SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2111.08095 · 2021

TimeVAE: A Variational Auto-Encoder for Multivariate Time Series Generation

arXiv · PDF · Open in the Atlas

Code that ran

6 of 6 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 4 have no contract verdict; 1 failure of our instrument; 0 no recorded run), measured 2026-11-21; 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/2111.08095.json · badge: /api/ran/2111.08095.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
abudesai/timeVAE canonical (classifier label)
classifier basis not recorded on the link
5 ran · 0 no recorded run
wangyz1999/timeVAE-pytorch community (classifier label)
classifier basis not recorded on the link
1 ran · 0 no recorded run
FunctionStatusWhere it lives
avg_over_dim Ran
ran on a synthesized input
abudesai/timeVAE/src/visualize.py
code served (permissive licence) · get_code("cb3b6d5e7c398574")
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

# Create a small numpy array with distinct dimensions
# Shape: (2, 4, 3) - batch of 2, 4 features, 3 time steps
data = np.random.randn(2, 4, 3)

# axis parameter - averaging over axis 1 (feature dimension)
axis = 1

ARGS = {
    "data": data,
    "axis": axis,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, pandas — 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
get_npz_data Ran
ran on a synthesized input
abudesai/timeVAE/src/data_utils.py
code served (permissive licence) · get_code("28360302e713cbf1")
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, 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 numpy as np
import tempfile
import os

# Create a temporary .npz file with sample data
temp_dir = tempfile.mkdtemp()
temp_npz_path = os.path.join(temp_dir, "test_data.npz")

# Create sample data and save to .npz file
sample_data = np.array([[1.0, 2.0, 3.0, 4.0],
                        [5.0, 6.0, 7.0, 8.0]])
np.savez(temp_npz_path, data=sample_data)

ARGS = {
    "input_file": temp_npz_path
}
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, 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
get_posterior_samples Ran
ran on a synthesized input
abudesai/timeVAE/src/vae/vae_utils.py
code served (permissive licence) · get_code("d6a5d70dbe0a6a4b")
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, 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 torch.nn as nn
import numpy as np

torch.manual_seed(0)

class SimpleVAE(nn.Module):
    """Minimal VAE that implements predict method"""
    def __init__(self, input_dim=4, latent_dim=3):
        super().__init__()
        self.input_dim = input_dim
        self.latent_dim = latent_dim
        
        # Encoder
        self.encoder = nn.Sequential(
            nn.Linear(input_dim, 8),
            nn.ReLU(),
            nn.Linear(8, latent_dim * 2)
        )
        
        # Decoder
        self.decoder = nn.Sequential(
            nn.Linear(latent_dim, 8),
            nn.ReLU(),
            nn.Linear(8, input_dim)
        )
    
    def encode(self, x):
        """Return mean and log_var"""
        h = self.encoder(x)
        mu = h[:, :self.latent_dim]
        log_var = h[:, self.latent_dim:]
        return mu, log_var
    
    def reparameterize(self, mu, log_var):
        """Sample from latent distribution"""
        std = torch.exp(0.5 * log_var)
        eps = torch.randn_like(std)
        return mu + eps * std
    
    def decode(self, z):
        """Reconstruct from latent"""
        return self.decoder(z)
    
    def forward(self, x):
        mu, log_var = self.encode(x)
        z = self.reparameterize(mu, log_var)
        return self.decode(z), mu, log_var
    
    def predict(self, data, verbose=0):
        """Generate posterior samples from data"""
        # Convert numpy to tensor
        if isinstance(data, np.ndarray):
            x = torch.from_numpy(data).float()
        else:
            x = data.float()
        
        # Encode to get posterior parameters
        with torch.no_grad():
            mu, log_var = self.encode(x)
            # Sample from posterior
            z = self.reparameterize(mu, log_var)
            # Decode to get samples
            samples = self.decode(z)
        
        # Return as numpy
        return samples.numpy()


# Create VAE model
vae = SimpleVAE(input_dim=4, latent_dim=3)
vae.eval()

# Create sample data (batch_size=2, features=4)
data = np.random.randn(2, 4).astype(np.float32)

ARGS = {
    "vae": vae,
    "data": data
}
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 ndarray, 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
get_posterior_samples Ran
ran on a synthesized input
wangyz1999/timeVAE-pytorch/src/vae/vae_utils.py
code served (permissive licence) · get_code("43055cf5ba0cd817")
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 torch
import torch.nn as nn
import numpy as np

torch.manual_seed(0)

class SimpleVAE(nn.Module):
    """Minimal VAE implementation with predict method."""
    def __init__(self, input_dim=4, latent_dim=3):
        super().__init__()
        self.input_dim = input_dim
        self.latent_dim = latent_dim
        
        # Encoder
        self.encoder = nn.Sequential(
            nn.Linear(input_dim, 8),
            nn.ReLU(),
            nn.Linear(8, 6)
        )
        
        # Latent projections
        self.fc_mu = nn.Linear(6, latent_dim)
        self.fc_logvar = nn.Linear(6, latent_dim)
        
        # Decoder
        self.decoder = nn.Sequential(
            nn.Linear(latent_dim, 8),
            nn.ReLU(),
            nn.Linear(8, input_dim)
        )
    
    def encode(self, x):
        h = self.encoder(x)
        mu = self.fc_mu(h)
        logvar = self.fc_logvar(h)
        return mu, logvar
    
    def reparameterize(self, mu, logvar):
        std = torch.exp(0.5 * logvar)
        eps = torch.randn_like(std)
        z = mu + eps * std
        return z
    
    def decode(self, z):
        return self.decoder(z)
    
    def forward(self, x):
        mu, logvar = self.encode(x)
        z = self.reparameterize(mu, logvar)
        recon = self.decode(z)
        return recon, mu, logvar, z
    
    def predict(self, data):
        """
        Generate posterior samples from input data.
        
        Args:
            data (np.ndarray): Input data of shape (batch_size, input_dim)
            
        Returns:
            np.ndarray: Posterior samples (latent representations)
        """
        with torch.no_grad():
            x = torch.from_numpy(data).float()
            mu, logvar = self.encode(x)
            z = self.reparameterize(mu, logvar)
            return z.numpy()

# Create model
vae = SimpleVAE(input_dim=4, latent_dim=3)
vae.eval()

# Create dummy data
data = np.random.randn(2, 4).astype(np.float32)

ARGS = {
    'vae': vae,
    'data': data
}
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 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_data Ran
ran, honoured the contract we drafted
abudesai/timeVAE/src/data_utils.py
code served (permissive licence) · get_code("67129d93b7abfb9f")
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, 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 os
import numpy as np
import tempfile

# Create a temporary directory for the test data
temp_dir = tempfile.mkdtemp()

# Create a sample .npz file with test data
data_array = np.array([[1, 2, 3, 4], [5, 6, 7, 8]], dtype=np.float32)
npz_path = os.path.join(temp_dir, 'test_dataset.npz')
np.savez(npz_path, data=data_array)

# Define the arguments for load_data function
ARGS = {
    'data_dir': temp_dir,
    'dataset': 'test_dataset'
}
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, 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
load_yaml_file Ran
ran; our contract draft was wrong, not the code
abudesai/timeVAE/src/data_utils.py
pointer only (licence: MIT); the stored copy get_code serves, from Amorim009/Grasynda, is pointer only (licence: NONE) · get_code("55cbda5ae15d39e5")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from Amorim009/Grasynda, and GitHub detected no licence in that repository 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.

Also present in other papers' code

Of 6 samples lifted from this paper's linked repositories, 6 carry a function identity and 0 do not. Of the 6 distinct functions with an identity, 2 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 2 later) and 4 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
load_data 1 other paper
1 later
2608.10891 (2026-08)
Benchmarking Synthetic Time Series Generation Methods for Privacy-Preserving Forecasting
load_yaml_file 1 other paper
1 later
2608.10891 (2026-08)
Benchmarking Synthetic Time Series Generation Methods for Privacy-Preserving Forecasting

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 2026-11-21.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Recent work in synthetic data generation in the time-series domain has focused on the use of Generative Adversarial Networks. We propose a novel architecture for synthetically generating time-series data with the use of Variational Auto-Encoders (VAEs). The proposed architecture has several distinct properties: interpretability, ability to encode domain knowledge, and reduced training times. We evaluate data generation quality by similarity and predictability against four multivariate datasets. We experiment with varying sizes of training data to measure the impact of data availability on generation quality for our VAE method as well as several state-of-the-art data generation methods. Our results on similarity tests show that the VAE approach is able to accurately represent the temporal attributes of the original data. On next-step prediction tasks using generated data, the proposed VAE architecture consistently meets or exceeds performance of state-of-the-art data generation methods. While noise reduction may cause the generated data to deviate from original data, we demonstrate the resulting de-noised data can significantly improve performance for next-step prediction using generated data. Finally, the proposed architecture can incorporate domain-specific time-patterns such as polynomial trends and seasonalities to provide interpretable outputs. Such interpretability can be highly advantageous in applications requiring transparency of model outputs or where users desire to inject prior knowledge of time-series patterns into the generative model.

For agents

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

get_harvested_code_for_paper("2111.08095")
get_code_for_paper("2111.08095")
have("2111.08095")

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

curl https://syntology.ai/api/ran/2111.08095.json

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

[![Syntology run record](https://syntology.ai/api/ran/2111.08095.svg)](https://syntology.ai/paper/2111.08095)

Connect an agent — have() is free.