SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2301.10540 · 2023

Modelling Long Range Dependencies in $N$D: From Task-Specific to a General Purpose CNN

arXiv · PDF · Open in the Atlas

Code that ran

6 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; 2 failures of our instrument; 0 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/2301.10540.json · badge: /api/ran/2301.10540.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
david-knigge/ccnn canonical (classifier label)
classifier basis not recorded on the link
6 ran · 0 no recorded run
FunctionStatusWhere it lives
databatch_add Ran
ran on a synthesized input
david-knigge/ccnn/datamodules/modelnet.py
code served (permissive licence) · get_code("001cd7c419cfca80")
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 DataBatch. 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

torch.manual_seed(0)

class DataBatch:
    def __init__(self, x):
        self.x = x

batch_1 = DataBatch(torch.randn(2, 4))
batch_2 = DataBatch(torch.randn(2, 4))

ARGS = {
    "batch_1": batch_1,
    "batch_2": batch_2,
}
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 DataBatch — a DataBatch output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a DataBatch 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
listops_tokenizer Ran
ran; our contract draft was wrong, not the code
david-knigge/ccnn/datamodules/listops.py
code served (permissive licence) · get_code("72d464924b5dee96")
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, ndim 1, 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)

def listops_tokenizer(s):
    return s.translate({ord(']'): ord('X'), ord('('): None, ord(')'): None}).split()

# The function takes a single string parameter 's' and:
# 1. Calls translate() on it with a translation table that replaces ']' with 'X' and removes '(' and ')'
# 2. Calls split() on the result to return a list of tokens
# 
# We need to provide a valid string that demonstrates the tokenizer works

s = "[ nested [ list ] ( with ) parens ] here"

ARGS = {
    "s": s
}
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 list, ndim 1, dtype family float — a list 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
load_data Ran
ran; our contract draft was wrong, not the code
david-knigge/ccnn/datamodules/utils.py
code served (permissive licence) · get_code("e1fd01b18f5800a0")
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 dict. 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 tempfile
import os
from pathlib import Path

torch.manual_seed(0)

# Create a temporary directory with some .pt files
temp_dir = tempfile.mkdtemp()
temp_path = Path(temp_dir)

# Create some test tensors and save them
tensor1 = torch.randn(2, 4)
tensor2 = torch.randn(2, 3)
tensor3 = torch.randn(5, 4)

torch.save(tensor1, temp_path / "tensor_a.pt")
torch.save(tensor2, temp_path / "tensor_b.pt")
torch.save(tensor3, temp_path / "tensor_c.pt")

# Also create a non-.pt file to verify it's ignored
with open(temp_path / "ignore_me.txt", "w") as f:
    f.write("this should be ignored")

ARGS = {
    "dir": temp_path
}
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 dict — a dict output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a dict 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
pad Ran
ran on a synthesized input
david-knigge/ccnn/datamodules/utils.py
code served (permissive licence) · get_code("a06af5ba6942100d")
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 1, dtype family float, shape (8,) 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)

# Analyze the function:
# - pad takes two parameters: channel and maxlen
# - channel is converted to a tensor and indexed with [-1]
# - channel.size(0) is called, so it needs to be a tensor-like with a size method
# - maxlen is used to create a tensor of shape (maxlen,)
# - channel is assigned into out[:channel.size(0)]

# Create a small channel tensor
channel = [1.0, 2.0, 3.0, 4.0, 5.0]

# maxlen should be larger than the channel length to test padding
maxlen = 8

ARGS = {
    "channel": channel,
    "maxlen": maxlen
}
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 1, dtype family float, shape (8,) — shape (8,) 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
pil_loader_grayscale Ran
ran on a synthesized input
david-knigge/ccnn/datamodules/pathfinder.py
code served (permissive licence) · get_code("db553cebdcfc9688")
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 Image. 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 tempfile
import os
from PIL import Image

# Create a temporary grayscale image file
temp_dir = tempfile.mkdtemp()
temp_image_path = os.path.join(temp_dir, "test_image.png")

# Create a simple grayscale image and save it
img = Image.new('L', (4, 3), color=128)
img.save(temp_image_path)

ARGS = {
    'path': temp_image_path
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
PIL — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Image — a Image output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Image output the recorded ndim 2 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
subsample Ran
ran on a synthesized input
david-knigge/ccnn/datamodules/utils.py
code served (permissive licence) · get_code("d9f8c8bfd8781483")
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 torch
import numpy as np

torch.manual_seed(0)

# X is a 3D tensor that gets sliced along dimension 2
# Shape: (batch, features, time_steps)
X = torch.randn(2, 4, 8)

# y is a target tensor (1D or 2D)
y = torch.randn(2, 1)

# subsample_rate is an integer that controls slicing
subsample_rate = 2

ARGS = {
    "X": X,
    "y": y,
    "subsample_rate": subsample_rate,
}
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 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

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, 3 are also present in other papers whose code we hold (3 with at least one paper dated earlier, 0 the same month, 1 later) and 3 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
listops_tokenizer 6 other papers
2 dated earlier, 4 later
2206.05852 (2022-06)
ChordMixer: A Scalable Neural Attention Model for Sequences with Different Lengths
2208.04933 (2022-08)
Simplified State Space Layers for Sequence Modeling
2402.15584 (2024-02)
State Space Models for Event Cameras
and 3 more not named here
load_data 1 other paper
1 dated earlier
2208.04933 (2022-08)
Simplified State Space Layers for Sequence Modeling
pad 1 other paper
1 dated earlier
2208.04933 (2022-08)
Simplified State Space Layers for Sequence Modeling

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

Performant Convolutional Neural Network (CNN) architectures must be tailored to specific tasks in order to consider the length, resolution, and dimensionality of the input data. In this work, we tackle the need for problem-specific CNN architectures. We present the Continuous Convolutional Neural Network (CCNN): a single CNN able to process data of arbitrary resolution, dimensionality and length without any structural changes. Its key component are its continuous convolutional kernels which model long-range dependencies at every layer, and thus remove the need of current CNN architectures for task-dependent downsampling and depths. We showcase the generality of our method by using the same architecture for tasks on sequential ($1{\rm D}$), visual ($2{\rm D}$) and point-cloud ($3{\rm D}$) data. Our CCNN matches and often outperforms the current state-of-the-art across all tasks considered.

For agents

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

get_harvested_code_for_paper("2301.10540")
get_code_for_paper("2301.10540")
have("2301.10540")

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

curl https://syntology.ai/api/ran/2301.10540.json

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

[![Syntology run record](https://syntology.ai/api/ran/2301.10540.svg)](https://syntology.ai/paper/2301.10540)

Connect an agent — have() is free.