SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2202.07857 · ICLR · 2022

Graph-Augmented Normalizing Flows for Anomaly Detection of Multiple Time Series

Jie Chen, Enyan Dai

arXiv · PDF · Open in the Atlas

Code that ran

13 of 24 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (6 of them constructed an object rather than computing a result; 1 honoured the contract we drafted, 0 violated it and 11 have no contract verdict; 1 failure of our instrument; 11 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/2202.07857.json · badge: /api/ran/2202.07857.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
khalooei/ALOCC-CVPR2018 canonical (classifier label)
classifier basis not recorded on the link
3 ran · 6 no recorded run
enyandai/ganf community
Papers with Code archive
7 ran · 3 no recorded run
D3-AI/Orion community (classifier label)
classifier basis not recorded on the link
3 ran · 2 no recorded run
FunctionStatusWhere it lives
BatchNorm Ran
ran on a synthesized input · constructed an object; no result was computed
enyandai/ganf/models/GANF.py
pointer only (licence: NONE) · get_code("161cda5cabbb68c3")
How it ran

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

GNN Ran
ran on a synthesized input · constructed an object; no result was computed
enyandai/ganf/models/GANF.py
pointer only (licence: NONE) · get_code("9115fcfda4b932e3")
How it ran

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

LinearMaskedCoupling Ran
ran on a synthesized input · constructed an object; no result was computed
enyandai/ganf/models/GANF.py
pointer only (licence: NONE) · get_code("892f63ab6c5f2f84")
How it ran

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

MADE Ran
ran on a synthesized input · constructed an object; no result was computed
enyandai/ganf/models/GANF.py
pointer only (licence: NONE) · get_code("b5885c7b74843b05")
How it ran

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

MaskedLinear Ran
ran on a synthesized input · constructed an object; no result was computed
enyandai/ganf/models/GANF.py
pointer only (licence: NONE) · get_code("466de1ea4db58ebc")
How it ran

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

RealNVP Ran
ran on a synthesized input · constructed an object; no result was computed
enyandai/ganf/models/GANF.py
pointer only (licence: NONE) · get_code("0b745b7baaf925c0")
How it ran

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

conv_out_size_same Ran
ran, honoured the contract we drafted
khalooei/ALOCC-CVPR2018/utils.py
pointer only (licence: MIT); the stored copy get_code serves, from xtarx/Unsupervised-Anomaly-Detection-with-Generative-Adversarial-Networks, is pointer only (licence: NONE) · get_code("40125e1efb67fa92")
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 xtarx/Unsupervised-Anomaly-Detection-with-Generative-Adversarial-Networks, and GitHub detected no licence in that repository 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.

create_masks Ran
ran; our contract draft was wrong, not the code
enyandai/ganf/models/GANF.py
pointer only (licence: NONE) · get_code("e1243b39051334f9")
How it ran

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

download Ran
ran on a synthesized input
D3-AI/Orion/orion/data.py
code served (permissive licence) · get_code("b1b2e280183a2f78")
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 DataFrame. 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 os
import tempfile
import pandas as pd

# Create a temporary directory for testing
temp_dir = tempfile.mkdtemp()

# Create a test CSV file
test_csv_path = os.path.join(temp_dir, 'test_data.csv')
test_df = pd.DataFrame({
    'col1': [1, 2, 3, 4, 5],
    'col2': ['a', 'b', 'c', 'd', 'e'],
    'col3': [1.1, 2.2, 3.3, 4.4, 5.5]
})
test_df.to_csv(test_csv_path, index=False)

# Create subdirectory structure for nested path test
nested_dir = os.path.join(temp_dir, 'nested', 'path')
os.makedirs(nested_dir, exist_ok=True)
nested_csv_path = os.path.join(nested_dir, 'nested_data.csv')
nested_df = pd.DataFrame({
    'x': [10, 20, 30],
    'y': [100, 200, 300]
})
nested_df.to_csv(nested_csv_path, index=False)

ARGS = {
    'name': 'test_data',
    'test_size': None,
    'data_path': temp_dir
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
pandas — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type DataFrame — a DataFrame output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a DataFrame output the recorded ndim 2 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
format_csv Ran
ran on a synthesized input
D3-AI/Orion/orion/data.py
code served (permissive licence) · get_code("fc4f07905e94f225")
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 DataFrame. 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 pandas as pd
import numpy as np

# Create a small DataFrame with timestamp and value columns
data = {
    'timestamp': [1609459200, 1609545600],
    'value1': [10.5, 20.3],
    'value2': [30.1, 40.7]
}
df = pd.DataFrame(data)

# Define ARGS with all parameters
ARGS = {
    'df': df,
    'timestamp_column': 0,
    'value_columns': [1, 2]
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, pandas — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type DataFrame — a DataFrame output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a DataFrame output the recorded ndim 2 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
get_f1_scores Ran
ran on a synthesized input
D3-AI/Orion/orion/results.py
code served (permissive licence) · get_code("1267f9f70dc9e57e")
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 DataFrame. 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 pandas as pd
import numpy as np

# Create a minimal results dataframe that will be processed by get_f1_scores
# The function expects columns: dataset, pipeline, fp, fn, tp
results = pd.DataFrame({
    'dataset': ['MSL', 'MSL', 'SMAP', 'SMAP', 'UCR', 'UCR'],
    'pipeline': ['model_a', 'model_b', 'model_a', 'model_b', 'model_a', 'model_b'],
    'fp': [10, 5, 8, 3, 12, 7],
    'fn': [2, 4, 3, 1, 5, 2],
    'tp': [100, 105, 95, 98, 110, 108]
})

ARGS = {
    'results': results
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, pandas — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type DataFrame — a DataFrame output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a DataFrame output the recorded ndim 2 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
get_noisy_data Ran
ran on a synthesized input
khalooei/ALOCC-CVPR2018/kh_tools.py
code served (permissive licence) · get_code("489e2c5f7ad2b380")
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 3, dtype family float, shape (2, 4, 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

# The function expects 'data' to be an iterable of images
# Each image should be a 2D or 3D array that random_noise can process
# Creating small synthetic images for testing

# Create a batch of 2 small grayscale images (each 4x3)
image1 = np.random.rand(4, 3).astype(np.float64)
image2 = np.random.rand(4, 3).astype(np.float64)

data = [image1, image2]

ARGS = {
    "data": data
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, skimage — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type ndarray, ndim 3, dtype family float, shape (2, 4, 3) — shape (2, 4, 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
read_dataset_image_path Ran
ran on a synthesized input
khalooei/ALOCC-CVPR2018/kh_tools.py
code served (permissive licence) · get_code("3dff213b8ae5a2d4")
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 list, ndim 1, 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 os
import tempfile
import shutil

# Create a temporary directory structure that mimics a dataset
temp_dir = tempfile.mkdtemp()

# Create subdirectories (like class folders)
subdir1 = os.path.join(temp_dir, 'class1')
subdir2 = os.path.join(temp_dir, 'class2')
os.makedirs(subdir1)
os.makedirs(subdir2)

# Create dummy image files
open(os.path.join(subdir1, 'image1.jpg'), 'w').close()
open(os.path.join(subdir1, 'image2.jpg'), 'w').close()
open(os.path.join(subdir2, 'image3.jpg'), 'w').close()
open(os.path.join(subdir2, 'image4.jpg'), 'w').close()

ARGS = {
    's_dataset_url': temp_dir,
    'n_number_count': None
}
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 list, ndim 1, dtype family float — a list output has no array shape of its own; none is stated
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
FlowSequential Not yet run
unverified (harvested, no recorded run)
enyandai/ganf/models/GANF.py
pointer only (licence: NONE) · get_code("213315d48b01e0a7")
How it ran

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

GANF Not yet run
unverified (harvested, no recorded run)
enyandai/ganf/models/GANF.py
pointer only (licence: NONE) · get_code("2a25b017dff45e00")
How it ran

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

MAF Not yet run
unverified (harvested, no recorded run)
enyandai/ganf/models/GANF.py
pointer only (licence: NONE) · get_code("02e105c797e3990c")
How it ran

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

conv2d Not yet run
unverified (harvested, no recorded run)
khalooei/ALOCC-CVPR2018/ops.py
code served (permissive licence) · get_code("f0cb37d52c4b56e2")
How it ran

no invocation recorded.

conv_cond_concat Not yet run
unverified (harvested, no recorded run)
khalooei/ALOCC-CVPR2018/ops.py
code served (permissive licence) · get_code("97a17fbee43a92bd")
How it ran

no invocation recorded.

deconv2d Not yet run
unverified (harvested, no recorded run)
khalooei/ALOCC-CVPR2018/ops.py
code served (permissive licence) · get_code("f43eeb47efdaf9c4")
How it ran

no invocation recorded.

get_image Not yet run
unverified (harvested, no recorded run)
khalooei/ALOCC-CVPR2018/utils.py
code served (permissive licence) · get_code("a0b95d6b4e00d081")
How it ran

no invocation recorded.

get_image_Slicization Not yet run
unverified (harvested, no recorded run)
khalooei/ALOCC-CVPR2018/utils.py
code served (permissive licence) · get_code("0ac44cb4f2a04c3e")
How it ran

no invocation recorded.

get_summary_page Not yet run
unverified (harvested, no recorded run)
D3-AI/Orion/orion/results.py
code served (permissive licence) · get_code("6601ccd471fa6c41")
How it ran

no invocation recorded.

load_csv Not yet run
unverified (harvested, no recorded run)
D3-AI/Orion/orion/data.py
code served (permissive licence) · get_code("04aff2c366db2eed")
How it ran

no invocation recorded.

read_image_w_noise Not yet run
unverified (harvested, no recorded run)
khalooei/ALOCC-CVPR2018/kh_tools.py
code served (permissive licence) · get_code("4c27080e85e975e7")
How it ran

no invocation recorded.

Also present in other papers' code

Of 24 samples lifted from this paper's linked repositories, 24 carry a function identity and 0 do not. Of the 24 distinct functions with an identity, 8 are also present in other papers whose code we hold (7 with at least one paper dated earlier, 0 the same month, 2 later) and 16 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
conv_out_size_same 6 other papers
6 dated earlier
1511.06434 (2015-11)
Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks
1703.05921 (2017-03)
Unsupervised Anomaly Detection with Generative Adversarial Networks to Guide Marker Discovery
1804.04391 (2018-04)
MGGAN: Solving Mode Collapse using Manifold Guided Training
and 3 more not named here
conv2d 4 other papers
4 dated earlier
1609.07009 (2016-09)
Is the deconvolution layer the same as a convolutional layer?
1611.04488 (2016-11)
Generative Models and Model Criticism via Optimized Maximum Mean Discrepancy
1611.07004 (2016-11)
Image-to-Image Translation with Conditional Adversarial Networks
and 1 more not named here
FlowSequential
brick of this paper's assembly: helper
3 other papers
2 dated earlier, 1 later · 3 only as an assembly brick
1705.07057 (2017-05)
Masked Autoregressive Flow for Density Estimation
2103.15977 (2021-03)
Flow-based Kernel Prior with Application to Blind Super-Resolution
2406.09135 (2024-06)
AdaRevD: Adaptive Patch Exiting Reversible Decoder Pushes the Limit of Image Deblurring
conv_cond_concat 2 other papers
2 dated earlier
1703.05921 (2017-03)
Unsupervised Anomaly Detection with Generative Adversarial Networks to Guide Marker Discovery
1811.03205 (2018-11)
Robustness of Conditional GANs to Noisy Labels
create_masks
brick of this paper's assembly: helper
2 other papers
2 later
aaai_25623 (2023 (year only))
Detecting Multivariate Time Series Anomalies with Zero Known Label
2410.08877 (2024-10)
Interdependency Matters: Graph Alignment for Multivariate Time Series Anomaly Detection
MaskedLinear
brick of this paper's assembly: helper
1 other paper
1 dated earlier
1705.07057 (2017-05)
Masked Autoregressive Flow for Density Estimation
deconv2d 1 other paper
1 dated earlier
1811.03205 (2018-11)
Robustness of Conditional GANs to Noisy Labels
get_image 1 other paper
1 dated earlier
1811.03205 (2018-11)
Robustness of Conditional GANs to Noisy Labels

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

Anomaly detection is a widely studied task for a broad variety of data types; among them, multiple time series appear frequently in applications, including for example, power grids and traffic networks. Detecting anomalies for multiple time series, however, is a challenging subject, owing to the intricate interdependencies among the constituent series. We hypothesize that anomalies occur in low density regions of a distribution and explore the use of normalizing flows for unsupervised anomaly detection, because of their superior quality in density estimation. Moreover, we propose a novel flow model by imposing a Bayesian network among constituent series. A Bayesian network is a directed acyclic graph (DAG) that models causal relationships; it factorizes the joint probability of the series into the product of easy-to-evaluate conditional probabilities. We call such a graph-augmented normalizing flow approach GANF and propose joint estimation of the DAG with flow parameters. We conduct extensive experiments on real-world datasets and demonstrate the effectiveness of GANF for density estimation, anomaly detection, and identification of time series distribution drift.

For agents

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

get_harvested_code_for_paper("2202.07857")
get_code_for_paper("2202.07857")
have("2202.07857")

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

curl https://syntology.ai/api/ran/2202.07857.json

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

[![Syntology run record](https://syntology.ai/api/ran/2202.07857.svg)](https://syntology.ai/paper/2202.07857)

Connect an agent — have() is free.