SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2202.11202 · ICLR · 2023

Indiscriminate Poisoning Attacks on Unsupervised Contrastive Learning

Hao He, Dina Katabi, Kaiwen Zha

arXiv · PDF · Open in the Atlas

Code that ran

13 of 18 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (5 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 0 violated it and 9 have no contract verdict; 4 failures of our instrument; 5 no recorded run), measured 2026-11-22; 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/2202.11202.json · badge: /api/ran/2202.11202.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
kaiwenzha/contrastive-poisoning canonical (classifier label)
classifier basis: classifier_2025
13 ran · 5 no recorded run
FunctionStatusWhere it lives
BYOL Ran
ran on a synthesized input · constructed an object; no result was computed
kaiwenzha/contrastive-poisoning/model.py
code served (permissive licence) · get_code("f5329be21bc798d0")
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, BYOL: 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 a minimal backbone that outputs tensors of shape (batch_size, num_ftrs)
class MinimalBackbone(nn.Module):
    def __init__(self, out_features=512):
        super().__init__()
        self.linear = nn.Linear(4, out_features)
    
    def forward(self, x):
        return self.linear(x)

# Create backbone instance
backbone = MinimalBackbone(out_features=512)

ARGS = {
    "backbone": backbone,
    "num_ftrs": 512,
    "hidden_dim": 4096,
    "out_dim": 256,
    "m": 0.999,
    "allow_mmt_grad": 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 BYOL — 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 BYOL 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
BasicBlock Ran
ran on a synthesized input · constructed an object; no result was computed
kaiwenzha/contrastive-poisoning/model.py
code served (permissive licence) · get_code("e93841d2aa94ddad")
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, BasicBlock: 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)

# BasicBlock is initialized with:
# - in_planes: int (number of input channels)
# - planes: int (number of output channels)
# - stride: int (default 1)
# - is_last: bool (default False)

# The forward method expects input x to be a tensor with shape (batch, in_planes, height, width)
# It returns either out (a tensor) or (out, preact) tuple depending on is_last

ARGS = {
    "in_planes": 3,
    "planes": 4,
    "stride": 1,
    "is_last": 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 BasicBlock — 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 BasicBlock 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
Bottleneck Ran
ran on a synthesized input · constructed an object; no result was computed
kaiwenzha/contrastive-poisoning/model.py
code served (permissive licence) · get_code("613844ebc89b237b")
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, Bottleneck: 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 = {
    'in_planes': 64,
    'planes': 64,
    'stride': 1,
    'is_last': 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 Bottleneck — 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 Bottleneck 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
ResNet Ran
ran on a synthesized input
kaiwenzha/contrastive-poisoning/model.py
code served (permissive licence) · get_code("396b12c0d690c96b")
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 2, 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

# Import the block classes that ResNet needs
class BasicBlock(nn.Module):
    expansion = 1

    def __init__(self, in_planes, planes, stride=1, is_last=False):
        super(BasicBlock, self).__init__()
        self.is_last = is_last
        self.conv1 = nn.Conv2d(in_planes, planes, kernel_size=3, stride=stride, padding=1, bias=False)
        self.bn1 = nn.BatchNorm2d(planes)
        self.conv2 = nn.Conv2d(planes, planes, kernel_size=3, stride=1, padding=1, bias=False)
        self.bn2 = nn.BatchNorm2d(planes)
        self.shortcut = nn.Sequential()
        if stride != 1 or in_planes != self.expansion * planes:
            self.shortcut = nn.Sequential(nn.Conv2d(in_planes, self.expansion * planes, kernel_size=1, stride=stride, bias=False), nn.BatchNorm2d(self.expansion * planes))

    def forward(self, x):
        out = torch.nn.functional.relu(self.bn1(self.conv1(x)))
        out = self.bn2(self.conv2(out))
        out += self.shortcut(x)
        preact = out
        out = torch.nn.functional.relu(out)
        if self.is_last:
            return (out, preact)
        else:
            return out

class Bottleneck(nn.Module):
    expansion = 4

    def __init__(self, in_planes, planes, stride=1, is_last=False):
        super(Bottleneck, self).__init__()
        self.is_last = is_last
        self.conv1 = nn.Conv2d(in_planes, planes, kernel_size=1, bias=False)
        self.bn1 = nn.BatchNorm2d(planes)
        self.conv2 = nn.Conv2d(planes, planes, kernel_size=3, stride=stride, padding=1, bias=False)
        self.bn2 = nn.BatchNorm2d(planes)
        self.conv3 = nn.Conv2d(planes, self.expansion * planes, kernel_size=1, bias=False)
        self.bn3 = nn.BatchNorm2d(self.expansion * planes)
        self.shortcut = nn.Sequential()
        if stride != 1 or in_planes != self.expansion * planes:
            self.shortcut = nn.Sequential(nn.Conv2d(in_planes, self.expansion * planes, kernel_size=1, stride=stride, bias=False), nn.BatchNorm2d(self.expansion * planes))

    def forward(self, x):
        out = torch.nn.functional.relu(self.bn1(self.conv1(x)))
        out = torch.nn.functional.relu(self.bn2(self.conv2(out)))
        out = self.bn3(self.conv3(out))
        out += self.shortcut(x)
        preact = out
        out = torch.nn.functional.relu(out)
        if self.is_last:
            return (out, preact)
        else:
            return out

INIT_ARGS = {
    'block': BasicBlock,
    'num_blocks': [1, 1, 1, 1],
    'in_channel': 3,
    'zero_init_residual': False
}

ARGS = {
    'x': torch.randn(2, 3, 16, 16)
}
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 2, 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)
ResNetNoHead Ran
ran on a synthesized input · constructed an object; no result was computed
kaiwenzha/contrastive-poisoning/model.py
code served (permissive licence) · get_code("bb2b7357a288f84c")
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, ResNetNoHead: 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 = {
    'arch': 'resnet50'
}
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 ResNetNoHead — 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 ResNetNoHead 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
ResNetWithHead Ran
ran on a synthesized input · constructed an object; no result was computed
kaiwenzha/contrastive-poisoning/model.py
code served (permissive licence) · get_code("2e47d5200e06bb5d")
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, ResNetWithHead: 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 = {
    'arch': 'resnet50',
    'head': 'mlp',
    'feat_dim': 128
}
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 ResNetWithHead — 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 ResNetWithHead 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
TextFormat Ran
ran on a synthesized input
kaiwenzha/contrastive-poisoning/model.py
code served (permissive licence) · get_code("dd9595263567cf07")
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 str. 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 numpy as np

class TextFormat:
    ColorCode = {'black': '\x1b[30m', 'darkred': '\x1b[31m', 'darkgreen': '\x1b[32m', 'darkyellow': '\x1b[33m', 'darkblue': '\x1b[34m', 'darkpink': '\x1b[35m', 'darkcyan': '\x1b[36m', 'grey': '\x1b[37m', 'white': '\x1b[38m', 'darkgrey': '\x1b[90m', 'red': '\x1b[91m', 'green': '\x1b[92m', 'yellow': '\x1b[93m', 'blue': '\x1b[94m', 'pink': '\x1b[95m', 'cyan': '\x1b[96m'}
    StyleCode = {'normal': '\x1b[0m', 'bold': '\x1b[01m', 'disable': '\x1b[02m', 'underline': '\x1b[04m', 'reverse': '\x1b[07m', 'strikethrough': '\x1b[09m', 'invisible': '\x1b[08m'}
    EndCode = '\x1b[0m'

    @classmethod
    def format(cls, text, color='white'):
        return cls.ColorCode[color] + text + cls.EndCode


INIT_ARGS = {}

ARGS = {
    'text': 'Hello World',
    'color': 'green'
}

METHOD = 'format'

if __name__ == '__main__':
    instance = TextFormat(**INIT_ARGS)
    result = getattr(instance, METHOD)(**ARGS)
    print(result)
Setup block drafted by
a language model, class construct-then-call prompt, model not recorded
Imports
numpy, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type str — a str output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a str 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: torch and numpy seeded to 0 by the harness immediately before the class was constructed from INIT_ARGS (fixture_check.py)
_get_byol_mlp Ran
ran; our contract draft was wrong, not the code
kaiwenzha/contrastive-poisoning/model.py
code served (permissive licence) · get_code("fc4d4f310d9bfc0e")
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 Sequential. 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_ftrs": 64,
    "hidden_dim": 128,
    "out_dim": 256,
}
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 Sequential — a Sequential output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Sequential output the recorded ndim 1 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
log Ran
ran; our contract draft was wrong, not the code
kaiwenzha/contrastive-poisoning/model.py
code served (permissive licence) · get_code("0f408c13a7b48d93")
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 str. 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 datetime
import logging
import io

# Set up logging to capture output
logging.basicConfig(level=logging.INFO, format='%(message)s')

# Create a file handle for testing
file_handle = io.StringIO()

# Define ARGS dict with all parameters for the log function
ARGS = {
    'text': 'Test message for logging',
    'color': 'green',
    'style': 'bold',
    'with_time': True,
    'handle': file_handle
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
none outside the standard library — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type str — a str output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a str 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
resnet101 Ran
ran on a synthesized input
kaiwenzha/contrastive-poisoning/model.py
code served (permissive licence) · get_code("188a542bb3d0c413")
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 ResNet. 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 = {}
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 ResNet — a ResNet output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a ResNet 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
resnet18 Ran
ran; our contract draft was wrong, not the code
kaiwenzha/contrastive-poisoning/model.py
code served (permissive licence) · get_code("907fb9d80310a75f")
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 ResNet. 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 = {
    'in_channel': 3,
    'zero_init_residual': 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 ResNet — a ResNet output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a ResNet 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
resnet34 Ran
ran; our contract draft was wrong, not the code
kaiwenzha/contrastive-poisoning/model.py
code served (permissive licence) · get_code("b5e082eee874ab6a")
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 ResNet. 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 = {
    'in_channel': 3,
    'zero_init_residual': 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 ResNet — a ResNet output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a ResNet 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
resnet50 Ran
ran on a synthesized input
kaiwenzha/contrastive-poisoning/model.py
code served (permissive licence) · get_code("bc02a35848587cf8")
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 ResNet. 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 = {}
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 ResNet — a ResNet output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a ResNet 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
AttackModel Not yet run
unverified (harvested, no recorded run)
kaiwenzha/contrastive-poisoning/model.py
code served (permissive licence) · get_code("3e90e9281a3090fb")
How it ran

no invocation recorded.

MoCo Not yet run
unverified (harvested, no recorded run)
kaiwenzha/contrastive-poisoning/model.py
code served (permissive licence) · get_code("3806b767e591b869")
How it ran

no invocation recorded.

_MomentumEncoderMixin Not yet run
unverified (harvested, no recorded run)
kaiwenzha/contrastive-poisoning/model.py
code served (permissive licence) · get_code("de6d1a439b0eb3ae")
How it ran

no invocation recorded.

_deactivate_requires_grad Not yet run
unverified (harvested, no recorded run)
kaiwenzha/contrastive-poisoning/model.py
code served (permissive licence) · get_code("d2c729d46218e6c7")
How it ran

no invocation recorded.

_do_momentum_update Not yet run
unverified (harvested, no recorded run)
kaiwenzha/contrastive-poisoning/model.py
code served (permissive licence) · get_code("9ff781762297580d")
How it ran

no invocation recorded.

Also present in other papers' code

Of 18 samples lifted from this paper's linked repositories, 18 carry a function identity and 0 do not. Of the 18 distinct functions with an identity, 4 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 4 later) and 14 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
resnet101
brick of this paper's assembly: helper
1 other paper
1 later
2210.09879 (2022-10)
Unsupervised visualization of image datasets using contrastive learning
resnet18
brick of this paper's assembly: helper
1 other paper
1 later
2210.09879 (2022-10)
Unsupervised visualization of image datasets using contrastive learning
resnet34
brick of this paper's assembly: helper
1 other paper
1 later
2210.09879 (2022-10)
Unsupervised visualization of image datasets using contrastive learning
resnet50
brick of this paper's assembly: helper
1 other paper
1 later
2210.09879 (2022-10)
Unsupervised visualization of image datasets using contrastive 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

Indiscriminate data poisoning attacks are quite effective against supervised learning. However, not much is known about their impact on unsupervised contrastive learning (CL). This paper is the first to consider indiscriminate poisoning attacks of contrastive learning. We propose Contrastive Poisoning (CP), the first effective such attack on CL. We empirically show that Contrastive Poisoning, not only drastically reduces the performance of CL algorithms, but also attacks supervised learning models, making it the most generalizable indiscriminate poisoning attack. We also show that CL algorithms with a momentum encoder are more robust to indiscriminate poisoning, and propose a new countermeasure based on matrix completion. Code is available at: https://github.com/kaiwenzha/contrastive-poisoning.

For agents

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

get_harvested_code_for_paper("2202.11202")
get_code_for_paper("2202.11202")
have("2202.11202")

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

curl https://syntology.ai/api/ran/2202.11202.json

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

[![Syntology run record](https://syntology.ai/api/ran/2202.11202.svg)](https://syntology.ai/paper/2202.11202)

Connect an agent — have() is free.