SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1907.05600 · 2019

Generative Modeling by Estimating Gradients of the Data Distribution

Yang Song, Stefano Ermon

arXiv · PDF · Open in the Atlas

Code that ran

14 of 22 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (9 of them constructed an object rather than computing a result; 1 honoured the contract we drafted, 0 violated it and 10 have no contract verdict; 3 failures of our instrument; 8 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/1907.05600.json · badge: /api/ran/1907.05600.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
ermongroup/ncsnv2 community
Papers with Code archive
8 ran · 3 no recorded run
xiwei-cheng/chained_ld community
Papers with Code archive
3 ran · 0 no recorded run
Lornatang/PyTorch-NCSN community
Papers with Code archive
1 ran · 0 no recorded run
Xemnas0/NCSN-TF2.0 community
Papers with Code archive
1 ran · 0 no recorded run
guillaumeboniface/super_resolution community
Papers with Code archive
1 ran · 0 no recorded run
PeterZhizhin/HSE-DeepLearning-NCSN community
Papers with Code archive
0 ran · 2 no recorded run
mbordyuh/score_matching community
Papers with Code archive
0 ran · 2 no recorded run
yang-song/score_sde_pytorch community
Papers with Code archive
0 ran · 1 no recorded run
FunctionStatusWhere it lives
ConditionalBatchNorm2d Ran
ran on a synthesized input · constructed an object; no result was computed
ermongroup/ncsnv2/models/ncsnv2.py
code served (permissive licence) · get_code("a36c0d3f631164cf")
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 an instance of its own class, ConditionalBatchNorm2d: the run constructed the object and did not call it, so no result was computed. 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)

# ConditionalBatchNorm2d constructor parameters:
# - num_features: int (number of channels)
# - num_classes: int (number of classes for embedding)
# - bias: bool (whether to use bias)

ARGS = {
    "num_features": 4,
    "num_classes": 3,
    "bias": True,
}
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 ConditionalBatchNorm2d — the run constructed an instance of its own class and did not call it; no shape is stated — the instrument coerces any output to an array; for a ConditionalBatchNorm2d output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not 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
ConditionalInstanceNorm2d Ran
ran on a synthesized input · constructed an object; no result was computed
ermongroup/ncsnv2/models/ncsnv2.py
code served (permissive licence) · get_code("b67d9759d330f8e9")
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 an instance of its own class, ConditionalInstanceNorm2d: the run constructed the object and did not call it, so no result was computed. 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 ConditionalInstanceNorm2d(nn.Module):

    def __init__(self, num_features, num_classes, bias=True):
        super().__init__()
        self.num_features = num_features
        self.bias = bias
        self.instance_norm = nn.InstanceNorm2d(num_features, affine=False, track_running_stats=False)
        if bias:
            self.embed = nn.Embedding(num_classes, num_features * 2)
            self.embed.weight.data[:, :num_features].uniform_()
            self.embed.weight.data[:, num_features:].zero_()
        else:
            self.embed = nn.Embedding(num_classes, num_features)
            self.embed.weight.data.uniform_()

    def forward(self, x, y):
        h = self.instance_norm(x)
        if self.bias:
            gamma, beta = self.embed(y).chunk(2, dim=-1)
            out = gamma.view(-1, self.num_features, 1, 1) * h + beta.view(-1, self.num_features, 1, 1)
        else:
            gamma = self.embed(y)
            out = gamma.view(-1, self.num_features, 1, 1) * h
        return out

ARGS = {
    "num_features": 4,
    "num_classes": 3,
    "bias": True
}
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 ConditionalInstanceNorm2d — the run constructed an instance of its own class and did not call it; no shape is stated — the instrument coerces any output to an array; for a ConditionalInstanceNorm2d output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not 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
ConditionalInstanceNorm2dPlus Ran
ran on a synthesized input · constructed an object; no result was computed
ermongroup/ncsnv2/models/ncsnv2.py
code served (permissive licence) · get_code("543e9573790e3f36")
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 an instance of its own class, ConditionalInstanceNorm2dPlus: the run constructed the object and did not call it, so no result was computed. 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 ConditionalInstanceNorm2dPlus(nn.Module):

    def __init__(self, num_features, num_classes, bias=True):
        super().__init__()
        self.num_features = num_features
        self.bias = bias
        self.instance_norm = nn.InstanceNorm2d(num_features, affine=False, track_running_stats=False)
        if bias:
            self.embed = nn.Embedding(num_classes, num_features * 3)
            self.embed.weight.data[:, :2 * num_features].normal_(1, 0.02)
            self.embed.weight.data[:, 2 * num_features:].zero_()
        else:
            self.embed = nn.Embedding(num_classes, 2 * num_features)
            self.embed.weight.data.normal_(1, 0.02)

    def forward(self, x, y):
        means = torch.mean(x, dim=(2, 3))
        m = torch.mean(means, dim=-1, keepdim=True)
        v = torch.var(means, dim=-1, keepdim=True)
        means = (means - m) / torch.sqrt(v + 1e-05)
        h = self.instance_norm(x)
        if self.bias:
            gamma, alpha, beta = self.embed(y).chunk(3, dim=-1)
            h = h + means[..., None, None] * alpha[..., None, None]
            out = gamma.view(-1, self.num_features, 1, 1) * h + beta.view(-1, self.num_features, 1, 1)
        else:
            gamma, alpha = self.embed(y).chunk(2, dim=-1)
            h = h + means[..., None, None] * alpha[..., None, None]
            out = gamma.view(-1, self.num_features, 1, 1) * h
        return out


num_features = 4
num_classes = 5
bias = True

model = ConditionalInstanceNorm2dPlus(num_features=num_features, num_classes=num_classes, bias=bias)

x = torch.randn(2, num_features, 3, 3)
y = torch.randint(0, num_classes, (2,))

ARGS = {
    "num_features": num_features,
    "num_classes": num_classes,
    "bias": bias
}
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 ConditionalInstanceNorm2dPlus — the run constructed an instance of its own class and did not call it; no shape is stated — the instrument coerces any output to an array; for a ConditionalInstanceNorm2dPlus output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not 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
ConditionalNoneNorm2d Ran
ran on a synthesized input · constructed an object; no result was computed
ermongroup/ncsnv2/models/ncsnv2.py
code served (permissive licence) · get_code("28b6b8fdea88c99d")
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 an instance of its own class, ConditionalNoneNorm2d: the run constructed the object and did not call it, so no result was computed. 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)

# ConditionalNoneNorm2d takes:
# - num_features: int - number of features/channels
# - num_classes: int - number of classes for embedding
# - bias: bool - whether to use bias

# The forward method expects:
# - x: tensor of shape (batch, num_features, height, width)
# - y: tensor of class indices of shape (batch,)

# Create a simple instance to test
num_features = 4
num_classes = 3

ARGS = {
    "num_features": num_features,
    "num_classes": num_classes,
    "bias": True
}
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 ConditionalNoneNorm2d — the run constructed an instance of its own class and did not call it; no shape is stated — the instrument coerces any output to an array; for a ConditionalNoneNorm2d output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not 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
InstanceNorm2dPlus Ran
ran on a synthesized input · constructed an object; no result was computed
ermongroup/ncsnv2/models/ncsnv2.py
code served (permissive licence) · get_code("d217a4b1f1925355")
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 an instance of its own class, InstanceNorm2dPlus: the run constructed the object and did not call it, so no result was computed. 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)

# Create an instance of InstanceNorm2dPlus with num_features=4 and bias=True
num_features = 4
bias = True

# Create a dummy input tensor: (batch_size=2, channels=4, height=3, width=3)
x = torch.randn(2, 4, 3, 3)

ARGS = {
    "num_features": num_features,
    "bias": bias,
}
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 InstanceNorm2dPlus — the run constructed an instance of its own class and did not call it; no shape is stated — the instrument coerces any output to an array; for a InstanceNorm2dPlus output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not 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
NoneNorm2d Ran
ran on a synthesized input · constructed an object; no result was computed
ermongroup/ncsnv2/models/ncsnv2.py
code served (permissive licence) · get_code("f02dfb63731445ee")
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 an instance of its own class, NoneNorm2d: the run constructed the object and did not call it, so no result was computed. 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)

ARGS = {
    'num_features': 4,
    'bias': True
}
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 NoneNorm2d — the run constructed an instance of its own class and did not call it; no shape is stated — the instrument coerces any output to an array; for a NoneNorm2d output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not 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
ResNetScore Ran
ran on a synthesized input · constructed an object; no result was computed
xiwei-cheng/chained_ld/models/scorenet.py
pointer only (licence: NONE) · get_code("55fdb754c0cda85c")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, xiwei-cheng/chained_ld 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.

ResnetBlock Ran
ran on a synthesized input · constructed an object; no result was computed
xiwei-cheng/chained_ld/models/scorenet.py
pointer only (licence: NONE) · get_code("495f6791fda7d15e")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, xiwei-cheng/chained_ld 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.

Score Ran
ran on a synthesized input
Lornatang/PyTorch-NCSN/models/scorenet.py
code served (permissive licence) · get_code("04ab830c8352fa59")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, class construct-then-call prompt, model not recorded) and returned Tensor, ndim 4, 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 torch
import torch.nn as nn
from types import SimpleNamespace

# Build a minimal config object
config = SimpleNamespace()
config.model = SimpleNamespace()
config.model.nef = 8  # small number of filters

config.data = SimpleNamespace()
config.data.channels = 1  # grayscale

config.training = SimpleNamespace()
config.training.ngpu = 1  # single GPU (CPU in this case)

INIT_ARGS = {
    'config': config
}

# Create a batch of 2 images with 1 channel, 28x28 pixels
# The network expects 28x28 based on the fc layer definition
x = torch.randn(2, 1, 28, 28)

ARGS = {
    'x': x
}
Setup block drafted by
a language model, class construct-then-call prompt, model not recorded
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 4, dtype family float — no output shape is stated: observe_signature.py observed this class with its constructor sizes canonicalised where it could, which the node does not record, so its shape is not stated as this setup block's
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: torch and numpy seeded to 0 by the harness immediately before the class was constructed from INIT_ARGS (fixture_check.py)
VarianceNorm2d Ran
ran on a synthesized input · constructed an object; no result was computed
ermongroup/ncsnv2/models/ncsnv2.py
code served (permissive licence) · get_code("2ceaba81d90f5640")
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 an instance of its own class, VarianceNorm2d: the run constructed the object and did not call it, so no result was computed. 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)

# VarianceNorm2d expects:
# - num_features: int (number of channels)
# - bias: bool (optional, defaults to False)

ARGS = {
    "num_features": 4,
    "bias": False,
}
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 VarianceNorm2d — the run constructed an instance of its own class and did not call it; no shape is stated — the instrument coerces any output to an array; for a VarianceNorm2d output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not 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
dsm_loss Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
Xemnas0/NCSN-TF2.0/losses/losses.py
pointer only (licence: NONE) · get_code("cff1bdc3f34eb185")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, Xemnas0/NCSN-TF2.0 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.

generate_noisy_image_batch Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
guillaumeboniface/super_resolution/sr3/noise_utils.py
pointer only (licence: NONE) · get_code("7c385bfdbcac9ebc")
How it ran

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

get_norm_layer Ran
ran; our contract draft was wrong, not the code
xiwei-cheng/chained_ld/models/scorenet.py
pointer only (licence: NONE) · get_code("05f3653dd76468d9")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, xiwei-cheng/chained_ld 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.

get_sigmas Ran
ran, honoured the contract we drafted
ermongroup/ncsnv2/models/ncsnv2.py
code served (permissive licence) · get_code("308c9ffe9425921a")
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 (5,) 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 torch

torch.manual_seed(0)

class Config:
    def __init__(self):
        self.device = 'cpu'
        self.model = ModelConfig()

class ModelConfig:
    def __init__(self):
        self.sigma_dist = 'geometric'
        self.sigma_begin = 0.1
        self.sigma_end = 10.0
        self.num_classes = 5

config = Config()

ARGS = {
    'config': config
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, 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 (5,) — shape (5,) 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
ConditionalVarianceNorm2d Not yet run
unverified (harvested, no recorded run)
ermongroup/ncsnv2/models/ncsnv2.py
code served (permissive licence) · get_code("2985c25add4b01dc")
How it ran

no invocation recorded.

NCSNv2 Not yet run
unverified (harvested, no recorded run)
ermongroup/ncsnv2/models/ncsnv2.py
code served (permissive licence) · get_code("9979dc271f83e97a")
How it ran

no invocation recorded.

SDE Not yet run
unverified (harvested, no recorded run)
yang-song/score_sde_pytorch/sde_lib.py
code served (permissive licence) · get_code("2149b8836f88ca16")
How it ran

no invocation recorded.

ToyExperimentDataset Not yet run
unverified (harvested, no recorded run)
PeterZhizhin/HSE-DeepLearning-NCSN/langevin.py
pointer only (licence: GPL-3.0) · get_code("45b72aead272b1d0")
How it ran

The body of this sample is withheld: GPL-3.0, as GitHub detects it on this paper's repository, PeterZhizhin/HSE-DeepLearning-NCSN, 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. No invocation recorded.

anneal_langevin Not yet run
unverified (harvested, no recorded run)
PeterZhizhin/HSE-DeepLearning-NCSN/langevin.py
pointer only (licence: GPL-3.0) · get_code("4208709a6798c6ab")
How it ran

The body of this sample is withheld: GPL-3.0, as GitHub detects it on this paper's repository, PeterZhizhin/HSE-DeepLearning-NCSN, 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. No invocation recorded.

get_normalization Not yet run
unverified (harvested, no recorded run)
ermongroup/ncsnv2/models/ncsnv2.py
code served (permissive licence) · get_code("c0db9b95b0194d7a")
How it ran

no invocation recorded.

jacobian Not yet run
unverified (harvested, no recorded run)
mbordyuh/score_matching/model.py
pointer only (licence: NONE) · get_code("1a2134b893169239")
How it ran

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

score_matching Not yet run
unverified (harvested, no recorded run)
mbordyuh/score_matching/model.py
pointer only (licence: NONE) · get_code("9a46fa84765de343")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, mbordyuh/score_matching 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 22 samples lifted from this paper's linked repositories, 22 carry a function identity and 0 do not. Of the 22 distinct functions with an identity, 12 are also present in other papers whose code we hold (1 with at least one paper dated earlier, 0 the same month, 12 later) and 10 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_norm_layer
brick of this paper's assembly: helper
4 other papers
1 dated earlier, 3 later
1807.09251 (2018-07)
GANimation: Anatomically-aware Facial Animation from a Single Image
1910.13049 (2019-10)
Category Anchor-Guided Unsupervised Domain Adaptation for Semantic Segmentation
2108.08012 (2021-08)
Multi-Anchor Active Domain Adaptation for Semantic Segmentation
and 1 more not named here
get_normalization
brick of this paper's assembly: helper
4 other papers
4 later · 1 only as an assembly brick
2105.14951 (2021-05)
SNIPS: Solving Noisy Inverse Problems Stochastically
2209.03954 (2022-09)
Learning to Generate Realistic LiDAR Point Clouds
2307.11308 (2023-07)
DPM-OT: A New Diffusion Probabilistic Model Based on Optimal Transport
and 1 more not named here
ConditionalBatchNorm2d
brick of this paper's assembly: helper
2 other papers
2 later · 2 only as an assembly brick
2105.14951 (2021-05)
SNIPS: Solving Noisy Inverse Problems Stochastically
2209.03954 (2022-09)
Learning to Generate Realistic LiDAR Point Clouds
ConditionalInstanceNorm2d
brick of this paper's assembly: helper
2 other papers
2 later · 2 only as an assembly brick
2105.14951 (2021-05)
SNIPS: Solving Noisy Inverse Problems Stochastically
2209.03954 (2022-09)
Learning to Generate Realistic LiDAR Point Clouds
ConditionalInstanceNorm2dPlus
brick of this paper's assembly: helper
2 other papers
2 later · 1 only as an assembly brick
2105.14951 (2021-05)
SNIPS: Solving Noisy Inverse Problems Stochastically
2209.03954 (2022-09)
Learning to Generate Realistic LiDAR Point Clouds
ConditionalNoneNorm2d
brick of this paper's assembly: helper
2 other papers
2 later · 2 only as an assembly brick
2105.14951 (2021-05)
SNIPS: Solving Noisy Inverse Problems Stochastically
2209.03954 (2022-09)
Learning to Generate Realistic LiDAR Point Clouds
ConditionalVarianceNorm2d
brick of this paper's assembly: helper
2 other papers
2 later · 1 only as an assembly brick
2105.14951 (2021-05)
SNIPS: Solving Noisy Inverse Problems Stochastically
2209.03954 (2022-09)
Learning to Generate Realistic LiDAR Point Clouds
InstanceNorm2dPlus
brick of this paper's assembly: helper
2 other papers
2 later · 1 only as an assembly brick
2105.14951 (2021-05)
SNIPS: Solving Noisy Inverse Problems Stochastically
2209.03954 (2022-09)
Learning to Generate Realistic LiDAR Point Clouds
NoneNorm2d
brick of this paper's assembly: helper
2 other papers
2 later · 2 only as an assembly brick
2105.14951 (2021-05)
SNIPS: Solving Noisy Inverse Problems Stochastically
2209.03954 (2022-09)
Learning to Generate Realistic LiDAR Point Clouds
VarianceNorm2d
brick of this paper's assembly: helper
2 other papers
2 later · 1 only as an assembly brick
2105.14951 (2021-05)
SNIPS: Solving Noisy Inverse Problems Stochastically
2209.03954 (2022-09)
Learning to Generate Realistic LiDAR Point Clouds
get_sigmas
brick of this paper's assembly: helper
2 other papers
2 later · 1 only as an assembly brick
2105.14951 (2021-05)
SNIPS: Solving Noisy Inverse Problems Stochastically
2209.03954 (2022-09)
Learning to Generate Realistic LiDAR Point Clouds
NCSNv2
brick of this paper's assembly: entry
1 other paper
1 later
2105.14951 (2021-05)
SNIPS: Solving Noisy Inverse Problems Stochastically

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 introduce a new generative model where samples are produced via Langevin dynamics using gradients of the data distribution estimated with score matching. Because gradients can be ill-defined and hard to estimate when the data resides on low-dimensional manifolds, we perturb the data with different levels of Gaussian noise, and jointly estimate the corresponding scores, i.e., the vector fields of gradients of the perturbed data distribution for all noise levels. For sampling, we propose an annealed Langevin dynamics where we use gradients corresponding to gradually decreasing noise levels as the sampling process gets closer to the data manifold. Our framework allows flexible model architectures, requires no sampling during training or the use of adversarial methods, and provides a learning objective that can be used for principled model comparisons. Our models produce samples comparable to GANs on MNIST, CelebA and CIFAR-10 datasets, achieving a new state-of-the-art inception score of 8.87 on CIFAR-10. Additionally, we demonstrate that our models learn effective representations via image inpainting experiments.

For agents

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

get_harvested_code_for_paper("1907.05600")
get_code_for_paper("1907.05600")
have("1907.05600")

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

curl https://syntology.ai/api/ran/1907.05600.json

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

[![Syntology run record](https://syntology.ai/api/ran/1907.05600.svg)](https://syntology.ai/paper/1907.05600)

Connect an agent — have() is free.