SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1803.09196 · 2018

Learning Type-Aware Embeddings for Fashion Compatibility

arXiv · PDF · Open in the Atlas

Code that ran

15 of 16 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 14 have no contract verdict; 1 failure of our instrument; 1 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/1803.09196.json · badge: /api/ran/1803.09196.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
mvasil/fashion-compatibility canonical (classifier label)
classifier basis: census
8 ran · 0 no recorded run
owj0421/DeepFashion community (classifier label)
classifier basis not recorded on the link
7 ran · 1 no recorded run
FunctionStatusWhere it lives
accuracy Ran
ran on a synthesized input
mvasil/fashion-compatibility/tripletnet.py
code served (permissive licence) · get_code("e4dd841456c7cc95")
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 1, dtype family float, shape (1,) as a later run recorded it. 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, 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 numpy as np

torch.manual_seed(0)

# The function expects:
# - pos_samples: a tensor with distances between positive pairs
# - neg_samples: a tensor with distances between negative pairs
# Both should have .is_cuda, .cpu(), .data, .size() methods (torch.Tensor)
# and be comparable for > operation

# Create small sample tensors with batch size 2
pos_samples = torch.randn(2, requires_grad=True)
neg_samples = torch.randn(2, requires_grad=True)

ARGS = {
    "pos_samples": pos_samples,
    "neg_samples": neg_samples,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Tensor, ndim 1, dtype family float, shape (1,) — shape (1,) 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
compute_cir_scores Ran
ran on a synthesized input
owj0421/DeepFashion/src/evaluation/metrics.py
code served (permissive licence) · get_code("8fed54184c09baea")
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

torch.manual_seed(0)

# Create tiny tensors for predictions and labels
# predictions: model outputs (logits or class indices)
# labels: ground truth class indices
# Using batch size 2, with 4 possible classes
predictions = torch.tensor([0, 2, 1, 3], dtype=torch.long)
labels = torch.tensor([0, 2, 3, 3], dtype=torch.long)

ARGS = {
    'predictions': predictions,
    'labels': labels,
}
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
compute_cp_scores Ran
ran on a synthesized input
owj0421/DeepFashion/src/evaluation/metrics.py
code served (permissive licence) · get_code("96971605709f6e86")
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
from sklearn.metrics import roc_auc_score

torch.manual_seed(0)

# Create predictions tensor (probabilities between 0 and 1)
predictions = torch.tensor([0.9, 0.2, 0.8, 0.1], dtype=torch.float32)

# Create labels tensor (binary labels)
labels = torch.tensor([1, 0, 1, 0], dtype=torch.int64)

ARGS = {
    'predictions': predictions,
    'labels': labels
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
sklearn, 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
conv3x3 Ran
ran; our contract draft was wrong, not the code
mvasil/fashion-compatibility/Resnet_18.py
pointer only (licence: BSD-3-Clause); the stored copy get_code serves, from lixiaotong97/DSU, is pointer only (licence: NONE) · get_code("fac5364e2f53c6db")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (BSD-3-Clause), but get_code serves the stored copy, first harvested from lixiaotong97/DSU, 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.

ddp_to_std Ran
ran on a synthesized input
owj0421/DeepFashion/src/models/load.py
code served (permissive licence) · get_code("194e3b30b4aaa9e5")
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)

# Construct a state_dict that mimics a DDP (DistributedDataParallel) model
# DDP wraps models and prefixes all keys with 'module.'
state_dict = {
    'module.layer1.weight': torch.randn(4, 3),
    'module.layer1.bias': torch.randn(4),
    'module.layer2.weight': torch.randn(5, 4),
    'module.layer2.bias': torch.randn(5),
    'module.bn.running_mean': torch.randn(4),
    'module.bn.running_var': torch.randn(4),
}

ARGS = {
    'state_dict': state_dict
}
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
default_image_loader Ran
ran on a synthesized input
mvasil/fashion-compatibility/polyvore_outfits.py
code served (permissive licence) · get_code("dd93840741a221e7")
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 Image. 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
from PIL import Image
import io

# Create a small valid RGB image in memory
def create_test_image():
    # Create a simple 4x3 RGB image
    img = Image.new('RGB', (4, 3), color=(255, 0, 0))
    return img

# Save image to a bytes buffer to simulate a file path
img_buffer = io.BytesIO()
test_img = create_test_image()
test_img.save(img_buffer, format='PNG')
img_buffer.seek(0)

# For this function, we need to provide a path parameter
# Since we can't do actual file I/O, we'll create a temporary file-like path
# But since the function uses Image.open(path), we need an actual file path
# Create a simple workaround by writing to a temp location in memory

import tempfile
import os

# Create a temporary directory and save our test image there
temp_dir = tempfile.gettempdir()
test_image_path = os.path.join(temp_dir, 'test_image_temp.png')
test_img.save(test_image_path)

ARGS = {
    'path': test_image_path
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
PIL, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Image — a Image output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Image output the recorded ndim 3 and dtype family int 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
gather_results Ran
ran on a synthesized input
owj0421/DeepFashion/src/utils/distributed_utils.py
code served (permissive licence) · get_code("31d8ae5162014982")
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 tuple. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import torch.distributed as dist
from unittest.mock import MagicMock, patch

torch.manual_seed(0)

# Mock the distributed functions since we're running in a non-distributed environment
def mock_get_world_size():
    return 1

def mock_all_gather(tensor_list, tensor):
    tensor_list[0] = tensor

def mock_all_reduce(tensor, op=None):
    pass

# Patch distributed functions
dist.get_world_size = mock_get_world_size
dist.all_gather = mock_all_gather
dist.all_reduce = mock_all_reduce

# Create small test tensors
all_loss = torch.tensor(0.5)
all_preds = torch.randn(2, 4)
all_labels = torch.randint(0, 2, (2, 4))

ARGS = {
    "all_loss": all_loss,
    "all_preds": all_preds,
    "all_labels": all_labels,
}
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 tuple — a tuple output has no array shape of its own; none is stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
get_device Ran
ran on a synthesized input
owj0421/DeepFashion/src/models/csa_net.py
code served (permissive licence) · get_code("d68e5599bba94323")
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 device. 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 model with parameters
model = nn.Linear(4, 3)

# The function calls next(model.parameters()).device
# So we need a model with at least one parameter
# nn.Linear has weight and bias parameters, so this works

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 device — a device output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a device 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
get_logger Ran
ran on a synthesized input
owj0421/DeepFashion/src/utils/logger_utils.py
code served (permissive licence) · get_code("b5a7546483113625")
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 Logger. 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 logging
import pathlib
import tempfile

# Create a temporary directory for logs
temp_dir = tempfile.TemporaryDirectory()
log_dir_path = pathlib.Path(temp_dir.name)

ARGS = {
    'name': 'test_logger',
    'log_dir': log_dir_path,
    'rank': 0
}
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 Logger — a Logger output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Logger 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
load_typespaces Ran
ran on a synthesized input
mvasil/fashion-compatibility/polyvore_outfits.py
code served (permissive licence) · get_code("53d887c7aafb755c")
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 os
import tempfile
import pickle
import numpy as np

# Create a temporary directory for this test
tmpdir = tempfile.mkdtemp()

# Create the typespaces.p file that the function expects
# This should be a list of type pairs or type identifiers
typespaces_data = [('int', 'str'), ('float', 'bool'), ('list', 'dict'), ('tuple', 'set')]
typespaces_path = os.path.join(tmpdir, 'typespaces.p')
with open(typespaces_path, 'wb') as f:
    pickle.dump(typespaces_data, f)

# Set up the ARGS dictionary
ARGS = {
    'rootdir': tmpdir,
    'rand_typespaces': False,
    'num_rand_embed': 2
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type 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
make_fc_1d Ran
ran on a synthesized input
mvasil/fashion-compatibility/tripletnet.py
code served (permissive licence) · get_code("b07513a5b7a4e7d2")
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 = {
    "f_in": 4,
    "f_out": 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 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
parse_iminfo Ran
ran on a synthesized input
mvasil/fashion-compatibility/polyvore_outfits.py
code served (permissive licence) · get_code("800cd884053adb56")
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 tuple. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import numpy as np

# Define the arguments for parse_iminfo

# im2index: Dictionary mapping image names to indices in a feature matrix
im2index = {
    'outfit_shirt_1': 0,
    'outfit_pants_1': 1,
    'outfit_shoes_1': 2,
    'other_shirt_2': 3,
}

# id2im: Dictionary mapping image IDs to image names
id2im = {
    'outfit_shirt_1': 'outfit_shirt_1',
    'outfit_pants_1': 'outfit_pants_1',
    'outfit_shoes_1': 'outfit_shoes_1',
    'other_shirt_2': 'other_shirt_2',
}

# question: List of image IDs to measure compatibility between
question = [
    'outfit_shirt_1',
    'outfit_pants_1',
]

# gt: Optional ground truth outfit set ID (will be inferred from first image if None)
gt = None

ARGS = {
    'question': question,
    'im2index': im2index,
    'id2im': id2im,
    'gt': gt,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type tuple — a tuple output has no array shape of its own; none is stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
resnet18 Ran
ran on a synthesized input
mvasil/fashion-compatibility/Resnet_18.py
code served (permissive licence) · get_code("dca32d9a409dda05")
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 = {
    'pretrained': False,
    'embedding_size': 64
}
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
safe_divide Ran
ran on a synthesized input
owj0421/DeepFashion/src/models/loss.py
code served (permissive licence) · get_code("6e063d74f933e308")
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 2, dtype family float, shape (2, 4) 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 numpy as np

torch.manual_seed(0)

# The function safe_divide(a, b, eps=1e-07) performs element-wise division
# with a small epsilon added to the denominator for numerical stability.
# Parameters:
# - a: numerator (tensor or array)
# - b: denominator (tensor or array)
# - eps: small constant to avoid division by zero (default 1e-07)

# Create small test tensors
a = torch.randn(2, 4)
b = torch.randn(2, 4)
eps = 1e-07

ARGS = {
    "a": a,
    "b": b,
    "eps": eps,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, 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, shape (2, 4) — shape (2, 4) 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
selective_margin_loss Ran
ran on a synthesized input
mvasil/fashion-compatibility/tripletnet.py
code served (permissive licence) · get_code("1be9808eff045cfb")
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

torch.manual_seed(0)

# pos_samples: Distance between positive pair - should be a tensor of distances
pos_samples = torch.tensor([0.5, 0.3], dtype=torch.float32)

# neg_samples: Distance between negative pair - should be a tensor of distances
neg_samples = torch.tensor([2.0, 1.5], dtype=torch.float32)

# margin: minimum desired margin between pos and neg samples - a scalar float
margin = 0.5

# has_sample: Indicates if the sample should be used to calculate the loss - boolean tensor
has_sample = torch.tensor([1.0, 1.0], dtype=torch.float32)

ARGS = {
    "pos_samples": pos_samples,
    "neg_samples": neg_samples,
    "margin": margin,
    "has_sample": has_sample,
}
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
load_model Not yet run
unverified (harvested, no recorded run)
owj0421/DeepFashion/src/models/load.py
code served (permissive licence) · get_code("a0f17a05cbef8b55")
How it ran

no invocation recorded.

Also present in other papers' code

Of 16 samples lifted from this paper's linked repositories, 16 carry a function identity and 0 do not. Of the 16 distinct functions with an identity, 1 are also present in other papers whose code we hold (1 with at least one paper dated earlier, 1 the same month, 1 later) and 15 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
conv3x3 686 other papers
37 dated earlier, 8 the same month, 641 later · 31 only as an assembly brick
1406.2661 (2014-06)
Generative Adversarial Networks
1409.0575 (2014-09)
ImageNet Large Scale Visual Recognition Challenge
1412.6572 (2014-12)
Explaining and Harnessing Adversarial Examples
and 683 more not named here

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

Outfits in online fashion data are composed of items of many different types (e.g. top, bottom, shoes) that share some stylistic relationship with one another. A representation for building outfits requires a method that can learn both notions of similarity (for example, when two tops are interchangeable) and compatibility (items of possibly different type that can go together in an outfit). This paper presents an approach to learning an image embedding that respects item type, and jointly learns notions of item similarity and compatibility in an end-to-end model. To evaluate the learned representation, we crawled 68,306 outfits created by users on the Polyvore website. Our approach obtains 3-5% improvement over the state-of-the-art on outfit compatibility prediction and fill-in-the-blank tasks using our dataset, as well as an established smaller dataset, while supporting a variety of useful queries.

For agents

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

get_harvested_code_for_paper("1803.09196")
get_code_for_paper("1803.09196")
have("1803.09196")

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

curl https://syntology.ai/api/ran/1803.09196.json

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

[![Syntology run record](https://syntology.ai/api/ran/1803.09196.svg)](https://syntology.ai/paper/1803.09196)

Connect an agent — have() is free.