SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2401.09031 · 2024

Data Attribution for Diffusion Models: Timestep-induced Bias in Influence Estimation

arXiv · PDF · Open in the Atlas

Code that ran

9 of 9 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; 3 honoured the contract we drafted, 1 violated it and 0 have no contract verdict; 5 failures of our instrument; 0 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/2401.09031.json · badge: /api/ran/2401.09031.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
txie1/diffusion-retrac canonical (classifier label)
classifier basis: census
9 ran · 0 no recorded run
FunctionStatusWhere it lives
cosine_beta_schedule Ran
ran, honoured the contract we drafted
txie1/diffusion-retrac/scheduler/ddim.py
pointer only (licence: NONE) · get_code("b236cc9fdeeb2655")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, txie1/diffusion-retrac 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.

get_ckpts Ran
ran; our contract draft was wrong, not the code
txie1/diffusion-retrac/diffusion_tracin.py
pointer only (licence: NONE) · get_code("c4e48f83a9b0720f")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, txie1/diffusion-retrac 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.

get_downsample_layer Ran
ran; our contract draft was wrong, not the code
txie1/diffusion-retrac/model/unet.py
pointer only (licence: NONE) · get_code("88d9fe4f428f01fc")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, txie1/diffusion-retrac 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.

get_upsample_layer Ran
ran; our contract draft was wrong, not the code
txie1/diffusion-retrac/model/unet.py
pointer only (licence: NONE) · get_code("379841fe547e7314")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, txie1/diffusion-retrac 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.

l2norm Ran
ran; our contract draft was wrong, not the code
txie1/diffusion-retrac/model/_attention.py
pointer only (licence: NONE); the stored copy get_code serves, from tmlresearchgroup-cas/clipure, is pointer only (licence: NONE) · get_code("3eb58dae620046d3")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, txie1/diffusion-retrac 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.

normalize_to_neg_one_to_one Ran
ran, honoured the contract we drafted
txie1/diffusion-retrac/utils.py
pointer only (licence: NONE); the stored copy get_code serves, from futurexiang/soda, is pointer only (licence: NONE) · get_code("a1229a9f4df127e2")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, txie1/diffusion-retrac 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.

numpy_to_pil Ran
ran, violated the contract we drafted
txie1/diffusion-retrac/utils.py
pointer only (licence: NONE) · get_code("6ab180a2829060f3")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, txie1/diffusion-retrac 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.

trans Ran
ran; our contract draft was wrong, not the code
txie1/diffusion-retrac/influence_function.py
pointer only (licence: NONE) · get_code("243e5ce0a6f6d207")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, txie1/diffusion-retrac 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.

unnormalize_to_zero_to_one Ran
ran, honoured the contract we drafted
txie1/diffusion-retrac/utils.py
pointer only (licence: NONE); the stored copy get_code serves, from futurexiang/soda, is pointer only (licence: NONE) · get_code("97e1bbd232dfe092")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, txie1/diffusion-retrac 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.

Also present in other papers' code

Of 9 samples lifted from this paper's linked repositories, 9 carry a function identity and 0 do not. Of the 9 distinct functions with an identity, 5 are also present in other papers whose code we hold (5 with at least one paper dated earlier, 3 the same month, 4 later) and 4 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
numpy_to_pil 23 other papers
15 dated earlier, 1 the same month, 6 later, 1 same year, order not determinable
2106.14490 (2021-06)
Making Images Real Again: A Comprehensive Survey on Deep Image Composition
2112.10752 (2021-12)
High-Resolution Image Synthesis with Latent Diffusion Models
2209.12330 (2022-09)
Personalizing Text-to-Image Generation via Aesthetic Gradients
and 20 more not named here
normalize_to_neg_one_to_one 18 other papers
7 dated earlier, 1 the same month, 10 later · 8 only as an assembly brick
1611.07004 (2016-11)
Image-to-Image Translation with Conditional Adversarial Networks
2006.11239 (2020-06)
Denoising Diffusion Probabilistic Models
2209.15571 (2022-09)
Building Normalizing Flows with Stochastic Interpolants
and 15 more not named here
unnormalize_to_zero_to_one 18 other papers
6 dated earlier, 1 the same month, 11 later · 9 only as an assembly brick
2006.11239 (2020-06)
Denoising Diffusion Probabilistic Models
2105.05233 (2021-05)
Diffusion Models Beat GANs on Image Synthesis
2209.15571 (2022-09)
Building Normalizing Flows with Stochastic Interpolants
and 15 more not named here
l2norm 16 other papers
11 dated earlier, 5 later · 4 only as an assembly brick
2112.05682 (2021-12)
Self-attention Does Not Need $O(n^2)$ Memory
2202.04200 (2022-02)
MaskGIT: Masked Generative Image Transformer
2203.07852 (2022-03)
Block-Recurrent Transformers
and 13 more not named here
cosine_beta_schedule 1 other paper
1 dated earlier
2105.05233 (2021-05)
Diffusion Models Beat GANs on Image Synthesis

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.

Abstract

Data attribution methods trace model behavior back to its training dataset, offering an effective approach to better understand ''black-box'' neural networks. While prior research has established quantifiable links between model output and training data in diverse settings, interpreting diffusion model outputs in relation to training samples remains underexplored. In particular, diffusion models operate over a sequence of timesteps instead of instantaneous input-output relationships in previous contexts, posing a significant challenge to extend existing frameworks to diffusion models directly. Notably, we present Diffusion-TracIn that incorporates this temporal dynamics and observe that samples' loss gradient norms are highly dependent on timestep. This trend leads to a prominent bias in influence estimation, and is particularly noticeable for samples trained on large-norm-inducing timesteps, causing them to be generally influential. To mitigate this effect, we introduce Diffusion-ReTrac as a re-normalized adaptation that enables the retrieval of training samples more targeted to the test sample of interest, facilitating a localized measurement of influence and considerably more intuitive visualization. We demonstrate the efficacy of our approach through various evaluation metrics and auxiliary tasks, reducing the amount of generally influential samples to $\frac{1}{3}$ of its original quantity.

For agents

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

get_harvested_code_for_paper("2401.09031")
get_code_for_paper("2401.09031")
have("2401.09031")

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

curl https://syntology.ai/api/ran/2401.09031.json

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

[![Syntology run record](https://syntology.ai/api/ran/2401.09031.svg)](https://syntology.ai/paper/2401.09031)

Connect an agent — have() is free.