SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1910.00698 · 2019

Re-balancing Variational Autoencoder Loss for Molecule Sequence Generation

arXiv · PDF · Open in the Atlas

Code that ran

3 of 3 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 3 have no contract verdict; 0 failures of our instrument; 0 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/1910.00698.json · badge: /api/ran/1910.00698.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
chaoyan1037/Re-balanced-VAE canonical (classifier label)
classifier basis: census
3 ran · 0 no recorded run
FunctionStatusWhere it lives
compute_kernel_numpy Ran
ran on a synthesized input
chaoyan1037/Re-balanced-VAE/bo/gauss.py
code served (permissive licence) · get_code("6c74edc2c0dc695e")
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 2, dtype family float, shape (2, 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 numpy as np

# Analyze the function:
# - lls: log length scale(s), used as np.exp(lls), then in np.outer with ls
#   appears to be 1D array of shape (n_features,)
# - lsf: log signal frequency, scalar or array, used as np.exp(lsf)
# - x: data array, can be 1D or 2D, shape (n_samples, n_features) after processing
# - z: data array, can be 1D or 2D, shape (m_samples, n_features) after processing

# The function computes a kernel matrix between x and z
# Let's create small distinct dimensions:
# - n_features = 4 (for lls dimension)
# - n_samples_x = 2 (for x)
# - n_samples_z = 3 (for z, different from x to avoid ambiguity)

np.random.seed(0)

# lls: log length scale, one per feature, shape (4,)
lls = np.array([-0.5, 0.0, 0.2, -0.3])

# lsf: log signal frequency, scalar
lsf = np.array(0.5)

# x: input data, shape (2, 4)
x = np.random.randn(2, 4)

# z: reference data, shape (3, 4)
z = np.random.randn(3, 4)

ARGS = {
    "lls": lls,
    "lsf": lsf,
    "x": x,
    "z": z
}
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 ndarray, ndim 2, dtype family float, shape (2, 3) — shape (2, 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
load_object Ran
ran on a synthesized input
chaoyan1037/Re-balanced-VAE/bo/print_result.py
code served (permissive licence) · get_code("efe304eb2d1e874e")
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 gzip
import pickle
import tempfile
import os

# Create a temporary gzip file with pickled data
temp_dir = tempfile.mkdtemp()
test_data = {"key": "value", "number": 42, "list": [1, 2, 3]}

temp_file = os.path.join(temp_dir, "test_object.pkl.gz")
with gzip.GzipFile(temp_file, 'wb') as f:
    f.write(pickle.dumps(test_data))

ARGS = {
    "filename": temp_file
}
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
load_object Ran
ran on a synthesized input
chaoyan1037/Re-balanced-VAE/bo/run_bo.py
code served (permissive licence) · get_code("0a5b664a833db116")
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 pickle
import gzip
import tempfile
import os

# Create a temporary gzip file with pickled content
temp_dir = tempfile.mkdtemp()
test_filename = os.path.join(temp_dir, "test_object.pkl.gz")

# Create test data to pickle and compress
test_data = {
    "key1": "value1",
    "key2": [1, 2, 3, 4],
    "key3": {"nested": "dict"}
}

# Write the test data to a gzip-compressed pickle file
with gzip.GzipFile(test_filename, 'wb') as f:
    f.write(pickle.dumps(test_data))

ARGS = {
    "filename": test_filename
}
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

Also present in other papers' code

Of 3 samples lifted from this paper's linked repositories, 3 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 (2 with at least one paper dated earlier, 0 the same month, 1 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
compute_kernel_numpy 2 other papers
1 dated earlier, 1 later
1904.11088 (2019-04)
D-VAE: A Variational Autoencoder for Directed Acyclic Graphs
2010.04683 (2020-10)
Smooth Variational Graph Embeddings for Efficient Neural Architecture Search
load_object 1 other paper
1 dated earlier
1904.11088 (2019-04)
D-VAE: A Variational Autoencoder for Directed Acyclic Graphs

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

Molecule generation is to design new molecules with specific chemical properties and further to optimize the desired chemical properties. Following previous work, we encode molecules into continuous vectors in the latent space and then decode the vectors into molecules under the variational autoencoder (VAE) framework. We investigate the posterior collapse problem of current RNN-based VAEs for molecule sequence generation. For the first time, we find that underestimated reconstruction loss leads to posterior collapse, and provide both theoretical and experimental evidence. We propose an effective and efficient solution to fix the problem and avoid posterior collapse. Without bells and whistles, our method achieves SOTA reconstruction accuracy and competitive validity on the ZINC 250K dataset. When generating 10,000 unique valid SMILES from random prior sampling, it costs JT-VAE1450s while our method only needs 9s. Our implementation is at https://github.com/chaoyan1037/Re-balanced-VAE.

For agents

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

get_harvested_code_for_paper("1910.00698")
get_code_for_paper("1910.00698")
have("1910.00698")

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

curl https://syntology.ai/api/ran/1910.00698.json

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

[![Syntology run record](https://syntology.ai/api/ran/1910.00698.svg)](https://syntology.ai/paper/1910.00698)

Connect an agent — have() is free.