SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2005.09682 · 2020

Data-driven derivation of stellar properties from photometric time series data using convolutional neural networks

arXiv · PDF · Open in the Atlas

Code that ran

10 of 11 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 10 have no contract verdict; 0 failures of our instrument; 1 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/2005.09682.json · badge: /api/ran/2005.09682.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
kblancato/theia-net canonical (classifier label)
classifier basis: census
10 ran · 1 no recorded run
FunctionStatusWhere it lives
create_log Ran
ran on a synthesized input
kblancato/theia-net/theia-net/classification/modules/mutils.py
code served (permissive licence) · get_code("5b2408e571829669")
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 TextIOWrapper. 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 os
import tempfile

# Create a temporary directory for the log file
temp_dir = tempfile.mkdtemp()
log_dir = temp_dir + os.sep

ARGS = {
    'dir': log_dir,
    'name': 'test_log'
}
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 TextIOWrapper — a TextIOWrapper 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
data_split Ran
ran on a synthesized input
kblancato/theia-net/theia-net/classification/modules/prepare_data.py
code served (permissive licence) · get_code("32603d33af9b46af")
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 numpy as np
import io

# Create a log file wrapper (StringIO for in-memory logging)
log = io.StringIO()

# Define parameters
len_data = 100  # Number of stars in sample

ARGS = {
    "len_data": len_data,
    "log": log,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, sklearn — 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
data_split Ran
ran on a synthesized input
kblancato/theia-net/theia-net/regression/modules/prepare_data.py
code served (permissive licence) · get_code("39276dfd7995f5d3")
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 numpy as np
from io import StringIO

# Create a log file-like object using StringIO
log = StringIO()

# Define the arguments
len_data = 100

ARGS = {
    "len_data": len_data,
    "log": log,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, sklearn — 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
inverse_scale Ran
ran on a synthesized input
kblancato/theia-net/theia-net/regression/modules/evaluate.py
code served (permissive licence) · get_code("e06a42d4ce4ea0dc")
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 1, dtype family float, shape (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 pickle
import numpy as np
import tempfile
import os
from sklearn.preprocessing import StandardScaler

# Create a temporary directory for the scaler files
tmpdir = tempfile.mkdtemp()

# Create and save a scaler for the test set
scaler = StandardScaler()
# Fit scaler on some dummy data
dummy_train_data = np.array([[1.0], [2.0], [3.0], [4.0], [5.0]])
scaler.fit(dummy_train_data)

# Save the scaler with the expected filename format
scaler_path = os.path.join(tmpdir, 'y_test_scaler.sav')
pickle.dump(scaler, open(scaler_path, 'wb'))

# Create scaled data to inverse transform
# Use data that's been scaled by the scaler
original_data = np.array([[1.5], [2.5], [3.5]])
scaled_data = scaler.transform(original_data).flatten()

ARGS = {
    'dir': tmpdir + '/',
    'set': 'test',
    'data': scaled_data
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, sklearn — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type ndarray, ndim 1, dtype family float, shape (3,) — shape (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
predictions Ran
ran on a synthesized input
kblancato/theia-net/theia-net/classification/modules/evaluate.py
code served (permissive licence) · get_code("0bfbd31dba0b4fd6")
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 1, dtype family int, shape (2,) 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 torch
from torch import nn
from torch.autograd import Variable
from torch.utils.data import DataLoader, TensorDataset

torch.manual_seed(0)

# Define a minimal model that takes xdata and sdata and outputs logits
class SimpleModel(nn.Module):
    def __init__(self):
        super().__init__()
        self.fc1 = nn.Linear(4, 8)
        self.fc2 = nn.Linear(3, 8)
        self.fc_out = nn.Linear(16, 3)  # 3 output classes for softmax
    
    def forward(self, xdata, sdata):
        x = torch.relu(self.fc1(xdata))
        s = torch.relu(self.fc2(sdata))
        combined = torch.cat([x, s], dim=1)
        return self.fc_out(combined)

# Create minimal tensors
xdata = torch.randn(2, 4)  # batch_size=2, feature_dim=4
sdata = torch.randn(2, 3)  # batch_size=2, secondary_feature_dim=3
ydata = torch.randint(0, 3, (2,))  # batch_size=2, 3 classes

# Create a dataset and data loader
dataset = TensorDataset(xdata, sdata, ydata)
data_loader = DataLoader(dataset, batch_size=2)

# Create model
model = SimpleModel()

# Set device to CPU
device = "cpu"

# Define arguments
ARGS = {
    "device": device,
    "model": model,
    "data_loader": data_loader
}
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 1, dtype family int, shape (2,) — shape (2,) 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
probs Ran
ran on a synthesized input
kblancato/theia-net/theia-net/classification/modules/evaluate.py
code served (permissive licence) · get_code("05b718118f0f79d8")
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, 2) 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
from torch.utils.data import DataLoader, TensorDataset

torch.manual_seed(0)

# Define a simple model that takes two inputs and outputs probabilities
class SimpleModel(nn.Module):
    def __init__(self):
        super(SimpleModel, self).__init__()
        self.fc1 = nn.Linear(4 + 3, 16)  # xdata is dim 4, sdata is dim 3
        self.fc2 = nn.Linear(16, 2)  # output 2 classes for softmax
    
    def forward(self, xdata, sdata):
        x = torch.cat([xdata, sdata], dim=1)
        x = torch.relu(self.fc1(x))
        x = self.fc2(x)
        return x

# Create small tensors for data
batch_size = 2
xdata = torch.randn(batch_size, 4)  # 4 features
sdata = torch.randn(batch_size, 3)  # 3 features
ydata = torch.randint(0, 2, (batch_size,))  # 2 classes

# Create dataset and data loader
dataset = TensorDataset(xdata, sdata, ydata)
data_loader = DataLoader(dataset, batch_size=batch_size)

# Create model
model = SimpleModel()

# Device
device = 'cpu'

ARGS = {
    'device': device,
    'model': model,
    'data_loader': data_loader
}
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, 2) — shape (2, 2) 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
r2 Ran
ran on a synthesized input
kblancato/theia-net/theia-net/regression/modules/evaluate.py
code served (permissive licence) · get_code("ff541345c9f09342")
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
from sklearn.metrics import r2_score

torch.manual_seed(0)

# Create small synthetic data for y_pred and y_true
# Both should be 1D or 2D array-like floats
y_pred = np.array([1.2, 2.1, 3.8, 4.1, 5.0])
y_true = np.array([1.0, 2.0, 4.0, 4.2, 5.1])

ARGS = {
    "y_pred": y_pred,
    "y_true": y_true,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, sklearn, 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
scale_data Ran
ran on a synthesized input
kblancato/theia-net/theia-net/classification/modules/prepare_data.py
code served (permissive licence) · get_code("8d3ceb89aebb690d")
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 (4, 2) 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 torch
from sklearn.preprocessing import StandardScaler

torch.manual_seed(0)

# Create sample time series data
# Shape: (n_samples, n_features) representing light curve flux values
data = np.random.randn(2, 4).astype(np.float32)

ARGS = {
    "data": data
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, sklearn, 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 (4, 2) — shape (4, 2) 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
scale_data Ran
ran on a synthesized input
kblancato/theia-net/theia-net/regression/modules/prepare_data.py
code served (permissive licence) · get_code("6bab47150a02639a")
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 numpy as np
import tempfile
import os

# Create temporary directory for scaler files
temp_dir = tempfile.mkdtemp() + "/"

# Create sample data
# data should be a 2D array where columns are samples and rows are features
data = np.random.randn(5, 8)  # 5 time points, 8 samples

# label should be a 1D array of stellar properties
label = np.random.randn(8)  # 8 samples

# set name
set_name = "train"

# directory path
dir_path = temp_dir

ARGS = {
    "data": data,
    "label": label,
    "set": set_name,
    "dir": dir_path
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, sklearn — 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
scale_stds Ran
ran on a synthesized input
kblancato/theia-net/theia-net/classification/modules/prepare_data.py
code served (permissive licence) · get_code("48704634e564b07d")
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 (5, 1) 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
from sklearn.preprocessing import StandardScaler, MinMaxScaler

# Create sample standard deviations
# Using positive values since they represent standard deviations
stds = np.array([0.1, 0.5, 1.0, 2.0, 5.0])

ARGS = {
    "stds": stds
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, sklearn — 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 (5, 1) — shape (5, 1) 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
predictions Not yet run
unverified (harvested, no recorded run)
kblancato/theia-net/theia-net/regression/modules/evaluate.py
code served (permissive licence) · get_code("80b0c7c31183d1d2")
How it ran

no invocation recorded.

Also present in other papers' code

Of 11 samples lifted from this paper's linked repositories, 11 carry a function identity and 0 do not. Of the 10 distinct functions with an identity, 0 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 0 later) and 10 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.

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

Stellar variability is driven by a multitude of internal physical processes that depend on fundamental stellar properties. These properties are our bridge to reconciling stellar observations with stellar physics, and for understanding the distribution of stellar populations within the context of galaxy formation. Numerous ongoing and upcoming missions are charting brightness fluctuations of stars over time, which encode information about physical processes such as rotation period, evolutionary state (such as effective temperature and surface gravity), and mass (via asteroseismic parameters). Here, we explore how well we can predict these stellar properties, across different evolutionary states, using only photometric time series data. To do this, we implement a convolutional neural network, and with data-driven modeling we predict stellar properties from light curves of various baselines and cadences. Based on a single quarter of \textit{Kepler} data, we recover stellar properties, including surface gravity for red giant stars (with an uncertainty of $\lesssim$ 0.06 dex), and rotation period for main sequence stars (with an uncertainty of $\lesssim$ 5.2 days, and unbiased from $\approx$5 to 40 days). Shortening the \textit{Kepler} data to a 27-day TESS-like baseline, we recover stellar properties with a small decrease in precision, $\sim$0.07 dex for log $g$ and $\sim$5.5 days for $P_{\rm rot}$, unbiased from $\approx$5 to 35 days. Our flexible data-driven approach leverages the full information content of the data, requires minimal feature engineering, and can be generalized to other surveys and datasets. This has the potential to provide stellar property estimates for many millions of stars in current and future surveys.

For agents

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

get_harvested_code_for_paper("2005.09682")
get_code_for_paper("2005.09682")
have("2005.09682")

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

curl https://syntology.ai/api/ran/2005.09682.json

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

[![Syntology run record](https://syntology.ai/api/ran/2005.09682.svg)](https://syntology.ai/paper/2005.09682)

Connect an agent — have() is free.