SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2302.01516 · AAAI · 2023

Class Overwhelms: Mutual Conditional Blended-Target Domain Adaptation

Boyu Wang, Charles Ling, Pengcheng Xu

arXiv · PDF · Open in the Atlas

Code that ran

2 of 4 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (0 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 0 violated it and 2 have no contract verdict; 0 failures of our instrument; 2 no recorded run), measured 2026-11-22; repository links from the Papers with Code archive attributed under CC BY-SA, no affiliation; bodies inline only under a permissive licence as GitHub detects it. Not a reproduction of the paper's results.

"Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results. This record, dated, as JSON: /api/ran/2302.01516.json · badge: /api/ran/2302.01516.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
Pengchengpcx/Class-overwhelms-Mutual-Conditional-Blended-Target-Domain-Adaptation canonical (classifier label)
classifier basis not recorded on the link
2 ran · 2 no recorded run
FunctionStatusWhere it lives
cal_acc Ran
ran on a synthesized input
Pengchengpcx/Class-overwhelms-Mutual-Conditional-Blended-Target-Domain-Adaptation/models/evaluation.py
code served (permissive licence) · get_code("96d1a27e3ffdf6f9")
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 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
from unittest.mock import MagicMock

torch.manual_seed(0)

# Create a minimal encoder model that outputs three values
class MinimalEncoder(nn.Module):
    def __init__(self):
        super().__init__()
        self.fc = nn.Linear(4, 3)  # 4 input dims, 3 output classes
    
    def forward(self, x):
        logits = self.fc(x)
        # Return three outputs as the function expects: _, _, preds
        return None, None, logits

# Create encoder
encoder = MinimalEncoder()

# Create test_set as a list of dictionaries with 'img' and 'target' keys
# Each item has batch_size=2, img_dim=4, num_classes=3
test_set = [
    {
        'img': torch.randn(2, 4),
        'target': torch.randint(0, 3, (2,))
    },
    {
        'img': torch.randn(2, 4),
        'target': torch.randint(0, 3, (2,))
    }
]

# Add dataset attribute that test_set.dataset accesses in the function
class TestSetWrapper(list):
    def __init__(self, *args, **kwargs):
        super().__init__(*args, **kwargs)
        self.dataset = self
    
    def __len__(self):
        return sum(item['target'].shape[0] for item in self)

test_set = TestSetWrapper(test_set)

# Create args as a minimal object/dict
args = {}

ARGS = {
    'encoder': encoder,
    'test_set': test_set,
    'args': args,
    'logger': None
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch, tqdm — 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
confidence_pseudo_label Ran
ran on a synthesized input
Pengchengpcx/Class-overwhelms-Mutual-Conditional-Blended-Target-Domain-Adaptation/util.py
code served (permissive licence) · get_code("8193561fbc0c0bdd")
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. 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 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

torch.manual_seed(0)

# Create a simple pseudo label dataloader
# The function expects (_, labs) tuples where labs is a tensor
# labs should have shape (batch_size, num_features) based on topk usage
batch_size = 2
num_features = 4

# Create mock pseudo labels with confidence scores
# These are typically distance/similarity scores that get filtered
labs_data = torch.randn(batch_size, num_features)

# Create a simple loader as a list of tuples
loader = [
    (None, labs_data),  # (dummy_input, pseudo_labels)
]

# Metric should be 'cosine' or 'L2'
metric = 'L2'

# Margin for filtering confident pseudo labels
margin = 0.5

ARGS = {
    'loader': loader,
    'metric': metric,
    'margin': margin,
}
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, 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
accuracy Not yet run
unverified (harvested, no recorded run)
Pengchengpcx/Class-overwhelms-Mutual-Conditional-Blended-Target-Domain-Adaptation/util.py
pointer only (licence: MIT); the stored copy get_code serves, from kkonstantinidis/ByzShield, is pointer only (licence: NONE) · get_code("4d3faaaa1c706b0b")
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 kkonstantinidis/ByzShield, 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.

load_model Not yet run
unverified (harvested, no recorded run)
Pengchengpcx/Class-overwhelms-Mutual-Conditional-Blended-Target-Domain-Adaptation/util.py
code served (permissive licence) · get_code("a5905023bd0121fc")
How it ran

no invocation recorded.

Also present in other papers' code

Of 4 samples lifted from this paper's linked repositories, 4 carry a function identity and 0 do not. Of the 4 distinct functions with an identity, 1 are also present in other papers whose code we hold (1 with at least one paper dated earlier, 1 the same month, 1 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
accuracy 23 other papers
19 dated earlier, 1 the same month, 3 later
1603.07285 (2016-03)
A guide to convolution arithmetic for deep learning
1608.07017 (2016-08)
Ambient Sound Provides Supervision for Visual Learning
1608.08710 (2016-08)
Pruning Filters for Efficient ConvNets
and 20 more not named here

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

Current methods of blended targets domain adaptation (BTDA) usually infer or consider domain label information but underemphasize hybrid categorical feature structures of targets, which yields limited performance, especially under the label distribution shift. We demonstrate that domain labels are not directly necessary for BTDA if categorical distributions of various domains are sufficiently aligned even facing the imbalance of domains and the label distribution shift of classes. However, we observe that the cluster assumption in BTDA does not comprehensively hold. The hybrid categorical feature space hinders the modeling of categorical distributions and the generation of reliable pseudo labels for categorical alignment. To address these, we propose a categorical domain discriminator guided by uncertainty to explicitly model and directly align categorical distributions P (Z|Y ). Simultaneously, we utilize the low-level features to augment the single source features with diverse target styles to rectify the biased classifier P (Y |Z) among diverse targets. Such a mutual conditional alignment of P (Z|Y ) and P (Y |Z) forms a mutual reinforced mechanism. Our approach outperforms the state-of-the-art in BTDA even compared with methods utilizing domain labels, especially under the label distribution shift, and in single target DA on DomainNet.

For agents

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

get_harvested_code_for_paper("2302.01516")
get_code_for_paper("2302.01516")
have("2302.01516")

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

curl https://syntology.ai/api/ran/2302.01516.json

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

[![Syntology run record](https://syntology.ai/api/ran/2302.01516.svg)](https://syntology.ai/paper/2302.01516)

Connect an agent — have() is free.