SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2006.10739 · 2020

Fourier Features Let Networks Learn High Frequency Functions in Low Dimensional Domains

Jonathan Barron, Utkarsh Singhal, Pratul Srinivasan, Ren Ng, Sara Fridovich-Keil, Matthew Tancik, Ben Mildenhall, Nithin Raghavan, Ravi Ramamoorthi

arXiv · PDF · Open in the Atlas

Code that ran

6 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 1 has no contract verdict; 5 failures of our instrument; 1 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/2006.10739.json · badge: /api/ran/2006.10739.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
jmclong/random-fourier-features-pytorch community (classifier label)
classifier basis not recorded on the link
4 ran · 1 no recorded run
leoshine/fourier-feature-networks.pytorch reimplementation (classifier label)
classifier basis: classifier_2025
2 ran · 0 no recorded run
FunctionStatusWhere it lives
Open Ran
ran; our contract draft was wrong, not the code
leoshine/fourier-feature-networks.pytorch/pylibs/common.py
pointer only (licence: NONE) · get_code("3c9c118f8a67a082")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, leoshine/fourier-feature-networks.pytorch 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.

argv2dict Ran
ran; our contract draft was wrong, not the code
leoshine/fourier-feature-networks.pytorch/pylibs/common.py
pointer only (licence: NONE) · get_code("c5fff0776239e04b")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, leoshine/fourier-feature-networks.pytorch 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.

basic_encoding Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
jmclong/random-fourier-features-pytorch/rff/functional.py
code served (permissive licence) · get_code("2d2bc5c34037e15b")
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; 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 torch
import numpy as np

torch.manual_seed(0)

# The function takes a single parameter 'v' which is a Tensor
# According to the docstring, it should have shape (N, *, input_size)
# where N is batch size, * means any number of intermediate dimensions, 
# and input_size is the feature dimension

# Create a small tensor with shape (2, 4) representing:
# - N=2 (batch size)
# - input_size=4 (feature dimension)
v = torch.randn(2, 4)

ARGS = {
    "v": v
}
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 — no output shape is stated: observe_signature.py could not observe it (import:OSError)
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
gaussian_encoding Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
jmclong/random-fourier-features-pytorch/rff/functional.py
code served (permissive licence) · get_code("93245a6fbe3c4415")
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; 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 torch
import numpy as np

torch.manual_seed(0)

# Set up the input tensor v
# Shape: (N, *, input_size) where N=2 (batch), input_size=4
v = torch.randn(2, 4)

# Set up the projection matrix b
# Shape: (encoded_layer_size, input_size) where encoded_layer_size=3, input_size=4
b = torch.randn(3, 4)

ARGS = {
    "v": v,
    "b": b,
}
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 — no output shape is stated: observe_signature.py could not observe it (import:OSError)
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
rectangular_coordinates Ran
ran on a synthesized input
jmclong/random-fourier-features-pytorch/rff/dataloader.py
code served (permissive licence) · get_code("26e7371df569e5d5")
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 (4, 3, 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 torch
from torch import Tensor

torch.manual_seed(0)

# The function takes a size parameter which is a tuple
# It uses this tuple to create linspaces for each dimension
# Then creates a meshgrid and stacks the coordinates
# The size should represent the shape of an image or volume

# Test with a 2D image size
size_2d = (4, 3)

# Test with a 3D volume size
size_3d = (2, 3, 4)

# Use 2D as the primary test case
ARGS = {
    "size": (4, 3)
}
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 (4, 3, 2) — shape (4, 3, 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
sample_b Ran
ran; our contract draft was wrong, not the code
jmclong/random-fourier-features-pytorch/rff/functional.py
pointer only (licence: MIT); the stored copy get_code serves, from tomburgert/georank, is pointer only (licence: NONE) · get_code("43e5f269780ac7f5")
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 tomburgert/georank, 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.

to_dataset Not yet run
unverified (harvested, no recorded run)
jmclong/random-fourier-features-pytorch/rff/dataloader.py
code served (permissive licence) · get_code("d8c3d477ca0ad0fe")
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, 3 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 3 later) and 4 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
basic_encoding 3 other papers
3 later
2403.16831 (2024-03)
UrbanVLP: Multi-Granularity Vision-Language Pretraining for Urban Socioeconomic Indicator Prediction
2405.14702 (2024-05)
G3: An Effective and Adaptive Framework for Worldwide Geolocalization Using Large Multi-Modality Models
2601.02289 (2026-01)
Rank-based Geographical Regularization: Revisiting Contrastive Self-Supervised Learning for Multispectral Remote Sensing Imagery
sample_b 3 other papers
3 later
2403.16831 (2024-03)
UrbanVLP: Multi-Granularity Vision-Language Pretraining for Urban Socioeconomic Indicator Prediction
2405.14702 (2024-05)
G3: An Effective and Adaptive Framework for Worldwide Geolocalization Using Large Multi-Modality Models
2601.02289 (2026-01)
Rank-based Geographical Regularization: Revisiting Contrastive Self-Supervised Learning for Multispectral Remote Sensing Imagery
gaussian_encoding 2 other papers
2 later
2403.16831 (2024-03)
UrbanVLP: Multi-Granularity Vision-Language Pretraining for Urban Socioeconomic Indicator Prediction
2405.14702 (2024-05)
G3: An Effective and Adaptive Framework for Worldwide Geolocalization Using Large Multi-Modality Models

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 show that passing input points through a simple Fourier feature mapping enables a multilayer perceptron (MLP) to learn high-frequency functions in lowdimensional problem domains. These results shed light on recent advances in computer vision and graphics that achieve state-of-the-art results by using MLPs to represent complex 3D objects and scenes. Using tools from the neural tangent kernel (NTK) literature, we show that a standard MLP fails to learn high frequencies both in theory and in practice. To overcome this spectral bias, we use a Fourier feature mapping to transform the effective NTK into a stationary kernel with a tunable bandwidth. We suggest an approach for selecting problem-specific Fourier features that greatly improves the performance of MLPs for low-dimensional regression tasks relevant to the computer vision and graphics communities.

For agents

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

get_harvested_code_for_paper("2006.10739")
get_code_for_paper("2006.10739")
have("2006.10739")

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

curl https://syntology.ai/api/ran/2006.10739.json

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

[![Syntology run record](https://syntology.ai/api/ran/2006.10739.svg)](https://syntology.ai/paper/2006.10739)

Connect an agent — have() is free.