SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2310.13852 · 2023

Gradual Domain Adaptation: Theory and Algorithms

arXiv · PDF · Open in the Atlas

Code that ran

10 of 15 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 0 have no contract verdict; 6 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/2310.13852.json · badge: /api/ran/2310.13852.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
yifei-he/goat canonical (classifier label)
classifier basis: census
10 ran · 5 no recorded run
FunctionStatusWhere it lives
calculate_modal_val_accuracy Ran
ran, honoured the contract we drafted
yifei-he/goat/train_model.py
code served (permissive licence) · get_code("87fd30c36abb62d4")
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 Tensor, ndim 0, dtype family float, shape () as a later run recorded it. The image it ran in was not recorded. The code mentions cuda, and the harness aliases cuda to the CPU for every sample; whether this run needed that is 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)

# Define a simple model that takes images and outputs class logits
class SimpleClassifier(nn.Module):
    def __init__(self, num_classes=5):
        super().__init__()
        self.fc = nn.Linear(4, num_classes)
    
    def forward(self, x):
        # Flatten if needed and pass through linear layer
        x = x.view(x.size(0), -1)
        return self.fc(x)

# Create model
model = SimpleClassifier(num_classes=5)

# Create validation loader with 2-item tuples (images, labels)
# Batch size 2, image dimension 4, 3 batches
valloader = [
    (torch.randn(2, 4), torch.randint(0, 5, (2,))),
    (torch.randn(2, 4), torch.randint(0, 5, (2,))),
    (torch.randn(2, 4), torch.randint(0, 5, (2,))),
]

ARGS = {
    "model": model,
    "valloader": valloader,
}
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 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_angles Ran
ran, honoured the contract we drafted
yifei-he/goat/util.py
code served (permissive licence) · get_code("2683447b0d0da61c")
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 torch
import numpy as np

torch.manual_seed(0)

# Analyzing the function:
# get_angles(step, target) takes two parameters:
# - step: used in angles[-1] + step (numeric, added to previous angle)
# - target: used in angles[-1] < target (numeric, comparison value)
# The function builds a list starting at 0, incrementing by step until >= target

# Create simple numeric arguments
step = 0.5
target = 3.0

ARGS = {
    "step": step,
    "target": target,
}
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 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_conf_idx Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
yifei-he/goat/ot_util.py
code served (permissive licence) · get_code("562768e28e0b7b68")
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

# Create small logits array (batch_size=2, num_classes=4)
logits = np.array([
    [0.1, 0.5, 0.3, 0.2],
    [0.4, 0.2, 0.6, 0.1]
], dtype=np.float32)

# confidence_q parameter - a quantile value between 0 and 1
confidence_q = 0.2

ARGS = {
    "logits": logits,
    "confidence_q": confidence_q
}
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
get_pseudo_labels Ran
ran; our contract draft was wrong, not the code
yifei-he/goat/da_algo.py
code served (permissive licence) · get_code("8fa39421d6d44541")
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. The code mentions cuda, and the harness aliases cuda to the CPU for every sample; whether this run needed that is 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)

device = torch.device('cpu')

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

# Create model
model = SimpleModel(input_dim=4, num_classes=3)

# Create dataloader with 2-tuples (data, label)
# Batch size 2, input dimension 4, two batches total
dataloader = [
    (torch.randn(2, 4), torch.tensor([0, 1])),
    (torch.randn(2, 4), torch.tensor([1, 2])),
]

# Set up arguments
ARGS = {
    'dataloader': dataloader,
    'model': model,
    'confidence_q': 0.1,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type tuple — a tuple output has no array shape of its own; none is stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
get_transported_labels Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
yifei-he/goat/ot_util.py
code served (permissive licence) · get_code("6dcd56b2f85f042b")
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 int, shape (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 numpy as np

# Create a small optimal transport plan (coupling matrix)
# plan should be a 2D array representing the transport coupling between source and target
np.random.seed(0)
plan = np.random.rand(5, 5)
plan = plan / plan.sum(axis=1, keepdims=True)  # normalize rows to make it a valid coupling

# Create labels for the source distribution
# ys should be a 1D array of class labels
ys = np.array([0, 0, 1, 1, 2])

# logit parameter - boolean flag
logit = False

ARGS = {
    "plan": plan,
    "ys": ys,
    "logit": logit,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, ot — 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 int, shape (5,) — shape (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
load_portraits_data Ran
ran; our contract draft was wrong, not the code
yifei-he/goat/dataset.py
code served (permissive licence) · get_code("e7acb448f66e84cb")
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 scipy.io
import tempfile
import os

# Create a temporary directory and a mock .mat file
temp_dir = tempfile.mkdtemp()
original_cwd = os.getcwd()
os.chdir(temp_dir)

# Create a mock dataset_32x32.mat file
import numpy as np
mock_data = {
    'Xs': np.random.randn(2, 32, 32).astype(np.float32),  # batch_size=2, 32x32 images
    'Ys': np.array([[0, 1]])  # class labels for 2 samples
}
scipy.io.savemat('./dataset_32x32.mat', mock_data)

ARGS = {
    'load_file': 'dataset_32x32.mat'
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, scipy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type tuple — a tuple output has no array shape of its own; none is stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
loss_function Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
yifei-he/goat/train_model.py
code served (permissive licence) · get_code("206142c1def9d0e8")
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 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 VAE loss function
batch_size = 2
latent_dim = 4
input_dim = 3

# recon_x: reconstructed output from decoder, should be probabilities [0, 1]
recon_x = torch.sigmoid(torch.randn(batch_size, input_dim))

# x: original input data, should be in [0, 1] for BCE
x = torch.rand(batch_size, input_dim)

# mu: mean of latent distribution
mu = torch.randn(batch_size, latent_dim)

# log_var: log variance of latent distribution
log_var = torch.randn(batch_size, latent_dim)

ARGS = {
    'recon_x': recon_x,
    'x': x,
    'mu': mu,
    'log_var': log_var
}
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 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
shuffle Ran
ran, honoured the contract we drafted
yifei-he/goat/dataset.py
code served (permissive licence) · get_code("73a5a29137cb1d07")
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 simple numpy arrays for xs and ys
# xs: shape (5, 4) - 5 samples, 4 features
# ys: shape (5, 3) - 5 samples, 3 classes/outputs
xs = np.random.randn(5, 4).astype(np.float32)
ys = np.random.randn(5, 3).astype(np.float32)

ARGS = {
    "xs": xs,
    "ys": ys,
}
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
split_sizes Ran
ran; our contract draft was wrong, not the code
yifei-he/goat/dataset.py
code served (permissive licence) · get_code("a2a03bffe9d25162")
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. 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

# Create a simple array to split
array = np.arange(10)

# Create sizes that sum to the length of the array
# The function will split the array into chunks of these sizes
sizes = [3, 4, 2, 1]

# Verify sizes sum to array length
assert sum(sizes) == len(array), f"sizes {sizes} must sum to array length {len(array)}"

ARGS = {
    "array": array,
    "sizes": sizes,
}
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 list — a list 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
test Ran
ran, honoured the contract we drafted
yifei-he/goat/train_model.py
code served (permissive licence) · get_code("0a027f0cb95c0e29")
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 float, ndim 0, dtype family float, shape () as a later run recorded it. The image it ran in was not recorded. The code mentions cuda, and the harness aliases cuda to the CPU for every sample; whether this run needed that is 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)

# Build a simple classifier model
class SimpleClassifier(nn.Module):
    def __init__(self, input_dim=4, num_classes=3):
        super().__init__()
        self.fc1 = nn.Linear(input_dim, 8)
        self.fc2 = nn.Linear(8, num_classes)
    
    def forward(self, x):
        x = torch.relu(self.fc1(x))
        x = self.fc2(x)
        return x

# Build a simple VAE model
class SimpleVAE(nn.Module):
    def __init__(self, input_dim=4, latent_dim=2):
        super().__init__()
        self.fc1 = nn.Linear(input_dim, 8)
        self.fc_mu = nn.Linear(8, latent_dim)
        self.fc_log_var = nn.Linear(8, latent_dim)
        self.fc_decode = nn.Linear(latent_dim, 8)
        self.fc_out = nn.Linear(8, input_dim)
    
    def forward(self, x):
        h = torch.relu(self.fc1(x))
        mu = self.fc_mu(h)
        log_var = self.fc_log_var(h)
        z = mu + torch.exp(0.5 * log_var) * torch.randn_like(mu)
        h_decode = torch.relu(self.fc_decode(z))
        recon = torch.sigmoid(self.fc_out(h_decode))
        return recon, mu, log_var

# Create a simple data loader (list of batches)
# Each batch is a tuple of (data, labels) or (data, labels, weight)
batch_size = 2
num_features = 4
num_classes = 3

# Create batches for non-VAE case
data_batch_1 = torch.randn(batch_size, num_features)
labels_batch_1 = torch.randint(0, num_classes, (batch_size,))
data_batch_2 = torch.randn(batch_size, num_features)
labels_batch_2 = torch.randint(0, num_classes, (batch_size,))

val_loader_classifier = [
    (data_batch_1, labels_batch_1),
    (data_batch_2, labels_batch_2)
]

# Create batches for VAE case (data should be in [0, 1] for BCE)
vae_data_batch_1 = torch.sigmoid(torch.randn(batch_size, num_features))
vae_data_batch_2 = torch.sigmoid(torch.randn(batch_size, num_features))

val_loader_vae = [
    (vae_data_batch_1,),
    (vae_data_batch_2,)
]

# Create models
classifier_model = SimpleClassifier(input_dim=num_features, num_classes=num_classes)
vae_model = SimpleVAE(input_dim=num_features, latent_dim=2)

# Add dataset attribute to loader for len(val_loader.dataset)
class SimpleDataset:
    def __init__(self, size):
        self.size = size
    def __len__(self):
        return self.size

class DataLoaderWrapper:
    def __init__(self, batches, dataset_size):
        self.batches = batches
        self.dataset = SimpleDataset(dataset_size)
    
    def __iter__(self):
        return iter(self.batches)

wrapped_val_loader_classifier = DataLoaderWrapper(val_loader_classifier, batch_size * 2)
wrapped_val_loader_vae = DataLoaderWrapper(val_loader_vae, batch_size * 2)

ARGS = {
    'val_loader': wrapped_val_loader_classifier,
    'model': classifier_model,
    'vae': False,
    'verbose': True
}
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 float, 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_OT_plan Not yet run
unverified (harvested, no recorded run)
yifei-he/goat/ot_util.py
code served (permissive licence) · get_code("08b2a40007332655")
How it ran

no invocation recorded.

get_rotated_dataset Not yet run
unverified (harvested, no recorded run)
yifei-he/goat/util.py
code served (permissive licence) · get_code("99b23963ab09d0ec")
How it ran

no invocation recorded.

get_single_rotate Not yet run
unverified (harvested, no recorded run)
yifei-he/goat/util.py
code served (permissive licence) · get_code("21fe29bf19ff3038")
How it ran

no invocation recorded.

get_source_model Not yet run
unverified (harvested, no recorded run)
yifei-he/goat/experiments.py
code served (permissive licence) · get_code("8f756a4179f4b480")
How it ran

no invocation recorded.

self_train Not yet run
unverified (harvested, no recorded run)
yifei-he/goat/da_algo.py
code served (permissive licence) · get_code("e1f64f917e8fc686")
How it ran

no invocation recorded.

Also present in other papers' code

Of 15 samples lifted from this paper's linked repositories, 15 carry a function identity and 0 do not. Of the 15 distinct functions with an identity, 4 are also present in other papers whose code we hold (4 with at least one paper dated earlier, 0 the same month, 0 later) and 11 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
calculate_modal_val_accuracy 1 other paper
1 dated earlier
2204.08200 (2022-04)
Understanding Gradual Domain Adaptation: Improved Analysis, Optimal Path and Beyond
get_source_model 1 other paper
1 dated earlier
2204.08200 (2022-04)
Understanding Gradual Domain Adaptation: Improved Analysis, Optimal Path and Beyond
loss_function 1 other paper
1 dated earlier
2204.08200 (2022-04)
Understanding Gradual Domain Adaptation: Improved Analysis, Optimal Path and Beyond
test 1 other paper
1 dated earlier
2204.08200 (2022-04)
Understanding Gradual Domain Adaptation: Improved Analysis, Optimal Path and Beyond

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

Unsupervised domain adaptation (UDA) adapts a model from a labeled source domain to an unlabeled target domain in a one-off way. Though widely applied, UDA faces a great challenge whenever the distribution shift between the source and the target is large. Gradual domain adaptation (GDA) mitigates this limitation by using intermediate domains to gradually adapt from the source to the target domain. In this work, we first theoretically analyze gradual self-training, a popular GDA algorithm, and provide a significantly improved generalization bound compared with Kumar et al. (2020). Our theoretical analysis leads to an interesting insight: to minimize the generalization error on the target domain, the sequence of intermediate domains should be placed uniformly along the Wasserstein geodesic between the source and target domains. The insight is particularly useful under the situation where intermediate domains are missing or scarce, which is often the case in real-world applications. Based on the insight, we propose $\textbf{G}$enerative Gradual D$\textbf{O}$main $\textbf{A}$daptation with Optimal $\textbf{T}$ransport (GOAT), an algorithmic framework that can generate intermediate domains in a data-dependent way. More concretely, we first generate intermediate domains along the Wasserstein geodesic between two given consecutive domains in a feature space, then apply gradual self-training to adapt the source-trained classifier to the target along the sequence of intermediate domains. Empirically, we demonstrate that our GOAT framework can improve the performance of standard GDA when the given intermediate domains are scarce, significantly broadening the real-world application scenarios of GDA. Our code is available at https://github.com/uiuctml/GOAT.

For agents

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

get_harvested_code_for_paper("2310.13852")
get_code_for_paper("2310.13852")
have("2310.13852")

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

curl https://syntology.ai/api/ran/2310.13852.json

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

[![Syntology run record](https://syntology.ai/api/ran/2310.13852.svg)](https://syntology.ai/paper/2310.13852)

Connect an agent — have() is free.