Paper Citation Record · LEDGER

FPAN: Mitigating Replication in Diffusion Models through the Fine-Grained Probabilistic Addition of Noise to Token Embeddings

As of 8 August 2026, this Paper Citation Record lists 36 of 36 outbound references and 0 inbound Pith citation observations for arXiv:2505.21848.

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

pith.paper-citation-record.v1
2505.21848 v1

Coverage vector

measured 36 of 36 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-07T13:26:09.569617Z

measured 36 of 36 standing notices

One-hop event checks from named stored sources.

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

measured 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

36 of 36 outbound references displayed

verified exact3
verified fuzzy23
unresolved10
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 761a0c53-34ef-40e4-a4c7-61a99729d7e7 · outbound

This paper cites GPT-4 Technical Report.

FPAN: Mitigating Replication in Diffusion Models through the Fine-Grained Probabilistic Addition of Noise to Token Embeddings GPT-4 Technical Report

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-07T13:26:04.759240Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e5e64a7d-ff12-43ae-9612-69518edb119f · outbound

This paper cites Extracting training data from diffu- sion models.

FPAN: Mitigating Replication in Diffusion Models through the Fine-Grained Probabilistic Addition of Noise to Token Embeddings Extracting training data from diffu- sion models

Reference 2

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:26:15.016806Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation a9d3123b-d74d-48c3-b23a-20c9e87b3183 · outbound

This paper cites Exploring Local Memorization in Diffusion Models via Bright Ending Attention.

FPAN: Mitigating Replication in Diffusion Models through the Fine-Grained Probabilistic Addition of Noise to Token Embeddings Exploring Local Memorization in Diffusion Models via Bright Ending Attention

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-07T13:26:04.866637Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7264fcba-cdcf-4e2e-bee9-c1bd33a5770c · outbound

This paper cites Towards memorization-free diffusion models.

FPAN: Mitigating Replication in Diffusion Models through the Fine-Grained Probabilistic Addition of Noise to Token Embeddings Towards memorization-free diffusion models

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:26:14.871356Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 3b310a8d-023f-4e9e-b88c-ef9747117450 · outbound

This paper cites ELECTRA: Pre-training Text Encoders as Discriminators Rather Than Generators.

FPAN: Mitigating Replication in Diffusion Models through the Fine-Grained Probabilistic Addition of Noise to Token Embeddings ELECTRA: Pre-training Text Encoders as Discriminators Rather Than Generators

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-07T13:26:04.995050Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 33b8e1f5-36ca-4f65-bb1f-9547eeeb5d48 · outbound

This paper cites Diffusion models beat GANs on image synthesis.

FPAN: Mitigating Replication in Diffusion Models through the Fine-Grained Probabilistic Addition of Noise to Token Embeddings Diffusion models beat GANs on image synthesis

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:26:14.708574Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 6623414f-75c2-4e62-b91d-b6ebadc06015 · outbound

This paper cites On the inherent regulariza- tion effects of noise injection during training.

FPAN: Mitigating Replication in Diffusion Models through the Fine-Grained Probabilistic Addition of Noise to Token Embeddings On the inherent regulariza- tion effects of noise injection during training

Reference 7

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:26:14.514225Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation fbd8452d-0b49-45d6-909c-8cecbc3c7f93 · outbound

This paper cites Generative adversarial networks.

FPAN: Mitigating Replication in Diffusion Models through the Fine-Grained Probabilistic Addition of Noise to Token Embeddings Generative adversarial networks

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-07T13:26:05.175525Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 852b3feb-c1df-4bb7-825a-c03e91374bf1 · outbound

This paper cites On Memorization in Diffusion Models.

FPAN: Mitigating Replication in Diffusion Models through the Fine-Grained Probabilistic Addition of Noise to Token Embeddings On Memorization in Diffusion Models

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-07T13:26:05.238193Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4442f910-edc3-4b23-94f8-0eced1df83fa · outbound

This paper cites Finding NeMo: Localizing neurons responsible for memorization in diffu- sion models.

FPAN: Mitigating Replication in Diffusion Models through the Fine-Grained Probabilistic Addition of Noise to Token Embeddings Finding NeMo: Localizing neurons responsible for memorization in diffu- sion models

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:26:14.286829Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation ac07fae5-7d12-43a9-9c1b-867dd36b8b16 · outbound

This paper cites Denoising dif- fusion probabilistic models.

FPAN: Mitigating Replication in Diffusion Models through the Fine-Grained Probabilistic Addition of Noise to Token Embeddings Denoising dif- fusion probabilistic models

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-07T13:26:05.427660Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 39410939-c8c4-4110-b76c-6b0c56f5c448 · outbound

This paper cites An introduction to variational autoencoders.

FPAN: Mitigating Replication in Diffusion Models through the Fine-Grained Probabilistic Addition of Noise to Token Embeddings An introduction to variational autoencoders

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:26:14.082907Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 08071358-c136-4118-918b-b4b498dd3698 · outbound

This paper cites Learning to Perturb Word Embeddings for Out-of-distribution QA.

FPAN: Mitigating Replication in Diffusion Models through the Fine-Grained Probabilistic Addition of Noise to Token Embeddings Learning to Perturb Word Embeddings for Out-of-distribution QA

Reference 13

Resolution: verified exact; local_arxiv, observed 2026-08-07T13:26:10.565999Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 8c771320-e440-4ef5-9792-1d2dd404a58e · outbound

This paper cites Mitigate replication and copying in diffusion mod- els with generalized caption and dual fusion enhancement.

FPAN: Mitigating Replication in Diffusion Models through the Fine-Grained Probabilistic Addition of Noise to Token Embeddings Mitigate replication and copying in diffusion mod- els with generalized caption and dual fusion enhancement

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:26:13.917759Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 8b84adb6-66e6-4b45-8888-63927fdf6077 · outbound

This paper cites LoyalDiffusion: A Diffusion Model Guarding Against Data Replication.

FPAN: Mitigating Replication in Diffusion Models through the Fine-Grained Probabilistic Addition of Noise to Token Embeddings LoyalDiffusion: A Diffusion Model Guarding Against Data Replication

Reference 15

Resolution: verified exact; local_arxiv, observed 2026-08-07T13:26:10.406749Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 14eaab51-6911-4d9f-a476-ac9d66618601 · outbound

This paper cites Are GANs created equal? A large-scale study.

FPAN: Mitigating Replication in Diffusion Models through the Fine-Grained Probabilistic Addition of Noise to Token Embeddings Are GANs created equal? A large-scale study

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:26:13.788866Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation c9b655f0-a86a-4867-861f-72214a75f697 · outbound

This paper cites Enhancing DreamBooth with LoRA for generating unlimited characters with Stable Dif- fusion.

FPAN: Mitigating Replication in Diffusion Models through the Fine-Grained Probabilistic Addition of Noise to Token Embeddings Enhancing DreamBooth with LoRA for generating unlimited characters with Stable Dif- fusion

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:26:13.557917Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 1c57f15e-6199-42e8-9215-3263304de062 · outbound

This paper cites A self-supervised descriptor for image copy detection.

FPAN: Mitigating Replication in Diffusion Models through the Fine-Grained Probabilistic Addition of Noise to Token Embeddings A self-supervised descriptor for image copy detection

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:26:13.372725Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 4b6deddd-8e59-4ed6-a513-5313eb165eee · outbound

This paper cites Learning transferable visual models from natural language supervi- sion.

FPAN: Mitigating Replication in Diffusion Models through the Fine-Grained Probabilistic Addition of Noise to Token Embeddings Learning transferable visual models from natural language supervi- sion

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:26:13.152408Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation f6d62584-30ba-4731-86a7-fd34bdd03346 · outbound

This paper cites Zero-shot text-to-image generation.

FPAN: Mitigating Replication in Diffusion Models through the Fine-Grained Probabilistic Addition of Noise to Token Embeddings Zero-shot text-to-image generation

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-07T13:26:06.045871Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9fceadd2-fe27-4a32-a02c-9be7d469da71 · outbound

This paper cites Unveiling and mitigating mem- orization in text-to-image diffusion models through cross at- tention.

FPAN: Mitigating Replication in Diffusion Models through the Fine-Grained Probabilistic Addition of Noise to Token Embeddings Unveiling and mitigating mem- orization in text-to-image diffusion models through cross at- tention

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:26:13.045332Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 46db90c4-eb2f-4587-af1f-74ee3a8450ee · outbound

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

FPAN: Mitigating Replication in Diffusion Models through the Fine-Grained Probabilistic Addition of Noise to Token Embeddings High-resolution image synthesis with latent diffusion models

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:26:12.817834Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 5f0d1f3e-4d0b-40d6-b42a-8dcd01d89d78 · outbound

This paper cites U- Net: Convolutional networks for biomedical image segmen- tation.

FPAN: Mitigating Replication in Diffusion Models through the Fine-Grained Probabilistic Addition of Noise to Token Embeddings U- Net: Convolutional networks for biomedical image segmen- tation

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:26:12.627034Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 599dab5a-7a1f-40e2-895e-e7f0b1814d74 · outbound

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

FPAN: Mitigating Replication in Diffusion Models through the Fine-Grained Probabilistic Addition of Noise to Token Embeddings Photorealistic text-to-image diffusion models with deep language understanding

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-07T13:26:06.386324Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 567930b9-1d68-4e7a-9e56-4385b0e1709d · outbound

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

FPAN: Mitigating Replication in Diffusion Models through the Fine-Grained Probabilistic Addition of Noise to Token Embeddings Safe latent diffusion: Mitigating inappro- priate degeneration in diffusion models

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:26:12.410737Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 38404cab-097b-44f5-8e78-f0e0656d0244 · outbound

This paper cites LAION-5B: An open large-scale dataset for train- ing next generation image-text models.

FPAN: Mitigating Replication in Diffusion Models through the Fine-Grained Probabilistic Addition of Noise to Token Embeddings LAION-5B: An open large-scale dataset for train- ing next generation image-text models

Reference 26

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:26:12.155278Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 8cab64d3-a69e-4c86-8b13-269b754d6662 · outbound

This paper cites Diffusion art or digital forgery? Investigating data replication in diffusion models.

FPAN: Mitigating Replication in Diffusion Models through the Fine-Grained Probabilistic Addition of Noise to Token Embeddings Diffusion art or digital forgery? Investigating data replication in diffusion models

Reference 27

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:26:11.909731Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation be1d0a5f-ca93-4a2d-b62f-687893797314 · outbound

This paper cites Understanding and mitigating copying in diffusion models.

FPAN: Mitigating Replication in Diffusion Models through the Fine-Grained Probabilistic Addition of Noise to Token Embeddings Understanding and mitigating copying in diffusion models

Reference 28

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:26:11.746969Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation b409235e-9eb1-460b-829f-e62bcf6b64fe · outbound

This paper cites LLaMA: Open and Efficient Foundation Language Models.

FPAN: Mitigating Replication in Diffusion Models through the Fine-Grained Probabilistic Addition of Noise to Token Embeddings LLaMA: Open and Efficient Foundation Language Models

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-07T13:26:06.891309Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 413470f1-02b7-4ede-a2a7-1093cc5ccf6d · outbound

This paper cites Lexical density and register differentiation.

FPAN: Mitigating Replication in Diffusion Models through the Fine-Grained Probabilistic Addition of Noise to Token Embeddings Lexical density and register differentiation

Reference 30

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:26:11.519522Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation d839a434-63c4-40d9-a0bb-158f40c9ec1e · outbound

This paper cites On the De-duplication of LAION-2B.

FPAN: Mitigating Replication in Diffusion Models through the Fine-Grained Probabilistic Addition of Noise to Token Embeddings On the De-duplication of LAION-2B

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-07T13:26:07.125999Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 92569f82-d648-4a55-831b-58af7b5df925 · outbound

This paper cites De- tecting, explaining, and mitigating memorization in diffusion models.

FPAN: Mitigating Replication in Diffusion Models through the Fine-Grained Probabilistic Addition of Noise to Token Embeddings De- tecting, explaining, and mitigating memorization in diffusion models

Reference 32

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:26:11.281506Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 6911a96d-ba42-4a1a-9cbe-d3469b86625a · outbound

This paper cites A Universal Discriminator for Zero-Shot Generalization.

FPAN: Mitigating Replication in Diffusion Models through the Fine-Grained Probabilistic Addition of Noise to Token Embeddings A Universal Discriminator for Zero-Shot Generalization

Reference 33

Resolution: verified exact; local_arxiv, observed 2026-08-07T13:26:10.169450Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 04aa0093-6d13-4d35-a698-61be745e622f · outbound

This paper cites Infusion: Preventing customized text-to-image diffusion from overfitting.

FPAN: Mitigating Replication in Diffusion Models through the Fine-Grained Probabilistic Addition of Noise to Token Embeddings Infusion: Preventing customized text-to-image diffusion from overfitting

Reference 34

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:26:11.103060Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation ee20f7fb-9666-427a-b8ad-ecd1a241a84a · outbound

This paper cites Forget-Me-Not: Learning to for- get in text-to-image diffusion models.

FPAN: Mitigating Replication in Diffusion Models through the Fine-Grained Probabilistic Addition of Noise to Token Embeddings Forget-Me-Not: Learning to for- get in text-to-image diffusion models

Reference 35

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:26:10.912001Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation d22c370d-605d-4389-be10-44fd4cb9c223 · outbound

This paper cites For the inference process, we generate sam- ples using S = 50 steps, uniformly spacing across the full diffusion process.

FPAN: Mitigating Replication in Diffusion Models through the Fine-Grained Probabilistic Addition of Noise to Token Embeddings For the inference process, we generate sam- ples using S = 50 steps, uniformly spacing across the full diffusion process

Reference 256

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:26:10.768749Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Pith citing papers

No inbound Pith citation observations are available.