SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2410.04555 · 2024

$\texttt{dattri}$: A Library for Efficient Data Attribution

arXiv · PDF · Open in the Atlas

Code that ran

2 of 3 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; 0 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 2 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/2410.04555.json · badge: /api/ran/2410.04555.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
trais-lab/dattri canonical (classifier label)
classifier basis: census
2 ran · 1 no recorded run
FunctionStatusWhere it lives
backtracking_line_search Ran
ran; our contract draft was wrong, not the code
trais-lab/dattri/dattri/algorithm/utils.py
code served (permissive licence) · get_code("ced4270fa2df6476")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned Tensor, ndim 2, dtype family float, shape (3, 4) as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
from torch import Tensor
from torch.autograd import Variable
import torch.nn as nn
import torch.nn.functional as F

torch.manual_seed(0)

# Create small tensors
batch_size = 2
input_dim = 4
output_dim = 3

x = torch.randn(batch_size, input_dim)
y = torch.randn(batch_size, output_dim)

# theta: weight matrix for last layer, shape (output_dim, input_dim)
theta = Variable(torch.randn(output_dim, input_dim), requires_grad=True)

# grad_theta: gradient with respect to theta
grad_theta = torch.randn(output_dim, input_dim)

# loss_func: use BCEWithLogitsLoss which accepts float inputs
loss_func = nn.BCEWithLogitsLoss(reduction='mean')

# val: current loss value (scalar float)
val = 0.5

# lambda_l2: L2 regularization strength
lambda_l2 = 0.01

ARGS = {
    'theta': theta,
    'grad_theta': grad_theta,
    'loss_func': loss_func,
    'x': x,
    'y': y,
    'val': val,
    'lambda_l2': lambda_l2
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Tensor, ndim 2, dtype family float, shape (3, 4) — shape (3, 4) as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
rps_finetune_model Ran
ran; our contract draft was wrong, not the code
trais-lab/dattri/dattri/algorithm/utils.py
code served (permissive licence) · get_code("0761df83ace218bb")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned tuple. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
from torch import Tensor

torch.manual_seed(0)

# x is used with .T (transpose) and passed to matmul
# It should be a 2D tensor representing batch data
# Shape: (batch_size, input_dim)
x = torch.randn(2, 4)

# theta is used with:
# - torch.matmul(theta, x.T) - matrix multiplication
# - torch.squeeze(theta) - squeeze operation
# theta should be a weight matrix that can multiply with x.T
# Shape: (output_dim, input_dim) to be compatible with matmul(theta, x.T)
theta = torch.autograd.Variable(torch.randn(3, 4), requires_grad=True)

ARGS = {
    "x": x,
    "theta": theta,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type tuple — a tuple output has no array shape of its own; none is stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
rps_finetune_theta Not yet run
unverified (harvested, no recorded run)
trais-lab/dattri/dattri/algorithm/utils.py
code served (permissive licence) · get_code("d9a83c435b3ed971")
How it ran

no invocation recorded.

Also present in other papers' code

Of 3 samples lifted from this paper's linked repositories, 3 carry a function identity and 0 do not. Of the 3 distinct functions with an identity, 0 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 0 later) and 3 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.

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 aim to quantify the influence of individual training samples on the prediction of artificial intelligence (AI) models. As training data plays an increasingly crucial role in the modern development of large-scale AI models, data attribution has found broad applications in improving AI performance and safety. However, despite a surge of new data attribution methods being developed recently, there lacks a comprehensive library that facilitates the development, benchmarking, and deployment of different data attribution methods. In this work, we introduce $\texttt{dattri}$, an open-source data attribution library that addresses the above needs. Specifically, $\texttt{dattri}$ highlights three novel design features. Firstly, $\texttt{dattri}$ proposes a unified and easy-to-use API, allowing users to integrate different data attribution methods into their PyTorch-based machine learning pipeline with a few lines of code changed. Secondly, $\texttt{dattri}$ modularizes low-level utility functions that are commonly used in data attribution methods, such as Hessian-vector product, inverse-Hessian-vector product or random projection, making it easier for researchers to develop new data attribution methods. Thirdly, $\texttt{dattri}$ provides a comprehensive benchmark framework with pre-trained models and ground truth annotations for a variety of benchmark settings, including generative AI settings. We have implemented a variety of state-of-the-art efficient data attribution methods that can be applied to large-scale neural network models, and will continuously update the library in the future. Using the developed $\texttt{dattri}$ library, we are able to perform a comprehensive and fair benchmark analysis across a wide range of data attribution methods. The source code of $\texttt{dattri}$ is available at https://github.com/TRAIS-Lab/dattri.

For agents

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

get_harvested_code_for_paper("2410.04555")
get_code_for_paper("2410.04555")
have("2410.04555")

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

curl https://syntology.ai/api/ran/2410.04555.json

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

[![Syntology run record](https://syntology.ai/api/ran/2410.04555.svg)](https://syntology.ai/paper/2410.04555)

Connect an agent — have() is free.