SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1502.03509 · 2015

MADE: Masked Autoencoder for Distribution Estimation

arXiv · PDF · Open in the Atlas

Code that ran

5 of 9 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; 2 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 3 failures of our instrument; 4 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/1502.03509.json · badge: /api/ran/1502.03509.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
naru-project/naru extension (classifier label)
classifier basis: classifier_2025
4 ran · 2 no recorded run
ANLGBOY/MADE-with-PyTorch reimplementation (classifier label)
classifier basis: classifier_2025
1 ran · 0 no recorded run
EugenHotaj/pytorch-generative reimplementation (classifier label)
classifier basis: classifier_2025
0 ran · 1 no recorded run
eyalbetzalel/pytorch-generative-v6 reimplementation (classifier label)
classifier basis: classifier_2025
0 ran · 1 no recorded run
FunctionStatusWhere it lives
Entropy Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
naru-project/naru/train_model.py
code served (permissive licence) · get_code("b6c3c093da58e8e3")
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 1, 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
import scipy.stats

torch = None  # Not needed for this function

# Construct the arguments
name = "test_distribution"

# Create sample probability data for entropy calculation
# scipy.stats.entropy expects a probability distribution (non-negative values that sum to 1)
data = np.array([0.1, 0.2, 0.3, 0.4])

# Define the bases to use for entropy calculation
bases = [2, 'e', None]

ARGS = {
    'name': name,
    'data': data,
    'bases': bases
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, scipy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type list, ndim 1, 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
ErrorMetric Ran
ran, honoured the contract we drafted
naru-project/naru/eval_model.py
code served (permissive licence) · get_code("06c2ddfbbcfd6c3f")
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 float, 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 numpy as np

torch.manual_seed(0)

# The function takes two parameters: est_card and card
# Both appear to be numeric values (cardinality estimates)
# The function performs comparisons and arithmetic operations on them

# Test case 1: Normal case where both are non-zero
est_card_val = 100
card_val = 50

ARGS = {
    "est_card": est_card_val,
    "card": card_val
}
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 float, 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
InvertOrder Ran
ran; our contract draft was wrong, not the code
naru-project/naru/eval_model.py
code served (permissive licence) · get_code("eb641f3aafc7f28c")
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 1, dtype family int; 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

torch.manual_seed(0)

# InvertOrder takes an 'order' parameter which should be a list or sequence
# The function creates an inverse ordering by iterating through the order
# and placing indices in the inverse array

# Create a simple ordering list
order = [2, 0, 3, 1]

ARGS = {
    "order": order
}
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 list, ndim 1, dtype family int — 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
ReportModel Ran
ran, honoured the contract we drafted
naru-project/naru/train_model.py
code served (permissive licence) · get_code("e6c57d84733e2f9d")
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 float64, 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 as nn
import numpy as np

torch.manual_seed(0)

class SimpleModel(nn.Module):
    def __init__(self):
        super().__init__()
        self.linear1 = nn.Linear(4, 3)
        self.linear2 = nn.Linear(3, 2)
    
    def forward(self, x):
        x = self.linear1(x)
        x = self.linear2(x)
        return x

model = SimpleModel()

ARGS = {
    'model': model,
    'blacklist': None
}
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 float64, 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
loss_function Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
ANLGBOY/MADE-with-PyTorch/made.py
pointer only (licence: NONE) · get_code("0fe5b1dc810c9785")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, ANLGBOY/MADE-with-PyTorch 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.

RunEpoch Not yet run
unverified (harvested, no recorded run)
naru-project/naru/train_model.py
code served (permissive licence) · get_code("102c922db0e8f637")
How it ran

no invocation recorded.

SampleTupleThenRandom Not yet run
unverified (harvested, no recorded run)
naru-project/naru/eval_model.py
code served (permissive licence) · get_code("397f2e703766c84e")
How it ran

no invocation recorded.

reproduce Not yet run
unverified (harvested, no recorded run)
EugenHotaj/pytorch-generative/pytorch_generative/models/autoregressive/made.py
code served (permissive licence) · get_code("57a4108d5f06492e")
How it ran

no invocation recorded.

reproduce Not yet run
unverified (harvested, no recorded run)
eyalbetzalel/pytorch-generative-v6/pytorch_generative/models/made.py
code served (permissive licence) · get_code("18d3650fbdec0da5")
How it ran

no invocation recorded.

Also present in other papers' code

Of 9 samples lifted from this paper's linked repositories, 9 carry a function identity and 0 do not. Of the 9 distinct functions with an identity, 4 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 4 later) and 5 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
Entropy 2 other papers
2 later
2210.05508 (2022-10)
Detect, Distill and Update: Learned DB Systems Facing Out of Distribution Data
2311.17276 (2023-11)
Machine Unlearning in Learned Databases: An Experimental Analysis
InvertOrder 2 other papers
2 later
2210.05508 (2022-10)
Detect, Distill and Update: Learned DB Systems Facing Out of Distribution Data
2311.17276 (2023-11)
Machine Unlearning in Learned Databases: An Experimental Analysis
ReportModel 1 other paper
1 later
2210.05508 (2022-10)
Detect, Distill and Update: Learned DB Systems Facing Out of Distribution Data
RunEpoch 1 other paper
1 later
2210.05508 (2022-10)
Detect, Distill and Update: Learned DB Systems Facing Out of Distribution Data

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

There has been a lot of recent interest in designing neural network models to estimate a distribution from a set of examples. We introduce a simple modification for autoencoder neural networks that yields powerful generative models. Our method masks the autoencoder's parameters to respect autoregressive constraints: each input is reconstructed only from previous inputs in a given ordering. Constrained this way, the autoencoder outputs can be interpreted as a set of conditional probabilities, and their product, the full joint probability. We can also train a single network that can decompose the joint probability in multiple different orderings. Our simple framework can be applied to multiple architectures, including deep ones. Vectorized implementations, such as on GPUs, are simple and fast. Experiments demonstrate that this approach is competitive with state-of-the-art tractable distribution estimators. At test time, the method is significantly faster and scales better than other autoregressive estimators.

For agents

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

get_harvested_code_for_paper("1502.03509")
get_code_for_paper("1502.03509")
have("1502.03509")

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

curl https://syntology.ai/api/ran/1502.03509.json

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

[![Syntology run record](https://syntology.ai/api/ran/1502.03509.svg)](https://syntology.ai/paper/1502.03509)

Connect an agent — have() is free.