SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2412.04833 · 2024

Wavelet Diffusion Neural Operator

arXiv · PDF · Open in the Atlas

Code that ran

11 of 13 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; 4 honoured the contract we drafted, 1 violated it and 0 have no contract verdict; 6 failures of our instrument; 2 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/2412.04833.json · badge: /api/ran/2412.04833.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
AI4Science-WestlakeU/wdno canonical (classifier label)
classifier basis: census
11 ran · 2 no recorded run
FunctionStatusWhere it lives
apply_conditioning Ran
ran; our contract draft was wrong, not the code
AI4Science-WestlakeU/wdno/smoke/ddpm/modules.py
code served (permissive licence) · get_code("b3d593fb33f79ac5")
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 3, dtype family float, shape (2, 5, 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 torch.nn as nn

torch.manual_seed(0)

# x: tensor that will be indexed and have values assigned
# The function indexes x[:, t, action_dim:] where t comes from conditions.keys()
# and assigns val.clone() to it
# So x needs shape (batch_size, time_steps, feature_dim)
# with feature_dim > action_dim
batch_size = 2
time_steps = 5
action_dim = 2
feature_dim = 4  # must be > action_dim

x = torch.randn(batch_size, time_steps, feature_dim)

# conditions: dict mapping timestep t to a tensor val
# The function does x[:, t, action_dim:] = val.clone()
# So val should have shape (batch_size, feature_dim - action_dim)
condition_shape = (batch_size, feature_dim - action_dim)
conditions = {
    1: torch.randn(condition_shape),
    3: torch.randn(condition_shape),
}

ARGS = {
    "x": x,
    "conditions": conditions,
    "action_dim": action_dim,
}
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 3, dtype family float, shape (2, 5, 4) — shape (2, 5, 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
coef_to_tensor Ran
ran, honoured the contract we drafted
AI4Science-WestlakeU/wdno/smoke/wave_trans_2d.py
code served (permissive licence) · get_code("e6337738e0098670")
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 3, dtype family float, shape (2, 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

torch.manual_seed(0)

# Construct a valid coef argument
# The function expects coef[0] to be a tensor (Yl)
# and coef[1] to be a dict with values that can be stacked (Yh)

Yl = torch.randn(2, 4)  # batch size 2, feature dim 4

Yh = {
    'cH': torch.randn(2, 4),
    'cV': torch.randn(2, 4),
    'cD': torch.randn(2, 4),
}

coef = (Yl, Yh)

ARGS = {
    'coef': coef,
    'pad': 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 3, dtype family float, shape (2, 4, 4) — shape (2, 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
cosine_beta_schedule Ran
ran, honoured the contract we drafted
AI4Science-WestlakeU/wdno/smoke/ddpm/modules.py
code served (permissive licence) · get_code("b6113e0f43155a33")
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 1, dtype family float, shape (10,) 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

torch.manual_seed(0)

ARGS = {
    "timesteps": 10,
    "s": 0.008,
    "dtype": torch.float32,
}
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 1, dtype family float, shape (10,) — shape (10,) 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
display_name Ran
ran; our contract draft was wrong, not the code
AI4Science-WestlakeU/wdno/smoke/phi/model.py
code served (permissive licence) · get_code("7d3807f597feb193")
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 str. 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 = {
    "python_name": "hello_world_example"
}
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 str — a str output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a str 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
exists Ran
ran, violated the contract we drafted
AI4Science-WestlakeU/wdno/burgers/ddpm_burgers/model_utils.py
code served (permissive licence) · get_code("608e364a9d2376a3")
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 bool, 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

def exists(x):
    return x is not None

ARGS = {
    "x": torch.tensor([1, 2, 3, 4])
}
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 bool, 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
normalize_to_neg_one_to_one Ran
ran, honoured the contract we drafted
AI4Science-WestlakeU/wdno/burgers/ddpm_burgers/model_utils.py
pointer only (licence: MIT); the stored copy get_code serves, from futurexiang/soda, is pointer only (licence: NONE) · get_code("a1229a9f4df127e2")
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 futurexiang/soda, 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.

synchronized_method Ran
ran; our contract draft was wrong, not the code
AI4Science-WestlakeU/wdno/smoke/phi/model.py
code served (permissive licence) · get_code("35eb6064f0c2c7a2")
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 function. 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 threading
import inspect

def synchronized_method(method):
    outer_lock = threading.Lock()
    lock_name = '__' + method.__name__ + '_lock' + '__'

    def sync_method(self, *args, **kws):
        with outer_lock:
            if not hasattr(self, lock_name):
                setattr(self, lock_name, threading.Lock())
            lock = getattr(self, lock_name)
            with lock:
                return method(self, *args, **kws)
    return sync_method


class TestClass:
    @synchronized_method
    def test_method(self, x, y=10):
        return x + y


def sample_function(a, b):
    return a + b


ARGS = {
    'method': sample_function
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, six — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type function — a function output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a function 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
tensor_to_coef Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
AI4Science-WestlakeU/wdno/burgers/wave_trans.py
code served (permissive licence) · get_code("3c22b7611e7a627e")
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)

# The function expects:
# - coef_tensor: shape [N, at_least_8, padded_h, padded_w]
#   It indexes into dim 1 at positions 0, 1:4, 4, 5:8
#   So we need at least 8 channels
# - shape: a tuple/list with at least 2 elements where shape[-2] and shape[-1]
#   are used for slicing height and width

# Create a small coef_tensor with batch=2, channels=8, height=6, width=5
coef_tensor = torch.randn(2, 8, 6, 5)

# Create a shape tuple - the function uses shape[-2] and shape[-1]
# Let's use shape that's smaller than the padded dimensions to test slicing
shape = (10, 4, 3)  # shape[-2]=4, shape[-1]=3

ARGS = {
    "coef_tensor": coef_tensor,
    "shape": shape,
}
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
tensor_to_coef Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
AI4Science-WestlakeU/wdno/smoke/wave_trans_2d.py
code served (permissive licence) · get_code("e21637a17a50b60c")
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)

# The function expects:
# - coef_tensor: shape [N, >=40, padded, padded, padded] (needs at least channels up to index 40)
# - shape: a tuple/list with at least 3 elements (shape[-3], shape[-2], shape[-1])
# - upsample_type: None, 'time', or 'space'

# Build a small coef_tensor with batch size 2, 41 channels (to cover indices 0-40), and spatial dims 4x4x4
batch_size = 2
num_channels = 41  # needs to go up to index 40
time_dim = 4
space_dim = 5

coef_tensor = torch.randn(batch_size, num_channels, time_dim, space_dim, space_dim)

# shape should be the target output shape, used for indexing
# The function uses shape[-3], shape[-2], shape[-1]
shape = (time_dim, space_dim, space_dim)

# upsample_type can be None, 'time', or 'space'
upsample_type = None

ARGS = {
    "coef_tensor": coef_tensor,
    "shape": shape,
    "upsample_type": upsample_type,
}
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
tensor_to_coef_super Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
AI4Science-WestlakeU/wdno/burgers/wave_trans.py
code served (permissive licence) · get_code("60adb43b6c0bca79")
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)

# Construct arguments for tensor_to_coef_super
# The function expects:
# - coef_tensor: shape [N, more than 2*(1+3), padded, padded]
#   which means [N, >8, H, W]
# - shape: a shape tuple used for slicing

# Create a coef_tensor with batch size 2, at least 8 channels (using 10 to be safe)
# and spatial dimensions 5x4
N = 2
num_channels = 10  # more than 2*(1+3) = 8
height = 5
width = 4

coef_tensor = torch.randn(N, num_channels, height, width)

# Create a shape tuple that will be used to slice the tensor
# The function uses :shape[-2] and :shape[-1] for the last two dimensions
shape = (N, num_channels, height, width)

ARGS = {
    "coef_tensor": coef_tensor,
    "shape": shape,
}
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
unnormalize_to_zero_to_one Ran
ran, honoured the contract we drafted
AI4Science-WestlakeU/wdno/burgers/ddpm_burgers/model_utils.py
pointer only (licence: MIT); the stored copy get_code serves, from futurexiang/soda, is pointer only (licence: NONE) · get_code("97e1bbd232dfe092")
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 futurexiang/soda, 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.

coef_to_tensor Not yet run
unverified (harvested, no recorded run)
AI4Science-WestlakeU/wdno/burgers/wave_trans.py
code served (permissive licence) · get_code("d06e979b38cba19b")
How it ran

no invocation recorded.

extract Not yet run
unverified (harvested, no recorded run)
AI4Science-WestlakeU/wdno/smoke/ddpm/modules.py
code served (permissive licence) · get_code("09c8479d9a5b3e06")
How it ran

no invocation recorded.

Also present in other papers' code

Of 13 samples lifted from this paper's linked repositories, 13 carry a function identity and 0 do not. Of the 13 distinct functions with an identity, 8 are also present in other papers whose code we hold (8 with at least one paper dated earlier, 3 the same month, 6 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
exists 144 other papers
108 dated earlier, 4 the same month, 27 later, 5 same year, order not determinable · 40 only as an assembly brick
1611.07004 (2016-11)
Image-to-Image Translation with Conditional Adversarial Networks
1711.11585 (2017-11)
High-Resolution Image Synthesis and Semantic Manipulation with Conditional GANs
2006.11239 (2020-06)
Denoising Diffusion Probabilistic Models
and 141 more not named here
extract 77 other papers
56 dated earlier, 3 the same month, 16 later, 2 same year, order not determinable · 32 only as an assembly brick
1711.11585 (2017-11)
High-Resolution Image Synthesis and Semantic Manipulation with Conditional GANs
2006.11239 (2020-06)
Denoising Diffusion Probabilistic Models
2102.05379 (2021-02)
Argmax Flows and Multinomial Diffusion: Learning Categorical Distributions
and 74 more not named here
cosine_beta_schedule 20 other papers
14 dated earlier, 1 the same month, 5 later · 8 only as an assembly brick
2208.06193 (2022-08)
Diffusion Policies as an Expressive Policy Class for Offline Reinforcement Learning
2210.15629 (2022-10)
Language Control Diffusion: Efficiently Scaling through Space, Time, and Tasks
2303.14676 (2023-03)
PDPP: Projected Diffusion for Procedure Planning in Instructional Videos
and 17 more not named here
normalize_to_neg_one_to_one 18 other papers
14 dated earlier, 4 later · 8 only as an assembly brick
1611.07004 (2016-11)
Image-to-Image Translation with Conditional Adversarial Networks
2006.11239 (2020-06)
Denoising Diffusion Probabilistic Models
2209.15571 (2022-09)
Building Normalizing Flows with Stochastic Interpolants
and 15 more not named here
unnormalize_to_zero_to_one 18 other papers
13 dated earlier, 5 later · 9 only as an assembly brick
2006.11239 (2020-06)
Denoising Diffusion Probabilistic Models
2105.05233 (2021-05)
Diffusion Models Beat GANs on Image Synthesis
2209.15571 (2022-09)
Building Normalizing Flows with Stochastic Interpolants
and 15 more not named here
apply_conditioning 9 other papers
5 dated earlier, 4 later · 2 only as an assembly brick
2210.15629 (2022-10)
Language Control Diffusion: Efficiently Scaling through Space, Time, and Tasks
2305.18459 (2023-05)
Diffusion Model is an Effective Planner and Data Synthesizer for Multi-Task Reinforcement Learning
2405.04235 (2024-05)
LTLDoG: Satisfying Temporally-Extended Symbolic Constraints for Safe Diffusion-based Planning
and 6 more not named here
display_name 2 other papers
2 dated earlier
2407.06494 (2024-07)
DiffPhyCon: A Generative Approach to Control Complex Physical Systems
2408.03124 (2024-08)
CL-DiffPhyCon: Closed-loop Diffusion Control of Complex Physical Systems
synchronized_method 2 other papers
2 dated earlier
2407.06494 (2024-07)
DiffPhyCon: A Generative Approach to Control Complex Physical Systems
2408.03124 (2024-08)
CL-DiffPhyCon: Closed-loop Diffusion Control of Complex Physical Systems

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

Simulating and controlling physical systems described by partial differential equations (PDEs) are crucial tasks across science and engineering. Recently, diffusion generative models have emerged as a competitive class of methods for these tasks due to their ability to capture long-term dependencies and model high-dimensional states. However, diffusion models typically struggle with handling system states with abrupt changes and generalizing to higher resolutions. In this work, we propose Wavelet Diffusion Neural Operator (WDNO), a novel PDE simulation and control framework that enhances the handling of these complexities. WDNO comprises two key innovations. Firstly, WDNO performs diffusion-based generative modeling in the wavelet domain for the entire trajectory to handle abrupt changes and long-term dependencies effectively. Secondly, to address the issue of poor generalization across different resolutions, which is one of the fundamental tasks in modeling physical systems, we introduce multi-resolution training. We validate WDNO on five physical systems, including 1D advection equation, three challenging physical systems with abrupt changes (1D Burgers' equation, 1D compressible Navier-Stokes equation and 2D incompressible fluid), and a real-world dataset ERA5, which demonstrates superior performance on both simulation and control tasks over state-of-the-art methods, with significant improvements in long-term and detail prediction accuracy. Remarkably, in the challenging context of the 2D high-dimensional and indirect control task aimed at reducing smoke leakage, WDNO reduces the leakage by 78% compared to the second-best baseline. The code can be found at https://github.com/AI4Science-WestlakeU/wdno.git.

For agents

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

get_harvested_code_for_paper("2412.04833")
get_code_for_paper("2412.04833")
have("2412.04833")

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

curl https://syntology.ai/api/ran/2412.04833.json

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

[![Syntology run record](https://syntology.ai/api/ran/2412.04833.svg)](https://syntology.ai/paper/2412.04833)

Connect an agent — have() is free.