SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1904.06487 · 2019

Semi-supervised Domain Adaptation via Minimax Entropy

arXiv · PDF · Open in the Atlas

Code that ran

19 of 24 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; 4 honoured the contract we drafted, 0 violated it and 12 have no contract verdict; 3 failures of our instrument; 5 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/1904.06487.json · badge: /api/ran/1904.06487.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
VisionLearningGroup/SSDA_MME canonical (classifier label)
classifier basis: census
10 ran · 3 no recorded run
PrasannaPulakurthi/SPM community (classifier label)
classifier basis not recorded on the link
7 ran · 2 no recorded run
userb2020/s3d extension (classifier label)
classifier basis: classifier_2025
2 ran · 0 no recorded run
FunctionStatusWhere it lives
adaptation_factor Ran
ran, honoured the contract we drafted
userb2020/s3d/main_stage2.py
pointer only (licence: NONE) · get_code("cc577af946e48249")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, userb2020/s3d 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.

cal_start_step_for_weight Ran
ran, honoured the contract we drafted
userb2020/s3d/main_stage2.py
pointer only (licence: NONE) · get_code("3db485aae510c043")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, userb2020/s3d 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.

check_file_name Ran
ran on a synthesized input
VisionLearningGroup/SSDA_MME/sample/eval_results.py
code served (permissive licence) · get_code("f476e57a273481b9")
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 bool, ndim 0, dtype family float, shape () 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

torch.manual_seed(0)

# The function iterates through file1, indexes into file2, and compares equality
# file1 and file2 should be sequences (lists, tuples, etc.) of comparable items
# The simplest case is two lists of strings

file1 = ["file_a.txt", "file_b.txt", "file_c.txt"]
file2 = ["file_a.txt", "file_b.txt", "file_c.txt"]

ARGS = {
    "file1": file1,
    "file2": file2,
}
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 bool, ndim 0, dtype family float, shape () — shape () 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
conv3x3 Ran
ran; our contract draft was wrong, not the code
VisionLearningGroup/SSDA_MME/model/resnet.py
pointer only (licence: MIT); the stored copy get_code serves, from lixiaotong97/DSU, is pointer only (licence: NONE) · get_code("fac5364e2f53c6db")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from lixiaotong97/DSU, and GitHub detected no licence in that repository 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.

create_feather_mask Ran
ran on a synthesized input
PrasannaPulakurthi/SPM/spm.py
code served (permissive licence) · get_code("c26abd7b60ba9d50")
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 (32, 48) 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

ARGS = {
    "height": 32,
    "width": 48,
    "feather_size": 4,
}
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 (32, 48) — shape (32, 48) 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
edgelogic Ran
ran on a synthesized input
PrasannaPulakurthi/SPM/spm.py
code served (permissive licence) · get_code("cf9fb585131a2ccc")
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, ndim 1, dtype family int; no output shape is stated. The image it ran in was not recorded. If your copy returns the same type and ndim 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
import numpy as np

torch.manual_seed(0)

ARGS = {
    "i": 1,
    "j": 1,
    "patch_height": 32,
    "patch_width": 48,
    "num_patches_h": 4,
    "num_patches_w": 3,
    "overlap": 8
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type tuple, ndim 1, dtype family int — a tuple output has no array shape of its own; none is stated
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
entropy Ran
ran on a synthesized input
VisionLearningGroup/SSDA_MME/utils/loss.py
code served (permissive licence) · get_code("b2ee349e9ce0fc83")
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 0, dtype family float, shape () 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
import torch.nn as nn
import torch.nn.functional as F

torch.manual_seed(0)

class F1Model(nn.Module):
    def __init__(self):
        super(F1Model, self).__init__()
        self.fc = nn.Linear(4, 3)
    
    def forward(self, feat, reverse=False, eta=1.0):
        out = self.fc(feat)
        if reverse:
            out = out * eta
        return out

F1 = F1Model()
feat = torch.randn(2, 4)
lamda = 0.5
eta = 1.0

ARGS = {
    'F1': F1,
    'feat': feat,
    'lamda': lamda,
    'eta': eta
}
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 0, dtype family float, shape () — shape () 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_categories Ran
ran on a synthesized input
PrasannaPulakurthi/SPM/utils.py
code served (permissive licence) · get_code("84a015f614f2cea5")
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 list, ndim 1, dtype family float; no output shape is stated. The image it ran in was not recorded. If your copy returns the same type and ndim 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 tempfile
import os
import yaml

# Create a temporary directory for test files
temp_dir = tempfile.mkdtemp()

# Create a test YAML file with categories
yaml_file = os.path.join(temp_dir, "categories.yaml")
category_mapping = {
    "cat_one": 0,
    "cat_two": 1,
    "cat_three": 2
}
with open(yaml_file, 'w') as f:
    yaml.dump(category_mapping, f)

# Create a test TXT file with categories
txt_file = os.path.join(temp_dir, "categories.txt")
with open(txt_file, 'w') as f:
    f.write("dog_breed\n")
    f.write("cat_breed\n")
    f.write("bird_species\n")

# Define ARGS with the YAML file path (can also use txt_file)
ARGS = {
    "category_file": yaml_file
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
yaml — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type list, ndim 1, dtype family float — a list output has no array shape of its own; none is stated
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_source_optimizer Ran
ran on a synthesized input
PrasannaPulakurthi/SPM/source.py
code served (permissive licence) · get_code("c1295fc23e5b74a4")
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 SGD. 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
import torch.nn as nn

torch.manual_seed(0)

class SimpleModel(nn.Module):
    def __init__(self):
        super().__init__()
        self.backbone = nn.Linear(4, 3)
        self.extra = nn.Linear(3, 2)
    
    def get_params(self):
        backbone_params = list(self.backbone.parameters())
        extra_params = list(self.extra.parameters())
        return backbone_params, extra_params
    
    def forward(self, x):
        x = self.backbone(x)
        x = self.extra(x)
        return x

class OptimConfig:
    def __init__(self):
        self.name = 'sgd'
        self.lr = 0.01
        self.momentum = 0.9
        self.weight_decay = 0.0005
        self.nesterov = True

class Args:
    def __init__(self):
        self.distributed = False
        self.optim = OptimConfig()

model = SimpleModel()
args = Args()

ARGS = {
    'model': model,
    'args': args
}
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 SGD — a SGD output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a SGD 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
inv_lr_scheduler Ran
ran; our contract draft was wrong, not the code
VisionLearningGroup/SSDA_MME/utils/lr_schedule.py
code served (permissive licence) · get_code("b8b37ea74e8fc664")
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 SGD. 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
import torch.nn as nn
from torch.optim import SGD

torch.manual_seed(0)

# Create a simple model
model = nn.Linear(4, 3)

# Create an optimizer with multiple param groups
optimizer = SGD([
    {'params': model.weight, 'lr': 0.001},
    {'params': model.bias, 'lr': 0.001}
], lr=0.001)

# Define arguments
ARGS = {
    'param_lr': [1.0, 0.5],  # multipliers for each param group
    'optimizer': optimizer,
    'iter_num': 100,
    'gamma': 0.0001,
    'power': 0.75,
    'init_lr': 0.001
}
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 SGD — a SGD output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a SGD 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
l2_norm Ran
ran on a synthesized input
VisionLearningGroup/SSDA_MME/model/basenet.py
code served (permissive licence) · get_code("7f26a8f9f7e7e915")
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 (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 torch

torch.manual_seed(0)

# Create a small input tensor for l2_norm
# The function expects a 2D tensor where it:
# - Gets size()
# - Computes element-wise power (2)
# - Sums along dimension 1
# - Takes sqrt
# - Divides input by the norm (expanded to match input shape)
# Expected shape: (batch_size, feature_dim)
input_tensor = torch.randn(2, 4)

ARGS = {
    "input": input_tensor
}
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 (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
load_image Ran
ran, honoured the contract we drafted
PrasannaPulakurthi/SPM/image_list.py
pointer only (licence: MIT); the stored copy get_code serves, from DianCh/AdaContrast, is pointer only (licence: NONE) · get_code("d41e65573feeba36")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from DianCh/AdaContrast, and GitHub detected no licence in that repository 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.

make_dataset_fromlist Ran
ran on a synthesized input
VisionLearningGroup/SSDA_MME/loaders/data_list.py
code served (permissive licence) · get_code("e93ddc5135657ae1")
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, ndim 2, dtype family float; no output shape is stated. The image it ran in was not recorded. If your copy returns the same type and ndim 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 tempfile
import os

# Create a temporary file with image list data
temp_file = tempfile.NamedTemporaryFile(mode='w', delete=False, suffix='.txt')
temp_file.write("image1.jpg 0\n")
temp_file.write("image2.jpg 1\n")
temp_file.write("image3.jpg 0\n")
temp_file.write("image4.jpg 2\n")
temp_file.close()

ARGS = {
    "image_list": temp_file.name
}
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, ndim 2, dtype family float — a tuple output has no array shape of its own; none is stated
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
pil_loader Ran
ran, honoured the contract we drafted
VisionLearningGroup/SSDA_MME/loaders/data_list.py
code served (permissive licence) · get_code("f321f54723433661")
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) and returned Image. 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
import numpy as np
from PIL import Image
import io
import os
import tempfile

# Create a temporary directory for test files
temp_dir = tempfile.mkdtemp()

# Create a simple RGB image and save it to a temporary file
img = Image.new('RGB', (10, 10), color=(73, 109, 137))
test_image_path = os.path.join(temp_dir, 'test_image.jpg')
img.save(test_image_path)

ARGS = {
    'path': test_image_path
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
PIL, numpy, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Image — a Image output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Image output the recorded ndim 3 and dtype family int 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
resnet18 Ran
ran; our contract draft was wrong, not the code
VisionLearningGroup/SSDA_MME/model/resnet.py
code served (permissive licence) · get_code("0f295141a5bc895d")
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 ResNet. 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
import torch.nn as nn

torch.manual_seed(0)

ARGS = {
    'pretrained': False
}
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 ResNet — a ResNet output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a ResNet 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
return_classlist Ran
ran on a synthesized input
VisionLearningGroup/SSDA_MME/loaders/data_list.py
code served (permissive licence) · get_code("eef0e62e0432535a")
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 list, ndim 1, dtype family float; no output shape is stated. The image it ran in was not recorded. If your copy returns the same type and ndim 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 tempfile
import os

# Create a temporary file with image paths and labels
temp_file = tempfile.NamedTemporaryFile(mode='w', delete=False, suffix='.txt')
temp_file.write('class1/image1.jpg 0\n')
temp_file.write('class1/image2.jpg 0\n')
temp_file.write('class2/image3.jpg 1\n')
temp_file.write('class2/image4.jpg 1\n')
temp_file.write('class3/image5.jpg 2\n')
temp_file.close()

ARGS = {
    'image_list': temp_file.name
}
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 list, ndim 1, dtype family float — a list output has no array shape of its own; none is stated
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
return_label2cat Ran
ran on a synthesized input
VisionLearningGroup/SSDA_MME/sample/eval_results.py
code served (permissive licence) · get_code("c7bbad42f8cc5c3b")
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 dict. 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 tempfile
import os

# Create a temporary file with the expected format
temp_file = tempfile.NamedTemporaryFile(mode='w', delete=False, suffix='.txt')
temp_file.write("0 cat_zero\n")
temp_file.write("1 cat_one\n")
temp_file.write("2 cat_two\n")
temp_file.flush()
temp_file.close()

ARGS = {
    'file': temp_file.name
}
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 dict — a dict output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a dict 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
smoothed_cross_entropy Ran
ran on a synthesized input
PrasannaPulakurthi/SPM/source.py
code served (permissive licence) · get_code("a1020db8c5cc6104")
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 0, dtype family float, shape () 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
import torch.nn.functional as F

torch.manual_seed(0)

# Create small tensors for testing
batch_size = 2
num_classes = 4

# logits: shape (batch_size, num_classes)
logits = torch.randn(batch_size, num_classes)

# labels: shape (batch_size,) with class indices
labels = torch.tensor([0, 2])

# num_classes: integer
num_classes_val = 4

# epsilon: smoothing parameter
epsilon_val = 0.1

ARGS = {
    "logits": logits,
    "labels": labels,
    "num_classes": num_classes_val,
    "epsilon": epsilon_val,
}
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 0, dtype family float, shape () — shape () 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
unnormalize Ran
ran on a synthesized input
PrasannaPulakurthi/SPM/usefull_files/visualize_augmentations.py
code served (permissive licence) · get_code("a3bebec7cc18aaa8")
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
import numpy as np

torch.manual_seed(0)

# The function unnormalizes a tensor by iterating through channels
# and applying: t.mul_(s).add_(m) for each channel t with std s and mean m
# This means:
# - tensor should be a multi-channel tensor (iterable over channels)
# - mean should be iterable with values to add
# - std should be iterable with values to multiply

# Create a normalized tensor with shape (3, 4) - 3 channels, 4 elements per channel
tensor = torch.randn(3, 4)

# Create mean and std lists with 3 elements (one per channel)
mean = [0.5, 0.4, 0.3]
std = [0.2, 0.25, 0.15]

ARGS = {
    "tensor": tensor,
    "mean": mean,
    "std": std
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, 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
calc_coeff Not yet run
unverified (harvested, no recorded run)
VisionLearningGroup/SSDA_MME/utils/loss.py
pointer only (licence: MIT); the stored copy get_code serves, from Yiyang98/BFUDA, is pointer only (licence: NONE) · get_code("e352afa5762c5a6b")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from Yiyang98/BFUDA, and GitHub detected no licence in that repository 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.

concat_all_gather Not yet run
unverified (harvested, no recorded run)
PrasannaPulakurthi/SPM/utils.py
pointer only (licence: MIT); the stored copy get_code serves, from tntek/source-free-domain-adaptation, is pointer only (licence: NONE) · get_code("a2ae53d34bc13317")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from tntek/source-free-domain-adaptation, and GitHub detected no licence in that repository 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.

grad_reverse Not yet run
unverified (harvested, no recorded run)
VisionLearningGroup/SSDA_MME/model/basenet.py
code served (permissive licence) · get_code("9546e8417b4bdc1a")
How it ran

no invocation recorded.

remove_wrap_arounds Not yet run
unverified (harvested, no recorded run)
PrasannaPulakurthi/SPM/utils.py
pointer only (licence: MIT); the stored copy get_code serves, from DianCh/AdaContrast, is pointer only (licence: NONE) · get_code("ee1a4a51e75b6f4e")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from DianCh/AdaContrast, and GitHub detected no licence in that repository 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.

return_label_list Not yet run
unverified (harvested, no recorded run)
VisionLearningGroup/SSDA_MME/sample/eval_results.py
code served (permissive licence) · get_code("1b8b5cb46997c745")
How it ran

no invocation recorded.

Also present in other papers' code

Of 24 samples lifted from this paper's linked repositories, 24 carry a function identity and 0 do not. Of the 24 distinct functions with an identity, 9 are also present in other papers whose code we hold (3 with at least one paper dated earlier, 1 the same month, 9 later) and 15 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
conv3x3 686 other papers
102 dated earlier, 16 the same month, 568 later · 31 only as an assembly brick
1406.2661 (2014-06)
Generative Adversarial Networks
1409.0575 (2014-09)
ImageNet Large Scale Visual Recognition Challenge
1412.6572 (2014-12)
Explaining and Harnessing Adversarial Examples
and 683 more not named here
pil_loader 66 other papers
4 dated earlier, 62 later
1502.03044 (2015-02)
Show, Attend and Tell: Neural Image Caption Generation with Visual Attention
1710.10196 (2017-10)
Progressive Growing of GANs for Improved Quality, Stability, and Variation
1711.02512 (2017-11)
Fine-tuning CNN Image Retrieval with No Human Annotation
and 63 more not named here
calc_coeff 14 other papers
1 dated earlier, 13 later · 2 only as an assembly brick
1505.07818 (2015-05)
Domain-Adversarial Training of Neural Networks
2003.02541 (2020-03)
A Balanced and Uncertainty-aware Approach for Partial Domain Adaptation
2007.14612 (2020-07)
Clarinet: A One-step Approach Towards Budget-friendly Unsupervised Domain Adaptation
and 11 more not named here
concat_all_gather 5 other papers
5 later · 2 only as an assembly brick
2003.04297 (2020-03)
Improved Baselines with Momentum Contrastive Learning
2204.10377 (2022-04)
Contrastive Test-Time Adaptation
2206.15369 (2022-06)
No Reason for No Supervision: Improved Generalization in Supervised Models
and 2 more not named here
grad_reverse 3 other papers
3 later
2006.12770 (2020-06)
Discriminative Feature Alignment: Improving Transferability of Unsupervised Domain Adaptation by Gaussian-guided Latent Alignment
2106.02874 (2021-06)
RDA: Robust Domain Adaptation via Fourier Adversarial Attacking
aaai_28150 (2024 (year only))
DiDA: Disambiguated Domain Alignment for Cross-Domain Retrieval with Partial Labels
inv_lr_scheduler 2 other papers
2 later · 1 only as an assembly brick
2104.09415 (2021-04)
Cross-Domain Adaptive Clustering for Semi-Supervised Domain Adaptation
2106.04732 (2021-06)
A UNIFIED APPROACH TO SEMI-SUPERVISED LEARNING AND DOMAIN ADAPTATION
load_image 2 other papers
2 later
2204.10377 (2022-04)
Contrastive Test-Time Adaptation
2505.18514 (2025-05)
Test-Time Adaptation with Binary Feedback
remove_wrap_arounds 2 other papers
2 later · 1 only as an assembly brick
2204.10377 (2022-04)
Contrastive Test-Time Adaptation
2303.17132 (2023-03)
C-SFDA: A Curriculum Learning Aided Self-Training Framework for Efficient Source Free Domain Adaptation
resnet18 1 other paper
1 later
2207.13048 (2022-07)
Domain Adaptation under Open Set Label Shift

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

Contemporary domain adaptation methods are very effective at aligning feature distributions of source and target domains without any target supervision. However, we show that these techniques perform poorly when even a few labeled examples are available in the target. To address this semi-supervised domain adaptation (SSDA) setting, we propose a novel Minimax Entropy (MME) approach that adversarially optimizes an adaptive few-shot model. Our base model consists of a feature encoding network, followed by a classification layer that computes the features' similarity to estimated prototypes (representatives of each class). Adaptation is achieved by alternately maximizing the conditional entropy of unlabeled target data with respect to the classifier and minimizing it with respect to the feature encoder. We empirically demonstrate the superiority of our method over many baselines, including conventional feature alignment and few-shot methods, setting a new state of the art for SSDA.

For agents

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

get_harvested_code_for_paper("1904.06487")
get_code_for_paper("1904.06487")
have("1904.06487")

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

curl https://syntology.ai/api/ran/1904.06487.json

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

[![Syntology run record](https://syntology.ai/api/ran/1904.06487.svg)](https://syntology.ai/paper/1904.06487)

Connect an agent — have() is free.