SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2601.20072 · 2026

Semi-Supervised Masked Autoencoders: Unlocking Vision Transformer Potential with Limited Data

Mohammad Rostami, Nikhil Muralidhar, Huaxia Wang, Atik Faysal, Reihaneh Gh, Roshan

arXiv · PDF · Open in the Atlas

Code that ran

5 of 5 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (4 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 0 violated it and 5 have no contract verdict; 0 failures of our instrument; 0 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/2601.20072.json · badge: /api/ran/2601.20072.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
atik666/ssmae community
Papers with Code archive
5 ran · 0 no recorded run
FunctionStatusWhere it lives
MLP Ran
ran on a synthesized input · constructed an object; no result was computed
atik666/ssmae/ssmae.py
pointer only (licence: NONE) · get_code("9af55144ae0f62dd")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, atik666/ssmae 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.

MaskedAutoencoder Ran
ran on a synthesized input · constructed an object; no result was computed
atik666/ssmae/ssmae.py
pointer only (licence: NONE) · get_code("f20706e3f1976363")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, atik666/ssmae 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.

MultiHeadAttention Ran
ran on a synthesized input · constructed an object; no result was computed
atik666/ssmae/ssmae.py
pointer only (licence: NONE) · get_code("a68b851d53be71ff")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, atik666/ssmae 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.

PatchEmbedding Ran
ran on a synthesized input · constructed an object; no result was computed
atik666/ssmae/ssmae.py
pointer only (licence: NONE) · get_code("1aeec5c113afde14")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, atik666/ssmae 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.

TransformerBlock Ran
ran on a synthesized input
atik666/ssmae/ssmae.py
pointer only (licence: NONE) · get_code("439300399e4bce24")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, atik666/ssmae 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.

Also present in other papers' code

Of 5 samples lifted from this paper's linked repositories, 5 carry a function identity and 0 do not. Of the 5 distinct functions with an identity, 0 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 0 later) and 5 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.

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

We address the challenge of training Vision Transformers (ViTs) when labeled data is scarce but unlabeled data is abundant. We propose Semi-Supervised Masked Autoencoder (SSMAE), a framework that jointly optimizes masked image reconstruction and classification using both unlabeled and labeled samples with dynamically selected pseudo-labels. SSMAE introduces a validation-driven gating mechanism that activates pseudo-labeling only after the model achieves reliable, highconfidence predictions that are consistent across both weakly and strongly augmented views of the same image, reducing confirmation bias. On CIFAR-10 and CIFAR-100, SSMAE consistently outperforms supervised ViT and fine-tuned MAE, with the largest gains in low-label regimes (+9.24% over ViT on CIFAR-10 with 10% labels). Our results demonstrate that when pseudolabels are introduced is as important as how they are generated for data-efficient transformer training. Codes are available at https://github.com/atik666/ssmae.

For agents

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

get_harvested_code_for_paper("2601.20072")
get_code_for_paper("2601.20072")
have("2601.20072")

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

curl https://syntology.ai/api/ran/2601.20072.json

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

[![Syntology run record](https://syntology.ai/api/ran/2601.20072.svg)](https://syntology.ai/paper/2601.20072)

Connect an agent — have() is free.