Paper Citation Record · LEDGER

You Don't Need All That Attention: Surgical Memorization Mitigation in Text-to-Image Diffusion Models

As of 7 August 2026, this Paper Citation Record lists 20 of 20 outbound references and 0 inbound Pith citation observations for arXiv:2603.00133.

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

pith.paper-citation-record.v1
2603.00133 v2

Coverage vector

measured 20 of 20 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-02T21:27:20.733982Z

measured 20 of 20 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-07T06:34:17.273281+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

20 of 20 outbound references displayed

verified exact0
verified fuzzy0
unresolved18
parse uncertain0
malformed identifier2
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation a7e02d56-52e3-45fb-a5e4-80d4342c1c1c · outbound

This paper cites Data Unlearning in Diffusion Models.

You Don't Need All That Attention: Surgical Memorization Mitigation in Text-to-Image Diffusion Models Data Unlearning in Diffusion Models

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-02T21:27:18.851174Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f90c13c3-d537-4666-9722-daf8fc4876a5 · outbound

This paper cites Robustness of CA Attenuation on Non-Memorized Prompts An important practical question is how memorization miti- gation affects prompts that are not memorized by the model.

You Don't Need All That Attention: Surgical Memorization Mitigation in Text-to-Image Diffusion Models Robustness of CA Attenuation on Non-Memorized Prompts An important practical question is how memorization miti- gation affects prompts that are not memorized by the model

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-02T21:27:20.050768Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 106922a2-0278-4806-8e2e-c5b4ccc8824c · outbound

This paper cites SAeUron: Interpretable Concept Unlearning in Diffusion Models with Sparse Autoencoders.

You Don't Need All That Attention: Surgical Memorization Mitigation in Text-to-Image Diffusion Models SAeUron: Interpretable Concept Unlearning in Diffusion Models with Sparse Autoencoders

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-02T21:27:18.974138Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 07a2b011-454a-425c-a4a5-be70884b042f · outbound

This paper cites Direct Unlearning Optimization for Robust and Safe Text-to-Image Models.

You Don't Need All That Attention: Surgical Memorization Mitigation in Text-to-Image Diffusion Models Direct Unlearning Optimization for Robust and Safe Text-to-Image Models

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-02T21:27:19.395757Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ef58b18d-71ef-4345-b99e-6fa37d8184dd · outbound

This paper cites Model Integrity when Unlearning with T2I Diffusion Models.

You Don't Need All That Attention: Surgical Memorization Mitigation in Text-to-Image Diffusion Models Model Integrity when Unlearning with T2I Diffusion Models

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-02T21:27:19.506756Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 494c81fd-c50d-43fd-9134-830013ed6c0b · outbound

This paper cites Unlearning via Sparse Representations.

You Don't Need All That Attention: Surgical Memorization Mitigation in Text-to-Image Diffusion Models Unlearning via Sparse Representations

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-02T21:27:19.621810Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f3dbb0e6-1852-4114-8a3b-9608f8482720 · outbound

This paper cites A Reproducible Extraction of Training Images from Diffusion Models.

You Don't Need All That Attention: Surgical Memorization Mitigation in Text-to-Image Diffusion Models A Reproducible Extraction of Training Images from Diffusion Models

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-02T21:27:19.758788Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3c49eee2-8177-4cd3-87e0-1513134194d7 · outbound

This paper cites UnlearnCanvas: Stylized Image Dataset for Enhanced Machine Unlearning Evaluation in Diffusion Models.

You Don't Need All That Attention: Surgical Memorization Mitigation in Text-to-Image Diffusion Models UnlearnCanvas: Stylized Image Dataset for Enhanced Machine Unlearning Evaluation in Diffusion Models

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-02T21:27:19.870621Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3bd906e3-33c7-4e02-824f-6bf7850b0c69 · outbound

This paper cites Appendix Contents A.1 Limitations.

You Don't Need All That Attention: Surgical Memorization Mitigation in Text-to-Image Diffusion Models Appendix Contents A.1 Limitations

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-02T21:27:19.974522Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b772f064-149e-4149-b32f-0a3336a88e55 · outbound

This paper cites positive targets.

You Don't Need All That Attention: Surgical Memorization Mitigation in Text-to-Image Diffusion Models positive targets

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-02T21:27:20.131437Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c63a7814-d631-4ae7-8af9-6add2c7c12e3 · outbound

This paper cites no mitiga- tion.

You Don't Need All That Attention: Surgical Memorization Mitigation in Text-to-Image Diffusion Models no mitiga- tion

Reference 16

Resolution: malformed identifier; no resolver link, observed 2026-08-02T21:27:20.218962Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f204250f-1482-48bd-95ad-3c5ea876195d · outbound

This paper cites Specifically, we construct SSCD-CLIP and SSCD-FID Pareto frontiers for each model version and memorization type setting.

You Don't Need All That Attention: Surgical Memorization Mitigation in Text-to-Image Diffusion Models Specifically, we construct SSCD-CLIP and SSCD-FID Pareto frontiers for each model version and memorization type setting

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-02T21:27:20.303773Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4eb0b44f-aa31-4366-8c44-04cf6aaf347a · outbound

This paper cites The advantage is particularly notable for the SSCD-CLIP trade-off, where both CA at- tenuation and CA-in-GUARD consistently dominate other methods.

You Don't Need All That Attention: Surgical Memorization Mitigation in Text-to-Image Diffusion Models The advantage is particularly notable for the SSCD-CLIP trade-off, where both CA at- tenuation and CA-in-GUARD consistently dominate other methods

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-02T21:27:20.488421Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 602ea8e4-1172-4021-b392-f4a2d4e77927 · outbound

This paper cites Lower scores indicate weaker similarity to the training set and therefore less memorization.

You Don't Need All That Attention: Surgical Memorization Mitigation in Text-to-Image Diffusion Models Lower scores indicate weaker similarity to the training set and therefore less memorization

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-02T21:27:20.578414Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fa51f47f-365b-4a58-b61c-682541070eb9 · outbound

This paper cites an unresolved cited work.

You Don't Need All That Attention: Surgical Memorization Mitigation in Text-to-Image Diffusion Models Unresolved cited work

Reference 20

Resolution: malformed identifier; no resolver link, observed 2026-08-02T21:27:20.733982Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 535f61ff-3636-46a6-8f3d-32274d53a160 · outbound

This paper cites Unlearning or Obfuscating? Jogging the Memory of Unlearned LLMs via Benign Relearning.

You Don't Need All That Attention: Surgical Memorization Mitigation in Text-to-Image Diffusion Models Unlearning or Obfuscating? Jogging the Memory of Unlearned LLMs via Benign Relearning

Reference 2017

Resolution: unresolved; no resolver link, observed 2026-08-02T21:27:19.216947Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ff3d4cac-bd9e-427e-8c3d-e38fac1ca59d · outbound

This paper cites Adjusting initial noise to mitigate memorization in text-to-image dif- fusion models.arXiv preprint arXiv:2510.08625,.

You Don't Need All That Attention: Surgical Memorization Mitigation in Text-to-Image Diffusion Models Adjusting initial noise to mitigate memorization in text-to-image dif- fusion models.arXiv preprint arXiv:2510.08625,

Reference 2021

Resolution: unresolved; no resolver link, observed 2026-08-02T21:27:19.153990Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d560bdf5-77c4-4315-ba8b-052c1424b66a · outbound

This paper cites An Adversarial Perspective on Machine Unlearning for AI Safety.

You Don't Need All That Attention: Surgical Memorization Mitigation in Text-to-Image Diffusion Models An Adversarial Perspective on Machine Unlearning for AI Safety

Reference 2023

Resolution: unresolved; no resolver link, observed 2026-08-02T21:27:19.292306Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0bca2805-20b0-4452-be2a-5ccf3e406c85 · outbound

This paper cites SalUn: Empowering Machine Unlearning via Gradient-based Weight Saliency in Both Image Classification and Generation.

You Don't Need All That Attention: Surgical Memorization Mitigation in Text-to-Image Diffusion Models SalUn: Empowering Machine Unlearning via Gradient-based Weight Saliency in Both Image Classification and Generation

Reference 2024

Resolution: unresolved; no resolver link, observed 2026-08-02T21:27:19.083449Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3edc99b9-0624-40ed-8ed2-100b1713175d · outbound

This paper cites Score Forgetting Distillation: A Swift, Data-Free Method for Machine Unlearning in Diffusion Models.

You Don't Need All That Attention: Surgical Memorization Mitigation in Text-to-Image Diffusion Models Score Forgetting Distillation: A Swift, Data-Free Method for Machine Unlearning in Diffusion Models

Reference 2025

Resolution: unresolved; no resolver link, observed 2026-08-02T21:27:18.901155Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

No inbound Pith citation observations are available.