SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2303.11249 · NeurIPS · 2023

What Makes Data Suitable for a Locally Connected Neural Network? A Necessary and Sufficient Condition Based on Quantum Entanglement

Noam Razin, Nadav Cohen, La Vega, Yotam Alexander, Nimrod De

arXiv · PDF · Open in the Atlas

Code that ran

14 of 15 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, 3 violated it and 8 have no contract verdict; 3 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/2303.11249.json · badge: /api/ran/2303.11249.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
nmd95/data_suitable_lc_nn_code canonical (classifier label)
classifier basis not recorded on the link
8 ran · 0 no recorded run
lucidrains/local-attention canonical (classifier label)
classifier basis not recorded on the link
6 ran · 1 no recorded run
FunctionStatusWhere it lives
FeedForward Ran
ran on a synthesized input
nmd95/data_suitable_lc_nn_code/models/local_attention.py
code served (permissive licence) · get_code("0d569724bd138801")
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 Sequential. 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
import torch.nn.functional as F

torch.manual_seed(0)

class GEGLU(nn.Module):
    def forward(self, x):
        x, gate = x.chunk(2, dim=-1)
        return x * F.gelu(gate)

def FeedForward(dim, mult=4, dropout=0.0):
    inner_dim = int(dim * mult * 2 / 3)
    return nn.Sequential(nn.LayerNorm(dim), nn.Linear(dim, inner_dim * 2, bias=False), GEGLU(), nn.Dropout(dropout), nn.Linear(inner_dim, dim, bias=False))

ARGS = {
    "dim": 64,
    "mult": 4,
    "dropout": 0.1,
}
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 Sequential — a Sequential output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Sequential output the recorded ndim 1 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
create_index_map Ran
ran on a synthesized input
nmd95/data_suitable_lc_nn_code/common/data_utils.py
code served (permissive licence) · get_code("a1046a51a674e467")
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 int, shape (4, 3) 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 create_index_map takes array_shape as a parameter
# Looking at the function body:
# - It uses np.prod(array_shape) to get the total number of elements
# - It creates an array with np.arange and reshapes it to array_shape
# - It expands dims and calls rearrange_partitions
# - The function expects array_shape to be a tuple that can be used with reshape
# - For rearrange_partitions to work correctly, the shape should have at least 2 dimensions
#   (first is batch, rest are spatial), and dimensions > 2 for recursion to work

# Create a small but valid array_shape tuple
# The function needs dimensions > 2 to avoid early termination
# Using shape (4, 3) - batch dimension 4, spatial dimension 3
array_shape = (4, 3)

ARGS = {
    "array_shape": array_shape
}
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 ndarray, ndim 2, dtype family int, shape (4, 3) — shape (4, 3) 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
create_q_multidim Ran
ran on a synthesized input
nmd95/data_suitable_lc_nn_code/rearrangement_algorithms/igtd.py
code served (permissive licence) · get_code("10e461943197ec33")
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 (6, 6) 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

# Create a small index mapping array
# This should be a 2D array where each element contains a unique index value
# that maps to its position in the array
index_mapping = np.array([
    [0, 1, 2],
    [3, 4, 5]
], dtype=int)

ARGS = {
    "index_mapping": index_mapping
}
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 (6, 6) — shape (6, 6) 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
default Ran
ran, violated the contract we drafted
lucidrains/local-attention/local_attention/transformer.py
pointer only (licence: MIT); the stored copy get_code serves, from ThomasMrY/VCT, is pointer only (licence: NONE) · get_code("60fff7c3c400d7ff")
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 ThomasMrY/VCT, 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.

default Ran
ran, violated the contract we drafted
lucidrains/local-attention/local_attention/local_attention.py
code served (permissive licence) · get_code("b5307f70349f5c27")
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) 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

def exists(val):
    return val is not None

def default(value, d):
    return d if not exists(value) else value

# Test case 1: value is None, should return d
value_1 = None
d_1 = "default_value"

# Test case 2: value is not None, should return value
value_2 = "provided_value"
d_2 = "default_value"

# Test case 3: value is 0 (falsy but not None), should return value
value_3 = 0
d_3 = 42

# Test case 4: value is empty list (falsy but not None), should return value
value_4 = []
d_4 = [1, 2, 3]

# Test case 5: value is a tensor
torch.manual_seed(0)
value_5 = torch.tensor([1.0, 2.0])
d_5 = torch.tensor([0.0, 0.0])

ARGS = {
    "value": None,
    "d": "default_value"
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
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
exists Ran
ran, violated the contract we drafted
lucidrains/local-attention/local_attention/local_attention.py
pointer only (licence: MIT); the stored copy get_code serves, from ThomasMrY/VCT, is pointer only (licence: NONE) · get_code("aa5486a3650902d8")
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 ThomasMrY/VCT, 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.

get_optimizer_and_scheduler Ran
ran on a synthesized input
nmd95/data_suitable_lc_nn_code/models/utils.py
code served (permissive licence) · get_code("b0ce87c616f140a4")
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, 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 torch.nn as nn
import torch.optim as optim

torch.manual_seed(0)

# Create a minimal model with parameters
class SimpleModel(nn.Module):
    def __init__(self):
        super().__init__()
        self.linear = nn.Linear(4, 3)
    
    def forward(self, x):
        return self.linear(x)

model = SimpleModel()

# Create baseline_params dict with valid optimizer and scheduler
baseline_params = {
    'optimizer_name': 'Adam',
    'optimizer_parameters': {
        'lr': 0.001,
        'betas': (0.9, 0.999),
        'eps': 1e-8,
        'weight_decay': 0.0
    },
    'scheduler_name': 'StepLR',
    'scheduler_params': {
        'step_size': 10,
        'gamma': 0.1
    }
}

ARGS = {
    'model': model,
    'baseline_params': baseline_params
}
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 tuple, ndim 1, 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
l2norm Ran
ran; our contract draft was wrong, not the code
lucidrains/local-attention/local_attention/transformer.py
pointer only (licence: MIT); the stored copy get_code serves, from tmlresearchgroup-cas/clipure, is pointer only (licence: NONE) · get_code("3eb58dae620046d3")
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 tmlresearchgroup-cas/clipure, 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.

load_configuration Ran
ran on a synthesized input
nmd95/data_suitable_lc_nn_code/configs/config_utils.py
code served (permissive licence) · get_code("19f6a689dc934e45")
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 yaml
import tempfile
import os

# Create a temporary YAML configuration file
temp_dir = tempfile.mkdtemp()
config_file_path = os.path.join(temp_dir, "test_config.yaml")

# Write a valid YAML configuration
config_content = """
model:
  name: test_model
  layers: 3
  hidden_dim: 64
training:
  epochs: 10
  batch_size: 32
  learning_rate: 0.001
data:
  dataset: test_dataset
  split: 0.8
"""

with open(config_file_path, 'w') as f:
    f.write(config_content)

# Define ARGS with the config_path parameter
ARGS = {
    'config_path': config_file_path
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch, yaml — 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
permute_elements Ran
ran on a synthesized input
nmd95/data_suitable_lc_nn_code/common/data_utils.py
code served (permissive licence) · get_code("ca019c11c4f8c20a")
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 (2, 4, 3) 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)

# Create a small batch of arrays with shape (batch_size=2, dim1=4, dim2=3)
input_array = torch.arange(2 * 4 * 3, dtype=torch.float32).reshape(2, 4, 3)

# Create a permutation list for the flattened dimension (4 * 3 = 12 elements)
permutation = [11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0]

ARGS = {
    "input_array": input_array,
    "permutation": permutation,
}
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 3, dtype family float, shape (2, 4, 3) — shape (2, 4, 3) 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
prepare_model Ran
ran on a synthesized input
nmd95/data_suitable_lc_nn_code/models/utils.py
code served (permissive licence) · get_code("7109b50374757d1d")
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 MinimalModel. 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)

# Create a minimal model
class MinimalModel(nn.Module):
    def __init__(self):
        super().__init__()
        self.linear = nn.Linear(4, 3)
    
    def forward(self, x):
        return self.linear(x)

model = MinimalModel()

baseline_params = {
    'multiple_gpu': False,
    'model_name': 'S4Model',
    'device_ids': [0],
    'device': 'cpu'
}

ARGS = {
    'model': model,
    'baseline_params': baseline_params
}
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 MinimalModel — a MinimalModel output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a MinimalModel 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
rearrange_partitions Ran
ran on a synthesized input
nmd95/data_suitable_lc_nn_code/common/data_utils.py
code served (permissive licence) · get_code("970d663a0ca4c94d")
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, shape (2, 16) 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 numpy as np

torch.manual_seed(0)

# Test with a torch tensor - batch size 2, spatial dimensions 4x4
input_tensor = torch.randn(2, 4, 4)

ARGS = {
    "input_array": input_tensor
}
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, shape (2, 16) — shape (2, 16) 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
rotate_half Ran
ran; our contract draft was wrong, not the code
lucidrains/local-attention/local_attention/rotary.py
code served (permissive licence) · get_code("1147383164fd3a66")
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 (2, 3, 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 torch
from einops import rearrange

torch.manual_seed(0)

# The function rotate_half takes a single parameter 'x' which is a tensor
# It rearranges the tensor, unbinds it, and concatenates parts together
# The function expects x to have a shape where the last dimension is even
# (since it's split into r=2 parts)

# Create a small tensor with batch size 2 and last dimension as even number (4)
# Shape: (batch=2, ..., last_dim=4) where last_dim will be split into r=2, d=2
x = torch.randn(2, 3, 4)

ARGS = {
    'x': x
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
einops, 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 (2, 3, 4) — shape (2, 3, 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
to Ran
ran; our contract draft was wrong, not the code
lucidrains/local-attention/local_attention/local_attention.py
code served (permissive licence) · get_code("f092dd8a37a00a6e")
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

torch.manual_seed(0)

# Create a small tensor to pass to the function
t = torch.randn(2, 4, dtype=torch.float32, device='cpu')

# The function takes parameter 't' and accesses t.device and t.dtype
# We need to pass a tensor with these attributes
ARGS = {
    't': t
}
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
apply_rotary_pos_emb Not yet run
unverified (harvested, no recorded run)
lucidrains/local-attention/local_attention/rotary.py
code served (permissive licence) · get_code("7b83cdd495fff4d9")
How it ran

no invocation recorded.

Also present in other papers' code

Of 15 samples lifted from this paper's linked repositories, 15 carry a function identity and 0 do not. Of the 15 distinct functions with an identity, 6 are also present in other papers whose code we hold (5 with at least one paper dated earlier, 3 the same month, 6 later) and 9 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
exists 486 other papers
150 dated earlier, 15 the same month, 315 later, 4 same year, order not determinable, 2 undated · 78 only as an assembly brick
1603.08155 (2016-03)
Perceptual Losses for Real-Time Style Transfer and Super-Resolution
1611.07004 (2016-11)
Image-to-Image Translation with Conditional Adversarial Networks
1804.04637 (2018-04)
EMBER: An Open Dataset for Training Static PE Malware Machine Learning Models
and 483 more not named here
default 163 other papers
75 dated earlier, 4 the same month, 82 later, 1 same year, order not determinable, 1 undated · 27 only as an assembly brick
1603.08155 (2016-03)
Perceptual Losses for Real-Time Style Transfer and Super-Resolution
1810.00825 (2018-10)
Set Transformer: A Framework for Attention-based Permutation-Invariant Neural Networks
1907.01470 (2019-07)
Augmenting Self-attention with Persistent Memory
and 160 more not named here
l2norm 16 other papers
6 dated earlier, 1 the same month, 9 later · 4 only as an assembly brick
2112.05682 (2021-12)
Self-attention Does Not Need $O(n^2)$ Memory
2202.04200 (2022-02)
MaskGIT: Masked Generative Image Transformer
2203.07852 (2022-03)
Block-Recurrent Transformers
and 13 more not named here
default 4 other papers
3 dated earlier, 1 later
1812.01243 (2018-12)
Efficient Attention: Attention with Linear Complexities
2002.05202 (2020-02)
GLU Variants Improve Transformer
2006.16236 (2020-06)
Transformers are RNNs: Fast Autoregressive Transformers with Linear Attention
and 1 more not named here
rotate_half 3 other papers
3 later
2310.02980 (2023-10)
Never Train from Scratch: Fair Comparison of Long-Sequence Models Requires Data-Driven Priors
2406.10056 (2024-06)
UniAudio 1.5: Large Language Model-driven Audio Codec is A Few-shot Audio Task Learner
2410.14411 (2024-10)
SNAC: Multi-Scale Neural Audio Codec
to 2 other papers
1 dated earlier, 1 later
2108.12630 (2021-08)
GroupFormer: Group Activity Recognition with Clustered Spatial-Temporal Transformer
2310.02980 (2023-10)
Never Train from Scratch: Fair Comparison of Long-Sequence Models Requires Data-Driven Priors

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

The question of what makes a data distribution suitable for deep learning is a fundamental open problem. Focusing on locally connected neural networks (a prevalent family of architectures that includes convolutional and recurrent neural networks as well as local self-attention models), we address this problem by adopting theoretical tools from quantum physics. Our main theoretical result states that a certain locally connected neural network is capable of accurate prediction over a data distribution if and only if the data distribution admits low quantum entanglement under certain canonical partitions of features. As a practical application of this result, we derive a preprocessing method for enhancing the suitability of a data distribution to locally connected neural networks. Experiments with widespread models over various datasets demonstrate our findings. We hope that our use of quantum entanglement will encourage further adoption of tools from physics for formally reasoning about the relation between deep learning and real-world data.

For agents

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

get_harvested_code_for_paper("2303.11249")
get_code_for_paper("2303.11249")
have("2303.11249")

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

curl https://syntology.ai/api/ran/2303.11249.json

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

[![Syntology run record](https://syntology.ai/api/ran/2303.11249.svg)](https://syntology.ai/paper/2303.11249)

Connect an agent — have() is free.