SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2107.04556 · 2021

Deep Learning for Reduced Order Modelling and Efficient Temporal Evolution of Fluid Simulations

arXiv · PDF · Open in the Atlas

Code that ran

4 of 4 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; 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/2107.04556.json · badge: /api/ran/2107.04556.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
pranshupant/DL-ROM canonical (classifier label)
classifier basis: census
4 ran · 0 no recorded run
FunctionStatusWhere it lives
latent_data Ran
ran on a synthesized input
pranshupant/DL-ROM/code/utils.py
code served (permissive licence) · get_code("682b0c35b5c277c3")
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, ndim 4, 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 numpy as np
import tempfile
import os

# Create a temporary .npy file with dummy latent data
# The function expects shape (N, 1) where N >= 26 (so we can iterate up to temp.shape[0] - 25)
# Each element at [i, 0] should be a 1D array of shape (10,)

# Create dummy latent data: 30 samples, each containing a (10,) array
dummy_latent_data = np.zeros((30, 1), dtype=object)
for i in range(30):
    dummy_latent_data[i, 0] = np.random.randn(10)

# Save to a temporary file
temp_dir = tempfile.gettempdir()
latent_file = os.path.join(temp_dir, "test_latent.npy")
np.save(latent_file, dummy_latent_data)

ARGS = {
    "latent": latent_file
}
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 tuple, ndim 4, 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
loadVar Ran
ran on a synthesized input
pranshupant/DL-ROM/code/dataset_create.py
code served (permissive licence) · get_code("31b26592613ae6e5")
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 numpy file for testing
temp_dir = tempfile.mkdtemp()
temp_file = os.path.join(temp_dir, "test_array.npy")

# Create and save a small numpy array
test_array = np.array([[1, 2, 3, 4], [5, 6, 7, 8]], dtype=np.float32)
np.save(temp_file, test_array)

ARGS = {
    "file_name": temp_file
}
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_transfer_learning Ran
ran on a synthesized input
pranshupant/DL-ROM/code/utils.py
code served (permissive licence) · get_code("232350d7f818d01b")
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 SimpleModel2. 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)

# Build a simple pretrained model
class SimpleModel(nn.Module):
    def __init__(self):
        super().__init__()
        self.fc1 = nn.Linear(4, 3)
        self.fc2 = nn.Linear(3, 2)
    
    def forward(self, x):
        x = self.fc1(x)
        x = self.fc2(x)
        return x

# Build a model with the same architecture to load state into
class SimpleModel2(nn.Module):
    def __init__(self):
        super().__init__()
        self.fc1 = nn.Linear(4, 3)
        self.fc2 = nn.Linear(3, 2)
    
    def forward(self, x):
        x = self.fc1(x)
        x = self.fc2(x)
        return x

# Create instances
pretrained = SimpleModel()
model = SimpleModel2()

# Create a checkpoint and save it to a temporary location
checkpoint_dict = pretrained.state_dict()

# We need to use a temporary file for torch.load to work
import tempfile
import os

temp_dir = tempfile.gettempdir()
checkpoint_path = os.path.join(temp_dir, "test_checkpoint.pt")
torch.save(checkpoint_dict, checkpoint_path)

ARGS = {
    "pretrained": pretrained,
    "model": model,
    "PATH": checkpoint_path
}
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 SimpleModel2 — a SimpleModel2 output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a SimpleModel2 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
to_img Ran
ran on a synthesized input
pranshupant/DL-ROM/code/utils.py
code served (permissive licence) · get_code("062ea17c7d4e91b1")
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 Tensor, ndim 4, dtype family float, shape (2, 1, 80, 640) 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

torch.manual_seed(0)

# The function expects a tensor x that will be:
# 1. Scaled by 0.5 * (x + 1)
# 2. Clamped to [0, 1]
# 3. Viewed/reshaped to (batch_size, 1, 80, 640)
# 
# So the input tensor must have total elements = batch_size * 1 * 80 * 640
# For batch_size=2, that's 2 * 51200 = 102400 elements
# We'll create a tensor with shape (2, 51200) that can be viewed as (2, 1, 80, 640)

x = torch.randn(2, 51200)

ARGS = {
    "x": x
}
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 Tensor, ndim 4, dtype family float, shape (2, 1, 80, 640) — shape (2, 1, 80, 640) 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

Also present in other papers' code

Of 4 samples lifted from this paper's linked repositories, 4 carry a function identity and 0 do not. Of the 4 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 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.

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

Reduced Order Modelling (ROM) has been widely used to create lower order, computationally inexpensive representations of higher-order dynamical systems. Using these representations, ROMs can efficiently model flow fields while using significantly lesser parameters. Conventional ROMs accomplish this by linearly projecting higher-order manifolds to lower-dimensional space using dimensionality reduction techniques such as Proper Orthogonal Decomposition (POD). In this work, we develop a novel deep learning framework DL-ROM (Deep Learning - Reduced Order Modelling) to create a neural network capable of non-linear projections to reduced order states. We then use the learned reduced state to efficiently predict future time steps of the simulation using 3D Autoencoder and 3D U-Net based architectures. Our model DL-ROM is able to create highly accurate reconstructions from the learned ROM and is thus able to efficiently predict future time steps by temporally traversing in the learned reduced state. All of this is achieved without ground truth supervision or needing to iteratively solve the expensive Navier-Stokes(NS) equations thereby resulting in massive computational savings. To test the effectiveness and performance of our approach, we evaluate our implementation on five different Computational Fluid Dynamics (CFD) datasets using reconstruction performance and computational runtime metrics. DL-ROM can reduce the computational runtimes of iterative solvers by nearly two orders of magnitude while maintaining an acceptable error threshold.

For agents

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

get_harvested_code_for_paper("2107.04556")
get_code_for_paper("2107.04556")
have("2107.04556")

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

curl https://syntology.ai/api/ran/2107.04556.json

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

[![Syntology run record](https://syntology.ai/api/ran/2107.04556.svg)](https://syntology.ai/paper/2107.04556)

Connect an agent — have() is free.