SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2408.13983 · 2024

Dual-Path Adversarial Lifting for Domain Shift Correction in Online Test-time Adaptation

arXiv · PDF · Open in the Atlas

Code that ran

16 of 20 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; 1 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 15 failures of our instrument; 4 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/2408.13983.json · badge: /api/ran/2408.13983.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
yushuntang/dpal canonical (classifier label)
classifier basis: census
16 ran · 4 no recorded run
FunctionStatusWhere it lives
clean_state_dict Ran
ran; our contract draft was wrong, not the code
yushuntang/dpal/models/helpers.py
code served (permissive licence) · get_code("9d8a74383a0f33dc")
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 OrderedDict. 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 collections import OrderedDict

torch.manual_seed(0)

# Create a sample state dict with both 'module.' prefixed and non-prefixed keys
state_dict = OrderedDict([
    ('module.layer1.weight', torch.randn(4, 3)),
    ('module.layer1.bias', torch.randn(4)),
    ('layer2.weight', torch.randn(5, 4)),
    ('layer2.bias', torch.randn(5)),
    ('module.final.weight', torch.randn(2, 5)),
])

ARGS = {
    'state_dict': state_dict
}
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 OrderedDict — a OrderedDict output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a OrderedDict 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
collect_params Ran
ran; our contract draft was wrong, not the code
yushuntang/dpal/dpal.py
code served (permissive licence) · get_code("841322c61130157b")
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 torch
import torch.nn as nn

torch.manual_seed(0)

class SimpleModel(nn.Module):
    def __init__(self):
        super().__init__()
        self.layer1 = nn.Sequential(
            nn.Conv2d(3, 4, kernel_size=3),
            nn.BatchNorm2d(4),
            nn.ReLU()
        )
        self.layer2 = nn.Sequential(
            nn.Conv2d(4, 8, kernel_size=3),
            nn.LayerNorm(8),
            nn.ReLU()
        )
        self.layer3 = nn.GroupNorm(2, 8)
        self.layer4 = nn.BatchNorm2d(8)
        self.blocks = nn.ModuleList([
            nn.BatchNorm2d(8) for _ in range(25)
        ])
        self.norm = nn.BatchNorm2d(8)
        self.prompt_embedding = nn.Parameter(torch.randn(1, 4))

model = SimpleModel()

class Args:
    def __init__(self):
        self.norm_lr = 0.001
        self.prompt_lr = 0.0001

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
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 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
collect_prodictor_params Ran
ran; our contract draft was wrong, not the code
yushuntang/dpal/dpal.py
code served (permissive licence) · get_code("5eb7311dbc0e7ad9")
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 torch
import torch.nn as nn

torch.manual_seed(0)

class PredictorModel(nn.Module):
    def __init__(self):
        super().__init__()
        self.predictor_layer = nn.Linear(4, 3)
        self.other_layer = nn.Linear(4, 2)
    
    def forward(self, x):
        return self.predictor_layer(x)

class Args:
    def __init__(self):
        self.predictor_lr = 0.001

model = PredictorModel()
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
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 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
conv1x1 Ran
ran; our contract draft was wrong, not the code
yushuntang/dpal/models/Res.py
code served (permissive licence) · get_code("d9def42110729a85")
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 Conv2d. 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)

# The function conv1x1 takes in_planes, out_planes, and stride as parameters
# It returns an nn.Conv2d layer configured for 1x1 convolution
# We need to provide valid integer arguments for these parameters

ARGS = {
    "in_planes": 3,
    "out_planes": 64,
    "stride": 1
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Conv2d — a Conv2d output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Conv2d 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
conv3x3 Ran
ran; our contract draft was wrong, not the code
yushuntang/dpal/models/Res.py
code served (permissive licence) · get_code("160bb14bd76201b4")
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 Conv2d. 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 = {
    "in_planes": 3,
    "out_planes": 64,
    "stride": 1,
    "groups": 1,
    "dilation": 1,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Conv2d — a Conv2d output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Conv2d 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
forward_and_adapt Ran
ran; our contract draft was wrong, not the code
yushuntang/dpal/tent.py
code served (permissive licence) · get_code("dbdbd9c45e96c572")
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; 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 torch.nn as nn

torch.manual_seed(0)

# Build a minimal model that takes input x and returns logits
class SimpleModel(nn.Module):
    def __init__(self, input_dim=4, output_dim=3):
        super().__init__()
        self.linear = nn.Linear(input_dim, output_dim)
    
    def forward(self, x):
        return self.linear(x)

# Create instances
x = torch.randn(2, 4, requires_grad=True)
model = SimpleModel(input_dim=4, output_dim=3)
optimizer = torch.optim.SGD(model.parameters(), lr=0.01)

ARGS = {
    "x": x,
    "model": model,
    "optimizer": optimizer
}
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 — no output shape is stated: observe_signature.py could not observe it (import:OSError)
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
generate_sample_indices_and_ys Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
yushuntang/dpal/dataset/generate_shifted_sample_indices.py
code served (permissive licence) · get_code("5f093779a87d9678")
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 (100,) 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

# Set seed for reproducibility
np.random.seed(2022)

# Create q_all: a probability distribution matrix
# Shape should be (num_tests, num_classes)
# For imagenet1k, num_classes = 1000
num_tests = 100
num_classes = 1000

q_all = np.random.dirichlet(np.ones(num_classes), size=num_tests)

ARGS = {
    'q_all': q_all,
    'dataset_name': 'imagenet1k'
}
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 1, dtype family float, shape (100,) — shape (100,) 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
mish Ran
ran; our contract draft was wrong, not the code
yushuntang/dpal/models/layers/activations.py
code served (permissive licence) · get_code("801c85b8903bfff5")
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
import torch.nn.functional as F

torch.manual_seed(0)

# Create a small tensor for testing
x = torch.randn(2, 4)

# Define ARGS dict with all parameters
ARGS = {
    'x': x,
    'inplace': 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 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
monotone_shift_constructor Ran
ran; our contract draft was wrong, not the code
yushuntang/dpal/dataset/generate_shifted_sample_indices.py
code served (permissive licence) · get_code("e0f5922439b9e115")
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 function. 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

# q1 and q2 are used in the monotone_shift function with numpy operations
# They are multiplied by scalars and added together
# They should be numpy arrays of the same shape
# Using distinct shapes: 4 for q1, 3 for q2 to make them distinguishable

q1 = np.array([1.0, 2.0, 3.0, 4.0])
q2 = np.array([5.0, 6.0, 7.0, 8.0])

ARGS = {
    "q1": q1,
    "q2": q2,
}
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 function — a function output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a function 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
sigmoid Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
yushuntang/dpal/models/layers/activations.py
code served (permissive licence) · get_code("d83b6ecf3cdc1d6a")
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
import torch.nn as nn

torch.manual_seed(0)

# Create a small tensor for the sigmoid function to operate on
x = torch.randn(2, 4)

# Define ARGS mapping all parameters to values
ARGS = {
    "x": x,
    "inplace": 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 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
softmax_entropy Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
yushuntang/dpal/dct.py
pointer only (licence: MIT); the stored copy get_code serves, from Feliciaxyao/ICML2024-FSTTA, is pointer only (licence: NONE) · get_code("3078648c75e3e1e3")
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 Feliciaxyao/ICML2024-FSTTA, 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.

swish Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
yushuntang/dpal/models/layers/activations.py
code served (permissive licence) · get_code("717e4d22b6d103e6")
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 tensor for the swish function
x = torch.randn(2, 4)

ARGS = {
    "x": x,
    "inplace": 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 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
tensor_rot_180 Ran
ran; our contract draft was wrong, not the code
yushuntang/dpal/dataset/selectedRotateImageFolder.py
code served (permissive licence) · get_code("890d94991798f654")
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 4, dtype family float, shape (2, 3, 4, 5) 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 4D tensor for testing
# Shape: (batch=2, channels=3, height=4, width=5)
x = torch.randn(2, 3, 4, 5)

ARGS = {
    "x": x
}
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 4, dtype family float, shape (2, 3, 4, 5) — shape (2, 3, 4, 5) 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
tensor_rot_270 Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
yushuntang/dpal/dataset/selectedRotateImageFolder.py
code served (permissive licence) · get_code("599b8f7cc5b4ef6d")
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 3, dtype family float, shape (2, 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

torch.manual_seed(0)

# Create a small tensor with distinct dimensions
# Shape: (batch=2, height=4, width=3)
x = torch.randn(2, 4, 3)

ARGS = {
    "x": x
}
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 3, dtype family float, shape (2, 3, 4) — shape (2, 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
tensor_rot_90 Ran
ran; our contract draft was wrong, not the code
yushuntang/dpal/dataset/selectedRotateImageFolder.py
code served (permissive licence) · get_code("de9a9c1253646b04")
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 4, dtype family float, shape (2, 3, 4, 5) 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 tensor_rot_90 takes a tensor x and:
# - calls x.flip(2) to flip along dimension 2
# - calls transpose(1, 2) to transpose dimensions 1 and 2
# So x needs to be a tensor with at least 3 dimensions (indices 0, 1, 2)

# Create a small tensor with shape (batch=2, height=4, width=3, channels=5)
# This gives us distinct dimensions so we can track the rotation
x = torch.randn(2, 4, 3, 5)

ARGS = {
    "x": x
}
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 4, dtype family float, shape (2, 3, 4, 5) — shape (2, 3, 4, 5) 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
update_ema Ran
ran, honoured the contract we drafted
yushuntang/dpal/dpal.py
code served (permissive licence) · get_code("17259eab7993e1c7")
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
import torch.nn as nn

torch.manual_seed(0)

# The function update_ema takes two parameters:
# 1. ema: Can be None or a tensor (based on the conditional check and arithmetic operations)
# 2. new_data: A tensor (used in arithmetic with ema)

# Create small test tensors
ema_tensor = torch.randn(2, 4)
new_data_tensor = torch.randn(2, 4)

ARGS = {
    "ema": ema_tensor,
    "new_data": new_data_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
conv2d_same Not yet run
unverified (harvested, no recorded run)
yushuntang/dpal/models/helpers.py
code served (permissive licence) · get_code("d68221a69e61e4fc")
How it ran

no invocation recorded.

create_conv2d_pad Not yet run
unverified (harvested, no recorded run)
yushuntang/dpal/models/helpers.py
code served (permissive licence) · get_code("2366213b73f20069")
How it ran

no invocation recorded.

generate_test_probs_and_ys Not yet run
unverified (harvested, no recorded run)
yushuntang/dpal/dataset/generate_shifted_sample_indices.py
code served (permissive licence) · get_code("d0e36060db3376e6")
How it ran

no invocation recorded.

resnet18 Not yet run
unverified (harvested, no recorded run)
yushuntang/dpal/models/Res.py
code served (permissive licence) · get_code("48cd44b7f9a2e1d9")
How it ran

no invocation recorded.

Also present in other papers' code

Of 20 samples lifted from this paper's linked repositories, 20 carry a function identity and 0 do not. Of the 20 distinct functions with an identity, 17 are also present in other papers whose code we hold (14 with at least one paper dated earlier, 3 the same month, 8 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.

FunctionAlso present inEarliest-datedOthers named
conv1x1 431 other papers
375 dated earlier, 5 the same month, 40 later, 10 same year, order not determinable, 1 undated · 38 only as an assembly brick
1409.1556 (2014-09)
Very Deep Convolutional Networks for Large-Scale Image Recognition
1506.01186 (2015-06)
Cyclical Learning Rates for Training Neural Networks
1507.05717 (2015-07)
An End-to-End Trainable Neural Network for Image-based Sequence Recognition and Its Application to Scene Text Recognition
and 428 more not named here
conv3x3 312 other papers
266 dated earlier, 4 the same month, 31 later, 10 same year, order not determinable, 1 undated · 31 only as an assembly brick
1409.1556 (2014-09)
Very Deep Convolutional Networks for Large-Scale Image Recognition
1507.05717 (2015-07)
An End-to-End Trainable Neural Network for Image-based Sequence Recognition and Its Application to Scene Text Recognition
1512.03385 (2015-12)
Deep Residual Learning for Image Recognition
and 309 more not named here
resnet18 95 other papers
76 dated earlier, 1 the same month, 14 later, 3 same year, order not determinable, 1 undated
1805.00907 (2018-05)
Glow: Graph Lowering Compiler Techniques for Neural Networks
1902.08153 (2019-02)
Learned Step Size Quantization
1904.01355 (2019-04)
FCOS: Fully Convolutional One-Stage Object Detection
and 92 more not named here
softmax_entropy 22 other papers
16 dated earlier, 5 later, 1 undated · 4 only as an assembly brick
2006.10726 (2020-06)
TENT: FULLY TEST-TIME ADAPTATION BY ENTROPY MINIMIZATION
2105.08714 (2021-05)
Fighting Gradients with Gradients: Dynamic Defenses against Adversarial Attacks
2110.14038 (2021-10)
Robustness of Graph Neural Networks at Scale
and 19 more not named here
swish 10 other papers
9 dated earlier, 1 later
2207.14676 (2022-07)
Global-Local Self-Distillation for Visual Representation Learning
Lee_BAAM_Monocular_3D_Pose_and_Shape_Reconstruction_With_Bi-Contextual_Attention_CVPR_2023_paper (2023 (year only))
BAAM: Monocular 3D pose and shape reconstruction with bi-contextual attention module and attention-guided modeling
2308.13177 (2023-08)
How to Evaluate the Generalization of Detection? A Benchmark for Comprehensive Open-Vocabulary Detection
and 7 more not named here
mish 7 other papers
6 dated earlier, 1 later
2309.12530 (2023-09)
A Sentence Speaks a Thousand Images: Domain Generalization through Distilling CLIP with Language Guidance
2401.17992 (2024-01)
Multilinear Operator Networks
2402.04129 (2024-02)
OVOR: OnePrompt with Virtual Outlier Regularization for Rehearsal-Free Class-Incremental Learning
and 4 more not named here
sigmoid 7 other papers
6 dated earlier, 1 later
2309.12530 (2023-09)
A Sentence Speaks a Thousand Images: Domain Generalization through Distilling CLIP with Language Guidance
2401.17992 (2024-01)
Multilinear Operator Networks
2402.04129 (2024-02)
OVOR: OnePrompt with Virtual Outlier Regularization for Rehearsal-Free Class-Incremental Learning
and 4 more not named here
forward_and_adapt 5 other papers
4 dated earlier, 1 undated
2006.10726 (2020-06)
TENT: FULLY TEST-TIME ADAPTATION BY ENTROPY MINIMIZATION
2105.08714 (2021-05)
Fighting Gradients with Gradients: Dynamic Defenses against Adversarial Attacks
2306.04344 (2023-06)
ViDA: Homeostatic Visual Domain Adapter for Continual Test Time Adaptation
and 2 more not named here
update_ema 5 other papers
2 dated earlier, 2 later, 1 undated
2302.12400 (2023-02)
Towards Stable Test-Time Adaptation in Dynamic Wild World
2311.14402 (2023-11)
TEA: Test-time Energy Adaptation
2505.20704 (2025-05)
Beyond Entropy: Region Confidence Proxy for Wild Test-Time Adaptation
and 2 more not named here
conv2d_same 3 other papers
3 dated earlier
2206.00843 (2022-06)
DepthShrinker: A New Compression Paradigm Towards Boosting Real-Hardware Efficiency of Compact Neural Networks
2402.04129 (2024-02)
OVOR: OnePrompt with Virtual Outlier Regularization for Rehearsal-Free Class-Incremental Learning
2402.19460 (2024-02)
Benchmarking Uncertainty Disentanglement: Specialized Uncertainties for Specialized Tasks
tensor_rot_180 3 other papers
2 dated earlier, 1 undated
1909.11825 (2019-09)
Unsupervised Domain Adaptation through Self-Supervision
2404.01650 (2024-04)
Test-Time Model Adaptation with Only Forward Passes
openreview_QYPKLGyz7K
SaTeen: Learning Structural Alignment for Continual Test-Time Adaptation
tensor_rot_90 3 other papers
2 dated earlier, 1 undated
1909.11825 (2019-09)
Unsupervised Domain Adaptation through Self-Supervision
2404.01650 (2024-04)
Test-Time Model Adaptation with Only Forward Passes
openreview_QYPKLGyz7K
SaTeen: Learning Structural Alignment for Continual Test-Time Adaptation
create_conv2d_pad 2 other papers
2 dated earlier
2206.00843 (2022-06)
DepthShrinker: A New Compression Paradigm Towards Boosting Real-Hardware Efficiency of Compact Neural Networks
2402.04129 (2024-02)
OVOR: OnePrompt with Virtual Outlier Regularization for Rehearsal-Free Class-Incremental Learning
tensor_rot_270 2 other papers
1 dated earlier, 1 undated
2404.01650 (2024-04)
Test-Time Model Adaptation with Only Forward Passes
openreview_QYPKLGyz7K
SaTeen: Learning Structural Alignment for Continual Test-Time Adaptation
generate_sample_indices_and_ys 1 other paper
1 undated
no dated paper among those named
openreview_QYPKLGyz7K
SaTeen: Learning Structural Alignment for Continual Test-Time Adaptation
generate_test_probs_and_ys 1 other paper
1 undated
no dated paper among those named
openreview_QYPKLGyz7K
SaTeen: Learning Structural Alignment for Continual Test-Time Adaptation
monotone_shift_constructor 1 other paper
1 undated
no dated paper among those named
openreview_QYPKLGyz7K
SaTeen: Learning Structural Alignment for Continual Test-Time Adaptation

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

Transformer-based methods have achieved remarkable success in various machine learning tasks. How to design efficient test-time adaptation methods for transformer models becomes an important research task. In this work, motivated by the dual-subband wavelet lifting scheme developed in multi-scale signal processing which is able to efficiently separate the input signals into principal components and noise components, we introduce a dual-path token lifting for domain shift correction in test time adaptation. Specifically, we introduce an extra token, referred to as \textit{domain shift token}, at each layer of the transformer network. We then perform dual-path lifting with interleaved token prediction and update between the path of domain shift tokens and the path of class tokens at all network layers. The prediction and update networks are learned in an adversarial manner. Specifically, the task of the prediction network is to learn the residual noise of domain shift which should be largely invariant across all classes and all samples in the target domain. In other words, the predicted domain shift noise should be indistinguishable between all sample classes. On the other hand, the task of the update network is to update the class tokens by removing the domain shift from the input image samples so that input samples become more discriminative between different classes in the feature space. To effectively learn the prediction and update networks with two adversarial tasks, both theoretically and practically, we demonstrate that it is necessary to use smooth optimization for the update network but non-smooth optimization for the prediction network. Experimental results on the benchmark datasets demonstrate that our proposed method significantly improves the online fully test-time domain adaptation performance. Code is available at \url{https://github.com/yushuntang/DPAL}.

For agents

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

get_harvested_code_for_paper("2408.13983")
get_code_for_paper("2408.13983")
have("2408.13983")

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

curl https://syntology.ai/api/ran/2408.13983.json

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

[![Syntology run record](https://syntology.ai/api/ran/2408.13983.svg)](https://syntology.ai/paper/2408.13983)

Connect an agent — have() is free.