SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2107.02408 · 2021

CoReD: Generalizing Fake Media Detection with Continual Representation using Distillation

arXiv · PDF · Open in the Atlas

Code that ran

8 of 15 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; 0 honoured the contract we drafted, 0 violated it and 3 have no contract verdict; 5 failures of our instrument; 7 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/2107.02408.json · badge: /api/ran/2107.02408.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
alsgkals2/CoReD_Released community (classifier label)
classifier basis not recorded on the link
7 ran · 5 no recorded run
alsgkals2/cored community (classifier label)
classifier basis not recorded on the link
1 ran · 2 no recorded run
FunctionStatusWhere it lives
GetListTeacherFeatureFakeReal Ran
ran on a synthesized input
alsgkals2/CoReD_Released/Function_CoReD.py
code served (permissive licence) · get_code("8530c4f7671d4a93")
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. The image it ran in was not recorded. The code mentions cuda, and the harness aliases cuda to the CPU for every sample; whether this run needed that is 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
import numpy as np

torch.manual_seed(0)

# Create a minimal model that has the required attributes and methods
class MinimalModel(nn.Module):
    def __init__(self):
        super().__init__()
        self.features = nn.Sequential(
            nn.Conv2d(3, 8, kernel_size=3, padding=1),
            nn.ReLU()
        )
        self.fc = nn.Linear(8 * 4 * 4, 2)
    
    def forward(self, x):
        x = self.features(x)
        x = x.view(x.size(0), -1)
        x = self.fc(x)
        return x
    
    def extract_features(self, x):
        return self.features(x)

# Create model instance
model = MinimalModel()

# Create minimal data loaders
# Structure: list of 2 elements, each containing list of dataloaders per batch
# Each dataloader is either empty (None) or contains (img, label) tuples

# Create small batches: batch_size=2, image channels=3, spatial dims=4x4
img1 = torch.randn(2, 3, 4, 4)
img2 = torch.randn(2, 3, 4, 4)
label1 = torch.tensor([0, 1])
label2 = torch.tensor([1, 0])

# Inner dataloader structure: list of (img, label) tuples
dataloader_batch1 = [(img1, label1), (img2, label2)]
dataloader_batch2 = [(img1, label1)]

# Outer loader structure: list of 2 elements (fake and real)
# Each element is a list of dataloaders
loader = [
    [dataloader_batch1, None, dataloader_batch2],
    [dataloader_batch2, dataloader_batch1, None]
]

ARGS = {
    'model': model,
    'loader': loader,
    'mode': 'Xception',
    'showScatter': False,
    'device': 'cpu'
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
matplotlib, numpy, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type list — a list 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
drop_connect Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
alsgkals2/CoReD_Released/utils.py
code served (permissive licence) · get_code("f1e3c822763f3ebb")
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 4, dtype family float, shape (2, 4, 3, 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 torch

torch.manual_seed(0)

# Construct arguments for drop_connect function
inputs = torch.randn(2, 4, 3, 5)  # BCWH format: batch=2, channels=4, width=3, height=5
p = 0.5  # probability of drop connection between 0 and 1
training = True  # boolean flag for training mode

ARGS = {
    "inputs": inputs,
    "p": p,
    "training": training
}
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 4, dtype family float, shape (2, 4, 3, 5) — shape (2, 4, 3, 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
get_params Ran
ran on a synthesized input
alsgkals2/CoReD_Released/TGD.py
code served (permissive licence) · get_code("a6a51242455508a3")
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 dict. 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 SimpleModel(nn.Module):
    def __init__(self):
        super().__init__()
        self.linear1 = nn.Linear(4, 3)
        self.linear2 = nn.Linear(3, 2)
    
    def forward(self, x):
        x = self.linear1(x)
        x = self.linear2(x)
        return x

model = SimpleModel()

ARGS = {
    "model": model
}
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 dict — a dict output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a dict 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
rand_bbox Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
alsgkals2/cored/Function_common.py
pointer only (licence: MIT); the stored copy get_code serves, from drimpossible/corrective-unlearning-bench, is pointer only (licence: GPL-3.0) · get_code("2e865549db6f7e9c")
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 drimpossible/corrective-unlearning-bench, 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.

round_filters Ran
ran; our contract draft was wrong, not the code
alsgkals2/CoReD_Released/utils.py
pointer only (licence: MIT); the stored copy get_code serves, from ZackZikaiXiao/FedGraB, is pointer only (licence: NONE) · get_code("bde7e7ccb8dae4f5")
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 ZackZikaiXiao/FedGraB, 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.

round_repeats Ran
ran; our contract draft was wrong, not the code
alsgkals2/CoReD_Released/utils.py
pointer only (licence: MIT); the stored copy get_code serves, from ZackZikaiXiao/FedGraB, is pointer only (licence: NONE) · get_code("70f48a3907311f52")
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 ZackZikaiXiao/FedGraB, 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.

xception Ran
ran; our contract draft was wrong, not the code
alsgkals2/CoReD_Released/xception_origin.py
pointer only (licence: MIT); the stored copy get_code serves, from razla/xai-based-detection-of-adversarial-attacks-on-deepfake-detectors, is pointer only (licence: NONE) · get_code("31914a9457df6d95")
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 razla/xai-based-detection-of-adversarial-attacks-on-deepfake-detectors, 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.

xception_concat Ran
ran on a synthesized input
alsgkals2/CoReD_Released/xception_origin.py
code served (permissive licence) · get_code("a4688c2b5f940c53")
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 Xception_concat. 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)

# The Xception_concat model expects:
# - input: a tensor of shape (batch_size, 15, height, width)
#   The first conv1 expects 15 input channels
#   The model processes images through various blocks
#   num_classes: number of output classes (default 1000)

# Create a small input tensor: batch_size=2, channels=15, height=4, width=4
input_tensor = torch.randn(2, 15, 4, 4)

ARGS = {
    'num_classes': 10
}
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 Xception_concat — a Xception_concat output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Xception_concat 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
Make_DataLoader Not yet run
unverified (harvested, no recorded run)
alsgkals2/CoReD_Released/Function_common.py
code served (permissive licence) · get_code("0b5386bdd86563dc")
How it ran

no invocation recorded.

Make_DataLoader Not yet run
unverified (harvested, no recorded run)
alsgkals2/cored/Function_common.py
code served (permissive licence) · get_code("8cfdd4cb2db988e7")
How it ran

no invocation recorded.

initialization Not yet run
unverified (harvested, no recorded run)
alsgkals2/CoReD_Released/Function_common.py
code served (permissive licence) · get_code("0948525602698fe1")
How it ran

no invocation recorded.

initialization Not yet run
unverified (harvested, no recorded run)
alsgkals2/cored/Function_common.py
code served (permissive licence) · get_code("018b4130520f8b58")
How it ran

no invocation recorded.

rand_bbox Not yet run
unverified (harvested, no recorded run)
alsgkals2/CoReD_Released/Function_common.py
pointer only (licence: MIT); the stored copy get_code serves, from deeplearning-wisc/dream-ood, is pointer only (licence: NOASSERTION) · get_code("d34a085d71b8f4b5")
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 deeplearning-wisc/dream-ood, and GitHub could not classify the licence of that repository (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.

reg_cls Not yet run
unverified (harvested, no recorded run)
alsgkals2/CoReD_Released/TGD.py
code served (permissive licence) · get_code("6e572e9393f8c9cd")
How it ran

no invocation recorded.

reg_l2sp Not yet run
unverified (harvested, no recorded run)
alsgkals2/CoReD_Released/TGD.py
code served (permissive licence) · get_code("3bb5ee319013ac13")
How it ran

no invocation recorded.

Also present in other papers' code

Of 15 samples lifted from this paper's linked repositories, 15 carry a function identity and 0 do not. Of the 15 distinct functions with an identity, 6 are also present in other papers whose code we hold (4 with at least one paper dated earlier, 3 the same month, 6 later) and 9 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
round_filters 31 other papers
14 dated earlier, 2 the same month, 15 later · 3 only as an assembly brick
1808.08127 (2018-08)
Recalibrating Fully Convolutional Networks with Spatial and Channel 'Squeeze & Excitation' Blocks
1905.11946 (2019-05)
EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks
1911.09070 (2019-11)
EfficientDet: Scalable and Efficient Object Detection
and 28 more not named here
round_repeats 30 other papers
15 dated earlier, 2 the same month, 13 later · 3 only as an assembly brick
1808.08127 (2018-08)
Recalibrating Fully Convolutional Networks with Spatial and Channel 'Squeeze & Excitation' Blocks
1905.11946 (2019-05)
EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks
1911.09070 (2019-11)
EfficientDet: Scalable and Efficient Object Detection
and 27 more not named here
drop_connect 23 other papers
3 dated earlier, 2 the same month, 18 later · 2 only as an assembly brick
1905.11946 (2019-05)
EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks
1912.01588 (2019-12)
Leveraging Procedural Generation to Benchmark Reinforcement Learning
2010.00475 (2020-10)
FSD50K: An Open Dataset of Human-Labeled Sound Events
and 20 more not named here
rand_bbox 13 other papers
7 dated earlier, 6 later
1905.04899 (2019-05)
CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Features
2002.11102 (2020-02)
On Feature Normalization and Data Augmentation
2003.05438 (2020-03)
Un-Mix: Rethinking Image Mixtures for Unsupervised Visual Representation Learning
and 10 more not named here
rand_bbox 1 other paper
1 later
2402.14015 (2024-02)
Corrective Machine Unlearning
xception 1 other paper
1 later
2403.02955 (2024-03)
XAI-Based Detection of Adversarial Attacks on Deepfake Detectors

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

Over the last few decades, artificial intelligence research has made tremendous strides, but it still heavily relies on fixed datasets in stationary environments. Continual learning is a growing field of research that examines how AI systems can learn sequentially from a continuous stream of linked data in the same way that biological systems do. Simultaneously, fake media such as deepfakes and synthetic face images have emerged as significant to current multimedia technologies. Recently, numerous method has been proposed which can detect deepfakes with high accuracy. However, they suffer significantly due to their reliance on fixed datasets in limited evaluation settings. Therefore, in this work, we apply continuous learning to neural networks' learning dynamics, emphasizing its potential to increase data efficiency significantly. We propose Continual Representation using Distillation (CoReD) method that employs the concept of Continual Learning (CL), Representation Learning (RL), and Knowledge Distillation (KD). We design CoReD to perform sequential domain adaptation tasks on new deepfake and GAN-generated synthetic face datasets, while effectively minimizing the catastrophic forgetting in a teacher-student model setting. Our extensive experimental results demonstrate that our method is efficient at domain adaptation to detect low-quality deepfakes videos and GAN-generated images from several datasets, outperforming the-state-of-art baseline methods.

For agents

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

get_harvested_code_for_paper("2107.02408")
get_code_for_paper("2107.02408")
have("2107.02408")

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

curl https://syntology.ai/api/ran/2107.02408.json

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

[![Syntology run record](https://syntology.ai/api/ran/2107.02408.svg)](https://syntology.ai/paper/2107.02408)

Connect an agent — have() is free.