SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1907.04502 · 2019

DeepXDE: A deep learning library for solving differential equations

arXiv · PDF · Open in the Atlas

Code that ran

12 of 14 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, 1 violated it and 11 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/1907.04502.json · badge: /api/ran/1907.04502.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
PhysicsTeacher13/Deepxde community (classifier label)
classifier basis not recorded on the link
10 ran · 2 no recorded run
copy not recorded community
not in the paper's declared repositories
1 ran · 0 no recorded run
yiwang89/lululxvi-deepxde community (classifier label)
classifier basis not recorded on the link
1 ran · 0 no recorded run
FunctionStatusWhere it lives
accuracy Ran
ran on a synthesized input
PhysicsTeacher13/Deepxde/deepxde/metrics.py
code served (permissive licence) · get_code("88820f35c43353d2")
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 float64, ndim 0, dtype family float; no output shape is stated. The image it ran in was not recorded. If your copy returns the same type and ndim 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 small numpy arrays for y_true and y_pred
# The function uses np.argmax on axis=-1, so we need 2D arrays (batch_size, num_classes)
# Using batch_size=2 and num_classes=4

np.random.seed(0)

# y_pred: shape (2, 4) - logits or probabilities for 2 samples, 4 classes
y_pred = np.random.randn(2, 4)

# y_true: shape (2, 4) - one-hot encoded labels for 2 samples, 4 classes
y_true = np.zeros((2, 4))
y_true[0, 1] = 1  # first sample is class 1
y_true[1, 3] = 1  # second sample is class 3

ARGS = {
    "y_true": y_true,
    "y_pred": y_pred,
}
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 float64, ndim 0, dtype family float — no output shape is stated: observe_signature.py recorded float ndim 0, which disagrees with the fixture run
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
cross_entropy Ran
ran on a synthesized input
PhysicsTeacher13/Deepxde/deepxde/math_ops.py
code served (permissive licence) · get_code("2c419a89a220d342")
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 1, dtype family float, shape (2,) 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

# cross_entropy takes two parameters: p and q
# Both are used with np.sum(p * np.log(q), axis=1)
# This means:
# - p and q should be 2D numpy arrays (to use axis=1)
# - p and q should have the same shape
# - q values should be positive (for np.log)

# Create small 2D arrays: batch_size=2, num_classes=4
p = np.array([
    [0.1, 0.2, 0.3, 0.4],
    [0.25, 0.25, 0.25, 0.25]
], dtype=np.float32)

# q should be probability-like (positive values, ideally sum to 1)
q = np.array([
    [0.2, 0.3, 0.25, 0.25],
    [0.1, 0.4, 0.3, 0.2]
], dtype=np.float32)

ARGS = {
    "p": p,
    "q": q
}
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 ndarray, ndim 1, dtype family float, shape (2,) — shape (2,) 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
istensor Ran
ran on a synthesized input
PhysicsTeacher13/Deepxde/deepxde/array_ops.py
code served (permissive licence) · get_code("1da5d1a073cf6188")
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 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 tensorflow as tf

# The function istensor takes a single parameter 'value' and checks if it's
# an instance of tf.Tensor, tf.Variable, or tf.SparseTensor.
# We need to provide test values for this parameter.

# Create a regular TensorFlow tensor
regular_tensor = tf.constant([[1.0, 2.0, 3.0, 4.0],
                               [5.0, 6.0, 7.0, 8.0]])

# Create a TensorFlow Variable
variable_tensor = tf.Variable([[1.0, 2.0, 3.0, 4.0],
                                [5.0, 6.0, 7.0, 8.0]])

# Create a SparseTensor
indices = tf.constant([[0, 1], [1, 2]], dtype=tf.int64)
values = tf.constant([1.0, 2.0])
shape = tf.constant([2, 4], dtype=tf.int64)
sparse_tensor = tf.SparseTensor(indices=indices, values=values, dense_shape=shape)

# Test with a non-tensor value
non_tensor = [1, 2, 3, 4]

# Define ARGS dict with the 'value' parameter
ARGS = {
    'value': regular_tensor
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
tensorflow — 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
istensorlist Ran
ran on a synthesized input
PhysicsTeacher13/Deepxde/deepxde/array_ops.py
code served (permissive licence) · get_code("62ec6e60132a5d4c")
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 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 tensorflow as tf
import numpy as np

# Test case 1: list with at least one TensorFlow tensor
values_with_tensor = [
    tf.constant([1.0, 2.0, 3.0, 4.0]),
    [5, 6, 7],
    "string",
    42
]

# Test case 2: list with TensorFlow Variable
values_with_variable = [
    "string",
    tf.Variable([1.0, 2.0, 3.0, 4.0]),
    np.array([1, 2, 3])
]

# Test case 3: list with SparseTensor
indices = [[0, 0], [1, 1], [2, 2]]
values_sparse = [1.0, 2.0, 3.0]
shape = [3, 3]
sparse_tensor = tf.SparseTensor(indices=indices, values=values_sparse, dense_shape=shape)
values_with_sparse = [
    "no tensor",
    sparse_tensor,
    123
]

# Test case 4: list with no tensors
values_no_tensor = [
    "string",
    42,
    [1, 2, 3],
    {"key": "value"}
]

ARGS = {
    "values": values_with_tensor
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, tensorflow — 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
l2_relative_error Ran
ran on a synthesized input
PhysicsTeacher13/Deepxde/deepxde/metrics.py
code served (permissive licence) · get_code("32c851eacf652fb9")
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 float32, 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 numpy as np
import torch

torch.manual_seed(0)

# The function l2_relative_error takes two numpy arrays (y_true and y_pred)
# and computes the L2 relative error between them.
# It uses:
# - np.linalg.norm() on both arrays
# - array subtraction

# Create small numpy arrays with distinct shapes to probe dimensions
y_true = np.random.randn(2, 4).astype(np.float32)
y_pred = np.random.randn(2, 4).astype(np.float32)

ARGS = {
    "y_true": y_true,
    "y_pred": y_pred,
}
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 float32, 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
list_to_str Ran
ran on a synthesized input
PhysicsTeacher13/Deepxde/deepxde/display.py
code served (permissive licence) · get_code("ba75ef2ea10ace5c")
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
import numpy as np

torch.manual_seed(0)

# Analyze the function:
# - list_to_str takes a parameter 'nums'
# - It checks if nums is None
# - If not None, it iterates over nums and formats each element as '{:.2e}'
# - This means nums should be iterable of numeric values

# Test case 1: None
# nums = None

# Test case 2: List of numbers
nums = [1.234, 5.678e-3, 0.00123, 42.0]

ARGS = {
    'nums': nums
}
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 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
lorenz Ran
ran, violated the contract we drafted
this paper's copy was not recorded; identical code first harvested from cianmscannell/pinns
pointer only · get_code("3d3bd15404080e16")
How it ran

The body of this sample is withheld: this paper's copy of the code was not recorded (its link names no repository or source path), so no licence was read for it. 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.

mean_absolute_percentage_error Ran
ran on a synthesized input
PhysicsTeacher13/Deepxde/deepxde/losses.py
code served (permissive licence) · get_code("b6b3f1e69c63519d")
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 EagerTensor, 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 tensorflow as tf
import numpy as np

# Create small tensors for y_true and y_pred
# The function computes: 100 * mean(|y_true - y_pred| / y_true)
# We need y_true to be non-zero to avoid division by zero
y_true = tf.constant([[1.0, 2.0, 3.0, 4.0], [5.0, 6.0, 7.0, 8.0]], dtype=tf.float32)
y_pred = tf.constant([[1.1, 2.2, 2.9, 4.1], [4.9, 6.3, 7.2, 7.8]], dtype=tf.float32)

ARGS = {
    "y_true": y_true,
    "y_pred": y_pred,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, tensorflow — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type EagerTensor, 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
mean_absolute_percentage_error Ran
ran on a synthesized input
yiwang89/lululxvi-deepxde/deepxde/metrics.py
code served (permissive licence) · get_code("7685754d1df284cc")
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 float64, ndim 0, dtype family float; no output shape is stated. The image it ran in was not recorded. If your copy returns the same type and ndim 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 data for mean absolute percentage error calculation
# y_true: actual values (must be non-zero to avoid division by zero)
y_true = np.array([100.0, 50.0, 75.0, 200.0])

# y_pred: predicted values
y_pred = np.array([110.0, 48.0, 80.0, 190.0])

ARGS = {
    "y_true": y_true,
    "y_pred": y_pred,
}
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 float64, ndim 0, dtype family float — no output shape is stated: observe_signature.py recorded float ndim 0, which disagrees with the fixture run
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
shape Ran
ran on a synthesized input
PhysicsTeacher13/Deepxde/deepxde/array_ops.py
code served (permissive licence) · get_code("ad6ca018121d1980")
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 TensorShape. 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 tensorflow as tf
import numpy as np

# Create a simple TensorFlow tensor
tensor_value = tf.constant([[1.0, 2.0, 3.0, 4.0],
                             [5.0, 6.0, 7.0, 8.0]])

# Create a TensorFlow Variable
variable_value = tf.Variable([[1.0, 2.0, 3.0, 4.0],
                               [5.0, 6.0, 7.0, 8.0]])

# Create a TensorFlow SparseTensor
indices = [[0, 0], [1, 2]]
values = [1.0, 2.0]
shape_sparse = [2, 4]
sparse_value = tf.SparseTensor(indices=indices, values=values, dense_shape=shape_sparse)

# Create a numpy array (non-tensor object with .shape attribute)
numpy_value = np.array([[1, 2, 3, 4],
                         [5, 6, 7, 8]])

# Test with a regular Python list (also has .shape via numpy conversion)
list_value = [[1, 2, 3, 4], [5, 6, 7, 8]]

ARGS = {
    "value": tensor_value
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, tensorflow — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type TensorShape — a TensorShape output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a TensorShape output the recorded ndim 1 and dtype family int 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
softmax Ran
ran on a synthesized input
PhysicsTeacher13/Deepxde/deepxde/math_ops.py
code served (permissive licence) · get_code("6f58b8df8556a3aa")
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 (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 numpy as np

# The softmax function takes a 2D array X where:
# - Each row is a set of scores
# - It computes softmax across axis=1 (each row independently)
# - It uses np.max, np.exp, np.sum with axis=1 parameter

# Create a small 2D numpy array (batch_size=2, num_classes=4)
X = np.array([
    [1.0, 2.0, 3.0, 4.0],
    [5.0, 1.0, 2.0, 3.0]
], dtype=np.float32)

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 ndarray, 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
uniformly_continuous_delta Ran
ran on a synthesized input
PhysicsTeacher13/Deepxde/deepxde/math_ops.py
code served (permissive licence) · get_code("87eec89fd7f6f6cb")
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 float64, ndim 0, dtype family float; no output shape is stated. The image it ran in was not recorded. If your copy returns the same type and ndim 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 scipy.spatial.distance

# Set random seed for reproducibility
np.random.seed(0)

# Create small test data
# X: N x d equispaced points
# For 1D case
N = 5
d = 1
X = np.linspace(0, 1, N).reshape(-1, 1)
Y = np.sin(np.linspace(0, 2*np.pi, N)).reshape(-1, 1)

# eps: threshold for uniform continuity
eps = 0.3

ARGS = {
    "X": X,
    "Y": Y,
    "eps": eps
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, scipy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type float64, ndim 0, dtype family float — no output shape is stated: observe_signature.py recorded float ndim 0, which disagrees with the fixture run
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
mean_squared_error Not yet run
unverified (harvested, no recorded run)
PhysicsTeacher13/Deepxde/deepxde/losses.py
code served (permissive licence) · get_code("7aef1f09fa638129")
How it ran

no invocation recorded.

softmax_cross_entropy Not yet run
unverified (harvested, no recorded run)
PhysicsTeacher13/Deepxde/deepxde/losses.py
code served (permissive licence) · get_code("d93e816132fd2cc1")
How it ran

no invocation recorded.

Also present in other papers' code

Of 14 samples lifted from this paper's linked repositories, 14 carry a function identity and 0 do not. Of the 14 distinct functions with an identity, 3 are also present in other papers whose code we hold (1 with at least one paper dated earlier, 0 the same month, 2 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
accuracy 1 other paper
1 later
2306.08827 (2023-06)
PINNacle: A Comprehensive Benchmark of Physics-Informed Neural Networks for Solving PDEs
l2_relative_error 1 other paper
1 later
2306.08827 (2023-06)
PINNacle: A Comprehensive Benchmark of Physics-Informed Neural Networks for Solving PDEs
lorenz 1 other paper
1 dated earlier
1711.10561 (2017-11)
Physics Informed Deep Learning (Part I): Data-driven Solutions of Nonlinear Partial Differential Equations

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

Deep learning has achieved remarkable success in diverse applications; however, its use in solving partial differential equations (PDEs) has emerged only recently. Here, we present an overview of physics-informed neural networks (PINNs), which embed a PDE into the loss of the neural network using automatic differentiation. The PINN algorithm is simple, and it can be applied to different types of PDEs, including integro-differential equations, fractional PDEs, and stochastic PDEs. Moreover, from the implementation point of view, PINNs solve inverse problems as easily as forward problems. We propose a new residual-based adaptive refinement (RAR) method to improve the training efficiency of PINNs. For pedagogical reasons, we compare the PINN algorithm to a standard finite element method. We also present a Python library for PINNs, DeepXDE, which is designed to serve both as an education tool to be used in the classroom as well as a research tool for solving problems in computational science and engineering. Specifically, DeepXDE can solve forward problems given initial and boundary conditions, as well as inverse problems given some extra measurements. DeepXDE supports complex-geometry domains based on the technique of constructive solid geometry, and enables the user code to be compact, resembling closely the mathematical formulation. We introduce the usage of DeepXDE and its customizability, and we also demonstrate the capability of PINNs and the user-friendliness of DeepXDE for five different examples. More broadly, DeepXDE contributes to the more rapid development of the emerging Scientific Machine Learning field.

For agents

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

get_harvested_code_for_paper("1907.04502")
get_code_for_paper("1907.04502")
have("1907.04502")

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

curl https://syntology.ai/api/ran/1907.04502.json

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

[![Syntology run record](https://syntology.ai/api/ran/1907.04502.svg)](https://syntology.ai/paper/1907.04502)

Connect an agent — have() is free.