SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1705.09792 · 2017

Deep Complex Networks

arXiv · PDF · Open in the Atlas

Code that ran

3 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; 1 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 2 failures of our instrument; 3 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/1705.09792.json · badge: /api/ran/1705.09792.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
ispamm/htorch extension (classifier label)
classifier basis: classifier_2025
3 ran · 0 no recorded run
omrijsharon/torchlex extension (classifier label)
classifier basis: classifier_2025
0 ran · 3 no recorded run
FunctionStatusWhere it lives
chunk Ran
ran, honoured the contract we drafted
ispamm/htorch/htorch/quaternion.py
code served (permissive licence) · get_code("d45ce81b9e40c437")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Sonnet 4.5, prompt python_fixture_v1) and returned tuple, ndim 3, 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

torch.manual_seed(0)

class ScalarTensor:
    """Stand-in class that has a .q attribute"""
    def __init__(self, tensor):
        self.q = tensor

# Create a small tensor for the input
input_tensor = ScalarTensor(torch.randn(2, 8))

# The function signature is chunk(input, *args, **kwargs)
# Looking at the body: torch.chunk(input.q, *args, chunks=4, **kwargs)
# torch.chunk signature is: torch.chunk(input, chunks, dim=0)
# The function hardcodes chunks=4, so *args would typically contain dim
# We can pass dim as a positional arg or kwarg

ARGS = {
    'input': input_tensor,
}
Setup block drafted by
a language model, Claude Sonnet 4.5, prompt python_fixture_v1
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type tuple, ndim 3, dtype family float — a tuple output has no array shape of its own; none is stated
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
conj Ran
ran; our contract draft was wrong, not the code
ispamm/htorch/htorch/quaternion.py
code served (permissive licence) · get_code("2c35f59635cf57df")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Sonnet 4.5, prompt python_fixture_v1) and returned QuaternionTensor. 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 functools

HANDLED_FUNCTIONS = {}

def implements(torch_function):
    """Register a torch function override for ScalarTensor"""
    @functools.wraps(torch_function)
    def decorator(func):
        HANDLED_FUNCTIONS[torch_function] = func
        return func
    return decorator

class QuaternionTensor:
    def __init__(self, data, from_parts=True):
        if from_parts:
            if isinstance(data, list):
                self.a = data[0]
                self.b = data[1]
                self.c = data[2]
                self.d = data[3]
            else:
                # Assume data is a tensor with quaternion components concatenated
                if len(data.shape) > 1:
                    n = data.shape[1] // 4
                    self.a = data[:, :n]
                    self.b = data[:, n:2*n]
                    self.c = data[:, 2*n:3*n]
                    self.d = data[:, 3*n:]
                else:
                    n = data.shape[0] // 4
                    self.a = data[:n]
                    self.b = data[n:2*n]
                    self.c = data[2*n:3*n]
                    self.d = data[3*n:]
        else:
            # data is already split or processed
            if isinstance(data, list):
                self.a = data[0]
                self.b = data[1]
                self.c = data[2]
                self.d = data[3]
            else:
                if len(data.shape) > 1:
                    n = data.shape[1] // 4
                    self.a = data[:, :n]
                    self.b = data[:, n:2*n]
                    self.c = data[:, 2*n:3*n]
                    self.d = data[:, 3*n:]
                else:
                    n = data.shape[0] // 4
                    self.a = data[:n]
                    self.b = data[n:2*n]
                    self.c = data[2*n:3*n]
                    self.d = data[3*n:]
        
        self.shape = self.a.shape if hasattr(self.a, 'shape') else (len(self.a),)
    
    def conj(self):
        """
        Quaternion conjugate
        """
        if len(self.shape) > 1:
            con = torch.cat([self.a, -self.b, -self.c, -self.d], 1)
        else:
            con = [self.a, -self.b, -self.c, -self.d]
        return self.__class__(con, False)

torch.manual_seed(0)

# Create a quaternion tensor with batch dimension
# Shape: (2, 8) where 8 = 4 components * 2 dimensions per component
quat_data_2d = torch.randn(2, 8)
quat_tensor_2d = QuaternionTensor(quat_data_2d, from_parts=True)

ARGS = {"self": quat_tensor_2d}
Setup block drafted by
a language model, Claude Sonnet 4.5, prompt python_fixture_v1
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type QuaternionTensor — a QuaternionTensor output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a QuaternionTensor 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
implements Ran
ran; our contract draft was wrong, not the code
ispamm/htorch/htorch/quaternion.py
code served (permissive licence) · get_code("ca24c08883bb62da")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Sonnet 4.5, prompt python_fixture_v1) and returned function. 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 torch.nn as nn

# The function `implements` is a decorator factory that takes a torch_function as parameter
# and returns a decorator. We need to provide a valid torch function.

# Let's use a simple torch function like torch.add
torch_function_arg = torch.add

ARGS = {
    'torch_function': torch_function_arg
}
Setup block drafted by
a language model, Claude Sonnet 4.5, prompt python_fixture_v1
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type function — a function output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a function 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
exp Not yet run
unverified (harvested, no recorded run)
omrijsharon/torchlex/torchlex.py
pointer only (licence: NONE) · get_code("80bac485fc1b3e81")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, omrijsharon/torchlex 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. No invocation recorded.

log Not yet run
unverified (harvested, no recorded run)
omrijsharon/torchlex/torchlex.py
pointer only (licence: NONE) · get_code("57da8118b3cadb86")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, omrijsharon/torchlex 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. No invocation recorded.

sin Not yet run
unverified (harvested, no recorded run)
omrijsharon/torchlex/torchlex.py
pointer only (licence: NONE) · get_code("f0b6b7d360712efa")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, omrijsharon/torchlex 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. 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, 1 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 1 later) and 5 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
implements 1 other paper
1 later
2207.08867 (2022-07)
MCTensor: A High-Precision Deep Learning Library with Multi-Component Floating-Point

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

At present, the vast majority of building blocks, techniques, and architectures for deep learning are based on real-valued operations and representations. However, recent work on recurrent neural networks and older fundamental theoretical analysis suggests that complex numbers could have a richer representational capacity and could also facilitate noise-robust memory retrieval mechanisms. Despite their attractive properties and potential for opening up entirely new neural architectures, complex-valued deep neural networks have been marginalized due to the absence of the building blocks required to design such models. In this work, we provide the key atomic components for complex-valued deep neural networks and apply them to convolutional feed-forward networks and convolutional LSTMs. More precisely, we rely on complex convolutions and present algorithms for complex batch-normalization, complex weight initialization strategies for complex-valued neural nets and we use them in experiments with end-to-end training schemes. We demonstrate that such complex-valued models are competitive with their real-valued counterparts. We test deep complex models on several computer vision tasks, on music transcription using the MusicNet dataset and on Speech Spectrum Prediction using the TIMIT dataset. We achieve state-of-the-art performance on these audio-related tasks.

For agents

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

get_harvested_code_for_paper("1705.09792")
get_code_for_paper("1705.09792")
have("1705.09792")

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

curl https://syntology.ai/api/ran/1705.09792.json

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

[![Syntology run record](https://syntology.ai/api/ran/1705.09792.svg)](https://syntology.ai/paper/1705.09792)

Connect an agent — have() is free.