SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1905.07720 · 2019

Butterfly: One-step Approach towards Wildly Unsupervised Domain Adaptation

arXiv · PDF · Open in the Atlas

Code that ran

1 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 1 has no contract verdict; 0 failures of our instrument; 2 no recorded run), measured 2026-11-21; 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/1905.07720.json · badge: /api/ran/1905.07720.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
fengliu90/Butterfly community (classifier label)
classifier basis not recorded on the link
1 ran · 2 no recorded run
FunctionStatusWhere it lives
return_svhn Ran
ran on a synthesized input
fengliu90/Butterfly/utils.py
code served (permissive licence) · get_code("160ca18353e10810")
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 numpy as np
from scipy.io import savemat
import tempfile
import os

# Create temporary directory for test mat files
tmpdir = tempfile.mkdtemp()

# Create mock SVHN training data
# SVHN format: X should be (32, 32, 3, num_samples) before transpose
num_train_samples = 2
num_test_samples = 2

# Training data
X_train = np.random.randint(0, 256, (32, 32, 3, num_train_samples), dtype=np.uint8)
y_train = np.array([[1], [10]], dtype=np.int64)  # Include a 10 to test the conversion
train_data = {'X': X_train, 'y': y_train}

# Test data
X_test = np.random.randint(0, 256, (32, 32, 3, num_test_samples), dtype=np.uint8)
y_test = np.array([[3], [5]], dtype=np.int64)
test_data = {'X': X_test, 'y': y_test}

# Save as mat files
path_train = os.path.join(tmpdir, 'train.mat')
path_test = os.path.join(tmpdir, 'test.mat')

savemat(path_train, train_data)
savemat(path_test, test_data)

ARGS = {
    'path_train': path_train,
    'path_test': path_test
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, scipy — 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
return_Amazon Not yet run
unverified (harvested, no recorded run)
fengliu90/Butterfly/utils.py
code served (permissive licence) · get_code("f9f0ffb2a5381fbe")
How it ran

no invocation recorded.

return_Obj_data Not yet run
unverified (harvested, no recorded run)
fengliu90/Butterfly/utils.py
code served (permissive licence) · get_code("e31d3391e5613f52")
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 2026-11-21.

Repositories linked to this paper

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

Abstract

In unsupervised domain adaptation (UDA), classifiers for the target domain (TD) are trained with clean labeled data from the source domain (SD) and unlabeled data from TD. However, in the wild, it is difficult to acquire a large amount of perfectly clean labeled data in SD given limited budget. Hence, we consider a new, more realistic and more challenging problem setting, where classifiers have to be trained with noisy labeled data from SD and unlabeled data from TD -- we name it wildly UDA (WUDA). We show that WUDA ruins all UDA methods if taking no care of label noise in SD, and to this end, we propose a Butterfly framework, a powerful and efficient solution to WUDA. Butterfly maintains four deep networks simultaneously, where two take care of all adaptations (i.e., noisy-to-clean, labeled-to-unlabeled, and SD-to-TD-distributional) and then the other two can focus on classification in TD. As a consequence, Butterfly possesses all the conceptually necessary components for solving WUDA. Experiments demonstrate that, under WUDA, Butterfly significantly outperforms existing baseline methods.

For agents

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

get_harvested_code_for_paper("1905.07720")
get_code_for_paper("1905.07720")
have("1905.07720")

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

curl https://syntology.ai/api/ran/1905.07720.json

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

[![Syntology run record](https://syntology.ai/api/ran/1905.07720.svg)](https://syntology.ai/paper/1905.07720)

Connect an agent — have() is free.