SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2002.10003 · NeurIPS · 2020

NeurIPS 2019 Disentanglement Challenge: Improved Disentanglement through Aggregated Convolutional Feature Maps

Maximilian Seitzer

arXiv · PDF · Open in the Atlas

Code that ran

2 of 2 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; 1 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 1 failure of our instrument; 0 no recorded run), measured 2026-11-22; bodies inline only under a permissive licence as GitHub detects it. Not a reproduction of the paper's results.

"Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results. This record, dated, as JSON: /api/ran/2002.10003.json · badge: /api/ran/2002.10003.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
mseitzer/neurips2019-disentanglement-challenge canonical (classifier label)
classifier basis: classifier_2025
2 ran · 0 no recorded run
FunctionStatusWhere it lives
get_and_dump_features Ran
ran; our contract draft was wrong, not the code
mseitzer/neurips2019-disentanglement-challenge/pytorch/train_feature_vae.py
code served (permissive licence) · get_code("60908437f431c01e")
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) and returned memmap. 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
import numpy as np
import tempfile

torch.manual_seed(0)

# Create a minimal extractor model
class SimpleExtractor(nn.Module):
    def __init__(self):
        super().__init__()
        self.linear = nn.Linear(4, 8)
    
    def forward(self, x):
        return self.linear(x)

# Create a minimal data loader (list of batches)
def create_loader():
    # Each batch is a tensor of shape (batch_size, 4)
    batch1 = torch.randn(2, 4)
    batch2 = torch.randn(2, 4)
    return [batch1, batch2]

# Create extractor
extractor = SimpleExtractor()

# Create loader
loader = create_loader()

# Device
device = 'cpu'

# Path for saving features
temp_dir = tempfile.gettempdir()
path = f"{temp_dir}/test_features.npy"

# Dataset size (total number of samples across all batches)
dataset_size = 4

# Log interval
log_interval = 1

ARGS = {
    'extractor': extractor,
    'loader': loader,
    'device': device,
    'path': path,
    'dataset_size': dataset_size,
    'log_interval': log_interval
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
numpy, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type memmap — a memmap output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a memmap output the recorded ndim 2 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_feature_array Ran
ran, honoured the contract we drafted
mseitzer/neurips2019-disentanglement-challenge/pytorch/train_feature_vae.py
code served (permissive licence) · get_code("b0a3bc1cdcf97e0c")
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) and returned ndarray, ndim 2, dtype family float, shape (10, 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
import tempfile
import os

torch.manual_seed(0)

# Create a simple iterator that yields batches of features
class FeatureIterator:
    def __init__(self, num_batches, batch_size, feature_dim):
        self.num_batches = num_batches
        self.batch_size = batch_size
        self.feature_dim = feature_dim
        self.current_batch = 0
    
    def __iter__(self):
        self.current_batch = 0
        return self
    
    def __next__(self):
        if self.current_batch >= self.num_batches:
            raise StopIteration
        # Create a tensor of shape (batch_size, feature_dim)
        batch = torch.randn(self.batch_size, self.feature_dim)
        self.current_batch += 1
        return batch

# Set up parameters
batch_size = 2
feature_dim = 4
num_batches = 5
dataset_size = batch_size * num_batches  # 10 total samples

# Create the iterator
extract_iter = FeatureIterator(num_batches=num_batches, batch_size=batch_size, feature_dim=feature_dim)

# Create a temporary file path for testing with file_path parameter
temp_dir = tempfile.gettempdir()
file_path = os.path.join(temp_dir, "test_features.npy")

# Clean up any existing file
if os.path.exists(file_path):
    os.remove(file_path)

ARGS = {
    'extract_iter': extract_iter,
    'dataset_size': dataset_size,
    'num_batches': num_batches,
    'log_interval': 2,
    'file_path': None
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
numpy, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type ndarray, ndim 2, dtype family float, shape (10, 4) — shape (10, 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

Also present in other papers' code

Of 2 samples lifted from this paper's linked repositories, 2 carry a function identity and 0 do not. Of the 2 distinct functions with an identity, 2 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 2 the same month, 0 later) and 0 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
get_and_dump_features 1 other paper
1 the same month
2002.12356 (2020-02)
NeurIPS 2019 Disentanglement Challenge: Improved Disentanglement through Learned Aggregation of Convolutional Feature Maps
get_feature_array 1 other paper
1 the same month
2002.12356 (2020-02)
NeurIPS 2019 Disentanglement Challenge: Improved Disentanglement through Learned Aggregation of Convolutional Feature Maps

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

This report to our stage 1 submission to the NeurIPS 2019 disentanglement challenge presents a simple image preprocessing method for training VAEs leading to improved disentanglement compared to directly using the images. In particular, we propose to use regionally aggregated feature maps extracted from CNNs pretrained on ImageNet. Our method achieved the 2nd place in stage 1 of the challenge (AIcrowd, 2019). Code is available at https://github.com/mseitzer/neurips2019-disentanglement-challenge.

For agents

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

get_harvested_code_for_paper("2002.10003")
get_code_for_paper("2002.10003")
have("2002.10003")

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

curl https://syntology.ai/api/ran/2002.10003.json

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

[![Syntology run record](https://syntology.ai/api/ran/2002.10003.svg)](https://syntology.ai/paper/2002.10003)

Connect an agent — have() is free.