SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2204.03972 · 2022

Contrastive language and vision learning of general fashion concepts

arXiv · PDF · Open in the Atlas

Code that ran

4 of 6 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 4 have no contract verdict; 0 failures of our instrument; 2 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/2204.03972.json · badge: /api/ran/2204.03972.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
patrickjohncyh/fashion-clip canonical (classifier label)
classifier basis not recorded on the link
4 ran · 2 no recorded run
FunctionStatusWhere it lives
display_images Ran
ran on a synthesized input
patrickjohncyh/fashion-clip/fashion_clip/utils.py
code served (permissive licence) · get_code("954adf1bb45ba47b")
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 Figure. 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
from PIL import Image
import io
import matplotlib.pyplot as plt
import tempfile
import os

# Create temporary directory for test images
temp_dir = tempfile.mkdtemp()

# Create small test images and save them
def create_test_image(size=(100, 100), color=(255, 0, 0)):
    img = Image.new('RGB', size, color=color)
    return img

# Generate 3 test image files
image_paths = []
for i in range(3):
    img = create_test_image(size=(100, 100), color=(i*50, i*70, i*100))
    img_path = os.path.join(temp_dir, f'test_image_{i}.png')
    img.save(img_path)
    image_paths.append(img_path)

# Create product info list
product_info = [
    {
        'product_id': 'PROD001',
        'name': 'Test Product One',
        'price': '$99.99',
        'description': 'This is a longer description that should wrap across multiple lines'
    },
    {
        'product_id': 'PROD002',
        'name': 'Test Product Two',
        'price': '$149.99',
        'description': 'Another product with details'
    },
    {
        'product_id': 'PROD003',
        'name': 'Test Product Three',
        'price': '$199.99',
        'rating': '4.5 stars'
    }
]

ARGS = {
    'image_paths': image_paths,
    'product_info': product_info,
    'columns': 2,
    'width': 12,
    'height': 6,
    'max_images': 15,
    'font_size': 8,
    'text_wrap_length': 35
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
PIL, matplotlib, numpy, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Figure — a Figure output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Figure 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
file_sha256 Ran
ran on a synthesized input
patrickjohncyh/fashion-clip/fashion_clip/utils.py
code served (permissive licence) · get_code("55b709f744380b0b")
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 hashlib
import tempfile
import os

# Create a temporary file with some content
temp_file = tempfile.NamedTemporaryFile(mode='wb', delete=False, suffix='.txt')
temp_file.write(b"test content for sha256 hashing")
temp_file.close()

ARGS = {
    "file_path": temp_file.name
}
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
generate_horizontal_masks Ran
ran on a synthesized input
patrickjohncyh/fashion-clip/fashion_clip/attention_map.py
code served (permissive licence) · get_code("a62fb34689828455")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned list, ndim 4, 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 numpy as np

ARGS = {
    "image_size": 16,
    "pixel_size": 4,
    "channels": 3,
}
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 list, ndim 4, dtype family float — a list output has no array shape of its own; none is stated
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
generate_vertical_masks Ran
ran on a synthesized input
patrickjohncyh/fashion-clip/fashion_clip/attention_map.py
code served (permissive licence) · get_code("9e9c243453bdcc2c")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned list, ndim 4, 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 numpy as np

# Analyze the function signature and body:
# - image_size: used as divisor and array dimension (int)
# - pixel_size: used as divisor and multiplier (int)
# - channels: used as array dimension (int, default=3)
# The function creates masks by slicing arrays with pixel_size intervals

ARGS = {
    "image_size": 16,
    "pixel_size": 4,
    "channels": 3,
}
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 list, ndim 4, dtype family float — a list output has no array shape of its own; none is stated
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
display_images_from_url Not yet run
unverified (harvested, no recorded run)
patrickjohncyh/fashion-clip/fashion_clip/utils.py
code served (permissive licence) · get_code("303f8acfee14813c")
How it ran

no invocation recorded.

pad_to_square Not yet run
unverified (harvested, no recorded run)
patrickjohncyh/fashion-clip/fashion_clip/attention_map.py
code served (permissive licence) · get_code("954092c03f1d3195")
How it ran

no invocation recorded.

Also present in other papers' code

Of 6 samples lifted from this paper's linked repositories, 6 carry a function identity and 0 do not. Of the 6 distinct functions with an identity, 0 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 0 later) and 6 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.

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

The steady rise of online shopping goes hand in hand with the development of increasingly complex ML and NLP models. While most use cases are cast as specialized supervised learning problems, we argue that practitioners would greatly benefit from more transferable representations of products. In this work, we build on recent developments in contrastive learning to train FashionCLIP, a CLIP-like model for the fashion industry. We showcase its capabilities for retrieval, classification and grounding, and release our model and code to the community.

For agents

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

get_harvested_code_for_paper("2204.03972")
get_code_for_paper("2204.03972")
have("2204.03972")

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

curl https://syntology.ai/api/ran/2204.03972.json

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

[![Syntology run record](https://syntology.ai/api/ran/2204.03972.svg)](https://syntology.ai/paper/2204.03972)

Connect an agent — have() is free.