SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2107.07871 · 2021

Finite Basis Physics-Informed Neural Networks (FBPINNs): a scalable domain decomposition approach for solving differential equations

arXiv · PDF · Open in the Atlas

Code that ran

4 of 6 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (0 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 0 violated it and 4 have no contract verdict; 0 failures of our instrument; 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/2107.07871.json · badge: /api/ran/2107.07871.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
benmoseley/FBPINNs canonical (classifier label)
classifier basis: census
4 ran · 2 no recorded run
FunctionStatusWhere it lives
get_subdomain_ws Ran
ran on a synthesized input
benmoseley/FBPINNs/fbpinns/constants.py
code served (permissive licence) · get_code("ee1b99166c84b955")
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 list. 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 sample subdomain_xs - a list of numpy arrays
# Each array represents x values for a subdomain
subdomain_xs = [
    np.array([1.0, 2.0, 3.0, 4.0]),
    np.array([0.5, 1.5, 2.5, 3.5, 4.5]),
    np.array([0.0, 1.0, 2.0])
]

# Create width parameter
width = 2.5

ARGS = {
    "subdomain_xs": subdomain_xs,
    "width": width
}
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 list — a list 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
inside_models_batch Ran
ran on a synthesized input
benmoseley/FBPINNs/fbpinns/decompositions_base.py
code served (permissive licence) · get_code("455298c49b1d9abc")
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 jax
import jax.numpy as jnp

# Set seed for reproducibility
key = jax.random.PRNGKey(0)

# Define a simple inside_fn that takes all_params, x_batch, and ims
# and returns a boolean array indicating which points are "inside"
def inside_fn(all_params, x_batch, ims):
    # x_batch shape: (batch_size, 4)
    # ims shape: (3,)
    # Returns shape: (batch_size, 3) - boolean array
    batch_size = x_batch.shape[0]
    n_ims = ims.shape[0]
    # Simple heuristic: points are "inside" if their first coordinate is positive
    result = jnp.tile(x_batch[:, 0:1] > 0, (1, n_ims))
    return result

# Create small tensors
batch_size = 2
n_points = 6
dim = 4
n_ims = 3

# x_batch: (6, 4) - 6 points in 4D space
x_batch = jnp.array([
    [1.0, 0.5, -0.2, 0.3],
    [-0.5, 0.1, 0.8, -0.1],
    [0.2, -0.3, 0.4, 0.6],
    [-0.8, 0.2, -0.5, 0.9],
    [0.7, 0.1, 0.2, -0.4],
    [0.3, -0.6, 0.5, 0.1]
], dtype=jnp.float32)

# all_params: can be any structure (dict, nested structure, etc.)
# The function doesn't examine its contents, just passes it to inside_fn
all_params = {"weights": jnp.array([0.1, 0.2, 0.3, 0.4])}

# ims: (3,) array
ims = jnp.array([1.0, 2.0, 3.0], dtype=jnp.float32)

# batch_size: 2
batch_size = 2

# inside_fn: function that takes (all_params, x_batch, ims) and returns boolean array
inside_fn_partial = inside_fn

ARGS = {
    "all_params": all_params,
    "x_batch": x_batch,
    "ims": ims,
    "batch_size": batch_size,
    "inside_fn": inside_fn_partial
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
jax — 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
norm Ran
ran on a synthesized input
benmoseley/FBPINNs/fbpinns/networks.py
code served (permissive licence) · get_code("e0956065c490bd14")
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 norm(mu, sd, x) performs normalization: (x - mu) / sd
# It expects:
# - mu: a scalar or tensor representing mean
# - sd: a scalar or tensor representing standard deviation
# - x: a tensor or array to normalize

# Create small tensors for the parameters
mu = torch.tensor(0.5)
sd = torch.tensor(0.2)
x = torch.randn(2, 4)

ARGS = {
    "mu": mu,
    "sd": sd,
    "x": x
}
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
unnorm Ran
ran on a synthesized input
benmoseley/FBPINNs/fbpinns/networks.py
code served (permissive licence) · get_code("bc1b592eccd4fdba")
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 unnorm(mu, sd, x) performs: x * sd + mu
# All three parameters are used in arithmetic operations
# They should be numeric types (tensors, arrays, or scalars)

mu = torch.tensor([1.0, 2.0, 3.0, 4.0])
sd = torch.tensor([0.5, 0.5, 0.5, 0.5])
x = torch.randn(2, 4)

ARGS = {
    "mu": mu,
    "sd": sd,
    "x": x
}
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
inside_points_batch Not yet run
unverified (harvested, no recorded run)
benmoseley/FBPINNs/fbpinns/decompositions_base.py
code served (permissive licence) · get_code("09217647b1d82805")
How it ran

no invocation recorded.

plot_1D_PINN Not yet run
unverified (harvested, no recorded run)
benmoseley/FBPINNs/fbpinns/plot_trainer_1D.py
code served (permissive licence) · get_code("366fccad7fa65e59")
How it ran

no invocation recorded.

Also present in other papers' code

Of 6 samples lifted from this paper's linked repositories, 6 carry a function identity and 0 do not. Of the 6 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 6 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

Recently, physics-informed neural networks (PINNs) have offered a powerful new paradigm for solving problems relating to differential equations. Compared to classical numerical methods PINNs have several advantages, for example their ability to provide mesh-free solutions of differential equations and their ability to carry out forward and inverse modelling within the same optimisation problem. Whilst promising, a key limitation to date is that PINNs have struggled to accurately and efficiently solve problems with large domains and/or multi-scale solutions, which is crucial for their real-world application. Multiple significant and related factors contribute to this issue, including the increasing complexity of the underlying PINN optimisation problem as the problem size grows and the spectral bias of neural networks. In this work we propose a new, scalable approach for solving large problems relating to differential equations called Finite Basis PINNs (FBPINNs). FBPINNs are inspired by classical finite element methods, where the solution of the differential equation is expressed as the sum of a finite set of basis functions with compact support. In FBPINNs neural networks are used to learn these basis functions, which are defined over small, overlapping subdomains. FBINNs are designed to address the spectral bias of neural networks by using separate input normalisation over each subdomain, and reduce the complexity of the underlying optimisation problem by using many smaller neural networks in a parallel divide-and-conquer approach. Our numerical experiments show that FBPINNs are effective in solving both small and larger, multi-scale problems, outperforming standard PINNs in both accuracy and computational resources required, potentially paving the way to the application of PINNs on large, real-world problems.

For agents

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

get_harvested_code_for_paper("2107.07871")
get_code_for_paper("2107.07871")
have("2107.07871")

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

curl https://syntology.ai/api/ran/2107.07871.json

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

[![Syntology run record](https://syntology.ai/api/ran/2107.07871.svg)](https://syntology.ai/paper/2107.07871)

Connect an agent — have() is free.