SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2006.06755 · 2020

Conditional Sampling with Monotone GANs: from Generative Models to Likelihood-Free Inference

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; 2 honoured the contract we drafted, 0 violated it and 0 have 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/2006.06755.json · badge: /api/ran/2006.06755.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
baptistar/mgan canonical (classifier label)
classifier basis: classifier_2025
3 ran · 0 no recorded run
FunctionStatusWhere it lives
gradient_penalty Ran
ran, honoured the contract we drafted
baptistar/mgan/DarcyFlow/learn_mgan.py
code served (permissive licence) · get_code("25206bb7bf6ae8d9")
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 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 torch

torch.manual_seed(0)

# The function expects a gradient tensor
# It will:
# 1. View/reshape it to (batch_size, -1)
# 2. Calculate L2 norm along dim=1
# 3. Calculate mean of squared differences from 1

# Create a small gradient tensor: batch_size=2, flattened_dim=4
# This represents gradients of shape (2, 4) which could come from
# critic scores with respect to mixed images
gradient = torch.randn(2, 4, requires_grad=True)

ARGS = {
    "gradient": gradient
}
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 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
kde_2d Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
baptistar/mgan/utilities.py
code served (permissive licence) · get_code("002c1e91eb93c067")
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 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 numpy as np
from scipy import stats

torch.manual_seed(0)

# Create sample 2D data
# x and y should be tensors that can be concatenated and converted to numpy
x = torch.randn(5, 1)  # 5 samples, 1 dimension
y = torch.randn(5, 1)  # 5 samples, 1 dimension

# Create a grid option (2D array with shape (2, n_points))
x_min, x_max = -2.0, 2.0
y_min, y_max = -2.0, 2.0
x_grid, y_grid = np.meshgrid(np.linspace(x_min, x_max, 10), np.linspace(y_min, y_max, 10), indexing='ij')
grid = np.vstack([x_grid.ravel(), y_grid.ravel()])

ARGS = {
    'x': x,
    'y': y,
    'grid': None,
    's': 32
}
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 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
synthethic_out_pdf Ran
ran, honoured the contract we drafted
baptistar/mgan/utilities.py
code served (permissive licence) · get_code("977df7af50294ef6")
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, 1) 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)

# The function takes a single parameter 'x' which is a tensor
# Looking at the function body:
# - x.size(0) is used to get batch size
# - x[:, 0] and x[:, 1] are accessed, so x needs at least 2 columns
# - x.device and x.dtype are used
# - torch.logical_and, torch.abs, torch.tanh, torch.exp are applied to x

# Create a small tensor with batch size 2 and at least 2 features
x = torch.randn(2, 2, dtype=torch.float32)

ARGS = {
    "x": x
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
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 (2, 1) — shape (2, 1) 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 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 (0 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
gradient_penalty 3 other papers
3 later
2109.00666 (2021-09)
TabFairGAN: Fair Tabular Data Generation with Generative Adversarial Networks
2203.12297 (2022-03)
Increasing the accuracy and resolution of precipitation forecasts using deep generative models
2409.05215 (2024-09)
Synthetic Tabular Data Generation for Class Imbalance and Fairness: A Comparative Study

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 present a novel framework for conditional sampling of probability measures, using block triangular transport maps. We develop the theoretical foundations of block triangular transport in a Banach space setting, establishing general conditions under which conditional sampling can be achieved and drawing connections between monotone block triangular maps and optimal transport. Based on this theory, we then introduce a computational approach, called monotone generative adversarial networks (M-GANs), to learn suitable block triangular maps. Our algorithm uses only samples from the underlying joint probability measure and is hence likelihood-free. Numerical experiments with M-GAN demonstrate accurate sampling of conditional measures in synthetic examples, Bayesian inverse problems involving ordinary and partial differential equations, and probabilistic image in-painting.

For agents

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

get_harvested_code_for_paper("2006.06755")
get_code_for_paper("2006.06755")
have("2006.06755")

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

curl https://syntology.ai/api/ran/2006.06755.json

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

[![Syntology run record](https://syntology.ai/api/ran/2006.06755.svg)](https://syntology.ai/paper/2006.06755)

Connect an agent — have() is free.