SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2510.03993 · NeurIPS · 2025

Keep It on a Leash: Controllable Pseudo-label Generation Towards Realistic Long-Tailed Semi-Supervised Learning

Bo Han, Junhui Hou, Hui Liu, Yuheng Jia, Yaxin Hou

arXiv · PDF · Open in the Atlas

Code that ran

7 of 9 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, 1 violated it and 0 have no contract verdict; 5 failures of our instrument; 2 no recorded run), measured 2026-11-22; 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/2510.03993.json · badge: /api/ran/2510.03993.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
yaxinhou/CPG canonical (classifier label)
classifier basis: census
7 ran · 2 no recorded run
FunctionStatusWhere it lives
ce_loss Ran
ran; our contract draft was wrong, not the code
yaxinhou/CPG/semilearn/core/criterions/cross_entropy.py
pointer only (licence: NONE) · get_code("6554d2f5118ba705")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, yaxinhou/CPG 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.

consistency_loss Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
yaxinhou/CPG/semilearn/core/criterions/consistency.py
pointer only (licence: NONE) · get_code("fed286760e483b83")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, yaxinhou/CPG 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.

group_parameters Ran
ran; our contract draft was wrong, not the code
yaxinhou/CPG/semilearn/nets/utils.py
pointer only (licence: NONE) · get_code("9f81b5759307e67f")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, yaxinhou/CPG 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.

interleave_offsets Ran
ran, honoured the contract we drafted
yaxinhou/CPG/semilearn/algorithms/utils/ops.py
pointer only (licence: NONE) · get_code("bcf56cf2755ad9fb")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, yaxinhou/CPG 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.

load_checkpoint Ran
ran; our contract draft was wrong, not the code
yaxinhou/CPG/semilearn/nets/utils.py
pointer only (licence: NONE) · get_code("641c72db6fa25923")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, yaxinhou/CPG 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.

param_groups_weight_decay Ran
ran; our contract draft was wrong, not the code
yaxinhou/CPG/semilearn/nets/utils.py
pointer only (licence: NONE); the stored copy get_code serves, from yewen1486/emtal, is pointer only (licence: NONE) · get_code("88f4962784e09b88")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, yaxinhou/CPG 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.

str2bool Ran
ran, violated the contract we drafted
yaxinhou/CPG/semilearn/algorithms/utils/misc.py
pointer only (licence: NONE) · get_code("8d9acf594cf19c23")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, yaxinhou/CPG 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.

concat_all_gather Not yet run
unverified (harvested, no recorded run)
yaxinhou/CPG/semilearn/algorithms/utils/ops.py
pointer only (licence: NONE); the stored copy get_code serves, from mingkai-zheng/ReSSL, is pointer only (licence: NONE) · get_code("ef79279f4fe37762")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, yaxinhou/CPG 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.

interleave Not yet run
unverified (harvested, no recorded run)
yaxinhou/CPG/semilearn/algorithms/utils/ops.py
pointer only (licence: NONE) · get_code("c56b7c3374c4b9cc")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, yaxinhou/CPG 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.

Also present in other papers' code

Of 9 samples lifted from this paper's linked repositories, 9 carry a function identity and 0 do not. Of the 9 distinct functions with an identity, 8 are also present in other papers whose code we hold (8 with at least one paper dated earlier, 1 the same month, 2 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
str2bool 175 other papers
161 dated earlier, 2 the same month, 10 later, 2 same year, order not determinable · 2 only as an assembly brick
1406.6247 (2014-06)
Recurrent Models of Visual Attention
1603.09382 (2016-03)
Deep Networks with Stochastic Depth
1710.10196 (2017-10)
Progressive Growing of GANs for Improved Quality, Stability, and Variation
and 172 more not named here
param_groups_weight_decay 15 other papers
14 dated earlier, 1 later
2210.08823 (2022-10)
Scaling & Shifting Your Features: A New Baseline for Efficient Model Tuning
2304.14065 (2023-04)
Lightweight, Pre-trained Transformers for Remote Sensing Timeseries
2305.13002 (2023-05)
Rethinking Semi-supervised Learning with Language Models
and 12 more not named here
group_parameters 6 other papers
6 dated earlier
2210.08823 (2022-10)
Scaling & Shifting Your Features: A New Baseline for Efficient Model Tuning
2307.11342 (2023-07)
Tuning Pre-trained Model via Moment Probing
2308.13168 (2023-08)
IOMatch: Simplifying Open-Set Semi-Supervised Learning with Joint Inliers and Outliers Utilization
and 3 more not named here
ce_loss 2 other papers
2 dated earlier
2308.13168 (2023-08)
IOMatch: Simplifying Open-Set Semi-Supervised Learning with Joint Inliers and Outliers Utilization
2503.02231 (2025-03)
CGMatch: A Different Perspective of Semi-supervised Learning
concat_all_gather 1 other paper
1 dated earlier
2203.08717 (2022-03)
Weak Augmentation Guided Relational Self-Supervised Learning
interleave 1 other paper
1 dated earlier
1905.02249 (2019-05)
MixMatch: A Holistic Approach to Semi-Supervised Learning
interleave_offsets 1 other paper
1 dated earlier
1905.02249 (2019-05)
MixMatch: A Holistic Approach to Semi-Supervised Learning
load_checkpoint 1 other paper
1 dated earlier
2308.13168 (2023-08)
IOMatch: Simplifying Open-Set Semi-Supervised Learning with Joint Inliers and Outliers Utilization

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 long-tailed semi-supervised learning methods assume that labeled data exhibit a long-tailed distribution, and unlabeled data adhere to a typical predefined distribution (i.e., long-tailed, uniform, or inverse long-tailed). However, the distribution of the unlabeled data is generally unknown and may follow an arbitrary distribution. To tackle this challenge, we propose a Controllable Pseudo-label Generation (CPG) framework, expanding the labeled dataset with the progressively identified reliable pseudo-labels from the unlabeled dataset and training the model on the updated labeled dataset with a known distribution, making it unaffected by the unlabeled data distribution. Specifically, CPG operates through a controllable self-reinforcing optimization cycle: (i) at each training step, our dynamic controllable filtering mechanism selectively incorporates reliable pseudo-labels from the unlabeled dataset into the labeled dataset, ensuring that the updated labeled dataset follows a known distribution; (ii) we then construct a Bayes-optimal classifier using logit adjustment based on the updated labeled data distribution; (iii) this improved classifier subsequently helps identify more reliable pseudo-labels in the next training step. We further theoretically prove that this optimization cycle can significantly reduce the generalization error under some conditions. Additionally, we propose a class-aware adaptive augmentation module to further improve the representation of minority classes, and an auxiliary branch to maximize data utilization by leveraging all labeled and unlabeled samples. Comprehensive evaluations on various commonly used benchmark datasets show that CPG achieves consistent improvements, surpassing state-of-the-art methods by up to 15.97% in accuracy. The code is available at https://github.com/yaxinhou/CPG.

For agents

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

get_harvested_code_for_paper("2510.03993")
get_code_for_paper("2510.03993")
have("2510.03993")

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

curl https://syntology.ai/api/ran/2510.03993.json

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

[![Syntology run record](https://syntology.ai/api/ran/2510.03993.svg)](https://syntology.ai/paper/2510.03993)

Connect an agent — have() is free.