SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1307.0414 · 2013

Challenges in Representation Learning: A report on three machine learning contests

arXiv · PDF · Open in the Atlas

Code that ran

6 of 12 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 6 have no contract verdict; 0 failures of our instrument; 6 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/1307.0414.json · badge: /api/ran/1307.0414.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
justinshenk/fer canonical (classifier label)
classifier basis: census
4 ran · 0 no recorded run
phamquiluan/ResidualMaskingNetwork community (classifier label)
classifier basis not recorded on the link
2 ran · 5 no recorded run
NJNischal/Facial-Expression-Recognition-with-CNNs community (classifier label)
classifier basis not recorded on the link
0 ran · 1 no recorded run
FunctionStatusWhere it lives
deepresunet Ran
ran on a synthesized input
phamquiluan/ResidualMaskingNetwork/models/brain_humor.py
code served (permissive licence) · get_code("ab4e945e1a4cd67c")
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 DeepResUNet. 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_channels': 3,
    'num_classes': 2,
}
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 DeepResUNet — a DeepResUNet output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a DeepResUNet 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
draw_annotations Ran
ran on a synthesized input
justinshenk/fer/src/fer/utils.py
code served (permissive licence) · get_code("cc0d5ba63e3c61db")
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 ndarray, ndim 3, dtype family int, shape (480, 640, 3) 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 cv2
import numpy as np

# Create a small test frame (480x640 with 3 channels for BGR)
frame = np.ones((480, 640, 3), dtype=np.uint8) * 255

# Create sample faces list with boxes and emotions
faces = [
    {
        'box': (50, 50, 100, 120),  # x, y, w, h
        'emotions': {
            'happy': 0.85,
            'sad': 0.05,
            'angry': 0.02,
            'neutral': 0.08
        }
    },
    {
        'box': (250, 100, 95, 115),
        'emotions': {
            'happy': 0.15,
            'sad': 0.70,
            'angry': 0.10,
            'neutral': 0.05
        }
    }
]

# Define emotions_dict for language support (needed by draw_scores when lang != 'en')
emotions_dict = {
    'happy': {'en': 'happy', 'es': 'feliz', 'fr': 'heureux'},
    'sad': {'en': 'sad', 'es': 'triste', 'fr': 'triste'},
    'angry': {'en': 'angry', 'es': 'enojado', 'fr': 'en colère'},
    'neutral': {'en': 'neutral', 'es': 'neutral', 'fr': 'neutre'}
}

ARGS = {
    'frame': frame,
    'faces': faces,
    'boxes': True,
    'scores': True,
    'color': (0, 155, 255),
    'lang': 'en',
    'size_multiplier': 1
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
cv2, numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type ndarray, ndim 3, dtype family int, shape (480, 640, 3) — shape (480, 640, 3) 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
loadBase64Img Ran
ran on a synthesized input
justinshenk/fer/src/fer/utils.py
code served (permissive licence) · get_code("f7f55ea9ce60fd3c")
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 ndarray, ndim 3, dtype family int, shape (10, 10, 3) 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 base64
import cv2
import numpy as np

# Create a small test image (10x10 BGR image with random values)
test_image = np.random.randint(0, 256, (10, 10, 3), dtype=np.uint8)

# Encode the image to PNG format
success, encoded_image = cv2.imencode('.png', test_image)
encoded_bytes = encoded_image.tobytes()

# Encode to base64
encoded_b64 = base64.b64encode(encoded_bytes).decode('utf-8')

# Create a valid data URI with base64 prefix
uri = f"data:image/png;base64,{encoded_b64}"

ARGS = {
    "uri": uri
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
cv2, numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type ndarray, ndim 3, dtype family int, shape (10, 10, 3) — shape (10, 10, 3) 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
parse_arguments Ran
ran on a synthesized input
justinshenk/fer/src/fer/fer.py
code served (permissive licence) · get_code("f362c8c447e17b24")
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 Namespace. 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 argparse
import sys

def setup_parse_arguments():
    # The function parse_arguments takes 'args' parameter
    # which is a list of command-line arguments to parse
    # We'll create a minimal list with just the --image argument
    
    args = ['--image', '/path/to/image.jpg']
    
    return args

ARGS = {
    'args': setup_parse_arguments()
}
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 Namespace — a Namespace output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Namespace 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
pil_to_bgr Ran
ran on a synthesized input
justinshenk/fer/src/fer/utils.py
code served (permissive licence) · get_code("cb44bc0903f47348")
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 ndarray, ndim 3, dtype family int, shape (3, 4, 3) 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 cv2
import numpy as np
from PIL import Image

# Create a small PIL Image object
# The function expects a PIL image and converts it to BGR using cv2
pil_img = Image.new('RGB', (4, 3), color=(255, 128, 64))

ARGS = {
    'pil_image': pil_img
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
PIL, cv2, numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type ndarray, ndim 3, dtype family int, shape (3, 4, 3) — shape (3, 4, 3) 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
transpose Ran
ran on a synthesized input
phamquiluan/ResidualMaskingNetwork/models/attention.py
code served (permissive licence) · get_code("6de3c5dbe991d885")
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 = {
    "in_channels": 3,
    "out_channels": 16,
    "kernel_size": 2,
    "stride": 2,
}
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
accuracy Not yet run
unverified (harvested, no recorded run)
phamquiluan/ResidualMaskingNetwork/legacy/main_imagenet.py
pointer only (licence: MIT); the stored copy get_code serves, from zbh2047/clipping-algorithms, is pointer only (licence: NONE) · get_code("9b8289076669fe4f")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from zbh2047/clipping-algorithms, 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. No invocation recorded.

alexnet Not yet run
unverified (harvested, no recorded run)
phamquiluan/ResidualMaskingNetwork/models/alexnet.py
code served (permissive licence) · get_code("8b9ffa45e293e7ef")
How it ran

no invocation recorded.

downsample Not yet run
unverified (harvested, no recorded run)
phamquiluan/ResidualMaskingNetwork/models/attention.py
code served (permissive licence) · get_code("40bd1ec9fed0d874")
How it ran

no invocation recorded.

get_dataset Not yet run
unverified (harvested, no recorded run)
phamquiluan/ResidualMaskingNetwork/legacy/main_affectnet.py
code served (permissive licence) · get_code("20e1d2a545b31c12")
How it ran

no invocation recorded.

plot_example_images Not yet run
unverified (harvested, no recorded run)
NJNischal/Facial-Expression-Recognition-with-CNNs/utils/datasets/fer.py
code served (permissive licence) · get_code("9f4d1b8055475a34")
How it ran

no invocation recorded.

validate Not yet run
unverified (harvested, no recorded run)
phamquiluan/ResidualMaskingNetwork/legacy/main_imagenet.py
code served (permissive licence) · get_code("c2afc02cfe9d6c56")
How it ran

no invocation recorded.

Also present in other papers' code

Of 12 samples lifted from this paper's linked repositories, 12 carry a function identity and 0 do not. Of the 12 distinct functions with an identity, 1 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 1 later) and 11 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
accuracy 80 other papers
80 later
1412.6553 (2014-12)
Speeding-up Convolutional Neural Networks Using Fine-tuned CP-Decomposition
1503.02531 (2015-03)
Distilling the Knowledge in a Neural Network
1511.06530 (2015-11)
Compression of Deep Convolutional Neural Networks for Fast and Low Power Mobile Applications
and 77 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

The ICML 2013 Workshop on Challenges in Representation Learning focused on three challenges: the black box learning challenge, the facial expression recognition challenge, and the multimodal learning challenge. We describe the datasets created for these challenges and summarize the results of the competitions. We provide suggestions for organizers of future challenges and some comments on what kind of knowledge can be gained from machine learning competitions.

For agents

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

get_harvested_code_for_paper("1307.0414")
get_code_for_paper("1307.0414")
have("1307.0414")

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

curl https://syntology.ai/api/ran/1307.0414.json

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

[![Syntology run record](https://syntology.ai/api/ran/1307.0414.svg)](https://syntology.ai/paper/1307.0414)

Connect an agent — have() is free.