SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1610.02415 · 2016

Automatic Chemical Design Using a Data-Driven Continuous Representation of Molecules

José Hernández-Lobato, David Duvenaud, Ryan Adams, Alán Aspuru-Guzik, Rafael Gómez-Bombarelli, Jorge Aguilera-Iparraguirre, Timothy Hirzel, Jennifer Wei, Benjamín Sánchez-Lengeling, Dennis Sheberla

arXiv · PDF · Open in the Atlas

Code that ran

17 of 26 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (1 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 0 violated it and 14 have no contract verdict; 3 failures of our instrument; 9 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/1610.02415.json · badge: /api/ran/1610.02415.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
aspuru-guzik-group/chemical_vae canonical (classifier label)
classifier basis: census
4 ran · 5 no recorded run
TrentBrick/PAE community
Papers with Code archive
4 ran · 2 no recorded run
brettin/keras-molecule community (classifier label)
classifier basis not recorded on the link
4 ran · 2 no recorded run
shamelmerchant/keras-molecules community (classifier label)
classifier basis not recorded on the link
3 ran · 0 no recorded run
Ishan-Kumar2/Molecular_VAE_Pytorch community
Papers with Code archive
1 ran · 0 no recorded run
tevang/keras-molecules community (classifier label)
classifier basis not recorded on the link
1 ran · 0 no recorded run
FunctionStatusWhere it lives
EncoderNet Ran
ran on a synthesized input · constructed an object; no result was computed
TrentBrick/PAE/models.py
pointer only (licence: NONE) · get_code("357f9708b1bc108f")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, TrentBrick/PAE 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.

VAE Ran
ran on a synthesized input
Ishan-Kumar2/Molecular_VAE_Pytorch/model.py
pointer only (licence: NONE) · get_code("9d3e8ba984573f39")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, Ishan-Kumar2/Molecular_VAE_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.

calculate_dihedral_angles Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
TrentBrick/PAE/models.py
pointer only (licence: NONE) · get_code("2759306b31600c75")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, TrentBrick/PAE 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.

calculate_dihedral_angles_over_minibatch Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
TrentBrick/PAE/models.py
pointer only (licence: NONE) · get_code("a65129b833351ed3")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, TrentBrick/PAE 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.

compute_dihedral_list Ran
ran; our contract draft was wrong, not the code
TrentBrick/PAE/models.py
pointer only (licence: NONE) · get_code("7cb1abfcf8bf5724")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, TrentBrick/PAE 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.

from_one_hot_array Ran
ran on a synthesized input
brettin/keras-molecule/molecules/utils.py
code served (permissive licence) · get_code("1fe2f6e70c6a05f4")
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 int, 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

# Create a valid one-hot encoded vector
# The function uses np.where to find the index where value == 1
# It returns the first index found, or None if no 1 is present

vec = np.array([0, 1, 0, 0])

ARGS = {
    "vec": vec
}
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 int, 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
load_dataset Ran
ran on a synthesized input
brettin/keras-molecule/gae_baseline_keras2.py
code served (permissive licence) · get_code("191bac36ba89d022")
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. 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 h5py
import numpy as np
import tempfile
import os

# Create a temporary HDF5 file with the required structure
temp_dir = tempfile.mkdtemp()
temp_file = os.path.join(temp_dir, "test_dataset.h5")

# Create HDF5 file with required datasets
h5f = h5py.File(temp_file, 'w')
h5f.create_dataset('data_train', data=np.random.rand(2, 4).astype(np.float32))
h5f.create_dataset('data_test', data=np.random.rand(3, 4).astype(np.float32))
h5f.create_dataset('charset', data=np.array([ord(c) for c in 'abc']).astype(np.int32))
h5f.close()

ARGS = {
    'filename': temp_file,
    'split': True
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
h5py, numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type tuple — a tuple output has no array shape of its own; none is 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
load_params Ran
ran on a synthesized input
aspuru-guzik-group/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
aspuru-guzik-group/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
one_hot_array Ran
ran on a synthesized input
shamelmerchant/keras-molecules/molecules/utils.py
code served (permissive licence) · get_code("5135dd76b5db5e1b")
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)

# one_hot_array takes two parameters:
# i: an index (integer)
# n: the size of the one-hot vector (integer)
# The function creates a one-hot encoded list where position i is 1 and all others are 0

ARGS = {
    "i": 2,
    "n": 5
}
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
one_hot_index Ran
ran on a synthesized input
brettin/keras-molecule/molecules/utils.py
code served (permissive licence) · get_code("f675b9db54c981a4")
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 map. 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

torch.manual_seed(0)

# The function takes a vector (iterable of items) and a charset (must have .index method)
# It maps charset.index over each element in vec

# vec should be an iterable of items that exist in charset
# charset should be a string or sequence with an .index method

vec = "hello"
charset = "helo"

ARGS = {
    "vec": vec,
    "charset": charset,
}
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 map — a map output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a map 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
one_hot_index Ran
ran on a synthesized input
shamelmerchant/keras-molecules/molecules/utils.py
code served (permissive licence) · get_code("d63552807afa0c83")
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
import numpy as np

# The function takes a vec (iterable) and charset (string-like with .index method)
# It maps charset.index over each element of vec
# So vec should be an iterable of characters, and charset should be a string

vec = "abc"
charset = "abcde"

ARGS = {
    "vec": vec,
    "charset": charset
}
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 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
one_hot_index Ran
ran on a synthesized input
tevang/keras-molecules/molecules/utils.py
code served (permissive licence) · get_code("bb81c69331a6c0b3")
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)

# The function takes two parameters: vec and charset
# vec: an iterable of items to look up
# charset: an iterable of items that will be converted to strings and indexed

# Based on the function body:
# - charset is converted to a list of strings
# - map(charset.index, vec) is called, which means each element in vec
#   must be findable in the charset list (after string conversion)

# Create a simple charset - a list of characters/items
charset = ['a', 'b', 'c', 'd']

# Create a vec that contains items from the charset
vec = ['a', 'c', 'b', 'd', 'a']

ARGS = {
    'vec': vec,
    'charset': charset
}
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
read_latent_data Ran
ran on a synthesized input
brettin/keras-molecule/sample.py
code served (permissive licence) · get_code("9fd2c3a0bcff17cb")
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. 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 h5py
import tempfile
import numpy as np
import os

# Create a temporary HDF5 file with the required datasets
temp_fd, temp_path = tempfile.mkstemp(suffix='.h5')
os.close(temp_fd)

try:
    h5f = h5py.File(temp_path, 'w')
    
    # Create latent_vectors dataset - small tensor with shape (2, 4)
    latent_data = np.random.randn(2, 4).astype(np.float32)
    h5f.create_dataset('latent_vectors', data=latent_data)
    
    # Create charset dataset - small string array
    charset_data = np.array([b'a', b'b', b'c', b'd'], dtype='S1')
    h5f.create_dataset('charset', data=charset_data)
    
    h5f.close()
    
    ARGS = {
        'filename': temp_path
    }
except Exception as e:
    raise e
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
h5py, numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type tuple — a tuple output has no array shape of its own; none is 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
read_latent_data Ran
ran on a synthesized input
shamelmerchant/keras-molecules/sample.py
code served (permissive licence) · get_code("c93e42c2bc417e34")
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. 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 h5py
import numpy as np
import tempfile
import os

# Create a temporary HDF5 file with the required structure
temp_dir = tempfile.mkdtemp()
temp_file = os.path.join(temp_dir, "test_latent_data.h5")

# Create the HDF5 file with the expected datasets
h5f = h5py.File(temp_file, 'w')

# Create latent_vectors dataset (shape: 2x4 as per requirements)
latent_data = np.random.randn(2, 4).astype(np.float32)
h5f.create_dataset('latent_vectors', data=latent_data)

# Create charset dataset as bytes
charset_list = [b'a', b'b', b'c']
h5f.create_dataset('charset', data=charset_list)

h5f.close()

ARGS = {
    'filename': temp_file
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
h5py, numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type tuple — a tuple output has no array shape of its own; none is 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
sample Ran
ran on a synthesized input
aspuru-guzik-group/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
aspuru-guzik-group/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
embed Not yet run
unverified (harvested, no recorded run)
TrentBrick/PAE/models.py
pointer only (licence: NONE) · get_code("b31e3a32763105ee")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, TrentBrick/PAE 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.

kl_loss Not yet run
unverified (harvested, no recorded run)
aspuru-guzik-group/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)
aspuru-guzik-group/chemical_vae/chemvae/models.py
code served (permissive licence) · get_code("f4d0cf89b5826b22")
How it ran

no invocation recorded.

load_models Not yet run
unverified (harvested, no recorded run)
aspuru-guzik-group/chemical_vae/chemvae/train_vae.py
code served (permissive licence) · get_code("9e16442ff698149f")
How it ran

no invocation recorded.

one_hot_array Not yet run
unverified (harvested, no recorded run)
brettin/keras-molecule/molecules/utils.py
code served (permissive licence) · get_code("9b9f450f2860db66")
How it ran

no invocation recorded.

read_smiles_data Not yet run
unverified (harvested, no recorded run)
brettin/keras-molecule/sample_gen.py
code served (permissive licence) · get_code("bc9aef878f647204")
How it ran

no invocation recorded.

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

no invocation recorded.

vectorize_data Not yet run
unverified (harvested, no recorded run)
aspuru-guzik-group/chemical_vae/chemvae/train_vae.py
code served (permissive licence) · get_code("4ad7fa717d84ee70")
How it ran

no invocation recorded.

write_out Not yet run
unverified (harvested, no recorded run)
TrentBrick/PAE/models.py
pointer only (licence: NONE) · get_code("ce44cbef729e1f6f")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, TrentBrick/PAE 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.

Also present in other papers' code

Of 26 samples lifted from this paper's linked repositories, 26 carry a function identity and 0 do not. Of the 26 distinct functions with an identity, 7 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 7 later) and 19 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 later
2201.04929 (2022-01)
Improving VAE based molecular representations for compound property prediction
load_encoder 1 other paper
1 later
2201.04929 (2022-01)
Improving VAE based molecular representations for compound property prediction
load_params 1 other paper
1 later
2201.04929 (2022-01)
Improving VAE based molecular representations for compound property prediction
no_schedule 1 other paper
1 later
2201.04929 (2022-01)
Improving VAE based molecular representations for compound property prediction
sample 1 other paper
1 later
2201.04929 (2022-01)
Improving VAE based molecular representations for compound property prediction
sampled_rnn 1 other paper
1 later
2201.04929 (2022-01)
Improving VAE based molecular representations for compound property prediction
sigmoid_schedule 1 other paper
1 later
2201.04929 (2022-01)
Improving VAE based molecular representations for compound property prediction

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

We report a method to convert discrete representations of molecules to and from a multidimensional continuous representation. This model allows us to generate new molecules for efficient exploration and optimization through open-ended spaces of chemical compounds.

For agents

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

get_harvested_code_for_paper("1610.02415")
get_code_for_paper("1610.02415")
have("1610.02415")

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

curl https://syntology.ai/api/ran/1610.02415.json

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

[![Syntology run record](https://syntology.ai/api/ran/1610.02415.svg)](https://syntology.ai/paper/1610.02415)

Connect an agent — have() is free.