SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2106.05682 · 2021

DASO: Distribution-Aware Semantics-Oriented Pseudo-label for Imbalanced Semi-Supervised Learning

arXiv · PDF · Open in the Atlas

Code that ran

3 of 3 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, 1 violated it and 2 have no contract verdict; 0 failures of our instrument; 0 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/2106.05682.json · badge: /api/ran/2106.05682.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
ytaek-oh/daso canonical (classifier label)
classifier basis: census
3 ran · 0 no recorded run
FunctionStatusWhere it lives
confusion Ran
ran on a synthesized input
ytaek-oh/daso/lib/algorithm/darp_estim.py
code served (permissive licence) · get_code("200e849084348f71")
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, 3) as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import torch.nn as nn

torch.manual_seed(0)

# Define a minimal model that accepts inputs and outputs logits
class SimpleModel(nn.Module):
    def __init__(self, input_dim, num_classes):
        super().__init__()
        self.fc = nn.Linear(input_dim, num_classes)
    
    def forward(self, x):
        return self.fc(x)

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

# Create a minimal data loader
# Each item is (inputs, targets, _)
# The function unpacks: (inputs, targets, _) from each batch
loader = [
    (torch.randn(2, 4), torch.tensor([0, 1]), None),
    (torch.randn(2, 4), torch.tensor([2, 0]), None),
]

num_class = 3
device = 'cpu'

ARGS = {
    'model': model,
    'loader': loader,
    'num_class': num_class,
    'device': device,
    'is_unlabeled': 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 (3, 3) — shape (3, 3) as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
estimate_q_y Ran
ran on a synthesized input
ytaek-oh/daso/lib/algorithm/darp_estim.py
code served (permissive licence) · get_code("0e6cb787c09c83c4")
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 torch
import torch.nn as nn
from torch.utils.data import DataLoader, TensorDataset

torch.manual_seed(0)

# Create a minimal model that accepts inputs and outputs logits
class SimpleModel(nn.Module):
    def __init__(self, input_dim, num_classes):
        super().__init__()
        self.fc = nn.Linear(input_dim, num_classes)
    
    def forward(self, x):
        return self.fc(x)

# Set up parameters
num_class = 3
input_dim = 4
batch_size = 2

# Create a minimal model
model = SimpleModel(input_dim, num_class)
model.eval()

device = 'cpu'

# Create validation loader
# Each item should be (inputs, targets, something_else)
val_inputs = torch.randn(6, input_dim)
val_targets = torch.tensor([0, 1, 2, 0, 1, 2], dtype=torch.long)
val_dummy = torch.zeros(6)  # Third element in tuple
val_dataset = TensorDataset(val_inputs, val_targets, val_dummy)
val_loader = DataLoader(val_dataset, batch_size=batch_size, shuffle=False)

# Create unlabeled loader
# Use -1 as target to indicate unlabeled data
u_inputs = torch.randn(4, input_dim)
u_targets = torch.tensor([-1, -1, -1, -1], dtype=torch.long)
u_dummy = torch.zeros(4)
u_dataset = TensorDataset(u_inputs, u_targets, u_dummy)
u_loader = DataLoader(u_dataset, batch_size=batch_size, shuffle=False)

ARGS = {
    'val_loader': val_loader,
    'u_loader': u_loader,
    'model': model,
    'num_class': num_class,
    'device': device
}
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 — 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
f Ran
ran, violated the contract we drafted
ytaek-oh/daso/lib/algorithm/darp_reproduce.py
code served (permissive licence) · get_code("f92ee98ae819cb89")
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 float64, ndim 0, 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 numpy as np

# Construct arguments for f(x, a, b, c, d)
# The function computes: np.sum(a * b * np.exp(-1 * x / c)) - d
# All parameters should be numeric arrays or scalars

x = np.array([0.5, 1.0, 1.5, 2.0])  # input array
a = np.array([1.0, 2.0, 3.0, 4.0])  # coefficient array
b = np.array([0.5, 1.0, 1.5, 2.0])  # coefficient array
c = np.array([1.0, 1.0, 1.0, 1.0])  # time constant array
d = 5.0  # scalar offset

ARGS = {
    'x': x,
    'a': a,
    'b': b,
    'c': c,
    'd': d
}
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 float64, ndim 0, dtype family float — no output shape is stated: observe_signature.py recorded float ndim 0, which disagrees with the fixture run
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

Also present in other papers' code

Of 3 samples lifted from this paper's linked repositories, 3 carry a function identity and 0 do not. Of the 3 distinct functions with an identity, 1 are also present in other papers whose code we hold (1 with at least one paper dated earlier, 0 the same month, 1 later) and 2 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
f 2 other papers
1 dated earlier, 1 later
2007.08844 (2020-07)
Distribution Aligning Refinery of Pseudo-label for Imbalanced Semi-supervised Learning
2403.10391 (2024-03)
CDMAD: Class-Distribution-Mismatch-Aware Debiasing for Class-Imbalanced Semi-Supervised Learning

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

The capability of the traditional semi-supervised learning (SSL) methods is far from real-world application due to severely biased pseudo-labels caused by (1) class imbalance and (2) class distribution mismatch between labeled and unlabeled data. This paper addresses such a relatively under-explored problem. First, we propose a general pseudo-labeling framework that class-adaptively blends the semantic pseudo-label from a similarity-based classifier to the linear one from the linear classifier, after making the observation that both types of pseudo-labels have complementary properties in terms of bias. We further introduce a novel semantic alignment loss to establish balanced feature representation to reduce the biased predictions from the classifier. We term the whole framework as Distribution-Aware Semantics-Oriented (DASO) Pseudo-label. We conduct extensive experiments in a wide range of imbalanced benchmarks: CIFAR10/100-LT, STL10-LT, and large-scale long-tailed Semi-Aves with open-set class, and demonstrate that, the proposed DASO framework reliably improves SSL learners with unlabeled data especially when both (1) class imbalance and (2) distribution mismatch dominate.

For agents

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

get_harvested_code_for_paper("2106.05682")
get_code_for_paper("2106.05682")
have("2106.05682")

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

curl https://syntology.ai/api/ran/2106.05682.json

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

[![Syntology run record](https://syntology.ai/api/ran/2106.05682.svg)](https://syntology.ai/paper/2106.05682)

Connect an agent — have() is free.