SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2407.11734 · 2024

Multi-Modal and Multi-Attribute Generation of Single Cells with CFGen

arXiv · PDF · Open in the Atlas

Code that ran

5 of 7 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 0 have no contract verdict; 4 failures of our instrument; 2 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/2407.11734.json · badge: /api/ran/2407.11734.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
theislab/CFGen canonical (classifier label)
classifier basis: census
5 ran · 2 no recorded run
FunctionStatusWhere it lives
compute_pairwise_distance Ran
ran, honoured the contract we drafted
theislab/CFGen/cfgen/eval/distribution_distances.py
code served (permissive licence) · get_code("6e6ba2d3fe1b0791")
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 ndarray, ndim 2, dtype family float, shape (2, 3) 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
import sklearn.metrics

# Create sample data
np.random.seed(0)
data_x = np.random.randn(2, 4).astype(np.float32)
data_y = np.random.randn(3, 4).astype(np.float32)

ARGS = {
    "data_x": data_x,
    "data_y": data_y,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, sklearn — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type ndarray, ndim 2, dtype family float, shape (2, 3) — shape (2, 3) 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
get_kth_value Ran
ran; our contract draft was wrong, not the code
theislab/CFGen/cfgen/eval/distribution_distances.py
code served (permissive licence) · get_code("280348f666658113")
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 ndarray, ndim 2, dtype family float, shape (2, 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 numpy as np

# Construct a small unsorted array with distinct dimensions
unsorted = np.array([
    [[9, 3, 7, 1], [5, 2, 8, 4]],
    [[6, 1, 9, 2], [3, 7, 4, 5]]
], dtype=np.float32)

# k should be a small positive integer less than the size along the axis
k = 2

# axis specifies which dimension to partition along
axis = -1

ARGS = {
    "unsorted": unsorted,
    "k": k,
    "axis": axis
}
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 ndarray, ndim 2, dtype family float, shape (2, 2) — shape (2, 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
linear_mmd2 Ran
ran; our contract draft was wrong, not the code
theislab/CFGen/cfgen/eval/mmd.py
code served (permissive licence) · get_code("bb890357a4a87c70")
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 two tensors f_of_X and f_of_Y
# It computes delta = f_of_X - f_of_Y
# Then accesses delta[:-1] and delta[1:], treating them as having shape (batch_size-1, features)
# It calls .sum(1) on the element-wise product, suggesting 2D tensors
# Finally it calls torch.mean on the result

# Create two tensors with shape (batch_size, features)
# Using batch_size=2 and features=4 as specified
f_of_X = torch.randn(2, 4)
f_of_Y = torch.randn(2, 4)

ARGS = {
    "f_of_X": f_of_X,
    "f_of_Y": f_of_Y,
}
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
mix_rbf_mmd2 Ran
ran; our contract draft was wrong, not the code
theislab/CFGen/cfgen/eval/mmd.py
pointer only (licence: MIT); the stored copy get_code serves, from msesia/deepknockoffs, is pointer only (licence: GPL-3.0) · get_code("661038d37be136e9")
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 msesia/deepknockoffs, and GPL-3.0, as GitHub detects it on that repository, is not in the permissive set Syntology serves inline. 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.

poly_mmd2 Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
theislab/CFGen/cfgen/eval/mmd.py
code served (permissive licence) · get_code("9970f30509d9c6ff")
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)

# Create small tensors for f_of_X and f_of_Y
# The function uses slicing [:-1] and [1:], so we need at least 2 elements
# Each element is summed over dimension 1, so we need a 2D tensor
# Let's make them (batch_size, feature_dim) = (3, 4) so slicing gives (2, 4)
f_of_X = torch.randn(3, 4)
f_of_Y = torch.randn(3, 4)

# Parameters for the function
d = 2
alpha = 1.0
c = 2.0

ARGS = {
    "f_of_X": f_of_X,
    "f_of_Y": f_of_Y,
    "d": d,
    "alpha": alpha,
    "c": c,
}
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
process_labels Not yet run
unverified (harvested, no recorded run)
theislab/CFGen/cfgen/eval/compute_evaluation_metrics.py
code served (permissive licence) · get_code("370a184a7bada287")
How it ran

no invocation recorded.

wasserstein Not yet run
unverified (harvested, no recorded run)
theislab/CFGen/cfgen/eval/optimal_transport.py
code served (permissive licence) · get_code("32f49750b3c8c6fc")
How it ran

no invocation recorded.

Also present in other papers' code

Of 7 samples lifted from this paper's linked repositories, 7 carry a function identity and 0 do not. Of the 7 distinct functions with an identity, 4 are also present in other papers whose code we hold (4 with at least one paper dated earlier, 0 the same month, 2 later) and 3 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
get_kth_value 5 other papers
4 dated earlier, 1 later · 1 only as an assembly brick
2002.09797 (2020-02)
Reliable Fidelity and Diversity Metrics for Generative Models
2103.09396 (2021-03)
Pros and Cons of GAN Evaluation Measures: New Developments
2105.14230 (2021-05)
Transforming the Latent Space of StyleGAN for Real Face Editing
and 2 more not named here
linear_mmd2 3 other papers
2 dated earlier, 1 later
2402.05098 (2024-02)
Improved off-policy training of diffusion samplers
2403.00999 (2024-03)
Distributional Dataset Distillation with Subtask Decomposition
2410.04386 (2024-10)
Data Distribution Valuation
poly_mmd2 2 other papers
2 dated earlier
2402.05098 (2024-02)
Improved off-policy training of diffusion samplers
2403.00999 (2024-03)
Distributional Dataset Distillation with Subtask Decomposition
mix_rbf_mmd2 1 other paper
1 dated earlier
2106.01528 (2021-06)
Normalizing Flows for Knockoff-free Controlled Feature Selection

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

Generative modeling of single-cell RNA-seq data is crucial for tasks like trajectory inference, batch effect removal, and simulation of realistic cellular data. However, recent deep generative models simulating synthetic single cells from noise operate on pre-processed continuous gene expression approximations, overlooking the discrete nature of single-cell data, which limits their effectiveness and hinders the incorporation of robust noise models. Additionally, aspects like controllable multi-modal and multi-label generation of cellular data remain underexplored. This work introduces CellFlow for Generation (CFGen), a flow-based conditional generative model that preserves the inherent discreteness of single-cell data. CFGen generates whole-genome multi-modal single-cell data reliably, improving the recovery of crucial biological data characteristics while tackling relevant generative tasks such as rare cell type augmentation and batch correction. We also introduce a novel framework for compositional data generation using Flow Matching. By showcasing CFGen on a diverse set of biological datasets and settings, we provide evidence of its value to the fields of computational biology and deep generative models.

For agents

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

get_harvested_code_for_paper("2407.11734")
get_code_for_paper("2407.11734")
have("2407.11734")

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

curl https://syntology.ai/api/ran/2407.11734.json

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

[![Syntology run record](https://syntology.ai/api/ran/2407.11734.svg)](https://syntology.ai/paper/2407.11734)

Connect an agent — have() is free.