.755005Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 333b3f4b-736b-4278-963c-369e3202a484 · outbound

This paper cites Unsafe diffusion: On the generation of unsafe images and hateful memes from text-to-image models.

T2ISafety: Benchmark for Assessing Fairness, Toxicity, and Privacy in Image Generation Unsafe diffusion: On the generation of unsafe images and hateful memes from text-to-image models

Reference 52

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T17:05:51.713024Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation cf78e14f-8020-4608-a7e7-1db26f3fdc79 · outbound

This paper cites Scalable diffusion models with transformers.

T2ISafety: Benchmark for Assessing Fairness, Toxicity, and Privacy in Image Generation Scalable diffusion models with transformers

Reference 53

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T17:05:51.729228Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation f846f29c-ea9b-430f-849f-5d80eceba00c · outbound

This paper cites SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis.

T2ISafety: Benchmark for Assessing Fairness, Toxicity, and Privacy in Image Generation SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis

Reference 54

Resolution: unresolved; no resolver link, observed 2026-08-10T17:05:50.759779Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e2cd63f5-d91b-4cc1-ad38-050c4a62631d · outbound

This paper cites Red-Teaming the Stable Diffusion Safety Filter.

T2ISafety: Benchmark for Assessing Fairness, Toxicity, and Privacy in Image Generation Red-Teaming the Stable Diffusion Safety Filter

Reference 55

Resolution: unresolved; no resolver link, observed 2026-08-10T17:05:50.779016Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ff3c2c8c-8b75-470e-9a1a-147b1a6da994 · outbound

This paper cites UnsafeBench: Benchmarking Image Safety Classifiers on Real-World and AI-Generated Images.

T2ISafety: Benchmark for Assessing Fairness, Toxicity, and Privacy in Image Generation UnsafeBench: Benchmarking Image Safety Classifiers on Real-World and AI-Generated Images

Reference 56

Resolution: unresolved; no resolver link, observed 2026-08-10T17:05:50.769339Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 09a691bb-7cef-4dc1-abf1-2b556721bff5 · outbound

This paper cites Learn- ing transferable visual models from natural language super- vision.

T2ISafety: Benchmark for Assessing Fairness, Toxicity, and Privacy in Image Generation Learn- ing transferable visual models from natural language super- vision

Reference 57

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T17:05:51.696515Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation b1a18be3-a11f-4a87-a8f8-43f71bbb9338 · outbound

This paper cites Sentence-bert: Sentence embeddings using siamese bert-networks.

T2ISafety: Benchmark for Assessing Fairness, Toxicity, and Privacy in Image Generation Sentence-bert: Sentence embeddings using siamese bert-networks

Reference 58

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T17:05:51.680945Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation ecf9746d-48c4-43ce-aa7e-0e0e57742d34 · outbound

This paper cites Kandinsky: an Improved Text-to-Image Synthesis with Image Prior and Latent Diffusion.

T2ISafety: Benchmark for Assessing Fairness, Toxicity, and Privacy in Image Generation Kandinsky: an Improved Text-to-Image Synthesis with Image Prior and Latent Diffusion

Reference 59

Resolution: unresolved; no resolver link, observed 2026-08-10T17:05:50.783602Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6f599f58-90a9-4bdb-81e6-caa323b7ef9d · outbound

This paper cites Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context.

T2ISafety: Benchmark for Assessing Fairness, Toxicity, and Privacy in Image Generation Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context

Reference 60

Resolution: unresolved; no resolver link, observed 2026-08-10T17:05:50.788911Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 63aa24a8-c340-4d7c-b7bf-c9358a3f59d8 · outbound

This paper cites Adversarial Diffusion Distillation.

T2ISafety: Benchmark for Assessing Fairness, Toxicity, and Privacy in Image Generation Adversarial Diffusion Distillation

Reference 61

Resolution: unresolved; no resolver link, observed 2026-08-10T17:05:50.806595Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bed5331d-c63f-452c-8b25-c128a1004088 · outbound

This paper cites High-resolution image synthesis with latent diffusion models.

T2ISafety: Benchmark for Assessing Fairness, Toxicity, and Privacy in Image Generation High-resolution image synthesis with latent diffusion models

Reference 62

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T17:05:51.665957Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation a135a694-e97b-4f8e-8f49-b08220421e8b · outbound

This paper cites Photorealistic text-to-image diffusion models with deep language understanding.

T2ISafety: Benchmark for Assessing Fairness, Toxicity, and Privacy in Image Generation Photorealistic text-to-image diffusion models with deep language understanding

Reference 63

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T17:05:51.650643Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 24a778cf-c068-4000-9de1-8d7f373e76ad · outbound

This paper cites Laion-5b: An open large-scale dataset for training next generation image-text models.

T2ISafety: Benchmark for Assessing Fairness, Toxicity, and Privacy in Image Generation Laion-5b: An open large-scale dataset for training next generation image-text models

Reference 64

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T17:05:51.603992Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation f6958399-3a21-4fb4-afe9-bd17e2779337 · outbound

This paper cites an unresolved cited work.

T2ISafety: Benchmark for Assessing Fairness, Toxicity, and Privacy in Image Generation Unresolved cited work

Reference 65

Resolution: unresolved; raw_fallback, observed 2026-08-10T17:05:51.635819Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 74602c29-ae06-4d05-b5ac-06d654383c4f · outbound

This paper cites Safe latent diffusion: Mitigating inappro- priate degeneration in diffusion models.

T2ISafety: Benchmark for Assessing Fairness, Toxicity, and Privacy in Image Generation Safe latent diffusion: Mitigating inappro- priate degeneration in diffusion models

Reference 66

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T17:05:51.619876Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation ec6ce904-0fff-4e70-a8a1-49cdd9871188 · outbound

This paper cites Finetuning Text-to-Image Diffusion Models for Fairness.

T2ISafety: Benchmark for Assessing Fairness, Toxicity, and Privacy in Image Generation Finetuning Text-to-Image Diffusion Models for Fairness

Reference 67

Resolution: unresolved; no resolver link, observed 2026-08-10T17:05:50.835178Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e6974cca-d625-42e2-a9a6-b3c2510619a5 · outbound

This paper cites Fairness and ab- straction in sociotechnical systems.

T2ISafety: Benchmark for Assessing Fairness, Toxicity, and Privacy in Image Generation Fairness and ab- straction in sociotechnical systems

Reference 68

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T17:05:51.589657Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 71b24fa4-0644-454f-9381-ccbfa807af61 · outbound

This paper cites The Bias Amplification Paradox in Text-to-Image Generation.

T2ISafety: Benchmark for Assessing Fairness, Toxicity, and Privacy in Image Generation The Bias Amplification Paradox in Text-to-Image Generation

Reference 69

Resolution: unresolved; no resolver link, observed 2026-08-10T17:05:50.830411Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1ec932bf-cb43-4f7b-afba-bb8e1a7de48b · outbound

This paper cites Dream studio terms of service.

T2ISafety: Benchmark for Assessing Fairness, Toxicity, and Privacy in Image Generation Dream studio terms of service

Reference 70

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T17:05:51.542488Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 48bdaa0b-203f-4933-b220-7afdfcda3ce8 · outbound

This paper cites In- stantbooth: Personalized text-to-image generation without test-time finetuning.

T2ISafety: Benchmark for Assessing Fairness, Toxicity, and Privacy in Image Generation In- stantbooth: Personalized text-to-image generation without test-time finetuning

Reference 71

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T17:05:51.574535Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 7b2259c2-b593-4ece-a214-3243b2e460f3 · outbound

This paper cites Divide, evaluate, and re- fine: Evaluating and improving text-to-image alignment with iterative vqa feedback.

T2ISafety: Benchmark for Assessing Fairness, Toxicity, and Privacy in Image Generation Divide, evaluate, and re- fine: Evaluating and improving text-to-image alignment with iterative vqa feedback

Reference 72

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T17:05:51.557680Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 293d69e7-0b08-4e3e-be7d-1c33425d421a · outbound

This paper cites Autoregressive Model Beats Diffusion: Llama for Scalable Image Generation.

T2ISafety: Benchmark for Assessing Fairness, Toxicity, and Privacy in Image Generation Autoregressive Model Beats Diffusion: Llama for Scalable Image Generation

Reference 73

Resolution: unresolved; no resolver link, observed 2026-08-10T17:05:50.866792Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 73542f78-1df1-4101-9219-258e129ab400 · outbound

This paper cites an unresolved cited work.

T2ISafety: Benchmark for Assessing Fairness, Toxicity, and Privacy in Image Generation Unresolved cited work

Reference 74

Resolution: unresolved; raw_fallback, observed 2026-08-10T17:05:52.074381Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation ff79b44e-fa55-4d94-b08b-c554f383c8e7 · outbound

This paper cites midjourney-prompts.

T2ISafety: Benchmark for Assessing Fairness, Toxicity, and Privacy in Image Generation midjourney-prompts

Reference 75

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T17:05:51.527268Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation afea2a76-a4d1-4919-8c15-d09a12ed4015 · outbound

This paper cites Journeydb: A benchmark for generative im- age understanding.

T2ISafety: Benchmark for Assessing Fairness, Toxicity, and Privacy in Image Generation Journeydb: A benchmark for generative im- age understanding

Reference 76

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T17:05:51.512913Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 25be7d72-c13e-4ae2-b6fa-130e01bafab5 · outbound

This paper cites A Comprehensive Study of Multimodal Large Language Models for Image Quality Assessment.

T2ISafety: Benchmark for Assessing Fairness, Toxicity, and Privacy in Image Generation A Comprehensive Study of Multimodal Large Language Models for Image Quality Assessment

Reference 77

Resolution: unresolved; no resolver link, observed 2026-08-10T17:05:50.885111Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7eb55474-f1aa-4dc6-ba96-5ecbc3052464 · outbound

This paper cites Security and privacy on generative data in aigc: A survey.

T2ISafety: Benchmark for Assessing Fairness, Toxicity, and Privacy in Image Generation Security and privacy on generative data in aigc: A survey

Reference 78

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T17:05:51.497539Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 3a932fab-d645-4edb-bf22-58967f98c58e · outbound

This paper cites VidProM: A Million-scale Real Prompt-Gallery Dataset for Text-to-Video Diffusion Models.

T2ISafety: Benchmark for Assessing Fairness, Toxicity, and Privacy in Image Generation VidProM: A Million-scale Real Prompt-Gallery Dataset for Text-to-Video Diffusion Models

Reference 79

Resolution: unresolved; no resolver link, observed 2026-08-10T17:05:50.875779Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e5c6b8f0-3a78-4061-8222-b9a0e7cc96fb · outbound

This paper cites DiffusionDB: A Large-scale Prompt Gallery Dataset for Text-to-Image Generative Models.

T2ISafety: Benchmark for Assessing Fairness, Toxicity, and Privacy in Image Generation DiffusionDB: A Large-scale Prompt Gallery Dataset for Text-to-Image Generative Models

Reference 80

Resolution: unresolved; no resolver link, observed 2026-08-10T17:05:50.880384Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 565df879-fb52-493d-83f2-1485a46bda3d · outbound

This paper cites A Survey on Multimodal Large Language Models.

T2ISafety: Benchmark for Assessing Fairness, Toxicity, and Privacy in Image Generation A Survey on Multimodal Large Language Models

Reference 81

Resolution: unresolved; no resolver link, observed 2026-08-10T17:05:50.903728Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7e32c2f3-baa8-4e3c-86d3-73fa7e703ad5 · outbound

This paper cites VILA-U: a Unified Foundation Model Integrating Visual Understanding and Generation.

T2ISafety: Benchmark for Assessing Fairness, Toxicity, and Privacy in Image Generation VILA-U: a Unified Foundation Model Integrating Visual Understanding and Generation

Reference 82

Resolution: unresolved; no resolver link, observed 2026-08-10T17:05:50.890028Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ef5bacd6-e09f-41fd-8a01-b77c03788f59 · outbound

This paper cites Show-o: One Single Transformer to Unify Multimodal Understanding and Generation.

T2ISafety: Benchmark for Assessing Fairness, Toxicity, and Privacy in Image Generation Show-o: One Single Transformer to Unify Multimodal Understanding and Generation

Reference 83

Resolution: unresolved; no resolver link, observed 2026-08-10T17:05:50.894763Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f3a7d260-aeb8-4d04-9134-1bcf7e3d08a7 · outbound

This paper cites Sneakyprompt: Jailbreaking text-to-image generative models.

T2ISafety: Benchmark for Assessing Fairness, Toxicity, and Privacy in Image Generation Sneakyprompt: Jailbreaking text-to-image generative models

Reference 84

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T17:05:51.482629Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 2a362566-aacb-4540-ba01-b6141c9ea150 · outbound

This paper cites MM-LLMs: Recent Advances in MultiModal Large Language Models.

T2ISafety: Benchmark for Assessing Fairness, Toxicity, and Privacy in Image Generation MM-LLMs: Recent Advances in MultiModal Large Language Models

Reference 86

Resolution: unresolved; no resolver link, observed 2026-08-10T17:05:50.908494Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cbf75cb0-07a1-4c49-ba7e-f7c88ba86ef8 · outbound

This paper cites an unresolved cited work.

T2ISafety: Benchmark for Assessing Fairness, Toxicity, and Privacy in Image Generation Unresolved cited work

Reference 2024

Resolution: unresolved; no resolver link, observed 2026-08-10T17:05:50.522483Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation bc9aae33-9a27-401b-b7c8-be632420679e · inbound

Multimodal LLMs as Customized Reward Models for Text-to-Image Generation cites this paper.

Multimodal LLMs as Customized Reward Models for Text-to-Image Generation T2ISafety: Benchmark for Assessing Fairness, Toxicity, and Privacy in Image Generation

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-06T12:54:35.249132Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 70e990ee-9fdc-4f59-9a6b-2253f0e42339 · inbound

Trade-offs in Image Generation: How Do Different Dimensions Interact? cites this paper.

Trade-offs in Image Generation: How Do Different Dimensions Interact? T2ISafety: Benchmark for Assessing Fairness, Toxicity, and Privacy in Image Generation

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-06T12:08:01.747925Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 24e2e53f-b187-4d69-95b1-ca861aceb3c2 · inbound

Inference Time Debiasing Concepts in Diffusion Models cites this paper.

Inference Time Debiasing Concepts in Diffusion Models T2ISafety: Benchmark for Assessing Fairness, Toxicity, and Privacy in Image Generation

Reference 11

Resolution: metadata mismatch; local_arxiv, observed 2026-08-05T18:47:20.988949Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.