SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2409.18359 · 2024

Generative AI for fast and accurate statistical computation of fluids

arXiv · PDF · Open in the Atlas

Code that ran

5 of 7 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 0 have no contract verdict; 5 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/2409.18359.json · badge: /api/ran/2409.18359.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
camlab-ethz/gencfd canonical (classifier label)
classifier basis: census
5 ran · 2 no recorded run
FunctionStatusWhere it lives
default_init Ran
ran; our contract draft was wrong, not the code
camlab-ethz/gencfd/GenCFD/utils/model_utils.py
code served (permissive licence) · get_code("ec800de8d7a491d0")
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 torch
import torch.nn as nn

torch.manual_seed(0)

# The function default_init takes a single parameter: scale (float)
# It returns an initializer function that can be applied to tensors
# The initializer differentiates between biases (1D tensors) and weights (multi-dimensional)

# Test with a simple scale value
ARGS = {
    "scale": 1e-10
}
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 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
logsnr2sigma Ran
ran; our contract draft was wrong, not the code
camlab-ethz/gencfd/GenCFD/diffusion/diffusion.py
code served (permissive licence) · get_code("ef098f3e4b165412")
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 InvertibleSchedule. 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 as th
import numpy as np
import dataclasses
from typing import Union, Callable

th.manual_seed(0)

Numeric = Union[bool, int, float, np.ndarray, th.Tensor]

ScheduleFn = Callable[[Numeric], Numeric]

@dataclasses.dataclass(frozen=True)
class InvertibleSchedule:
    forward: ScheduleFn
    inverse: ScheduleFn

    def __call__(self, t: Numeric) -> Numeric:
        return self.forward(t)

# Create a simple logsnr schedule
# forward: maps diffusion times t to logsnr values
# inverse: maps logsnr values back to diffusion times
def create_logsnr_schedule():
    def forward_fn(t):
        t_tensor = th.as_tensor(t, dtype=th.float32)
        # Simple linear schedule: logsnr = 10 - 20*t (for t in [0,1])
        return 10.0 - 20.0 * t_tensor
    
    def inverse_fn(logsnr):
        logsnr_tensor = th.as_tensor(logsnr, dtype=th.float32)
        # Inverse: t = (10 - logsnr) / 20
        return (10.0 - logsnr_tensor) / 20.0
    
    return InvertibleSchedule(forward=forward_fn, inverse=inverse_fn)

logsnr_schedule = create_logsnr_schedule()

ARGS = {
    "logsnr": logsnr_schedule,
    "device": th.device("cpu"),
}
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 InvertibleSchedule — a InvertibleSchedule output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a InvertibleSchedule 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
permute_tensor Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
camlab-ethz/gencfd/GenCFD/utils/model_utils.py
code served (permissive licence) · get_code("9c2b2e2cdc5d0104")
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, 3, 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)

# For kernel_dim=1, tensor needs shape (batch, channels, length)
# For kernel_dim=2, tensor needs shape (batch, channels, height, width)
# For kernel_dim=3, tensor needs shape (batch, channels, depth, height, width)

# We'll test with kernel_dim=2 case
# Shape: (batch=2, channels=4, height=3, width=5)
tensor_2d = torch.randn(2, 4, 3, 5)

ARGS = {
    "tensor": tensor_2d,
    "kernel_dim": 2
}
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, 5, 3, 4) — shape (2, 5, 3, 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
sigma2logsnr Ran
ran; our contract draft was wrong, not the code
camlab-ethz/gencfd/GenCFD/diffusion/diffusion.py
code served (permissive licence) · get_code("ecddf32972d7861a")
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 InvertibleSchedule. 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 as th
import numpy as np
import dataclasses
from typing import Union, Callable

th.manual_seed(0)

Numeric = Union[bool, int, float, np.ndarray, th.Tensor]
ScheduleFn = Callable[[Numeric], Numeric]

@dataclasses.dataclass(frozen=True)
class InvertibleSchedule:
    forward: ScheduleFn
    inverse: ScheduleFn

    def __call__(self, t: Numeric) -> Numeric:
        return self.forward(t)


# Create a simple sigma schedule that the function will use
def create_sigma_schedule():
    # forward: maps diffusion times to sigma values
    # inverse: maps sigma values back to diffusion times
    def forward_fn(t):
        t_tensor = th.as_tensor(t)
        return th.exp(-t_tensor)  # Simple exponential decay
    
    def inverse_fn(sigma):
        sigma_tensor = th.as_tensor(sigma)
        return -th.log(sigma_tensor)  # Inverse of exponential
    
    return InvertibleSchedule(forward=forward_fn, inverse=inverse_fn)


sigma_schedule = create_sigma_schedule()

ARGS = {
    "sigma": sigma_schedule,
    "device": th.device("cpu"),
}
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 InvertibleSchedule — a InvertibleSchedule output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a InvertibleSchedule 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
train_test_split Ran
ran; our contract draft was wrong, not the code
camlab-ethz/gencfd/GenCFD/dataloader/dataset.py
code served (permissive licence) · get_code("bb519c2de685640f")
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
from torch.utils.data import Dataset

torch.manual_seed(0)

class SimpleDataset(Dataset):
    """Minimal dataset implementation for testing."""
    def __init__(self, size=10):
        self.size = size
        self.data = torch.randn(size, 4)
        self.labels = torch.randint(0, 2, (size,))
    
    def __len__(self):
        return self.size
    
    def __getitem__(self, idx):
        return self.data[idx], self.labels[idx]

dataset = SimpleDataset(size=10)

ARGS = {
    "dataset": dataset,
    "split_ratio": 0.7,
    "seed": 42
}
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
init_distributed_mode Not yet run
unverified (harvested, no recorded run)
camlab-ethz/gencfd/GenCFD/eval/evaluate_gencfd.py
code served (permissive licence) · get_code("0bfaa74ea1d71e0f")
How it ran

no invocation recorded.

reshape_jax_torch Not yet run
unverified (harvested, no recorded run)
camlab-ethz/gencfd/GenCFD/utils/model_utils.py
code served (permissive licence) · get_code("2772d01c19339fc4")
How it ran

no invocation recorded.

Also present in other papers' code

Of 7 samples lifted from this paper's linked repositories, 7 carry a function identity and 0 do not. Of the 7 distinct functions with an identity, 0 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 0 later) and 7 are only here among the 52,977 papers whose code Syntology holds (as of 2026-09-26).

Only here means: among the 52,977 papers whose code Syntology holds (51,887 with lifted samples, 1,090 through their assemblies only), as of 2026-09-26, no other paper's lifted samples or current assembly bricks contain an identical function body after normalisation.

Presence, not direction: an identical function body in two papers' repositories does not say who wrote it, which came from which, or that either paper's method rests on it. Matching is exact after normalisation, so a renamed or edited function is not matched. Dates are when papers appeared, not when code was written. Only .py files the harvester lifted are covered; notebooks are not read. A new-style arXiv id YYMM.NNNN dates a paper to the month 20YY-MM; otherwise Paper.year dates it to the year; otherwise it is undated. Dates are when the paper appeared, not when the code was written. Read 2026-11-22.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

We present a generative AI algorithm for addressing the pressing task of fast, accurate, and robust statistical computation of three-dimensional turbulent fluid flows. Our algorithm, termed as GenCFD, is based on an end-to-end conditional score-based diffusion model. Through extensive numerical experimentation with a set of challenging fluid flows, we demonstrate that GenCFD provides an accurate approximation of relevant statistical quantities of interest while also efficiently generating high-quality realistic samples of turbulent fluid flows and ensuring excellent spectral resolution. In contrast, ensembles of deterministic ML algorithms, trained to minimize mean square errors, regress to the mean flow. We present rigorous theoretical results uncovering the surprising mechanisms through which diffusion models accurately generate fluid flows. These mechanisms are illustrated with solvable toy models that exhibit the mathematically relevant features of turbulent fluid flows while being amenable to explicit analytical formulae. Our codes are publicly available at https://github.com/camlab-ethz/GenCFD.

For agents

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

get_harvested_code_for_paper("2409.18359")
get_code_for_paper("2409.18359")
have("2409.18359")

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

curl https://syntology.ai/api/ran/2409.18359.json

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

[![Syntology run record](https://syntology.ai/api/ran/2409.18359.svg)](https://syntology.ai/paper/2409.18359)

Connect an agent — have() is free.