SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2011.10566 · 2020

Exploring Simple Siamese Representation Learning

Xinlei Chen

arXiv · PDF · Open in the Atlas

Code that ran

34 of 39 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (20 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 0 violated it and 25 have no contract verdict; 9 failures of our instrument; 5 no recorded run), measured 2026-11-21; 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/2011.10566.json · badge: /api/ran/2011.10566.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
Reza-Safdari/SimSiam community
Papers with Code archive
8 ran · 1 no recorded run
facebookresearch/clip-rocket community
Papers with Code archive
6 ran · 1 no recorded run
PatrickHua/SimSiam community
Papers with Code archive
4 ran · 0 no recorded run
lightly-ai/lightly community
Papers with Code archive
4 ran · 0 no recorded run
nikheelpandey/SimSiam-PyTorch community
Papers with Code archive
3 ran · 0 no recorded run
leaderj1001/SimSiam community
Papers with Code archive
2 ran · 0 no recorded run
FloCF/SSL_pytorch community
Papers with Code archive
2 ran · 0 no recorded run
taoyang1122/pytorch-SimSiam community
Papers with Code archive
2 ran · 0 no recorded run
facebookresearch/simsiam marked official in Papers with Code
Papers with Code archive
1 ran · 0 no recorded run
a07458666/simsiamfacenet community
Papers with Code archive
1 ran · 0 no recorded run
copy not recorded community
not in the paper's declared repositories
1 ran · 0 no recorded run
ahmdtaha/simsiam community
Papers with Code archive
0 ran · 3 no recorded run
FunctionStatusWhere it lives
Bottleneck Ran
ran on a synthesized input
Reza-Safdari/SimSiam/simsiam/model_factory.py
pointer only (licence: NONE) · get_code("47df0764b5090ea2")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, Reza-Safdari/SimSiam 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.

CL2L Ran
ran on a synthesized input · constructed an object; no result was computed
facebookresearch/clip-rocket/models.py
pointer only (licence: NOASSERTION) · get_code("bbe4c4713c60cb7b")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, facebookresearch/clip-rocket (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.

CLIP Ran
ran on a synthesized input · constructed an object; no result was computed
facebookresearch/clip-rocket/models.py
pointer only (licence: NOASSERTION) · get_code("4d45d7d0856d7377")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, facebookresearch/clip-rocket (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.

D Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
PatrickHua/SimSiam/models/simsiam.py
code served (permissive licence) · get_code("b2429807c9efa3f7")
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 0, dtype family float, shape () 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
import torch.nn.functional as F

torch.manual_seed(0)

# Create small tensors with distinct dimensions
# p and z should have shape (batch_size, feature_dim)
# batch_size = 2, feature_dim = 4
p = torch.randn(2, 4)
z = torch.randn(2, 4)

# version can be either 'original' or 'simplified'
version = 'simplified'

ARGS = {
    'p': p,
    'z': z,
    'version': version
}
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 0, dtype family float, shape () — shape () 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
D Ran
ran; our contract draft was wrong, not the code
nikheelpandey/SimSiam-PyTorch/model.py
code served (permissive licence) · get_code("dc05a6f71458b31e")
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 0, dtype family float, shape () 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
import torch.nn.functional as F

torch.manual_seed(0)

# The function D takes two parameters: p and z
# It computes -F.cosine_similarity(p, z.detach(), dim=-1).mean()
# Both p and z need to be tensors with a last dimension to compute cosine similarity
# They should have the same shape for cosine_similarity to work

p = torch.randn(2, 4)  # batch_size=2, dim=4
z = torch.randn(2, 4)  # batch_size=2, dim=4

ARGS = {
    "p": p,
    "z": z,
}
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 0, dtype family float, shape () — shape () 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
D Ran
ran on a synthesized input
leaderj1001/SimSiam/model.py
code served (permissive licence) · get_code("38628e7af88c5ed9")
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 0, 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 torch.nn.functional as F

class D(nn.Module):

    def __init__(self):
        super(D, self).__init__()

    def forward(self, p, z):
        z = z.detach()
        p = F.normalize(p, p=2, dim=1)
        z = F.normalize(z, p=2, dim=1)
        return -(p * z).sum(dim=1).mean()


INIT_ARGS = {}

ARGS = {
    'p': torch.randn(2, 4),
    'z': torch.randn(2, 4),
}

if __name__ == '__main__':
    model = D(**INIT_ARGS)
    output = model(**ARGS)
    print(f"Output: {output}")
    print(f"Output shape: {output.shape}")
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 0, 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)
DropPath Ran
ran on a synthesized input · constructed an object; no result was computed
facebookresearch/clip-rocket/models.py
pointer only (licence: NOASSERTION) · get_code("6bd663b5be82dccd")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, facebookresearch/clip-rocket (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.

MLP Ran
ran on a synthesized input · constructed an object; no result was computed
FloCF/SSL_pytorch/torchselfsup/models/simsiam.py
code served (permissive licence) · get_code("bb30a29172efa151")
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, MLP: 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_dim": 4,
    "hidden_dims": (8, 6, 3),
    "bias": True,
    "use_batchnorm": True,
    "batchnorm_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 MLP — 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 MLP 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
Model Ran
ran on a synthesized input · constructed an object; no result was computed
leaderj1001/SimSiam/model.py
code served (permissive licence) · get_code("516cd76945c13b46")
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, Model: 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 ArgsConfig:
    def __init__(self):
        self.proj_hidden = 8
        self.proj_out = 6
        self.pred_hidden = 5
        self.pred_out = 4
        self.checkpoints = None

ARGS = {
    'args': ArgsConfig(),
    'downstream': False
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch, torchvision — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Model — 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 Model 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
PredictionMLP Ran
ran on a synthesized input · constructed an object; no result was computed
taoyang1122/pytorch-SimSiam/models/simsiam.py
code served (permissive licence) · get_code("9d0e6a2eca652065")
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, PredictionMLP: 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_dim": 4,
    "mid_dim": 8,
    "out_dim": 3,
}
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 PredictionMLP — 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 PredictionMLP 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
ProjectionHead Ran
ran on a synthesized input · constructed an object; no result was computed
lightly-ai/lightly/lightly/models/simsiam.py
code served (permissive licence) · get_code("da76a8285671b345")
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, ProjectionHead: 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)

# Construct blocks for the ProjectionHead
# Each block is a tuple: (in_features, out_features, batch_norm_layer, non_linearity_layer, [use_bias])

blocks = [
    (4, 8, nn.BatchNorm1d(8), nn.ReLU()),
    (8, 16, nn.BatchNorm1d(16), nn.ReLU()),
    (16, 3, None, None)
]

ARGS = {
    "blocks": blocks
}
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 ProjectionHead — 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 ProjectionHead 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
Reza-Safdari/SimSiam/simsiam/model_factory.py
pointer only (licence: NONE) · get_code("0f2aaed67b1fc0a0")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, Reza-Safdari/SimSiam 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.

ResNet101 Ran
ran; our contract draft was wrong, not the code
Reza-Safdari/SimSiam/simsiam/model_factory.py
pointer only (licence: NONE) · get_code("ed0e4015879df242")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, Reza-Safdari/SimSiam 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.

ResNet152 Ran
ran; our contract draft was wrong, not the code
Reza-Safdari/SimSiam/simsiam/model_factory.py
pointer only (licence: NONE) · get_code("e6da00517c19b39c")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, Reza-Safdari/SimSiam 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.

ResNet18 Ran
ran; our contract draft was wrong, not the code
Reza-Safdari/SimSiam/simsiam/model_factory.py
pointer only (licence: NONE) · get_code("4a6376067215c5f6")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, Reza-Safdari/SimSiam 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.

ResNet34 Ran
ran; our contract draft was wrong, not the code
Reza-Safdari/SimSiam/simsiam/model_factory.py
pointer only (licence: NONE) · get_code("efbcdfcbc565884f")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, Reza-Safdari/SimSiam 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.

ResNet50 Ran
ran; our contract draft was wrong, not the code
Reza-Safdari/SimSiam/simsiam/model_factory.py
pointer only (licence: NONE) · get_code("1ace917fd995e564")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, Reza-Safdari/SimSiam 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.

ResidualAttentionBlock Ran
ran on a synthesized input · constructed an object; no result was computed
facebookresearch/clip-rocket/models.py
pointer only (licence: NOASSERTION) · get_code("009322dbbfd98763")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, facebookresearch/clip-rocket (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.

SimSiam Ran
ran on a synthesized input · constructed an object; no result was computed
facebookresearch/simsiam/simsiam/builder.py
pointer only (licence: NOASSERTION) · get_code("492cc68fb1110aa3")
How it ran

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

SimSiam Ran
ran on a synthesized input · constructed an object; no result was computed
FloCF/SSL_pytorch/torchselfsup/models/simsiam.py
code served (permissive licence) · get_code("815591f7486b47ff")
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, SimSiam: 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 network that takes input and outputs repre_dim
class MinimalBackbone(nn.Module):
    def __init__(self, input_dim: int, output_dim: int):
        super().__init__()
        self.linear = nn.Linear(input_dim, output_dim)
    
    def forward(self, x):
        return self.linear(x)

# Set up parameters
input_dim = 5
repre_dim = 4
batch_size = 2

# Create backbone
backbone_net = MinimalBackbone(input_dim, repre_dim)

# Define all arguments for SimSiam
ARGS = {
    "backbone_net": backbone_net,
    "repre_dim": repre_dim,
    "projector_hidden": (2048, 2048, 2048),
    "predictor_hidden": (512, 2048)
}
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 SimSiam — 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 SimSiam 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
SimSiam Ran
ran on a synthesized input · constructed an object; no result was computed
taoyang1122/pytorch-SimSiam/models/simsiam.py
code served (permissive licence) · get_code("d9b4a10391a8d49f")
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, SimSiam: 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
from torchvision.models import resnet50

torch.manual_seed(0)

ARGS = {
    'backbone': 'resnet50',
    'd': 2048,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch, torchvision — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type SimSiam — 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 SimSiam 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
SimSiam Ran
ran on a synthesized input · constructed an object; no result was computed
a07458666/simsiamfacenet/src/models/simsiam.py
pointer only (licence: NOASSERTION) · get_code("5ef921dde450036d")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, a07458666/simsiamfacenet (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.

SimSiam Ran
ran on a synthesized input · constructed an object; no result was computed
lightly-ai/lightly/lightly/models/simsiam.py
code served (permissive licence) · get_code("fb0cb8a440e873f9")
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, SimSiam: 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 SimpleBackbone(nn.Module):
    """Minimal backbone that outputs features of size num_ftrs."""
    def __init__(self, num_ftrs: int = 2048):
        super().__init__()
        self.num_ftrs = num_ftrs
        self.fc = nn.Linear(10, num_ftrs)
    
    def forward(self, x):
        return self.fc(x)

backbone = SimpleBackbone(num_ftrs=2048)

ARGS = {
    "backbone": backbone,
    "num_ftrs": 2048,
    "proj_hidden_dim": 2048,
    "pred_hidden_dim": 512,
    "out_dim": 2048,
}
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 SimSiam — 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 SimSiam 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
SimSiam Ran
ran on a synthesized input · constructed an object; no result was computed
PatrickHua/SimSiam/models/simsiam.py
code served (permissive licence) · get_code("32880b6d81ed25f9")
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, SimSiam: 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
from torchvision.models import resnet50

torch.manual_seed(0)

class TinyBackbone(nn.Module):
    def __init__(self, output_dim=2048):
        super().__init__()
        self.output_dim = output_dim
        self.fc = nn.Linear(3, output_dim)
    
    def forward(self, x):
        # Flatten input and project to output_dim
        x = x.reshape(x.size(0), -1)
        x = self.fc(x)
        return x

# Create a minimal backbone with output_dim attribute
backbone = TinyBackbone(output_dim=2048)

ARGS = {
    'backbone': backbone
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch, torchvision — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type SimSiam — 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 SimSiam 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
SimSiam Ran
ran on a synthesized input · constructed an object; no result was computed
nikheelpandey/SimSiam-PyTorch/model.py
code served (permissive licence) · get_code("752e4e769526a23c")
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, SimSiam: 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
from torchvision.models import resnet50

torch.manual_seed(0)

# Create a minimal backbone that mimics resnet50 structure
class MinimalBackbone(nn.Module):
    def __init__(self):
        super().__init__()
        self.fc = nn.Linear(2048, 1000)
        self.output_dim = 2048
        # Add a simple feature extraction layer
        self.feature_layer = nn.Linear(3, 2048)
    
    def forward(self, x):
        # x shape: (batch_size, 3, height, width) -> output (batch_size, 2048)
        batch_size = x.shape[0]
        x = x.view(batch_size, -1)  # Flatten
        x = self.feature_layer(x)
        return x

# Create backbone with proper structure
backbone = MinimalBackbone()

ARGS = {
    "backbone": backbone
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch, torchvision — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type SimSiam — 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 SimSiam 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
SimSiamPredictionHead Ran
ran on a synthesized input · constructed an object; no result was computed
lightly-ai/lightly/lightly/models/simsiam.py
code served (permissive licence) · get_code("7aa59b2768a14009")
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, SimSiamPredictionHead: 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 = {
    "input_dim": 2048,
    "hidden_dim": 512,
    "output_dim": 2048,
}
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 SimSiamPredictionHead — 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 SimSiamPredictionHead 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
SimSiamProjectionHead Ran
ran on a synthesized input · constructed an object; no result was computed
lightly-ai/lightly/lightly/models/simsiam.py
code served (permissive licence) · get_code("4e65e79a1e2a3fcc")
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, SimSiamProjectionHead: 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 = {
    "input_dim": 2048,
    "hidden_dim": 2048,
    "output_dim": 2048,
}
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 SimSiamProjectionHead — 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 SimSiamProjectionHead 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
Transformer Ran
ran on a synthesized input · constructed an object; no result was computed
facebookresearch/clip-rocket/models.py
pointer only (licence: NOASSERTION) · get_code("012204ec88654334")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, facebookresearch/clip-rocket (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.

drop_path Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
this paper's copy was not recorded; identical code first harvested from lRomul/sensorium
pointer only · get_code("971ae8d2d8313e30")
How it ran

The body of this sample is withheld: this paper's copy of the code was not recorded (its link names no repository or source path), so no licence was read for it. 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_backbone Ran
ran; our contract draft was wrong, not the code
nikheelpandey/SimSiam-PyTorch/model.py
code served (permissive licence) · get_code("baecb6445a98aac2")
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 SimpleBackbone. 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 SimpleBackbone(nn.Module):
    def __init__(self):
        super().__init__()
        self.features = nn.Linear(4, 8)
        self.fc = nn.Linear(8, 3)
    
    def forward(self, x):
        x = self.features(x)
        x = self.fc(x)
        return x

backbone = SimpleBackbone()

ARGS = {
    "backbone": backbone,
    "castrate": 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 SimpleBackbone — a SimpleBackbone output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a SimpleBackbone 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
infer_batchnorm_class Ran
ran on a synthesized input
facebookresearch/clip-rocket/models.py
pointer only (licence: NOASSERTION) · get_code("d23738a6312f956e")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, facebookresearch/clip-rocket (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.

prediction_MLP Ran
ran on a synthesized input · constructed an object; no result was computed
PatrickHua/SimSiam/models/simsiam.py
code served (permissive licence) · get_code("18a041c1ad13c81f")
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, prediction_MLP: 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_dim': 2048,
    'hidden_dim': 512,
    'out_dim': 2048,
}
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 prediction_MLP — 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 prediction_MLP 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
prediction_MLP Ran
ran on a synthesized input
Reza-Safdari/SimSiam/simsiam/model_factory.py
pointer only (licence: NONE) · get_code("4f89fc5dcdf63603")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, Reza-Safdari/SimSiam 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.

projection_MLP Ran
ran on a synthesized input · constructed an object; no result was computed
PatrickHua/SimSiam/models/simsiam.py
code served (permissive licence) · get_code("4eff742841c262a2")
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, projection_MLP: 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_dim': 4,
    'hidden_dim': 8,
    'out_dim': 6,
}
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 projection_MLP — 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 projection_MLP 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
SIAMLIP Not yet run
unverified (harvested, no recorded run)
facebookresearch/clip-rocket/models.py
pointer only (licence: NOASSERTION) · get_code("bd3b410047cb6c47")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, facebookresearch/clip-rocket (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.

SimSiam Not yet run
unverified (harvested, no recorded run)
ahmdtaha/simsiam/models/simsiam.py
pointer only (licence: NONE) · get_code("f2af91921deea94a")
How it ran

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

SimSiam Not yet run
unverified (harvested, no recorded run)
Reza-Safdari/SimSiam/simsiam/model_factory.py
pointer only (licence: NONE) · get_code("c9eb23d22a1f6e19")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, Reza-Safdari/SimSiam 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.

get_backbone Not yet run
unverified (harvested, no recorded run)
ahmdtaha/simsiam/models/simsiam.py
pointer only (licence: NONE) · get_code("1a35ab02b0214a3a")
How it ran

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

projection_MLP Not yet run
unverified (harvested, no recorded run)
ahmdtaha/simsiam/models/simsiam.py
pointer only (licence: NONE) · get_code("cb99b702c75951a5")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, ahmdtaha/simsiam 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 39 samples lifted from this paper's linked repositories, 39 carry a function identity and 0 do not. Of the 39 distinct functions with an identity, 13 are also present in other papers whose code we hold (2 with at least one paper dated earlier, 0 the same month, 13 later) and 26 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
drop_path
brick of this paper's assembly: helper
66 other papers
1 dated earlier, 63 later, 2 undated · 15 only as an assembly brick
1906.01502 (2019-06)
How multilingual is Multilingual BERT?
2103.03230 (2021-03)
Barlow Twins: Self-Supervised Learning via Redundancy Reduction
2104.09770 (2021-04)
M2TR: Multi-modal Multi-scale Transformers for Deepfake Detection
and 63 more not named here
DropPath
brick of this paper's assembly: helper
8 other papers
8 later · 2 only as an assembly brick
2103.03230 (2021-03)
Barlow Twins: Self-Supervised Learning via Redundancy Reduction
2210.10716 (2022-10)
CroCo: Self-Supervised Pre-training for 3D Vision Tasks by Cross-View Completion
2303.04249 (2023-03)
Where We Are and What We're Looking At: Query Based Worldwide Image Geo-localization Using Hierarchies and Scenes
and 5 more not named here
D
brick of this paper's assembly: loss
5 other papers
5 later
2105.00470 (2021-05)
On Feature Decorrelation in Self-Supervised Learning
2110.08406 (2021-10)
Surrogate- and invariance-boosted contrastive learning for data-scarce applications in science
2311.10100 (2023-11)
LenSiam: Self-Supervised Learning on Strong Gravitational Lens Images
and 2 more not named here
ProjectionHead
brick of this paper's assembly: helper
3 other papers
2 dated earlier, 1 later · 2 only as an assembly brick
1911.05722 (2019-11)
Momentum Contrast for Unsupervised Visual Representation Learning
2002.05709 (2020-02)
A Simple Framework for Contrastive Learning of Visual Representations
2104.14548 (2021-04)
With a Little Help from My Friends: Nearest-Neighbor Contrastive Learning of Visual Representations
Bottleneck
brick of this paper's assembly: helper
2 other papers
2 later · 1 only as an assembly brick
2109.05554 (2021-09)
No True State-of-the-Art? OOD Detection Methods are Inconsistent across Datasets
2305.19518 (2023-05)
Label-Retrieval-Augmented Diffusion Models for Learning from Noisy Labels
MLP
brick of this paper's assembly: helper
2 other papers
2 later · 1 only as an assembly brick
2103.03230 (2021-03)
Barlow Twins: Self-Supervised Learning via Redundancy Reduction
2105.04906 (2021-05)
VICReg: Variance-Invariance-Covariance Regularization for Self-Supervised Learning
CL2L
brick of this paper's assembly: helper
1 other paper
1 later · 1 only as an assembly brick
2103.03230 (2021-03)
Barlow Twins: Self-Supervised Learning via Redundancy Reduction
CLIP
brick of this paper's assembly: helper
1 other paper
1 later · 1 only as an assembly brick
2103.03230 (2021-03)
Barlow Twins: Self-Supervised Learning via Redundancy Reduction
D
brick of this paper's assembly: loss
1 other paper
1 later
2402.14430 (2024-02)
Robust Training of Federated Models with Extremely Label Deficiency
ResNet18
brick of this paper's assembly: helper
1 other paper
1 later
2403.18550 (2024-03)
OrCo: Towards Better Generalization via Orthogonality and Contrast for Few-Shot Class-Incremental Learning
ResidualAttentionBlock
brick of this paper's assembly: helper
1 other paper
1 later · 1 only as an assembly brick
2103.03230 (2021-03)
Barlow Twins: Self-Supervised Learning via Redundancy Reduction
Transformer
brick of this paper's assembly: helper
1 other paper
1 later · 1 only as an assembly brick
2103.03230 (2021-03)
Barlow Twins: Self-Supervised Learning via Redundancy Reduction
infer_batchnorm_class
brick of this paper's assembly: helper
1 other paper
1 later · 1 only as an assembly brick
2103.03230 (2021-03)
Barlow Twins: Self-Supervised Learning via Redundancy Reduction

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 2026-11-21.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Siamese networks have become a common structure in various recent models for unsupervised visual representation learning. These models maximize the similarity between two augmentations of one image, subject to certain conditions for avoiding collapsing solutions. In this paper, we report surprising empirical results that simple Siamese networks can learn meaningful representations even using none of the following: (i) negative sample pairs, (ii) large batches, (iii) momentum encoders. Our experiments show that collapsing solutions do exist for the loss and structure, but a stop-gradient operation plays an essential role in preventing collapsing. We provide a hypothesis on the implication of stop-gradient, and further show proof-of-concept experiments verifying it. Our "SimSiam" method achieves competitive results on ImageNet and downstream tasks. We hope this simple baseline will motivate people to rethink the roles of Siamese architectures for unsupervised representation learning. Code will be made available.

For agents

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

get_harvested_code_for_paper("2011.10566")
get_code_for_paper("2011.10566")
have("2011.10566")

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

curl https://syntology.ai/api/ran/2011.10566.json

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

[![Syntology run record](https://syntology.ai/api/ran/2011.10566.svg)](https://syntology.ai/paper/2011.10566)

Connect an agent — have() is free.