SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2201.04929 · 2022

Improving VAE based molecular representations for compound property prediction

arXiv · PDF · Open in the Atlas

Code that ran

6 of 10 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; 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/2201.04929.json · badge: /api/ran/2201.04929.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
znavoyan/vae-embeddings canonical (classifier label)
classifier basis not recorded on the link
6 ran · 4 no recorded run
FunctionStatusWhere it lives
adjust_learning_rate Ran
ran on a synthesized input
znavoyan/vae-embeddings/pvae/model_property2.py
code served (permissive licence) · get_code("424b8912cfe83a0e")
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, 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 torch
import torch.nn as nn
from torch.optim import SGD

torch.manual_seed(0)

# Create a simple model
model = nn.Linear(4, 3)

# Create an optimizer
optimizer = SGD(model.parameters(), lr=0.1)

# Define the arguments
ARGS = {
    'optimizer': optimizer,
    'epoch': 5,
    'learning_rate': 0.1
}
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, ndim 1, dtype family float — a tuple 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
load_params Ran
ran on a synthesized input
znavoyan/vae-embeddings/chemical_vae/chemvae/hyperparameters.py
code served (permissive licence) · get_code("477556f5d7718b5c")
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 json
import tempfile
import os
from collections import OrderedDict

# Create a temporary JSON file with sample hyperparameters
temp_params = {
    'batch_size': 64,
    'epochs': 10,
    'lr': 0.001,
    'conv_depth': 3,
    'hidden_dim': 128
}

# Write to a temporary file
temp_file = tempfile.NamedTemporaryFile(mode='w', suffix='.json', delete=False)
json.dump(temp_params, temp_file)
temp_file.close()

ARGS = {
    'param_file': temp_file.name,
    'verbose': True
}
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 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
no_schedule Ran
ran on a synthesized input
znavoyan/vae-embeddings/chemical_vae/chemvae/mol_callbacks.py
code served (permissive licence) · get_code("35a9e12221a43457")
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

torch.manual_seed(0)

ARGS = {
    'epoch_num': 0
}
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 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
sample Ran
ran on a synthesized input
znavoyan/vae-embeddings/chemical_vae/chemvae/mol_callbacks.py
code served (permissive licence) · get_code("9ec4e9feb8c0fd10")
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 int64, ndim 0, dtype family int, 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 numpy as np

# The function 'sample' takes:
# - a: a numpy array of probabilities (used with np.log, np.exp, np.sum, np.argmax, np.random.multinomial)
# - temperature: a float (default 0.01)

# We need to create a valid probability distribution for 'a'
# The function applies softmax-like operations and samples from a multinomial distribution
# So 'a' should be a 1D array of probabilities that sum to 1

np.random.seed(0)
a = np.array([0.1, 0.2, 0.3, 0.4])  # A simple probability distribution
temperature = 0.01

ARGS = {
    "a": a,
    "temperature": temperature,
}
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 int64, ndim 0, dtype family int, 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
sigmoid_schedule Ran
ran on a synthesized input
znavoyan/vae-embeddings/chemical_vae/chemvae/mol_callbacks.py
code served (permissive licence) · get_code("77da6e54bdddeda7")
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 numpy as np

ARGS = {
    "time_step": 5,
    "slope": 1.0,
    "start": 10
}
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 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
to_var Ran
ran on a synthesized input
znavoyan/vae-embeddings/pvae/model_property2.py
code served (permissive licence) · get_code("2c9ee1610b7b5f61")
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. 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
from torch.autograd import Variable

torch.manual_seed(0)

# Create a small tensor for testing
x = torch.randn(2, 4)

# Set up arguments for to_var function
ARGS = {
    'x': x,
    'device_id': 0,
    'gpu_exist': False,
    'volatile': False
}
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 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
batch2tensor Not yet run
unverified (harvested, no recorded run)
znavoyan/vae-embeddings/pvae/model_property2.py
code served (permissive licence) · get_code("ff750faf19b66abc")
How it ran

no invocation recorded.

kl_loss Not yet run
unverified (harvested, no recorded run)
znavoyan/vae-embeddings/chemical_vae/chemvae/train_vae.py
code served (permissive licence) · get_code("adafd809fa1dd2eb")
How it ran

no invocation recorded.

load_encoder Not yet run
unverified (harvested, no recorded run)
znavoyan/vae-embeddings/chemical_vae/chemvae/models.py
code served (permissive licence) · get_code("f4d0cf89b5826b22")
How it ran

no invocation recorded.

sampled_rnn Not yet run
unverified (harvested, no recorded run)
znavoyan/vae-embeddings/chemical_vae/chemvae/sampled_rnn_tf.py
code served (permissive licence) · get_code("ae4e7b0062e35c1c")
How it ran

no invocation recorded.

Also present in other papers' code

Of 10 samples lifted from this paper's linked repositories, 10 carry a function identity and 0 do not. Of the 10 distinct functions with an identity, 7 are also present in other papers whose code we hold (7 with at least one paper dated earlier, 0 the same month, 0 later) and 3 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
kl_loss 1 other paper
1 dated earlier
1610.02415 (2016-10)
Automatic Chemical Design Using a Data-Driven Continuous Representation of Molecules
load_encoder 1 other paper
1 dated earlier
1610.02415 (2016-10)
Automatic Chemical Design Using a Data-Driven Continuous Representation of Molecules
load_params 1 other paper
1 dated earlier
1610.02415 (2016-10)
Automatic Chemical Design Using a Data-Driven Continuous Representation of Molecules
no_schedule 1 other paper
1 dated earlier
1610.02415 (2016-10)
Automatic Chemical Design Using a Data-Driven Continuous Representation of Molecules
sample 1 other paper
1 dated earlier
1610.02415 (2016-10)
Automatic Chemical Design Using a Data-Driven Continuous Representation of Molecules
sampled_rnn 1 other paper
1 dated earlier
1610.02415 (2016-10)
Automatic Chemical Design Using a Data-Driven Continuous Representation of Molecules
sigmoid_schedule 1 other paper
1 dated earlier
1610.02415 (2016-10)
Automatic Chemical Design Using a Data-Driven Continuous Representation of Molecules

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

Collecting labeled data for many important tasks in chemoinformatics is time consuming and requires expensive experiments. In recent years, machine learning has been used to learn rich representations of molecules using large scale unlabeled molecular datasets and transfer the knowledge to solve the more challenging tasks with limited datasets. Variational autoencoders are one of the tools that have been proposed to perform the transfer for both chemical property prediction and molecular generation tasks. In this work we propose a simple method to improve chemical property prediction performance of machine learning models by incorporating additional information on correlated molecular descriptors in the representations learned by variational autoencoders. We verify the method on three property prediction asks. We explore the impact of the number of incorporated descriptors, correlation between the descriptors and the target properties, sizes of the datasets etc. Finally, we show the relation between the performance of property prediction models and the distance between property prediction dataset and the larger unlabeled dataset in the representation space.

For agents

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

get_harvested_code_for_paper("2201.04929")
get_code_for_paper("2201.04929")
have("2201.04929")

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

curl https://syntology.ai/api/ran/2201.04929.json

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

[![Syntology run record](https://syntology.ai/api/ran/2201.04929.svg)](https://syntology.ai/paper/2201.04929)

Connect an agent — have() is free.