SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2207.06283 · 2022

Implicit Neural Representations for Generative Modeling of Living Cell Shapes

arXiv · PDF · Open in the Atlas

Code that ran

5 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; 0 honoured the contract we drafted, 0 violated it and 4 have no contract verdict; 1 failure 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/2207.06283.json · badge: /api/ran/2207.06283.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
miagrouput/implicit-cell-surfaces community (classifier label)
classifier basis not recorded on the link
5 ran · 1 no recorded run
FunctionStatusWhere it lives
get_learning_rate_schedules Ran
ran; our contract draft was wrong, not the code
miagrouput/implicit-cell-surfaces/autodecoder/lib/utils.py
code served (permissive licence) · get_code("52a0dcc56e4d0c4f")
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 list, 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.

# Define the learning rate schedule classes
class LearningRateSchedule:
    def get_learning_rate(self, epoch):
        pass

class ConstantLearningRateSchedule(LearningRateSchedule):
    def __init__(self, value):
        self.value = value

    def get_learning_rate(self, epoch):
        return self.value

class StepLearningRateSchedule(LearningRateSchedule):
    def __init__(self, initial, interval, factor):
        self.initial = initial
        self.interval = interval
        self.factor = factor

    def get_learning_rate(self, epoch):
        return self.initial * self.factor ** (epoch // self.interval)

class WarmupLearningRateSchedule(LearningRateSchedule):
    def __init__(self, initial, warmed_up, length):
        self.initial = initial
        self.warmed_up = warmed_up
        self.length = length

    def get_learning_rate(self, epoch):
        if epoch > self.length:
            return self.warmed_up
        return self.initial + (self.warmed_up - self.initial) * epoch / self.length

def get_learning_rate_schedules(specs):
    schedule_specs = specs['LearningRateSchedule']
    schedules = []
    for schedule_specs in schedule_specs:
        if schedule_specs['Type'] == 'Step':
            schedules.append(StepLearningRateSchedule(schedule_specs['Initial'], schedule_specs['Interval'], schedule_specs['Factor']))
        elif schedule_specs['Type'] == 'Warmup':
            schedules.append(WarmupLearningRateSchedule(schedule_specs['Initial'], schedule_specs['Final'], schedule_specs['Length']))
        elif schedule_specs['Type'] == 'Constant':
            schedules.append(ConstantLearningRateSchedule(schedule_specs['Value']))
        else:
            raise Exception('no known learning rate schedule of type "{}"'.format(schedule_specs['Type']))
    return schedules

# Construct valid arguments for get_learning_rate_schedules
ARGS = {
    'specs': {
        'LearningRateSchedule': [
            {
                'Type': 'Constant',
                'Value': 0.001
            },
            {
                'Type': 'Step',
                'Initial': 0.01,
                'Interval': 10,
                'Factor': 0.5
            },
            {
                'Type': 'Warmup',
                'Initial': 0.0001,
                'Final': 0.001,
                'Length': 5
            }
        ]
    }
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
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 list, ndim 1, dtype family float — 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
load_cam_model_parameters Ran
ran on a synthesized input
miagrouput/implicit-cell-surfaces/autodecoder/lib/workspace.py
code served (permissive licence) · get_code("2c315f31f5cc54b2")
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 os
import torch
import torch.nn as nn
import tempfile
import shutil

torch.manual_seed(0)

# Create a minimal encoder model
class MinimalEncoder(nn.Module):
    def __init__(self):
        super().__init__()
        self.linear = nn.Linear(4, 3)
    
    def forward(self, x):
        return self.linear(x)

# Create a temporary experiment directory with model_parameters subdirectory
temp_dir = tempfile.mkdtemp()
model_params_dir = os.path.join(temp_dir, 'model_parameters')
os.makedirs(model_params_dir, exist_ok=True)

# Create a checkpoint file with model state dict and epoch
encoder = MinimalEncoder()
checkpoint_name = 'checkpoint_0'
checkpoint_path = os.path.join(model_params_dir, checkpoint_name + '.pth')

state_dict = encoder.state_dict()
checkpoint_data = {
    'model_state_dict': state_dict,
    'epoch': 42
}
torch.save(checkpoint_data, checkpoint_path)

# Create a fresh encoder instance to load into
encoder_for_loading = MinimalEncoder()

ARGS = {
    'experiment_directory': temp_dir,
    'checkpoint': checkpoint_name,
    'encoder': encoder_for_loading
}
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 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_experiment_specifications Ran
ran on a synthesized input
miagrouput/implicit-cell-surfaces/autodecoder/lib/workspace.py
code served (permissive licence) · get_code("809e534e476d8112")
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 os
import tempfile

# Create a temporary directory with a specs.json file
temp_dir = tempfile.mkdtemp()
specs_file = os.path.join(temp_dir, 'specs.json')

# Create a valid specs.json file with sample experiment specifications
specs_data = {
    "model": "test_model",
    "learning_rate": 0.001,
    "batch_size": 32,
    "epochs": 10,
    "layers": [64, 32, 16]
}

with open(specs_file, 'w') as f:
    json.dump(specs_data, f)

ARGS = {
    "experiment_directory": temp_dir
}
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_model_parameters Ran
ran on a synthesized input
miagrouput/implicit-cell-surfaces/autodecoder/lib/workspace.py
code served (permissive licence) · get_code("9fa7466a7eae87b7")
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 os
import torch
import torch.nn as nn
import tempfile
import shutil

torch.manual_seed(0)

# Create a temporary directory structure for the test
temp_dir = tempfile.mkdtemp()
model_params_dir = os.path.join(temp_dir, 'model_parameters')
os.makedirs(model_params_dir, exist_ok=True)

# Create a simple decoder model
class SimpleDecoder(nn.Module):
    def __init__(self):
        super().__init__()
        self.linear = nn.Linear(4, 3)
    
    def forward(self, x):
        return self.linear(x)

decoder = SimpleDecoder()

# Create checkpoint data with model state dict and epoch
checkpoint_name = 'test_checkpoint'
checkpoint_path = os.path.join(model_params_dir, checkpoint_name + '.pth')

checkpoint_data = {
    'model_state_dict': decoder.state_dict(),
    'epoch': 42
}

torch.save(checkpoint_data, checkpoint_path)

ARGS = {
    'experiment_directory': temp_dir,
    'checkpoint': checkpoint_name,
    'decoder': decoder
}
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 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
sample_fraction Ran
ran on a synthesized input
miagrouput/implicit-cell-surfaces/autodecoder/lib/data.py
code served (permissive licence) · get_code("859bb98c53ae267b")
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 torch

torch.manual_seed(0)

# Create a small dataset tuple with 4 elements
# data[0] should be a tensor where column 3 is used for filtering (values <= 0.3 vs > 0.3)
# We need at least 2 rows to test the sampling logic
# Shape: (num_samples, 4) where column 3 contains threshold values

data_tensor = torch.tensor([
    [1.0, 2.0, 3.0, 0.2],  # will be in ip_arr (column 3 <= 0.3)
    [4.0, 5.0, 6.0, 0.5],  # will be in op_arr (column 3 > 0.3)
], dtype=torch.float32)

# Create the full data tuple with 4 elements
data = (
    data_tensor,
    torch.tensor([0, 1]),  # data[1]
    torch.tensor([10, 20]),  # data[2]
    torch.tensor([100, 200]),  # data[3]
)

fraction = 0.5

ARGS = {
    "data": data,
    "fraction": fraction,
}
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 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
unpack_sdf_samples Not yet run
unverified (harvested, no recorded run)
miagrouput/implicit-cell-surfaces/autodecoder/lib/data.py
code served (permissive licence) · get_code("4d9342a3b0580511")
How it ran

no invocation 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, 1 are also present in other papers whose code we hold (1 with at least one paper dated earlier, 0 the same month, 1 later) and 5 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
get_learning_rate_schedules 2 other papers
1 dated earlier, 1 later
2003.10983 (2020-03)
Deep Local Shapes: Learning Local SDF Priors for Detailed 3D Reconstruction
2410.19680 (2024-10)
Inferring Neural Signed Distance Functions by Overfitting on Single Noisy Point Clouds through Finetuning Data-Driven based Priors

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

Methods allowing the synthesis of realistic cell shapes could help generate training data sets to improve cell tracking and segmentation in biomedical images. Deep generative models for cell shape synthesis require a light-weight and flexible representation of the cell shape. However, commonly used voxel-based representations are unsuitable for high-resolution shape synthesis, and polygon meshes have limitations when modeling topology changes such as cell growth or mitosis. In this work, we propose to use level sets of signed distance functions (SDFs) to represent cell shapes. We optimize a neural network as an implicit neural representation of the SDF value at any point in a 3D+time domain. The model is conditioned on a latent code, thus allowing the synthesis of new and unseen shape sequences. We validate our approach quantitatively and qualitatively on C. elegans cells that grow and divide, and lung cancer cells with growing complex filopodial protrusions. Our results show that shape descriptors of synthetic cells resemble those of real cells, and that our model is able to generate topologically plausible sequences of complex cell shapes in 3D+time.

For agents

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

get_harvested_code_for_paper("2207.06283")
get_code_for_paper("2207.06283")
have("2207.06283")

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

curl https://syntology.ai/api/ran/2207.06283.json

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

[![Syntology run record](https://syntology.ai/api/ran/2207.06283.svg)](https://syntology.ai/paper/2207.06283)

Connect an agent — have() is free.