SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2501.04126 · 2025

Stochastic Process Learning via Operator Flow Matching

arXiv · PDF · Open in the Atlas

Code that ran

7 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 4 have no contract verdict; 3 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/2501.04126.json · badge: /api/ran/2501.04126.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
yzshi5/spl_ofm canonical (classifier label)
classifier basis not recorded on the link
7 ran · 0 no recorded run
FunctionStatusWhere it lives
conds_allhot Ran
ran on a synthesized input
yzshi5/spl_ofm/models/fno.py
code served (permissive licence) · get_code("980915abbc542235")
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, 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
import torch.nn as nn

torch.manual_seed(0)

# Build valid arguments for conds_allhot
# The function expects:
# - conds: a tensor that will be unsqueezed and repeated
# - shape: a tuple/list representing target shape [batch_size, channels, *spatial_dims]

# For n_dim == 1 case (1D spatial)
conds_1d = torch.randn(2, 3)  # batch_size=2, num_conditions=3
shape_1d = [2, 5, 4]  # batch_size=2, channels=5, spatial_dim=4

# For n_dim == 2 case (2D spatial)
conds_2d = torch.randn(2, 3)  # batch_size=2, num_conditions=3
shape_2d = [2, 5, 4, 6]  # batch_size=2, channels=5, height=4, width=6

# For n_dim == 3 case (3D spatial)
conds_3d = torch.randn(2, 3)  # batch_size=2, num_conditions=3
shape_3d = [2, 5, 4, 6, 7]  # batch_size=2, channels=5, depth=4, height=6, width=7

# Test with 1D case as the primary example
ARGS = {
    "conds": conds_1d,
    "shape": shape_1d
}
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, 3, 4) — shape (2, 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
load_config Ran
ran on a synthesized input
yzshi5/spl_ofm/util/config.py
code served (permissive licence) · get_code("5180fb36f984f272")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned dict. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import yaml
import tempfile
import os

torch.manual_seed(0)

# Create a temporary YAML config file
config_content = """
x_min: 0.0
x_max: 1.0
n_x: 5
device: cpu
dtype: float
"""

with tempfile.NamedTemporaryFile(mode='w', suffix='.yml', delete=False) as f:
    f.write(config_content)
    cfg_path = f.name

try:
    ARGS = {
        'cfg_path': cfg_path
    }
finally:
    pass
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch, yaml — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type dict — a dict output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a dict output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
make_posn_embed Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
yzshi5/spl_ofm/models/diff_fno.py
pointer only (licence: MIT); the stored copy get_code serves, from gavinkerrigan/cot_fm, is pointer only (licence: NONE) · get_code("52972d8e3ebe09a6")
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 gavinkerrigan/cot_fm, 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.

make_posn_embed Ran
ran on a synthesized input
yzshi5/spl_ofm/models/fno.py
code served (permissive licence) · get_code("0ca1daddafe09ebd")
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, 1, 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)

ARGS = {
    "batch_size": 2,
    "dims": [4]
}
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, 1, 4) — shape (2, 1, 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
matern_kernel_cov Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
yzshi5/spl_ofm/util/true_gaussian_process.py
code served (permissive licence) · get_code("f79632b31c417a84")
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 (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 numpy as np
from sklearn.gaussian_process.kernels import Matern

# Create a small grid of points
# grids should be [n_points, 1 or 2]
grids = np.array([[1.0], [2.0], [3.0], [4.0]])

# Set length_scale parameter
length_scale = 1.0

# Set nu parameter for Matern kernel
nu = 1.5

ARGS = {
    'grids': grids,
    'length_scale': length_scale,
    'nu': nu
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, sklearn — 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 (4, 4) — shape (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
t_allhot Ran
ran; our contract draft was wrong, not the code
yzshi5/spl_ofm/models/diff_fno.py
pointer only (licence: MIT); the stored copy get_code serves, from gavinkerrigan/cot_fm, is pointer only (licence: NONE) · get_code("985c3b8589a3e3a6")
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 gavinkerrigan/cot_fm, 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.

t_allhot Ran
ran on a synthesized input
yzshi5/spl_ofm/models/fno.py
code served (permissive licence) · get_code("843b18a0982ddc0c")
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, 4, 5) 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)

# Analyze the function:
# - t: a tensor that gets reshaped and broadcasted
# - shape: a tuple/list used to extract batch_size, n_channels, and spatial dims
# The function reshapes t to (batch_size, 1, 1, ..., 1) then broadcasts to (batch_size, 1, *dim)

# Create a small tensor t with batch_size=2
t = torch.randn(2)

# Create a shape tuple: (batch_size, n_channels, *spatial_dims)
# Using distinct sizes: batch=2, channels=3, spatial=(4, 5)
shape = (2, 3, 4, 5)

ARGS = {
    "t": t,
    "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 Tensor, ndim 4, dtype family float, shape (2, 1, 4, 5) — shape (2, 1, 4, 5) 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 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, 4 are also present in other papers whose code we hold (3 with at least one paper dated earlier, 0 the same month, 1 later) and 3 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
make_posn_embed 2 other papers
2 dated earlier
2305.17209 (2023-05)
Functional Flow Matching
2404.04240 (2024-04)
Dynamic Conditional Optimal Transport through Simulation-Free Flows
t_allhot 2 other papers
2 dated earlier
2305.17209 (2023-05)
Functional Flow Matching
2404.04240 (2024-04)
Dynamic Conditional Optimal Transport through Simulation-Free Flows
load_config 1 other paper
1 dated earlier
2305.17209 (2023-05)
Functional Flow Matching
matern_kernel_cov 1 other paper
1 later
2606.22346 (2026-06)
Flow Annealing Posterior Sampling for Function-Space Regression and Inverse Problems

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

Expanding on neural operators, we propose a novel framework for stochastic process learning across arbitrary domains. In particular, we develop operator flow matching (OFM) for learning stochastic process priors on function spaces. OFM provides the probability density of the values of any collection of points and enables mathematically tractable functional regression at new points with mean and density estimation. Our method outperforms state-of-the-art models in stochastic process learning, functional regression, and prior learning.

For agents

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

get_harvested_code_for_paper("2501.04126")
get_code_for_paper("2501.04126")
have("2501.04126")

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

curl https://syntology.ai/api/ran/2501.04126.json

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

[![Syntology run record](https://syntology.ai/api/ran/2501.04126.svg)](https://syntology.ai/paper/2501.04126)

Connect an agent — have() is free.