SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2410.22149 · ICML · 2024

Capacity Control is an Effective Memorization Mitigation Mechanism in Text-Conditional Diffusion Models

Timothy Hospedales, Sotirios Tsaftaris, Ondrej Bohdal, Pedro Sanchez, Raman Dutt

arXiv · PDF · Open in the Atlas

Code that ran

9 of 10 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (0 of them constructed an object rather than computing a result; 2 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 7 failures of our instrument; 1 no recorded run), measured 2026-11-22; repository links from the Papers with Code archive attributed under CC BY-SA, no affiliation; bodies inline only under a permissive licence as GitHub detects it. Not a reproduction of the paper's results.

"Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results. This record, dated, as JSON: /api/ran/2410.22149.json · badge: /api/ran/2410.22149.svg

Each repository's role is a label: a classifier's output recorded on the link, or, where no role is recorded, what the Papers with Code archive marked. The line under it names its basis. Neither says who wrote the code.

RepositoryRoleRan
raman1121/diffusion_memorization_hpo canonical (classifier label)
classifier basis: census
9 ran · 1 no recorded run
FunctionStatusWhere it lives
construct_graph Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
raman1121/diffusion_memorization_hpo/extraction_attack.py
pointer only (licence: NONE) · get_code("80b0901668ac3b4b")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, raman1121/diffusion_memorization_hpo when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

contrastive_loss Ran
ran; our contract draft was wrong, not the code
raman1121/diffusion_memorization_hpo/difffit/modeling_clip.py
pointer only (licence: NONE); the stored copy get_code serves, from microsoft/xpretrain, is pointer only (licence: NOASSERTION) · get_code("4675779aec92d6c0")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, raman1121/diffusion_memorization_hpo when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

find_cliques Ran
ran; our contract draft was wrong, not the code
raman1121/diffusion_memorization_hpo/extraction_attack.py
pointer only (licence: NONE) · get_code("02589606db2535b0")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, raman1121/diffusion_memorization_hpo when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

insert_rand_word Ran
ran; our contract draft was wrong, not the code
raman1121/diffusion_memorization_hpo/imagenette_dataset.py
pointer only (licence: NONE) · get_code("64daf97f4f932ef7")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, raman1121/diffusion_memorization_hpo when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

prompt_augmentation Ran
ran; our contract draft was wrong, not the code
raman1121/diffusion_memorization_hpo/imagenette_dataset.py
pointer only (licence: NONE) · get_code("35c1d6e65f13ee7c")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, raman1121/diffusion_memorization_hpo when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

return_blockwise_param_sum Ran
ran; our contract draft was wrong, not the code
raman1121/diffusion_memorization_hpo/adaptors.py
pointer only (licence: NONE) · get_code("b4aa69078465b08e")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, raman1121/diffusion_memorization_hpo when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

return_norm_param_sum Ran
ran, honoured the contract we drafted
raman1121/diffusion_memorization_hpo/adaptors.py
pointer only (licence: NONE) · get_code("e5ef16b9b63da748")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, raman1121/diffusion_memorization_hpo when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

return_param_sum Ran
ran, honoured the contract we drafted
raman1121/diffusion_memorization_hpo/adaptors.py
pointer only (licence: NONE) · get_code("5b81be558f23d729")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, raman1121/diffusion_memorization_hpo when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

similarity Ran
ran; our contract draft was wrong, not the code
raman1121/diffusion_memorization_hpo/extraction_attack.py
pointer only (licence: NONE) · get_code("c13432a556516ef9")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, raman1121/diffusion_memorization_hpo when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

clip_loss Not yet run
unverified (harvested, no recorded run)
raman1121/diffusion_memorization_hpo/difffit/modeling_clip.py
pointer only (licence: NONE); the stored copy get_code serves, from PeterGriffinJin/InstructG2I, is pointer only (licence: NONE) · get_code("f2ca34eca05d40cd")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, raman1121/diffusion_memorization_hpo when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

Also present in other papers' code

Of 10 samples lifted from this paper's linked repositories, 10 carry a function identity and 0 do not. Of the 10 distinct functions with an identity, 2 are also present in other papers whose code we hold (2 with at least one paper dated earlier, 2 the same month, 2 later) and 8 are only here among the 52,977 papers whose code Syntology holds (as of 2026-09-26).

Only here means: among the 52,977 papers whose code Syntology holds (51,887 with lifted samples, 1,090 through their assemblies only), as of 2026-09-26, no other paper's lifted samples or current assembly bricks contain an identical function body after normalisation.

FunctionAlso present inEarliest-datedOthers named
contrastive_loss 27 other papers
17 dated earlier, 2 the same month, 7 later, 1 same year, order not determinable · 3 only as an assembly brick
2206.00621 (2022-06)
Cross-View Language Modeling: Towards Unified Cross-Lingual Cross-Modal Pre-training
2209.06430 (2022-09)
CLIP-ViP: Adapting Pre-trained Image-Text Model to Video-Language Alignment
2210.00312 (2022-10)
Multimodal Analogical Reasoning over Knowledge Graphs
and 24 more not named here
clip_loss 16 other papers
7 dated earlier, 2 the same month, 6 later, 1 same year, order not determinable · 1 only as an assembly brick
2305.13050 (2023-05)
AudioToken: Adaptation of Text-Conditioned Diffusion Models for Audio-to-Image Generation
2306.02583 (2023-06)
Stable Diffusion is Unstable
2309.16429 (2023-09)
Diverse and Aligned Audio-to-Video Generation via Text-to-Video Model Adaptation
and 13 more not named here

Presence, not direction: an identical function body in two papers' repositories does not say who wrote it, which came from which, or that either paper's method rests on it. Matching is exact after normalisation, so a renamed or edited function is not matched. Dates are when papers appeared, not when code was written. Only .py files the harvester lifted are covered; notebooks are not read. A new-style arXiv id YYMM.NNNN dates a paper to the month 20YY-MM; otherwise Paper.year dates it to the year; otherwise it is undated. Dates are when the paper appeared, not when the code was written. Read 2026-11-22.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2410.22149")
get_code_for_paper("2410.22149")
have("2410.22149")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2410.22149.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2410.22149.svg)](https://syntology.ai/paper/2410.22149)

Connect an agent — have() is free.