SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2211.14680 · 2022

A Physics-informed Diffusion Model for High-fidelity Flow Field Reconstruction

arXiv · PDF · Open in the Atlas

Code that ran

20 of 24 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, 1 violated it and 9 have no contract verdict; 9 failures of our instrument; 4 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/2211.14680.json · badge: /api/ran/2211.14680.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
BaratiLab/Diffusion-based-Fluid-Super-resolution canonical (classifier label)
classifier basis not recorded on the link
20 ran · 4 no recorded run
FunctionStatusWhere it lives
Normalize Ran
ran on a synthesized input
BaratiLab/Diffusion-based-Fluid-Super-resolution/models/diffusion_new.py
code served (permissive licence) · get_code("d3e493cb453bf21e")
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 GroupNorm. 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)

ARGS = {
    "in_channels": 16
}
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 GroupNorm — a GroupNorm output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a GroupNorm 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
check_integrity Ran
ran, violated the contract we drafted
BaratiLab/Diffusion-based-Fluid-Super-resolution/train_ddpm/datasets/utils.py
pointer only (licence: MIT); the stored copy get_code serves, from xingyu-zheng/bidm, is pointer only (licence: NONE) · get_code("7345763c9b9300fb")
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 xingyu-zheng/bidm, 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.

compute_alpha Ran
ran; our contract draft was wrong, not the code
BaratiLab/Diffusion-based-Fluid-Super-resolution/functions/denoising_step.py
code served (permissive licence) · get_code("9215fb189fbfb9f4")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Sonnet 4.5, prompt python_fixture_v1) and returned Tensor, ndim 4, dtype family float, shape (2, 1, 1, 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 torch

torch.manual_seed(0)

# beta should be a 1D tensor representing beta values for diffusion timesteps
# Let's use 10 timesteps
num_timesteps = 10
beta = torch.linspace(0.0001, 0.02, num_timesteps)

# t should be a 1D tensor of indices into the timesteps
# Let's use batch size 2
batch_size = 2
t = torch.randint(0, num_timesteps, (batch_size,))

ARGS = {
    'beta': beta,
    't': t
}
Setup block drafted by
a language model, Claude Sonnet 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 4, dtype family float, shape (2, 1, 1, 1) — shape (2, 1, 1, 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
data_blurring Ran
ran on a synthesized input
BaratiLab/Diffusion-based-Fluid-Super-resolution/functions/process_data.py
code served (permissive licence) · get_code("4c603260e9a53b23")
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 2, dtype family float, shape (8, 8) 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 PIL import Image

torch.manual_seed(0)

# Create a small sample tensor that the function will process
# The function expects a tensor with .numpy() method
fno_data_sample = torch.randn(8, 8)

ARGS = {
    "fno_data_sample": fno_data_sample
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
PIL, numpy, 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 (8, 8) — shape (8, 8) 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
ddpm_steps Ran
ran on a synthesized input
BaratiLab/Diffusion-based-Fluid-Super-resolution/train_ddpm/functions/denoising.py
code served (permissive licence) · get_code("4d1f19f21237eb7d")
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. The code mentions cuda, and the harness aliases cuda to the CPU for every sample; whether this run needed that is 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 minimal model that takes x and t as inputs and outputs noise predictions
class SimpleNoisePredictor(nn.Module):
    def __init__(self):
        super().__init__()
        self.linear = nn.Linear(4, 4)
    
    def forward(self, x, t):
        # x shape: (batch, 4, 1, 1) after squeeze operations in the function
        # t shape: (batch,)
        batch_size = x.size(0)
        x_flat = x.view(batch_size, -1)
        # Simple prediction: output same shape as x
        output = self.linear(x_flat)
        return output.view(batch_size, 4, 1, 1)

# Create beta schedule (noise schedule for diffusion)
# Beta should be a 1D tensor of length equal to number of timesteps
num_timesteps = 100
betas = torch.linspace(0.0001, 0.02, num_timesteps)

# Create input tensor: batch_size=2, channels=4, height=1, width=1
x = torch.randn(2, 4, 1, 1)

# Create sequence of timesteps to reverse through
seq = torch.tensor([99, 50, 25, 10, 0], dtype=torch.long)

# Create model
model = SimpleNoisePredictor()

ARGS = {
    'x': x,
    'seq': seq,
    'model': model,
    'b': betas
}
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
generalized_steps Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
BaratiLab/Diffusion-based-Fluid-Super-resolution/train_ddpm/functions/denoising.py
code served (permissive licence) · get_code("d47e6201b6d56d24")
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. The code mentions cuda, and the harness aliases cuda to the CPU for every sample; whether this run needed that is 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 minimal model that takes (x, t) and returns noise prediction
class NoisePredictor(nn.Module):
    def __init__(self):
        super().__init__()
        self.linear = nn.Linear(4, 4)
    
    def forward(self, x, t):
        # x shape: (batch, 4, 1, 1)
        # t shape: (batch,)
        # Return noise prediction same shape as x
        batch_size = x.size(0)
        x_flat = x.view(batch_size, -1)
        out = self.linear(x_flat)
        return out.view(batch_size, 4, 1, 1)

# Create beta schedule (noise schedule)
# Shape: (1000,) - timesteps from 0 to 999
beta = torch.linspace(0.0001, 0.02, 1000)

# Create input tensor: batch_size=2, channels=4, height=1, width=1
x = torch.randn(2, 4, 1, 1)

# Create sequence of timesteps to reverse through
seq = torch.tensor([999, 500, 250, 0], dtype=torch.long)

# Create model
model = NoisePredictor()

# Create kwargs with eta parameter
kwargs = {'eta': 0.5}

ARGS = {
    'x': x,
    'seq': seq,
    'model': model,
    'b': beta,
    'kwargs': kwargs
}
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
get_beta_schedule Ran
ran, honoured the contract we drafted
BaratiLab/Diffusion-based-Fluid-Super-resolution/train_ddpm/runners/diffusion_tub.py
pointer only (licence: MIT); the stored copy get_code serves, from weizhigao/modiff, is pointer only (licence: NONE) · get_code("ca0cea1ca1eeec89")
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 weizhigao/modiff, 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.

get_timestep_embedding Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
BaratiLab/Diffusion-based-Fluid-Super-resolution/models/diffusion_new.py
code served (permissive licence) · get_code("cb49209c125de1b4")
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, 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 math

torch.manual_seed(0)

# The function takes two parameters:
# 1. timesteps: a 1D tensor of timestep indices
# 2. embedding_dim: an integer specifying the embedding dimension

# Create a small 1D tensor of timesteps (batch size 2)
timesteps = torch.tensor([0, 5], dtype=torch.int64)

# Create an embedding dimension (use 4 as specified)
embedding_dim = 4

ARGS = {
    "timesteps": timesteps,
    "embedding_dim": embedding_dim,
}
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, 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
list_dir Ran
ran; our contract draft was wrong, not the code
BaratiLab/Diffusion-based-Fluid-Super-resolution/train_ddpm/datasets/utils.py
pointer only (licence: MIT); the stored copy get_code serves, from xiaoboxia/T-Revision, is pointer only (licence: NONE) · get_code("915e1c6c38494be9")
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 xiaoboxia/T-Revision, 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.

list_files Ran
ran; our contract draft was wrong, not the code
BaratiLab/Diffusion-based-Fluid-Super-resolution/train_ddpm/datasets/utils.py
pointer only (licence: MIT); the stored copy get_code serves, from xiaoboxia/T-Revision, is pointer only (licence: NONE) · get_code("208e196e9582a9a6")
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 xiaoboxia/T-Revision, 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.

load_flow_data Ran
ran on a synthesized input
BaratiLab/Diffusion-based-Fluid-Super-resolution/runners/rs256_guided_diffusion.py
code served (permissive licence) · get_code("efc699989983049d")
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 torch
import tempfile
import os

torch.manual_seed(0)

# Create a temporary numpy file with flow data
# The function expects data with shape (N, H, W, ...) and takes last 4 samples
# It also uses data[:-4] for computing mean/std, so we need at least 5 samples
temp_dir = tempfile.mkdtemp()
temp_path = os.path.join(temp_dir, 'flow_data.npy')

# Create data: 9 samples total, each with shape (5, 7, 3) for height, width, channels
# Using distinct dimensions: 9 samples, 5 height, 7 width, 3 channels
data = np.random.randn(9, 5, 7, 3).astype(np.float32)
np.save(temp_path, data)

ARGS = {
    'path': temp_path,
    'stat_path': None,
}
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 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
load_recons_data Ran
ran on a synthesized input
BaratiLab/Diffusion-based-Fluid-Super-resolution/runners/rs256_guided_diffusion.py
code served (permissive licence) · get_code("cd9733bb244e0eed")
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 torch
import tempfile
import os

torch.manual_seed(0)

# Create temporary files with .npz extension for sample_path
temp_dir = tempfile.gettempdir()
sample_file = os.path.join(temp_dir, "sample_temp.npz")
ref_file = os.path.join(temp_dir, "ref_temp.npy")

# Create sample data: shape (10, 5, 4, 4) - 10 samples, 5 timesteps, 4x4 spatial
sample_data = np.random.randn(10, 5, 4, 4).astype(np.float32)
np.savez(sample_file, arr=sample_data)

# Create reference data: shape (10, 5, 4, 4) - used for computing mean/std on first 6
ref_data = np.random.randn(10, 5, 4, 4).astype(np.float32)
np.save(ref_file, ref_data)

ARGS = {
    "ref_path": ref_file,
    "sample_path": sample_file,
    "data_kw": "arr",
    "smoothing": True,
    "smoothing_scale": 3
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, torch, torchvision — 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
md5_hash Ran
ran; our contract draft was wrong, not the code
BaratiLab/Diffusion-based-Fluid-Super-resolution/train_ddpm/functions/ckpt_util.py
pointer only (licence: MIT); the stored copy get_code serves, from zh460045050/V2L-Tokenizer, is pointer only (licence: NONE) · get_code("07d90bd6ae1be7db")
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 zh460045050/V2L-Tokenizer, 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.

nearest_blur_image Ran
ran on a synthesized input
BaratiLab/Diffusion-based-Fluid-Super-resolution/runners/rs256_guided_diffusion.py
code served (permissive licence) · get_code("b8eae635c8da0f75")
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, 3, 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

torch.manual_seed(0)

# Create a small 4D tensor (batch, channels, height, width)
# Using distinct sizes: batch=2, channels=3, height=4, width=5
data = torch.randn(2, 3, 4, 5)

# scale parameter for downsampling
scale = 2

ARGS = {
    "data": data,
    "scale": scale,
}
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, 3, 2, 3) — shape (2, 3, 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
noise_estimation_loss Ran
ran; our contract draft was wrong, not the code
BaratiLab/Diffusion-based-Fluid-Super-resolution/train_ddpm/functions/losses.py
code served (permissive licence) · get_code("36a45cceb1209d2f")
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 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 torch.nn as nn

torch.manual_seed(0)

# Define a simple model that takes (x, t) and outputs noise prediction
class NoisePredictor(nn.Module):
    def __init__(self):
        super().__init__()
        self.linear = nn.Linear(4, 4)
    
    def forward(self, x, t):
        # x shape: (batch, channels, height, width) = (2, 1, 1, 4)
        # t shape: (batch,) converted to float
        # output should match x shape
        batch_size = x.shape[0]
        x_flat = x.view(batch_size, -1)
        # t is (batch,), expand it to match
        t_expanded = t.unsqueeze(1)  # (batch, 1)
        combined = x_flat + t_expanded  # simple combination
        output = self.linear(combined)
        return output.view(batch_size, 1, 1, 4)

model = NoisePredictor()

# x0: original clean image, shape (batch=2, channels=1, height=1, width=4)
x0 = torch.randn(2, 1, 1, 4)

# t: timesteps, shape (batch=2,)
t = torch.LongTensor([0, 5])

# e: noise, same shape as x0
e = torch.randn(2, 1, 1, 4)

# b: betas (noise schedule), shape (num_timesteps,) - needs at least 6 elements for index 5
b = torch.linspace(0.0001, 0.02, 10)

ARGS = {
    "model": model,
    "x0": x0,
    "t": t,
    "e": e,
    "b": b,
    "keepdim": False,
}
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 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
nonlinearity Ran
ran; our contract draft was wrong, not the code
BaratiLab/Diffusion-based-Fluid-Super-resolution/models/diffusion_new.py
code served (permissive licence) · get_code("3137073275f8c21a")
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, 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

torch.manual_seed(0)

# The function takes a single parameter 'x' which is used with:
# - multiplication operator (*)
# - torch.sigmoid() function
# This means x should be a tensor

x = torch.randn(2, 4)

ARGS = {
    "x": x
}
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, 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
normalize_array Ran
ran on a synthesized input
BaratiLab/Diffusion-based-Fluid-Super-resolution/functions/process_data.py
code served (permissive licence) · get_code("a1e4ee18c7b28d29")
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

# Create a simple numpy array to normalize
x = np.array([[1.0, 2.0, 3.0, 4.0],
              [5.0, 6.0, 7.0, 8.0]])

ARGS = {
    "x": x
}
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 — 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
torch2hwcuint8 Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
BaratiLab/Diffusion-based-Fluid-Super-resolution/train_ddpm/runners/diffusion_tub.py
pointer only (licence: MIT); the stored copy get_code serves, from weizhigao/modiff, is pointer only (licence: NONE) · get_code("c27a10ca9f6b75f3")
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 weizhigao/modiff, 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.

unnormalize_array Ran
ran on a synthesized input
BaratiLab/Diffusion-based-Fluid-Super-resolution/functions/process_data.py
code served (permissive licence) · get_code("585244aea5474149")
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 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 numpy as np

torch.manual_seed(0)

# The function unnormalize_array takes three parameters:
# y: a normalized array/tensor to be unnormalized
# x_min: minimum value of the original range
# x_max: maximum value of the original range

# Create small tensors for testing
y = torch.randn(2, 4)  # normalized values, shape (2, 4)
x_min = torch.tensor(0.0)  # minimum of original range
x_max = torch.tensor(100.0)  # maximum of original range

ARGS = {
    "y": y,
    "x_min": x_min,
    "x_max": x_max
}
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 Tensor, 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
voriticity_residual Ran
ran on a synthesized input
BaratiLab/Diffusion-based-Fluid-Super-resolution/train_ddpm/functions/losses.py
code served (permissive licence) · get_code("50d3715e3fd0d2da")
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, 5, 4, 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 numpy as np

torch.manual_seed(0)

# Construct a valid tensor for vorticity residual computation
# The function expects w with shape (batchsize, time_steps, nx, ny)
# where time_steps >= 3 (used in w[:, 2:, :, :] and w[:, :-2, :, :])
# and nx = ny (spatial dimensions, used in FFT operations)

batchsize = 2
time_steps = 5
nx = 4
ny = 4

# Create a tensor with the expected shape
w = torch.randn(batchsize, time_steps, nx, ny, dtype=torch.float32)

ARGS = {
    "w": w,
    "re": 1000.0,
    "dt": 1 / 32
}
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 Tensor, ndim 4, dtype family float, shape (2, 5, 4, 4) — shape (2, 5, 4, 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
conditional_noise_estimation_loss Not yet run
unverified (harvested, no recorded run)
BaratiLab/Diffusion-based-Fluid-Super-resolution/train_ddpm/functions/losses.py
code served (permissive licence) · get_code("d78697dffb992697")
How it ran

no invocation recorded.

ddim_steps Not yet run
unverified (harvested, no recorded run)
BaratiLab/Diffusion-based-Fluid-Super-resolution/functions/denoising_step.py
code served (permissive licence) · get_code("bb65803997afc12c")
How it ran

no invocation recorded.

ddpm_steps Not yet run
unverified (harvested, no recorded run)
BaratiLab/Diffusion-based-Fluid-Super-resolution/functions/denoising_step.py
code served (permissive licence) · get_code("4552697bda36ebb2")
How it ran

no invocation recorded.

get_ckpt_path Not yet run
unverified (harvested, no recorded run)
BaratiLab/Diffusion-based-Fluid-Super-resolution/train_ddpm/functions/ckpt_util.py
pointer only (licence: MIT); the stored copy get_code serves, from xingyu-zheng/bidm, is pointer only (licence: NONE) · get_code("c37fc656e8bb2a80")
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 xingyu-zheng/bidm, 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. No invocation recorded.

Also present in other papers' code

Of 24 samples lifted from this paper's linked repositories, 24 carry a function identity and 0 do not. Of the 24 distinct functions with an identity, 13 are also present in other papers whose code we hold (13 with at least one paper dated earlier, 3 the same month, 11 later) and 11 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
nonlinearity 156 other papers
17 dated earlier, 2 the same month, 137 later · 25 only as an assembly brick
2104.07652 (2021-04)
Geometry-Free View Synthesis: Transformers and no 3D Priors
2106.00132 (2021-06)
On Fast Sampling of Diffusion Probabilistic Models
2106.06819 (2021-06)
D2C: Diffusion-Denoising Models for Few-shot Conditional Generation
and 153 more not named here
get_timestep_embedding 91 other papers
13 dated earlier, 1 the same month, 77 later · 7 only as an assembly brick
2104.07652 (2021-04)
Geometry-Free View Synthesis: Transformers and no 3D Priors
2106.00132 (2021-06)
On Fast Sampling of Diffusion Probabilistic Models
2106.06819 (2021-06)
D2C: Diffusion-Denoising Models for Few-shot Conditional Generation
and 88 more not named here
md5_hash 30 other papers
4 dated earlier, 26 later
2008.01777 (2020-08)
Making Sense of CNNs: Interpreting Deep Representations & Their Invariances with INNs
2104.07652 (2021-04)
Geometry-Free View Synthesis: Transformers and no 3D Priors
2112.00384 (2021-12)
Exploration into Translation-Equivariant Image Quantization
and 27 more not named here
get_beta_schedule 25 other papers
4 dated earlier, 21 later · 1 only as an assembly brick
2201.11760 (2022-01)
Unsupervised Denoising of Retinal OCT with Diffusion Probabilistic Model
2203.02923 (2022-03)
GeoDiff: a Geometric Diffusion Model for Molecular Conformation Generation
2206.02262 (2022-06)
Diffusion-GAN: Training GANs with Diffusion
and 22 more not named here
compute_alpha 23 other papers
5 dated earlier, 1 the same month, 17 later · 6 only as an assembly brick
2010.02502 (2020-10)
Denoising Diffusion Implicit Models
2102.09672 (2021-02)
Improved Denoising Diffusion Probabilistic Models
2106.06819 (2021-06)
D2C: Diffusion-Denoising Models for Few-shot Conditional Generation
and 20 more not named here
list_dir 19 other papers
6 dated earlier, 13 later
1803.02999 (2018-03)
On First-Order Meta-Learning Algorithms
1903.12648 (2019-03)
Overcoming Catastrophic Forgetting with Unlabeled Data in the Wild
1906.00189 (2019-06)
Are Anchor Points Really Indispensable in Label-Noise Learning?
and 16 more not named here
check_integrity 16 other papers
3 dated earlier, 13 later
1908.07724 (2019-08)
Restricted Recurrent Neural Networks
2206.02262 (2022-06)
Diffusion-GAN: Training GANs with Diffusion
2210.11633 (2022-10)
Graphically Structured Diffusion Models
and 13 more not named here
list_files 16 other papers
6 dated earlier, 10 later
1803.02999 (2018-03)
On First-Order Meta-Learning Algorithms
1903.12648 (2019-03)
Overcoming Catastrophic Forgetting with Unlabeled Data in the Wild
1906.00189 (2019-06)
Are Anchor Points Really Indispensable in Label-Noise Learning?
and 13 more not named here
noise_estimation_loss 14 other papers
2 dated earlier, 12 later
2106.06819 (2021-06)
D2C: Diffusion-Denoising Models for Few-shot Conditional Generation
2206.02262 (2022-06)
Diffusion-GAN: Training GANs with Diffusion
2301.07969 (2023-01)
Fast Inference in Denoising Diffusion Models via MMD Finetuning
and 11 more not named here
torch2hwcuint8 5 other papers
1 dated earlier, 4 later
2206.02262 (2022-06)
Diffusion-GAN: Training GANs with Diffusion
2302.03262 (2023-02)
Membership Inference Attacks against Diffusion Models
2305.18723 (2023-05)
Towards Accurate Post-training Quantization for Diffusion Models
and 2 more not named here
generalized_steps 2 other papers
2 dated earlier
2010.02502 (2020-10)
Denoising Diffusion Implicit Models
2206.02262 (2022-06)
Diffusion-GAN: Training GANs with Diffusion
get_ckpt_path 2 other papers
1 dated earlier, 1 later
2206.02262 (2022-06)
Diffusion-GAN: Training GANs with Diffusion
2412.05926 (2024-12)
BiDM: Pushing the Limit of Quantization for Diffusion Models
ddpm_steps 1 other paper
1 dated earlier
2206.02262 (2022-06)
Diffusion-GAN: Training GANs with Diffusion

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

Machine learning models are gaining increasing popularity in the domain of fluid dynamics for their potential to accelerate the production of high-fidelity computational fluid dynamics data. However, many recently proposed machine learning models for high-fidelity data reconstruction require low-fidelity data for model training. Such requirement restrains the application performance of these models, since their data reconstruction accuracy would drop significantly if the low-fidelity input data used in model test has a large deviation from the training data. To overcome this restraint, we propose a diffusion model which only uses high-fidelity data at training. With different configurations, our model is able to reconstruct high-fidelity data from either a regular low-fidelity sample or a sparsely measured sample, and is also able to gain an accuracy increase by using physics-informed conditioning information from a known partial differential equation when that is available. Experimental results demonstrate that our model can produce accurate reconstruction results for 2d turbulent flows based on different input sources without retraining.

For agents

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

get_harvested_code_for_paper("2211.14680")
get_code_for_paper("2211.14680")
have("2211.14680")

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

curl https://syntology.ai/api/ran/2211.14680.json

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

[![Syntology run record](https://syntology.ai/api/ran/2211.14680.svg)](https://syntology.ai/paper/2211.14680)

Connect an agent — have() is free.