SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1912.09784 · 2019

Triple Generative Adversarial Networks

arXiv · PDF · Open in the Atlas

Code that ran

5 of 8 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, 0 violated it and 4 have no contract verdict; 0 failures of our instrument; 3 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/1912.09784.json · badge: /api/ran/1912.09784.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
taufikxu/Triple-GAN canonical (classifier label)
classifier basis: census
5 ran · 3 no recorded run
FunctionStatusWhere it lives
linear_rampup Ran
ran, honoured the contract we drafted
taufikxu/Triple-GAN/library/loss_cla.py
pointer only (licence: MIT); the stored copy get_code serves, from y-research-sbu/otsurv, is pointer only (licence: NOASSERTION) · get_code("069122bd5268cc56")
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 y-research-sbu/otsurv, and GitHub could not classify the licence of that repository (NOASSERTION). 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.

loss_cross_entropy_ele Ran
ran on a synthesized input
taufikxu/Triple-GAN/library/loss_triplegan.py
code served (permissive licence) · get_code("d93071d043de21d5")
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 1, dtype family float, shape (2,) 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

torch.manual_seed(0)

# logits: output from model, shape (batch_size, num_classes)
# For batch_size=2, num_classes=4
logits = torch.randn(2, 4)

# label: target class indices, shape (batch_size,)
# For batch_size=2, values should be in range [0, num_classes)
label = torch.tensor([0, 2])

ARGS = {
    "logits": logits,
    "label": label
}
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 1, dtype family float, shape (2,) — shape (2,) 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
loss_hinge_dis Ran
ran on a synthesized input
taufikxu/Triple-GAN/library/loss_gan.py
code served (permissive licence) · get_code("1abccc079f315676")
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

torch.manual_seed(0)

class SimpleGenerator(nn.Module):
    def __init__(self):
        super().__init__()
        self.fc = nn.Linear(5, 4)
    
    def forward(self, z, label):
        # z: (batch, 5), label: (batch,)
        # Output fake image: (batch, 4)
        return self.fc(z)

class SimpleDiscriminator(nn.Module):
    def __init__(self):
        super().__init__()
        self.fc = nn.Linear(4, 1)
    
    def forward(self, x, label):
        # x: (batch, 4), label: (batch,)
        # Output discrimination score: (batch, 1)
        return self.fc(x)

netG = SimpleGenerator()
netD = SimpleDiscriminator()

# Batch size 2, feature dim 4
x_real = torch.randn(2, 4)
z_rand = torch.randn(2, 5)
label = torch.tensor([0, 1])

ARGS = {
    'netD': netD,
    'netG': netG,
    'x_real': x_real,
    'z_rand': z_rand,
    'label': label
}
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 — 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
sigmoid_rampdown Ran
ran on a synthesized input
taufikxu/Triple-GAN/library/loss_cla.py
code served (permissive licence) · get_code("2d9f6f3c7fd20be7")
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. 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 numpy as np

ARGS = {
    'global_step': 500,
    'rampdown_length': 100,
    'training_length': 1000,
}
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 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
sigmoid_rampup Ran
ran on a synthesized input
taufikxu/Triple-GAN/library/loss_cla.py
code served (permissive licence) · get_code("f8f34f7f96b293a1")
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

ARGS = {
    "global_step": 5,
    "rampup_length": 10
}
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
get_inception_score Not yet run
unverified (harvested, no recorded run)
taufikxu/Triple-GAN/library/eval_inception_score.py
code served (permissive licence) · get_code("335de19ad40af504")
How it ran

no invocation recorded.

loss_dcgan_dis Not yet run
unverified (harvested, no recorded run)
taufikxu/Triple-GAN/library/loss_gan.py
code served (permissive licence) · get_code("ae6e6873858f8ddf")
How it ran

no invocation recorded.

loss_dcgan_gen Not yet run
unverified (harvested, no recorded run)
taufikxu/Triple-GAN/library/loss_gan.py
code served (permissive licence) · get_code("98b3c5751e09b90b")
How it ran

no invocation recorded.

Also present in other papers' code

Of 8 samples lifted from this paper's linked repositories, 8 carry a function identity and 0 do not. Of the 8 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 7 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
linear_rampup 16 other papers
3 dated earlier, 13 later
1904.04717 (2019-04)
Label Propagation for Deep Semi-supervised Learning
1907.07034 (2019-07)
Uncertainty-aware Self-ensembling Model for Semi-supervised 3D Left Atrium Segmentation
1911.08177 (2019-11)
Rethinking deep active learning: Using unlabeled data at model training
and 13 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

We propose a unified game-theoretical framework to perform classification and conditional image generation given limited supervision. It is formulated as a three-player minimax game consisting of a generator, a classifier and a discriminator, and therefore is referred to as Triple Generative Adversarial Network (Triple-GAN). The generator and the classifier characterize the conditional distributions between images and labels to perform conditional generation and classification, respectively. The discriminator solely focuses on identifying fake image-label pairs. Under a nonparametric assumption, we prove the unique equilibrium of the game is that the distributions characterized by the generator and the classifier converge to the data distribution. As a byproduct of the three-player mechanism, Triple-GAN is flexible to incorporate different semi-supervised classifiers and GAN architectures. We evaluate Triple-GAN in two challenging settings, namely, semi-supervised learning and the extreme low data regime. In both settings, Triple-GAN can achieve excellent classification results and generate meaningful samples in a specific class simultaneously. In particular, using a commonly adopted 13-layer CNN classifier, Triple-GAN outperforms extensive semi-supervised learning methods substantially on more than 10 benchmarks no matter data augmentation is applied or not.

For agents

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

get_harvested_code_for_paper("1912.09784")
get_code_for_paper("1912.09784")
have("1912.09784")

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

curl https://syntology.ai/api/ran/1912.09784.json

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

[![Syntology run record](https://syntology.ai/api/ran/1912.09784.svg)](https://syntology.ai/paper/1912.09784)

Connect an agent — have() is free.