Paper Citation Record · LEDGER

SuMa: A Subspace Mapping Approach for Robust and Effective Concept Erasure in Text-to-Image Diffusion Models

As of 16 August 2026, this Paper Citation Record lists 41 of 41 outbound references and 0 inbound Pith citation observations for arXiv:2509.05625.

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

pith.paper-citation-record.v1
2509.05625 v1

Coverage vector

measured 41 of 41 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-15T16:26:06.124269Z

measured 41 of 41 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-15T06:32:42.880941+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

41 of 41 outbound references displayed

verified exact0
verified fuzzy21
unresolved19
parse uncertain0
malformed identifier1
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 4733efbb-e247-4b4a-99d9-ff41a4b63f37 · outbound

This paper cites An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale.

SuMa: A Subspace Mapping Approach for Robust and Effective Concept Erasure in Text-to-Image Diffusion Models An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-15T16:26:05.940503Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e2e6f983-c068-415c-8c9e-62127955d6d5 · outbound

This paper cites Hiding and Recovering Knowledge in Text-to-Image Diffusion Models via Learnable Prompts.

SuMa: A Subspace Mapping Approach for Robust and Effective Concept Erasure in Text-to-Image Diffusion Models Hiding and Recovering Knowledge in Text-to-Image Diffusion Models via Learnable Prompts

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-15T16:26:05.945956Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3e21fda7-dd12-4148-ac58-28f36cd9c7a3 · outbound

This paper cites Erasing Undesirable Concepts in Diffusion Models with Adversarial Preservation.

SuMa: A Subspace Mapping Approach for Robust and Effective Concept Erasure in Text-to-Image Diffusion Models Erasing Undesirable Concepts in Diffusion Models with Adversarial Preservation

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-15T16:26:05.950937Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b35ba0b1-ab3f-4dac-a896-575be86d7a7a · outbound

This paper cites Muse: Text- to-image generation via masked generative transformers.

SuMa: A Subspace Mapping Approach for Robust and Effective Concept Erasure in Text-to-Image Diffusion Models Muse: Text- to-image generation via masked generative transformers

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T16:26:06.836018Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 08713992-bc37-46dd-8b63-369716a8a424 · outbound

This paper cites Prompting4debugging: Red- teaming text-to-image diffusion models by finding problem- atic prompts.arXiv preprint arXiv:2309.06135, 2023.

SuMa: A Subspace Mapping Approach for Robust and Effective Concept Erasure in Text-to-Image Diffusion Models Prompting4debugging: Red- teaming text-to-image diffusion models by finding problem- atic prompts.arXiv preprint arXiv:2309.06135, 2023

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-15T16:26:05.960664Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4e8ce8f6-6ee2-4790-a2ca-5c33b9c6b7ac · outbound

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

SuMa: A Subspace Mapping Approach for Robust and Effective Concept Erasure in Text-to-Image Diffusion Models An Image is Worth One Word: Personalizing Text-to-Image Generation using Textual Inversion

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-15T16:26:05.965471Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 81b2b2c9-33e7-4c76-9648-8a74bcb7c613 · outbound

This paper cites Erasing concepts from diffusion models.

SuMa: A Subspace Mapping Approach for Robust and Effective Concept Erasure in Text-to-Image Diffusion Models Erasing concepts from diffusion models

Reference 7

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T16:26:06.819674Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation acfcf7bd-b656-40e4-8035-b6a2d9a9c0e6 · outbound

This paper cites Unified concept editing in diffusion models.

SuMa: A Subspace Mapping Approach for Robust and Effective Concept Erasure in Text-to-Image Diffusion Models Unified concept editing in diffusion models

Reference 8

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T16:26:06.803965Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 1d8ae3c1-5087-43ec-b099-29cde6b1e297 · outbound

This paper cites Giphy celebrity detector, 2022.

SuMa: A Subspace Mapping Approach for Robust and Effective Concept Erasure in Text-to-Image Diffusion Models Giphy celebrity detector, 2022

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T16:26:06.789102Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 78954cb2-798b-4bc8-8465-0c4e8c16ac49 · outbound

This paper cites Deep residual learning for image recognition.

SuMa: A Subspace Mapping Approach for Robust and Effective Concept Erasure in Text-to-Image Diffusion Models Deep residual learning for image recognition

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-15T16:26:05.983776Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4666ea68-b500-4e14-a615-119797f0de79 · outbound

This paper cites Classifier-Free Diffusion Guidance.

SuMa: A Subspace Mapping Approach for Robust and Effective Concept Erasure in Text-to-Image Diffusion Models Classifier-Free Diffusion Guidance

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-15T16:26:05.988127Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5e867ac6-44e5-4a3d-b342-3e8cebe77ace · outbound

This paper cites Fastai: a layered api for deep learning.Information, 11(2):108, 2020.

SuMa: A Subspace Mapping Approach for Robust and Effective Concept Erasure in Text-to-Image Diffusion Models Fastai: a layered api for deep learning.Information, 11(2):108, 2020

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T16:26:06.764193Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 4dba8ddf-155f-40d8-ae1e-997df20a74d2 · outbound

This paper cites LoRA: Low-Rank Adaptation of Large Language Models.

SuMa: A Subspace Mapping Approach for Robust and Effective Concept Erasure in Text-to-Image Diffusion Models LoRA: Low-Rank Adaptation of Large Language Models

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-15T16:26:05.997113Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b7fdc5b7-1e4d-4f1c-97c1-8a10f4ee3d2d · outbound

This paper cites Ai art and its impact on artists.

SuMa: A Subspace Mapping Approach for Robust and Effective Concept Erasure in Text-to-Image Diffusion Models Ai art and its impact on artists

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T16:26:06.749152Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 7e9079db-ebc8-4a7f-8a60-857bfcc83634 · outbound

This paper cites R.A.C.E.: Robust Adversarial Concept Erasure for Secure Text-to-Image Diffusion Model.

SuMa: A Subspace Mapping Approach for Robust and Effective Concept Erasure in Text-to-Image Diffusion Models R.A.C.E.: Robust Adversarial Concept Erasure for Secure Text-to-Image Diffusion Model

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-15T16:26:06.005956Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e5bd2bbc-f138-48c4-9205-e10147e0391a · outbound

This paper cites Ablating con- cepts in text-to-image diffusion models.

SuMa: A Subspace Mapping Approach for Robust and Effective Concept Erasure in Text-to-Image Diffusion Models Ablating con- cepts in text-to-image diffusion models

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T16:26:06.734907Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 2587ba98-069d-4d29-aeae-b2729027e2f8 · outbound

This paper cites Visual instruction tuning.Advances in neural information processing systems, 36, 2024.

SuMa: A Subspace Mapping Approach for Robust and Effective Concept Erasure in Text-to-Image Diffusion Models Visual instruction tuning.Advances in neural information processing systems, 36, 2024

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-15T16:26:06.014852Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c64ca8be-8009-4ec3-ada0-00edcb8352d4 · outbound

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

SuMa: A Subspace Mapping Approach for Robust and Effective Concept Erasure in Text-to-Image Diffusion Models Mace: Mass concept erasure in diffu- sion models

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T16:26:06.709152Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 773ef732-9b10-491d-963c-d8e9a5848ff3 · outbound

This paper cites One-dimensional adapter to rule them all: Concepts diffusion models and erasing applications.

SuMa: A Subspace Mapping Approach for Robust and Effective Concept Erasure in Text-to-Image Diffusion Models One-dimensional adapter to rule them all: Concepts diffusion models and erasing applications

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T16:26:06.693952Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation d32b1735-c15a-4e3f-8a74-6b17a27a0e00 · outbound

This paper cites Glide: Towards photorealis- tic image generation and editing with text-guided diffusion models.

SuMa: A Subspace Mapping Approach for Robust and Effective Concept Erasure in Text-to-Image Diffusion Models Glide: Towards photorealis- tic image generation and editing with text-guided diffusion models

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T16:26:06.676408Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation acad4af8-4b48-41b7-810f-920ffc4f4d76 · outbound

This paper cites Direct unlearning optimization for robust and safe text- to-image models.

SuMa: A Subspace Mapping Approach for Robust and Effective Concept Erasure in Text-to-Image Diffusion Models Direct unlearning optimization for robust and safe text- to-image models

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T16:26:06.660497Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation c032e771-57c8-4082-9890-c7a47ef264e4 · outbound

This paper cites Circumventing concept erasure meth- ods for text-to-image generative models.

SuMa: A Subspace Mapping Approach for Robust and Effective Concept Erasure in Text-to-Image Diffusion Models Circumventing concept erasure meth- ods for text-to-image generative models

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T16:26:06.645225Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 10cd81d0-38c6-4029-b7cf-a25e613e0731 · outbound

This paper cites Hierarchical Text-Conditional Image Generation with CLIP Latents.

SuMa: A Subspace Mapping Approach for Robust and Effective Concept Erasure in Text-to-Image Diffusion Models Hierarchical Text-Conditional Image Generation with CLIP Latents

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-15T16:26:06.043788Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dc73fee5-9bd5-40a3-8447-b19bf76da911 · outbound

This paper cites Stable diffusion v1-4 model card., 2022.

SuMa: A Subspace Mapping Approach for Robust and Effective Concept Erasure in Text-to-Image Diffusion Models Stable diffusion v1-4 model card., 2022

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T16:26:06.627436Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation ca6f2a9d-334a-48ca-a4eb-f271c7b4e370 · outbound

This paper cites Stable diffusion 2.0 release., 2022.

SuMa: A Subspace Mapping Approach for Robust and Effective Concept Erasure in Text-to-Image Diffusion Models Stable diffusion 2.0 release., 2022

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T16:26:06.610966Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation ad297d7c-9244-4919-b93d-898c952b19f6 · outbound

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

SuMa: A Subspace Mapping Approach for Robust and Effective Concept Erasure in Text-to-Image Diffusion Models High-resolution image synthesis with latent diffusion models

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-15T16:26:06.057162Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 22ddbad4-6d61-40b4-9255-daf1a58b9466 · outbound

This paper cites Imagenet large scale visual recognition challenge.International journal of computer vision, 115:211–252, 2015.

SuMa: A Subspace Mapping Approach for Robust and Effective Concept Erasure in Text-to-Image Diffusion Models Imagenet large scale visual recognition challenge.International journal of computer vision, 115:211–252, 2015

Reference 27

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T16:26:06.583957Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 0c4284ed-48f3-48af-bc1f-a3734757d12c · outbound

This paper cites Photorealistic text-to-image diffusion models with deep language understanding.Advances in neural information processing systems, 35:36479–36494, 2022.

SuMa: A Subspace Mapping Approach for Robust and Effective Concept Erasure in Text-to-Image Diffusion Models Photorealistic text-to-image diffusion models with deep language understanding.Advances in neural information processing systems, 35:36479–36494, 2022

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-15T16:26:06.066130Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 87bf4fb9-a535-4d42-8bd6-29f5fdb1b075 · outbound

This paper cites Large-scale Classification of Fine-Art Paintings: Learning The Right Metric on The Right Feature.

SuMa: A Subspace Mapping Approach for Robust and Effective Concept Erasure in Text-to-Image Diffusion Models Large-scale Classification of Fine-Art Paintings: Learning The Right Metric on The Right Feature

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-15T16:26:06.070482Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2bcbbf3e-52c6-4653-ad69-a454fda53306 · outbound

This paper cites Laion-5b: An open large-scale dataset for training next generation image-text models.Advances in Neural In- formation Processing Systems, 35:25278–25294, 2022.

SuMa: A Subspace Mapping Approach for Robust and Effective Concept Erasure in Text-to-Image Diffusion Models Laion-5b: An open large-scale dataset for training next generation image-text models.Advances in Neural In- formation Processing Systems, 35:25278–25294, 2022

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-15T16:26:06.075056Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5dfb621d-f3df-43f1-bdd6-ef5f797c7ecd · outbound

This paper cites Glaze: Protecting artists from style mimicry by{Text-to-Image}models.

SuMa: A Subspace Mapping Approach for Robust and Effective Concept Erasure in Text-to-Image Diffusion Models Glaze: Protecting artists from style mimicry by{Text-to-Image}models

Reference 31

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T16:26:06.549769Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 82caec22-b058-4031-ace6-aa22cbb26701 · outbound

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

SuMa: A Subspace Mapping Approach for Robust and Effective Concept Erasure in Text-to-Image Diffusion Models Diffusion art or digital forgery? investigating data replication in diffusion models

Reference 32

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T16:26:06.532290Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation dc49792c-a6f1-435c-bc39-161b5cb543e7 · outbound

This paper cites Stereo: A two- stage framework for adversarially robust concept erasing from text-to-image diffusion models.

SuMa: A Subspace Mapping Approach for Robust and Effective Concept Erasure in Text-to-Image Diffusion Models Stereo: A two- stage framework for adversarially robust concept erasing from text-to-image diffusion models

Reference 33

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T16:26:06.515734Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 27f99d8e-7235-406e-9e7e-b6a4975f20e1 · outbound

This paper cites Celebrity-1000 datasets, 2022.

SuMa: A Subspace Mapping Approach for Robust and Effective Concept Erasure in Text-to-Image Diffusion Models Celebrity-1000 datasets, 2022

Reference 34

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T16:26:06.500142Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation b544ddd6-5959-46ba-80b1-620da3defb80 · outbound

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

SuMa: A Subspace Mapping Approach for Robust and Effective Concept Erasure in Text-to-Image Diffusion Models Ring-A-Bell! How Reliable are Concept Removal Methods for Diffusion Models?

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-15T16:26:06.096383Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bbf5bfae-06fb-4ac5-99bd-c66cf5a43050 · outbound

This paper cites Diffusion model align- ment using direct preference optimization.

SuMa: A Subspace Mapping Approach for Robust and Effective Concept Erasure in Text-to-Image Diffusion Models Diffusion model align- ment using direct preference optimization

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-15T16:26:06.101269Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 55fdb879-2945-47d4-a05a-e7d4efbe037c · outbound

This paper cites Scaling autoregressive models for content-rich text-to-image generation.Transac- tions on Machine Learning Research, 2021.

SuMa: A Subspace Mapping Approach for Robust and Effective Concept Erasure in Text-to-Image Diffusion Models Scaling autoregressive models for content-rich text-to-image generation.Transac- tions on Machine Learning Research, 2021

Reference 37

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T16:26:06.473840Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 1e860992-38d1-4fc2-bcfb-448cdae924b9 · outbound

This paper cites Defensive Unlearning with Adversarial Training for Robust Concept Erasure in Diffusion Models.

SuMa: A Subspace Mapping Approach for Robust and Effective Concept Erasure in Text-to-Image Diffusion Models Defensive Unlearning with Adversarial Training for Robust Concept Erasure in Diffusion Models

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-15T16:26:06.109916Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 231d1276-23b3-415a-b1c5-251825f89266 · outbound

This paper cites naked” concept to a “dressed in.

SuMa: A Subspace Mapping Approach for Robust and Effective Concept Erasure in Text-to-Image Diffusion Models naked” concept to a “dressed in

Reference 39

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T16:26:06.457132Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation b3c3f719-b2a0-4b72-b8ee-f05d3bf0d4b3 · outbound

This paper cites an unresolved cited work.

SuMa: A Subspace Mapping Approach for Robust and Effective Concept Erasure in Text-to-Image Diffusion Models Unresolved cited work

Reference 40

Resolution: unresolved; raw_fallback, observed 2026-08-15T16:26:06.439275Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 90476cef-4e5a-44d4-bf11-3478926d9e7d · outbound

This paper cites So, in conclusion, our work could be combined with DUO to eliminate all kinds of concepts and advance the development of a safe text-to-image model.

SuMa: A Subspace Mapping Approach for Robust and Effective Concept Erasure in Text-to-Image Diffusion Models So, in conclusion, our work could be combined with DUO to eliminate all kinds of concepts and advance the development of a safe text-to-image model

Reference 41

Resolution: malformed identifier; raw_fallback, observed 2026-08-15T16:26:06.420323Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Pith citing papers

No inbound Pith citation observations are available.