SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2005.02359 · ICLR · 2020

Classification-Based Anomaly Detection for General Data

Liron Bergman, Yedid Hoshen

arXiv · PDF · Open in the Atlas

Code that ran

5 of 10 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (3 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 0 violated it and 5 have no contract verdict; 0 failures of our instrument; 5 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/2005.02359.json · badge: /api/ran/2005.02359.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
lironber/GOAD community
Papers with Code archive
3 ran · 1 no recorded run
xuhongzuo/DeepOD community
Papers with Code archive
2 ran · 4 no recorded run
FunctionStatusWhere it lives
BasicBlock Ran
ran on a synthesized input · constructed an object; no result was computed
lironber/GOAD/opt_tc.py
pointer only (licence: NOASSERTION) · get_code("cf4931227198dd5e")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, lironber/GOAD (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.

ConvNet Ran
ran on a synthesized input
xuhongzuo/DeepOD/deepod/models/tabular/goad.py
code served (permissive licence) · get_code("51a1f05a69ec1e74")
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 3, 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 importlib

def _instantiate_class(module_name: str, class_name: str):
    module = importlib.import_module(module_name)
    class_ = getattr(module, class_name)
    return class_()

class ConvNet(torch.nn.Module):
    """Convolutional Network

    Args:
        n_features (int):
            number of input data features
        kernel_size (int):
            kernel size (Default=1)
        n_hidden (int):
            number of hidden units in hidden layers (Default=8)
        n_layers (int):
            number of layers (Default=5)
        activation (str):
            name of activation layer,
            activation should be implemented in torch.nn.module.activation
            (Default='ReLU')
        bias (bool):
            use bias or not
            (Default=False)

    """

    def __init__(self, n_features, kernel_size=1, n_hidden=8, n_layers=5, activation='ReLU', bias=False):
        super(ConvNet, self).__init__()
        self.layers = []
        in_channels = n_features
        for i in range(n_layers + 1):
            self.layers += [torch.nn.Conv1d(in_channels, n_hidden, kernel_size=kernel_size, bias=bias)]
            if i != n_layers:
                self.layers += [_instantiate_class(module_name='torch.nn.modules.activation', class_name=activation)]
            in_channels = n_hidden
        self.net = torch.nn.Sequential(*self.layers)
        return

    def forward(self, x):
        return self.net(x)


INIT_ARGS = {
    'n_features': 4,
    'kernel_size': 1,
    'n_hidden': 8,
    'n_layers': 2,
    'activation': 'ReLU',
    'bias': False,
}

ARGS = {
    'x': torch.randn(2, 4, 3),
}

if __name__ == '__main__':
    model = ConvNet(**INIT_ARGS)
    output = model(**ARGS)
    print(f"Output shape: {output.shape}")
    print(f"Output: {output}")
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 3, 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)
GoadNet Ran
ran on a synthesized input
xuhongzuo/DeepOD/deepod/models/tabular/goad.py
code served (permissive licence) · get_code("4b1b91ea3ab31366")
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 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

INIT_ARGS = {
    'n_input': 4,
    'kernel_size': 1,
    'n_hidden': 8,
    'n_layers': 2,
    'n_output': 16,
    'activation': 'LeakyReLU',
    'bias': False,
}

ARGS = {
    'x': torch.randn(2, 4, 3),
}
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 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: torch and numpy seeded to 0 by the harness immediately before the class was constructed from INIT_ARGS (fixture_check.py)
TransClassifier Ran
ran on a synthesized input · constructed an object; no result was computed
lironber/GOAD/opt_tc.py
pointer only (licence: NOASSERTION) · get_code("ce56fb1d9e246c60")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, lironber/GOAD (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.

WideResNet Ran
ran on a synthesized input · constructed an object; no result was computed
lironber/GOAD/opt_tc.py
pointer only (licence: NOASSERTION) · get_code("e078996c88b6841f")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, lironber/GOAD (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.

BaseDeepAD Not yet run
unverified (harvested, no recorded run)
xuhongzuo/DeepOD/deepod/models/tabular/goad.py
code served (permissive licence) · get_code("50858634cfdf1e31")
How it ran

no invocation recorded.

GOAD Not yet run
unverified (harvested, no recorded run)
xuhongzuo/DeepOD/deepod/models/tabular/goad.py
code served (permissive licence) · get_code("a3682ac4cb5c81da")
How it ran

no invocation recorded.

GoadLoss Not yet run
unverified (harvested, no recorded run)
xuhongzuo/DeepOD/deepod/models/tabular/goad.py
code served (permissive licence) · get_code("6e0c09bc42f6e2c2")
How it ran

no invocation recorded.

tc_loss Not yet run
unverified (harvested, no recorded run)
lironber/GOAD/opt_tc.py
pointer only (licence: NOASSERTION) · get_code("145b6369ec05d217")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, lironber/GOAD (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. No invocation recorded.

weights_init Not yet run
unverified (harvested, no recorded run)
xuhongzuo/DeepOD/deepod/models/tabular/goad.py
code served (permissive licence) · get_code("058e8db0c4bedef9")
How it ran

no invocation recorded.

Also present in other papers' code

Of 10 samples lifted from this paper's linked repositories, 10 carry a function identity and 0 do not. Of the 10 distinct functions with an identity, 2 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 2 later) and 8 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
tc_loss
brick of this paper's assembly: loss
2 other papers
1 later, 1 undated
2109.14155 (2021-09)
Customs Fraud Detection in the Presence of Concept Drift
openreview_OVVsfomN1P
Denoising without Diffusion: Fixed-Noise Denoiser Anomaly Detection in Tabular Data
BaseDeepAD
brick of this paper's assembly: helper
1 other paper
1 later
2305.16114 (2023-05)
Fascinating Supervisory Signals and Where to Find Them: Deep Anomaly Detection with Scale Learning

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, finding patterns that substantially deviate from those seen previously, is one of the fundamental problems of artificial intelligence. Recently, classification-based methods were shown to achieve superior results on this task. In this work, we present a unifying view and propose an open-set method, GOAD, to relax current generalization assumptions. Furthermore, we extend the applicability of transformation-based methods to non-image data using random affine transformations. Our method is shown to obtain state-of-the-art accuracy and is applicable to broad data types. The strong performance of our method is extensively validated on multiple datasets from different domains.

For agents

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

get_harvested_code_for_paper("2005.02359")
get_code_for_paper("2005.02359")
have("2005.02359")

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

curl https://syntology.ai/api/ran/2005.02359.json

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

[![Syntology run record](https://syntology.ai/api/ran/2005.02359.svg)](https://syntology.ai/paper/2005.02359)

Connect an agent — have() is free.