SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2007.08844 · NeurIPS · 2020

Distribution Aligning Refinery of Pseudo-label for Imbalanced Semi-supervised Learning

Sejun Park, Jinwoo Shin, Eunho Yang, Sung Hwang, Jaehyung Kim, Youngbum Hur

arXiv · PDF · Open in the Atlas

Code that ran

2 of 2 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 1 has no contract verdict; 1 failure 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/2007.08844.json · badge: /api/ran/2007.08844.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
bbuing9/DARP canonical (classifier label)
classifier basis: classifier_2025
2 ran · 0 no recorded run
FunctionStatusWhere it lives
f Ran
ran on a synthesized input
bbuing9/DARP/common.py
code served (permissive licence) · get_code("73eab42215d7c5fb")
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 the function f(x, a, b, c, d)
# The function computes: sum(a * b * exp(-x / c)) - d

# x: should be a numeric array or scalar that can be used in arithmetic operations
x = np.array([1.0, 2.0, 3.0, 4.0])

# a: should be numeric, will be multiplied with b and the exponential term
a = np.array([0.5, 1.0, 1.5, 2.0])

# b: should be numeric, will be multiplied with a and the exponential term
b = np.array([2.0, 3.0, 4.0, 5.0])

# c: should be numeric (non-zero), used as divisor in the exponent
c = np.array([1.0, 2.0, 3.0, 4.0])

# d: should be numeric, subtracted from the sum at the end
d = np.float64(10.0)

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
opt_solver Ran
ran; our contract draft was wrong, not the code
bbuing9/DARP/common.py
code served (permissive licence) · get_code("771561d19c7365b9")
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 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 numpy as np
import math

torch.manual_seed(0)

# Create small test tensors
# probs: shape (N, K) - probability distribution, must be valid probabilities
N, K = 2, 4
probs = torch.rand(N, K)
probs = probs / probs.sum(dim=1, keepdim=True)  # normalize to valid probabilities

# target_distb: shape (K,) - target distribution
target_distb = torch.rand(K)
target_distb = target_distb / target_distb.sum()  # normalize to valid probabilities

# num_iter: number of iterations
num_iter = 10

# th: threshold for Newton's method tolerance
th = 0.1

# num_newton: max iterations for Newton's method
num_newton = 30

ARGS = {
    'probs': probs,
    'target_distb': target_distb,
    'num_iter': num_iter,
    'th': th,
    'num_newton': num_newton
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
numpy, scipy, 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

Also present in other papers' code

Of 2 samples lifted from this paper's linked repositories, 2 carry a function identity and 0 do not. Of the 2 distinct functions with an identity, 1 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 1 later) and 1 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
brick of this paper's assembly: helper
2 other papers
2 later
2106.05682 (2021-06)
DASO: Distribution-Aware Semantics-Oriented 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

While semi-supervised learning (SSL) has proven to be a promising way for leveraging unlabeled data when labeled data is scarce, the existing SSL algorithms typically assume that training class distributions are balanced. However, these SSL algorithms trained under imbalanced class distributions can severely suffer when generalizing to a balanced testing criterion, since they utilize biased pseudo-labels of unlabeled data toward majority classes. To alleviate this issue, we formulate a convex optimization problem to softly refine the pseudo-labels generated from a biased model, and develop a simple iterative algorithm, named Distribution Aligning Refinery of Pseudo-label (DARP) that solves it provably and efficiently. Under various class-imbalanced semi-supervised scenarios, we demonstrate the effectiveness of DARP and its compatibility with state-of-the-art SSL schemes.

For agents

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

get_harvested_code_for_paper("2007.08844")
get_code_for_paper("2007.08844")
have("2007.08844")

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

curl https://syntology.ai/api/ran/2007.08844.json

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

[![Syntology run record](https://syntology.ai/api/ran/2007.08844.svg)](https://syntology.ai/paper/2007.08844)

Connect an agent — have() is free.