SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2011.01243 · NeurIPS · 2020

Classification of Periodic Variable Stars with Novel Cyclic-Permutation Invariant Neural Networks

Keming Zhang, Joshua Bloom

arXiv · PDF · Open in the Atlas

Code that ran

7 of 7 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (4 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 0 violated it and 4 have no contract verdict; 3 failures of our instrument; 0 no recorded run), measured 2026-11-22; 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/2011.01243.json · badge: /api/ran/2011.01243.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
kmzzhang/periodicnetwork canonical (classifier label)
classifier basis: classifier_2025
4 ran · 0 no recorded run
jarrelscy/iResnet reimplementation (classifier label)
classifier basis: classifier_2025
3 ran · 0 no recorded run
FunctionStatusWhere it lives
Classifier Ran
ran on a synthesized input · constructed an object; no result was computed
kmzzhang/periodicnetwork/model/itcn.py
pointer only (licence: NONE) · get_code("fa53c9fd22a3e325")
How it ran

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

CyclicTemporalConvNet Ran
ran on a synthesized input · constructed an object; no result was computed
kmzzhang/periodicnetwork/model/itcn.py
pointer only (licence: NONE) · get_code("4837e320f3b94b42")
How it ran

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

SymmetryPadding Ran
ran on a synthesized input · constructed an object; no result was computed
kmzzhang/periodicnetwork/model/itcn.py
pointer only (licence: NONE) · get_code("c93ca2fda4e61bb7")
How it ran

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

TemporalBlock Ran
ran on a synthesized input · constructed an object; no result was computed
kmzzhang/periodicnetwork/model/itcn.py
pointer only (licence: NONE) · get_code("77706e8ce2c1fe18")
How it ran

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

apply_module_reverse Ran
ran; our contract draft was wrong, not the code
jarrelscy/iResnet/InvertibleResnet.py
code served (permissive licence) · get_code("6a49dcd69371259b")
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) and returned Tensor, 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

torch.manual_seed(0)

# Create a mock block module that accepts reverse and reverse_iterations
class MockBlock(nn.Module):
    def __init__(self):
        super().__init__()
        self.linear = nn.Linear(4, 3)
    
    def forward(self, x, reverse=False, reverse_iterations=None):
        if reverse:
            return self.linear(x)
        return self.linear(x)

# Create a mock non-block module that only accepts reverse
class MockNonBlock(nn.Module):
    def __init__(self):
        super().__init__()
        self.linear = nn.Linear(4, 3)
    
    def forward(self, x, reverse=False):
        if reverse:
            return self.linear(x)
        return self.linear(x)

# Test with block module
block_module = MockBlock()
x_tensor = torch.randn(2, 4)

ARGS = {
    'module': block_module,
    'x': x_tensor,
    'reverse_iterations': 5
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
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, 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
run_module_with_logdet Ran
ran; our contract draft was wrong, not the code
jarrelscy/iResnet/InvertibleResnet.py
code served (permissive licence) · get_code("63022952ae19c9ea")
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) 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 torch
import torch.nn as nn

torch.manual_seed(0)

# Create a mock block module that accepts logdet, reverse, and num_logdet_iter
class MockBlockModule(nn.Module):
    def __init__(self):
        super().__init__()
        self.linear = nn.Linear(4, 4)
    
    def forward(self, x, logdet=False, reverse=False, num_logdet_iter=1):
        x = self.linear(x)
        if logdet:
            dlogdet = torch.tensor([0.5, 0.3], dtype=torch.float32)
            return x, dlogdet
        return x

# Create a mock non-block module that accepts logdet and reverse
class MockNonBlockModule(nn.Module):
    def __init__(self):
        super().__init__()
        self.linear = nn.Linear(4, 4)
    
    def forward(self, x, logdet=False, reverse=False):
        x = self.linear(x)
        if logdet:
            dlogdet = torch.tensor([0.5, 0.3], dtype=torch.float32)
            return x, dlogdet
        return x

# Test with block module
block_module = MockBlockModule()
x_input = torch.randn(2, 4)
num_logdet_iter_value = 5

ARGS = {
    "module": block_module,
    "x": x_input,
    "num_logdet_iter": num_logdet_iter_value
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
torch — 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
vjp Ran
ran; our contract draft was wrong, not the code
jarrelscy/iResnet/InvertibleResnet.py
code served (permissive licence) · get_code("4fa05a183b0730d0")
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) 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

torch.manual_seed(0)

# Create small tensors for the VJP computation
# ys: output tensor that we're computing gradients of
ys = torch.randn(2, 4, requires_grad=True)

# xs: input tensor(s) we want gradients with respect to
xs = torch.randn(3, 4, requires_grad=True)

# v: vector for vector-jacobian product (same shape as ys)
v = torch.randn(2, 4)

ARGS = {
    "ys": ys,
    "xs": xs,
    "v": v,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
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

Also present in other papers' code

Of 7 samples lifted from this paper's linked repositories, 7 carry a function identity and 0 do not. Of the 7 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 7 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

Neural networks (NNs) have been shown to be competitive against state-of-the-art feature engineering and random forest (RF) classification of periodic variable stars. Although previous work utilising NNs commonly operated on period-folded lightcurves, no approach to date has taken advantage of the fact that network predictions should be invariant to the initial phase of the period-folded sequence. Initial phase is exogenous to the physical origin of the variability and should thus be immaterial to the downstream application. Here, we present cyclic-permutation invariant networks, a novel class of NNs for which the output is invariant to phase shifts by construction. We implement this invariance by means of "Symmetry Padding." Across three different datasets of variable star light curves, we show that two implementations of the cyclic-permutation invariant network: the iTCN and the iResNet, consistently outperform non-invariant baselines and reduce overall error rates by between 4% to 22%. Over a 10-class OGLE-III sample, the iTCN/iResNet achieves an average per-class accuracy of 93.4%/93.3%, compared to RNN/RF accuracies of 70.5%/89.5% in a recent study using the same data. Finding improvement on a non-astronomy benchmark, we suggest that the methodology introduced here should also be applicable to a wide range of science domains where periodic data abounds due to physical symmetries.

For agents

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

get_harvested_code_for_paper("2011.01243")
get_code_for_paper("2011.01243")
have("2011.01243")

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

curl https://syntology.ai/api/ran/2011.01243.json

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

[![Syntology run record](https://syntology.ai/api/ran/2011.01243.svg)](https://syntology.ai/paper/2011.01243)

Connect an agent — have() is free.