SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2205.08987 · ECCV · 2022

Trading Positional Complexity vs Deepness in Coordinate Networks

Simon Lucey, Xueqian Li, Sameera Ramasinghe, Jianqiao Zheng

arXiv · PDF · Open in the Atlas

Code that ran

4 of 9 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 3 have no contract verdict; 1 failure of our instrument; 5 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/2205.08987.json · badge: /api/ran/2205.08987.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
osiriszjq/complex_encoding canonical (classifier label)
classifier basis not recorded on the link
4 ran · 5 no recorded run
FunctionStatusWhere it lives
get_logger Ran
ran; our contract draft was wrong, not the code
osiriszjq/complex_encoding/2D_random_points.py
code served (permissive licence) · get_code("d8dad09165d593fd")
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 Logger. 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 os
import tempfile
import logging

torch.manual_seed(0)

# Create a temporary directory and file for logging
temp_dir = tempfile.mkdtemp()
log_filename = os.path.join(temp_dir, "test.log")

ARGS = {
    "filename": log_filename,
    "verbosity": 1,
    "name": "test_logger"
}
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 Logger — a Logger output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Logger 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
main Ran
ran on a synthesized input
osiriszjq/complex_encoding/3D_separable_points_GD.py
code served (permissive licence) · get_code("8fa27028f4b7a1e4")
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 int, ndim 0, dtype family int, shape () as a later run recorded it. The image it ran in was not recorded. The code mentions cuda, and the harness aliases cuda to the CPU for every sample; whether this run needed that is 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
import tempfile
import os

torch.manual_seed(0)

class MockArgs:
    def __init__(self):
        self.save_path = tempfile.mkdtemp() + "/"
        self.logger = "/test.log"
        self.data_path = None
        self.N_repeat = 1
        self.save_flag = False

def encoding_func_3D(method, params):
    """Mock encoding function for 3D"""
    class MockEncoding:
        def __init__(self, method, params):
            self.method = method
            self.params = params
        def __call__(self, x):
            return x
    return MockEncoding(method, params)

def encoding_func_1D(method, params):
    """Mock encoding function for 1D"""
    class MockEncoding:
        def __init__(self, method, params):
            self.method = method
            self.params = params
        def __call__(self, x):
            return x
    return MockEncoding(method, params)

def train_simple_3D(signals, ef, N_repeat, lr, epochs, depth, device, logger):
    """Mock training function for simple 3D"""
    batch_size = signals.shape[0]
    time_ = np.random.rand(batch_size, N_repeat)
    trn_psnr_ = np.random.rand(batch_size, epochs)
    tst_psnr_ = np.random.rand(batch_size, epochs)
    rec_ = np.random.rand(batch_size, 4, 4, 4)
    return time_, trn_psnr_, tst_psnr_, rec_

def train_kron_3D(signals, ef, N_repeat, lr, epochs, depth, device, logger):
    """Mock training function for kron 3D"""
    batch_size = signals.shape[0]
    time_ = np.random.rand(batch_size, N_repeat)
    trn_psnr_ = np.random.rand(batch_size, epochs)
    tst_psnr_ = np.random.rand(batch_size, epochs)
    rec_ = np.random.rand(batch_size, 4, 4, 4)
    return time_, trn_psnr_, tst_psnr_, rec_

def train_closed_form_3D(signals, ef, N_repeat, device, logger):
    """Mock training function for closed form 3D"""
    batch_size = signals.shape[0]
    time_ = np.random.rand(batch_size, N_repeat)
    trn_psnr_ = np.random.rand(batch_size, 1)
    tst_psnr_ = np.random.rand(batch_size, 1)
    rec_ = np.random.rand(batch_size, 4, 4, 4)
    return time_, trn_psnr_, tst_psnr_, rec_

# Create a temporary npz file with test data
temp_dir = tempfile.gettempdir()
data_file = os.path.join(temp_dir, "test_data.npz")
test_signals = np.random.rand(2, 4, 4, 4).astype(np.float32)
np.savez(data_file, test=test_signals)

args = MockArgs()
args.data_path = data_file

ARGS = {
    "args": args
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
imageio, numpy, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type int, ndim 0, dtype family int, 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
psnr_func Ran
ran on a synthesized input
osiriszjq/complex_encoding/utils.py
code served (permissive licence) · get_code("ef72fc9d6dba1927")
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 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 torch
import torch.nn as nn

torch.manual_seed(0)

# Create two small tensors for comparison
# Using distinct dimensions: batch=2, features=4
x = torch.randn(2, 4)
y = torch.randn(2, 4)

# Construct ARGS dict with all parameters
ARGS = {
    "x": x,
    "y": y,
    "return_mse": False
}
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 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
srank_func Ran
ran on a synthesized input
osiriszjq/complex_encoding/utils.py
code served (permissive licence) · get_code("0c6eb75c8d92b68c")
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 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 torch

torch.manual_seed(0)

# The function expects:
# - X: a tensor that can be passed to torch.svd()
# - return_l1: a boolean flag

# Create a small matrix for SVD computation
# SVD requires a 2D matrix, let's make it 4x3 to have distinct dimensions
X = torch.randn(4, 3)

ARGS = {
    "X": X,
    "return_l1": False
}
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 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
main Not yet run
unverified (harvested, no recorded run)
osiriszjq/complex_encoding/2D_random_points.py
code served (permissive licence) · get_code("d7746ecdd4b4e6d3")
How it ran

no invocation recorded.

main Not yet run
unverified (harvested, no recorded run)
osiriszjq/complex_encoding/2D_separable_points.py
code served (permissive licence) · get_code("80bda3a1667c4cca")
How it ran

no invocation recorded.

main Not yet run
unverified (harvested, no recorded run)
osiriszjq/complex_encoding/3D_random_points_GD.py
code served (permissive licence) · get_code("a884cd96321f23e2")
How it ran

no invocation recorded.

smooth Not yet run
unverified (harvested, no recorded run)
osiriszjq/complex_encoding/utils.py
code served (permissive licence) · get_code("0477b5983b9122c0")
How it ran

no invocation recorded.

train_closed_form_2D Not yet run
unverified (harvested, no recorded run)
osiriszjq/complex_encoding/trainer.py
code served (permissive licence) · get_code("7c3dbb048063e6a7")
How it ran

no invocation recorded.

Also present in other papers' code

Of 9 samples lifted from this paper's linked repositories, 9 carry a function identity and 0 do not. Of the 9 distinct functions with an identity, 1 are also present in other papers whose code we hold (1 with at least one paper dated earlier, 0 the same month, 1 later) and 8 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
get_logger 10 other papers
1 dated earlier, 9 later
2106.06716 (2021-06)
DS-TransUNet:Dual Swin Transformer U-Net for Medical Image Segmentation
2207.00012 (2022-07)
Reliable Representations Make A Stronger Defender: Unsupervised Structure Refinement for Robust GNN
2304.13098 (2023-04)
Uncovering the Representation of Spiking Neural Networks Trained with Surrogate Gradient
and 7 more not named here

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

It is well noted that coordinate-based MLPs benefit-in terms of preserving high-frequency information-through the encoding of coordinate positions as an array of Fourier features. Hitherto, the rationale for the effectiveness of these positional encodings has been mainly studied through a Fourier lens. In this paper, we strive to broaden this understanding by showing that alternative non-Fourier embedding functions can indeed be used for positional encoding. Moreover, we show that their performance is entirely determined by a trade-off between the stable rank of the embedded matrix and the distance preservation between embedded coordinates. We further establish that the now ubiquitous Fourier feature mapping of position is a special case that fulfills these conditions. Consequently, we present a more general theory to analyze positional encoding in terms of shifted basis functions. In addition, we argue that employing a more complex positional encoding-that scales exponentially with the number of modes-requires only a linear (rather than deep) coordinate function to achieve comparable performance. Counter-intuitively, we demonstrate that trading positional embedding complexity for network deepness is orders of magnitude faster than current state-of-the-art; despite the additional embedding complexity. To this end, we develop the necessary theoretical formulae and empirically verify that our theoretical claims hold in practice. Project page at https://osiriszjq.github.io/complex encoding.

For agents

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

get_harvested_code_for_paper("2205.08987")
get_code_for_paper("2205.08987")
have("2205.08987")

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

curl https://syntology.ai/api/ran/2205.08987.json

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

[![Syntology run record](https://syntology.ai/api/ran/2205.08987.svg)](https://syntology.ai/paper/2205.08987)

Connect an agent — have() is free.