SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2406.03386 · 2024

Learning Long Range Dependencies on Graphs via Random Walks

arXiv · PDF · Open in the Atlas

Code that ran

13 of 13 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; 2 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 11 failures of our instrument; 0 no recorded run), measured 2026-11-21; 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/2406.03386.json · badge: /api/ran/2406.03386.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
borgwardtlab/neuralwalker canonical (classifier label)
classifier basis: census
13 ran · 0 no recorded run
FunctionStatusWhere it lives
apply_rotary_pos_emb Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
borgwardtlab/neuralwalker/neuralwalker/modules/rotary_embedding.py
code served (permissive licence) · get_code("2a127d3ae372d7bd")
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

torch.manual_seed(0)

# Analyze function usage:
# - x: tensor that gets chunked on dim=-1, so needs even last dimension
# - cos: tensor indexed as cos[:, :x.shape[-2], :], so needs shape (batch, seq, dim)
# - sin: tensor indexed as sin[:, :x.shape[-2], :], so needs shape (batch, seq, dim)
# All tensors participate in element-wise operations

# Create small tensors with distinct dimensions
batch_size = 2
seq_len = 3
hidden_dim = 4

# x: (batch, seq_len, hidden_dim) - last dim must be even for rotate_half to chunk it
x = torch.randn(batch_size, seq_len, hidden_dim)

# cos and sin: (batch, seq_len, hidden_dim)
# They will be sliced to [:, :seq_len, :] which should work fine
cos = torch.randn(batch_size, seq_len + 1, hidden_dim)  # slightly larger to test slicing
sin = torch.randn(batch_size, seq_len + 1, hidden_dim)

ARGS = {
    "x": x,
    "cos": cos,
    "sin": sin,
}
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 (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
cauchy_naive Ran
ran; our contract draft was wrong, not the code
borgwardtlab/neuralwalker/neuralwalker/modules/s4.py
code served (permissive licence) · get_code("b7d9d94554e93b1b")
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 Tensor, ndim 2, dtype family float, shape (2, 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 torch

torch.manual_seed(0)

# v: (..., N) - shape (batch, N)
# z: (..., L) - shape (batch, L)
# w: (..., N) - shape (batch, N)

batch_size = 2
N = 4
L = 3

v = torch.randn(batch_size, N)
z = torch.randn(batch_size, L)
w = torch.randn(batch_size, N)

ARGS = {
    "v": v,
    "z": z,
    "w": w,
}
Setup block drafted by
a language model, Claude Haiku 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 Tensor, ndim 2, dtype family float, shape (2, 3) — shape (2, 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
code2_loss Ran
ran; our contract draft was wrong, not the code
borgwardtlab/neuralwalker/neuralwalker/loss.py
code served (permissive licence) · get_code("b3a8bb73de60c781")
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.functional as F

torch.manual_seed(0)

# The function expects:
# - pred: a list/sequence of tensors, each of shape (batch_size, num_classes)
# - true: a tensor of shape (batch_size, len(pred)) with class indices

# Create a small batch size of 2
batch_size = 2
num_pred_tensors = 4  # len(pred) will be 4
num_classes = 3

# pred: list of 4 tensors, each of shape (2, 3) - logits for batch_size=2, num_classes=3
pred = [
    torch.randn(batch_size, num_classes),
    torch.randn(batch_size, num_classes),
    torch.randn(batch_size, num_classes),
    torch.randn(batch_size, num_classes),
]

# true: tensor of shape (2, 4) - class indices for batch_size=2, num_pred_tensors=4
# Each entry should be a valid class index (0, 1, or 2)
true = torch.randint(0, num_classes, (batch_size, num_pred_tensors))

ARGS = {
    "pred": pred,
    "true": true,
}
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
get_1d_sine_pos_embed Ran
ran, honoured the contract we drafted
borgwardtlab/neuralwalker/neuralwalker/modules/pos_embed.py
code served (permissive licence) · get_code("b470ee5f2e9afb87")
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 (5, 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 math
import torch

torch.manual_seed(0)

ARGS = {
    "dim": 8,
    "length": 5,
    "max_period": 10000,
}
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 2, dtype family float, shape (5, 8) — shape (5, 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
get_constant_schedule_with_warmup Ran
ran; our contract draft was wrong, not the code
borgwardtlab/neuralwalker/neuralwalker/lr_schedulers.py
code served (permissive licence) · get_code("4c9b4ca1dcd1d6e0")
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 LambdaLR. 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 simple model
model = nn.Linear(4, 3)

# Create an optimizer
optimizer = torch.optim.SGD(model.parameters(), lr=0.1)

# Define arguments
ARGS = {
    "optimizer": optimizer,
    "warmup_epochs": 5,
    "max_epochs": 20
}
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 LambdaLR — a LambdaLR output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a LambdaLR 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
get_cosine_schedule_with_warmup Ran
ran; our contract draft was wrong, not the code
borgwardtlab/neuralwalker/neuralwalker/lr_schedulers.py
code served (permissive licence) · get_code("be4dbd83bb917452")
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 LambdaLR. 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 simple model for the optimizer
model = nn.Linear(4, 3)

# Create an optimizer with the model parameters
optimizer = torch.optim.SGD(model.parameters(), lr=0.1)

# Define the arguments
ARGS = {
    'optimizer': optimizer,
    'warmup_epochs': 5,
    'max_epochs': 100
}
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 LambdaLR — a LambdaLR output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a LambdaLR 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
get_global_layer Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
borgwardtlab/neuralwalker/neuralwalker/modules/mp_layer.py
code served (permissive licence) · get_code("5a4dbef456ab5726")
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 MultiheadAttention. 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
from torch import nn

torch.manual_seed(0)

class VirtualNodeLayer(nn.Module):
    def __init__(self, hidden_size, dropout, norm_first=True, norm_type='batchnorm', pooling='sum'):
        super().__init__()
        self.hidden_size = hidden_size
        self.dropout = dropout
        self.norm_first = norm_first
        self.norm_type = norm_type
        self.pooling = pooling
        
        if norm_type == 'batchnorm':
            self.norm = nn.BatchNorm1d(hidden_size)
        else:
            self.norm = nn.LayerNorm(hidden_size)
        
        self.dropout_layer = nn.Dropout(dropout)
    
    def forward(self, x):
        if self.norm_first:
            x = self.norm(x)
        x = self.dropout_layer(x)
        if not self.norm_first:
            x = self.norm(x)
        return x

ARGS = {
    'global_model_type': 'transformer',
    'hidden_size': 8,
    'num_heads': 2,
    'attn_dropout': 0.1,
    'dropout': 0.2,
    'vn_norm_first': True,
    'vn_norm_type': 'batchnorm',
    'vn_pooling': 'sum',
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
performer_pytorch, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type MultiheadAttention — a MultiheadAttention output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a MultiheadAttention 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
get_inverse_sqrt_schedule_with_warmup Ran
ran; our contract draft was wrong, not the code
borgwardtlab/neuralwalker/neuralwalker/lr_schedulers.py
code served (permissive licence) · get_code("b64bb26edbc3a64e")
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 LambdaLR. 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 math

torch.manual_seed(0)

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

model = TinyModel()
optimizer = torch.optim.SGD(model.parameters(), lr=0.1)

ARGS = {
    "optimizer": optimizer,
    "warmup_epochs": 5,
    "max_epochs": 100
}
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 LambdaLR — a LambdaLR output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a LambdaLR 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
get_logger Ran
ran; our contract draft was wrong, not the code
borgwardtlab/neuralwalker/neuralwalker/modules/s4.py
code served (permissive licence) · get_code("61139ec62260b411")
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 logging
from pytorch_lightning.utilities import rank_zero_only

# Construct arguments for get_logger function
ARGS = {
    "name": "test_logger",
    "level": logging.DEBUG
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
pytorch_lightning — 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
log_vandermonde_naive Ran
ran; our contract draft was wrong, not the code
borgwardtlab/neuralwalker/neuralwalker/modules/s4.py
code served (permissive licence) · get_code("e25911109ba29783")
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 Tensor, ndim 2, dtype family float, shape (2, 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 torch

torch.manual_seed(0)

# Create small tensors with distinct dimensions
batch_size = 2
N = 4
L = 3

# v: (..., N) - shape (2, 4)
v = torch.randn(batch_size, N)

# x: (..., N) - shape (2, 4)
x = torch.randn(batch_size, N)

ARGS = {
    "v": v,
    "x": x,
    "L": L,
    "conj": True,
}
Setup block drafted by
a language model, Claude Haiku 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 Tensor, ndim 2, dtype family float, shape (2, 3) — shape (2, 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
multilabel_cross_entropy Ran
ran; our contract draft was wrong, not the code
borgwardtlab/neuralwalker/neuralwalker/loss.py
code served (permissive licence) · get_code("3d91b44d6e828f49")
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
from torch import nn

torch.manual_seed(0)

# Create pred tensor: logits for multilabel classification
# Shape: (batch_size=2, num_labels=4)
pred = torch.randn(2, 4)

# Create true tensor: binary labels (0 or 1) or NaN for unlabeled
# Shape: (batch_size=2, num_labels=4)
# Using some NaN values to test the is_labeled masking
true = torch.tensor([
    [1.0, 0.0, 1.0, 0.0],
    [0.0, 1.0, float('nan'), 1.0]
])

ARGS = {
    "pred": pred,
    "true": true
}
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
rotate_half Ran
ran, honoured the contract we drafted
borgwardtlab/neuralwalker/neuralwalker/modules/rotary_embedding.py
pointer only (licence: BSD-3-Clause); the stored copy get_code serves, from tdooms/bilinear-decomposition, is pointer only (licence: NONE) · get_code("437c7011506995a3")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (BSD-3-Clause), but get_code serves the stored copy, first harvested from tdooms/bilinear-decomposition, 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.

weighted_cross_entropy Ran
ran; our contract draft was wrong, not the code
borgwardtlab/neuralwalker/neuralwalker/loss.py
code served (permissive licence) · get_code("cbedbb45b34d1889")
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.functional as F

torch.manual_seed(0)

# Multiclass case: pred is 2D, true is 1D with class indices
batch_size = 2
n_classes = 4

# Create predictions (logits) for multiclass classification
pred = torch.randn(batch_size, n_classes)

# Create true labels (class indices from 0 to n_classes-1)
# Make sure we have at least 2 different classes for realistic weighting
true = torch.tensor([0, 2], dtype=torch.long)

ARGS = {
    "pred": pred,
    "true": true,
}
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

Also present in other papers' code

Of 13 samples lifted from this paper's linked repositories, 13 carry a function identity and 0 do not. Of the 13 distinct functions with an identity, 5 are also present in other papers whose code we hold (5 with at least one paper dated earlier, 1 the same month, 5 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 15 other papers
11 dated earlier, 4 later · 3 only as an assembly brick
2009.09761 (2020-09)
DiffWave: A Versatile Diffusion Model for Audio Synthesis
2111.00396 (2021-11)
Efficiently Modeling Long Sequences with Structured State Spaces
2204.01692 (2022-04)
Long Movie Clip Classification with State-Space Video Models
and 12 more not named here
rotate_half 13 other papers
3 dated earlier, 1 the same month, 9 later · 2 only as an assembly brick
2202.03036 (2022-02)
Structure-Aware Transformer for Graph Representation Learning
2203.07852 (2022-03)
Block-Recurrent Transformers
2403.00043 (2024-03)
RiNALMo: General-Purpose RNA Language Models Can Generalize Well on Structure Prediction Tasks
and 10 more not named here
cauchy_naive 6 other papers
4 dated earlier, 2 later · 1 only as an assembly brick
1612.00796 (2016-12)
Overcoming catastrophic forgetting in neural networks
2111.00396 (2021-11)
Efficiently Modeling Long Sequences with Structured State Spaces
2312.00752 (2023-12)
Mamba: Linear-Time Sequence Modeling with Selective State Spaces
and 3 more not named here
log_vandermonde_naive 6 other papers
4 dated earlier, 2 later · 1 only as an assembly brick
1612.00796 (2016-12)
Overcoming catastrophic forgetting in neural networks
2111.00396 (2021-11)
Efficiently Modeling Long Sequences with Structured State Spaces
2312.00752 (2023-12)
Mamba: Linear-Time Sequence Modeling with Selective State Spaces
and 3 more not named here
apply_rotary_pos_emb 3 other papers
1 dated earlier, 2 later
2202.03036 (2022-02)
Structure-Aware Transformer for Graph Representation Learning
2408.11363 (2024-08)
ProteinGPT: Multimodal LLM for Protein Property Prediction and Structure Understanding
2606.18703 (2026-06)
Contextualizing Biological Language Models across Modalities via Logit-Space Contrastive Alignment

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 2026-11-21.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Message-passing graph neural networks (GNNs) excel at capturing local relationships but struggle with long-range dependencies in graphs. In contrast, graph transformers (GTs) enable global information exchange but often oversimplify the graph structure by representing graphs as sets of fixed-length vectors. This work introduces a novel architecture that overcomes the shortcomings of both approaches by combining the long-range information of random walks with local message passing. By treating random walks as sequences, our architecture leverages recent advances in sequence models to effectively capture long-range dependencies within these walks. Based on this concept, we propose a framework that offers (1) more expressive graph representations through random walk sequences, (2) the ability to utilize any sequence model for capturing long-range dependencies, and (3) the flexibility by integrating various GNN and GT architectures. Our experimental evaluations demonstrate that our approach achieves significant performance improvements on 19 graph and node benchmark datasets, notably outperforming existing methods by up to 13\% on the PascalVoc-SP and COCO-SP datasets. The code is available at https://github.com/BorgwardtLab/NeuralWalker.

For agents

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

get_harvested_code_for_paper("2406.03386")
get_code_for_paper("2406.03386")
have("2406.03386")

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

curl https://syntology.ai/api/ran/2406.03386.json

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

[![Syntology run record](https://syntology.ai/api/ran/2406.03386.svg)](https://syntology.ai/paper/2406.03386)

Connect an agent — have() is free.