SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2105.04051 · 2021

Aggregating From Multiple Target-Shifted Sources

arXiv · PDF · Open in the Atlas

Code that ran

7 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; 0 honoured the contract we drafted, 0 violated it and 7 have no contract verdict; 0 failures of our instrument; 2 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/2105.04051.json · badge: /api/ran/2105.04051.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
cjshui/wadn community (classifier label)
classifier basis not recorded on the link
7 ran · 2 no recorded run
FunctionStatusWhere it lives
BBSL Ran
ran on a synthesized input
cjshui/wadn/solver.py
code served (permissive licence) · get_code("e3d9c2e55bc8147e")
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 ndarray, ndim 1, dtype family float, shape (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 cvxpy as cp
import numpy as np

# Construct arguments for BBSL function
# C: confusion matrix (n_classes x n_classes)
# y_t: predicted target label distribution (n_classes,)
# y_s: ground truth source label distribution (n_classes,)

n_classes = 4

# Create a small confusion matrix (4x4)
# This represents classification confusion between 4 classes
C = np.array([
    [0.8, 0.1, 0.05, 0.05],
    [0.1, 0.7, 0.1, 0.1],
    [0.05, 0.1, 0.75, 0.1],
    [0.05, 0.1, 0.1, 0.75]
], dtype=np.float64)

# Predicted target label distribution (sums to 1)
y_t = np.array([0.25, 0.25, 0.25, 0.25], dtype=np.float64)

# Ground truth source label distribution (sums to 1)
y_s = np.array([0.4, 0.3, 0.2, 0.1], dtype=np.float64)

ARGS = {
    'C': C,
    'y_t': y_t,
    'y_s': y_s
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
cvxpy, numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type ndarray, ndim 1, dtype family float, shape (4,) — shape (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
Convex Ran
ran on a synthesized input
cjshui/wadn/solver.py
code served (permissive licence) · get_code("2e25d47d12c2dd79")
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 ndarray, ndim 1, dtype family float, shape (3,) 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 cvxpy as cp
import numpy as np

# The function expects:
# - loss: a list of scalar loss values (src_number losses)
# - L2_reg: a scalar regularization coefficient

# Create a small example with 3 sources
src_number = 3

# Create loss values for each source (small positive values)
loss = [1.5, 2.3, 0.8]

# Create L2 regularization coefficient
L2_reg = 0.1

ARGS = {
    "loss": loss,
    "L2_reg": L2_reg
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
cvxpy, numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type ndarray, ndim 1, dtype family float, shape (3,) — shape (3,) 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
get_logger Ran
ran on a synthesized input
cjshui/wadn/utils.py
code served (permissive licence) · get_code("e4b0642506057969")
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 RootLogger. 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 sys
import logging
import tempfile
import os

# Create a temporary file path for logging
temp_dir = tempfile.gettempdir()
log_filename = os.path.join(temp_dir, "test_logger.log")

ARGS = {
    "filename": log_filename
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
none outside the standard library — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type RootLogger — a RootLogger output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a RootLogger output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not 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
np_sigmoid Ran
ran on a synthesized input
cjshui/wadn/utils.py
code served (permissive licence) · get_code("6a42b4277c5eb6a8")
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 ndarray, ndim 2, dtype family float, shape (2, 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 numpy as np

# Create a small numpy array with a mix of positive, negative, and near-zero values
x = np.array([[-2.0, -0.5, 0.0, 1.5],
              [0.5, -1.0, 2.0, -0.1]], dtype=np.float32)

ARGS = {
    "x": x
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type ndarray, ndim 2, dtype family float, shape (2, 4) — shape (2, 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
np_softmax Ran
ran on a synthesized input
cjshui/wadn/utils.py
code served (permissive licence) · get_code("db82577adb193cb7")
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 ndarray, ndim 2, dtype family float, shape (4, 3) 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 numpy as np

# Construct a small test input for np_softmax
# The function expects a numpy array and computes softmax along axis 0
# We'll create a 2D array with shape (4, 3) - 4 samples, 3 classes
x = np.random.randn(4, 3).astype(np.float32)

ARGS = {
    'x': x
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type ndarray, ndim 2, dtype family float, shape (4, 3) — shape (4, 3) 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
partial_BBSL Ran
ran on a synthesized input
cjshui/wadn/solver.py
code served (permissive licence) · get_code("1a6fa08d45d156f2")
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 ndarray, ndim 1, dtype family float, shape (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 numpy as np
import cvxpy as cp

# Set seed for reproducibility
np.random.seed(0)

# Number of classes
n_classes = 4

# Construct a small confusion matrix (n_classes x n_classes)
# This represents predictions vs ground truth
C = np.array([
    [0.8, 0.1, 0.05, 0.05],
    [0.1, 0.7, 0.1, 0.1],
    [0.05, 0.15, 0.7, 0.1],
    [0.05, 0.05, 0.15, 0.75]
])

# Predicted target label distribution (should sum to 1)
y_t = np.array([0.25, 0.25, 0.25, 0.25])

# Ground truth source label distribution (should sum to 1)
y_s = np.array([0.3, 0.2, 0.25, 0.25])

# Sparsity coefficient (trade-off parameter)
sparse_coef = 0.1

ARGS = {
    'C': C,
    'y_t': y_t,
    'y_s': y_s,
    'sparse_coef': sparse_coef
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
cvxpy, numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type ndarray, ndim 1, dtype family float, shape (4,) — shape (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
shift_trainset Ran
ran on a synthesized input
cjshui/wadn/load_data.py
code served (permissive licence) · get_code("fb79e36c1dfacfc1")
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

# Set random seed for reproducibility
np.random.seed(0)

# Create sample training data
# xx: feature matrix with shape (10, 4) - 10 samples, 4 features
xx = np.random.randn(10, 4).astype(np.float32)

# yy: labels with shape (10,) - 10 labels
# Create labels with some distribution: [0, 0, 0, 1, 1, 1, 2, 2, 2, 2]
yy = np.array([0, 0, 0, 1, 1, 1, 2, 2, 2, 2], dtype=np.int64)

# lables_list: list of labels to drop samples from
lables_list = [0, 1, 2]

# drop_ratios: list of drop ratios for each label (must be between 0 and 1)
drop_ratios = [0.3, 0.5, 0.2]

ARGS = {
    "xx": xx,
    "yy": yy,
    "lables_list": lables_list,
    "drop_ratios": drop_ratios,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy — 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
load_numpy_data Not yet run
unverified (harvested, no recorded run)
cjshui/wadn/load_data.py
code served (permissive licence) · get_code("36d358886b874a0a")
How it ran

no invocation recorded.

load_shifted_data Not yet run
unverified (harvested, no recorded run)
cjshui/wadn/load_data.py
code served (permissive licence) · get_code("54f17e489bbbca68")
How it ran

no invocation 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, 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 9 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

Multi-source domain adaptation aims at leveraging the knowledge from multiple tasks for predicting a related target domain. Hence, a crucial aspect is to properly combine different sources based on their relations. In this paper, we analyzed the problem for aggregating source domains with different label distributions, where most recent source selection approaches fail. Our proposed algorithm differs from previous approaches in two key ways: the model aggregates multiple sources mainly through the similarity of semantic conditional distribution rather than marginal distribution; the model proposes a \emph{unified} framework to select relevant sources for three popular scenarios, i.e., domain adaptation with limited label on target domain, unsupervised domain adaptation and label partial unsupervised domain adaption. We evaluate the proposed method through extensive experiments. The empirical results significantly outperform the baselines.

For agents

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

get_harvested_code_for_paper("2105.04051")
get_code_for_paper("2105.04051")
have("2105.04051")

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

curl https://syntology.ai/api/ran/2105.04051.json

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

[![Syntology run record](https://syntology.ai/api/ran/2105.04051.svg)](https://syntology.ai/paper/2105.04051)

Connect an agent — have() is free.