SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2407.02013 · NeurIPS · 2024

DIGRAF: Diffeomorphic Graph-Adaptive Activation Function

Bruno Ribeiro, Carola-Bibiane Schönlieb, Beatrice Bevilacqua, Moshe Eliasof, Krishna Sri, Ipsit Mantri, Aurora Wang

arXiv · PDF · Open in the Atlas

Code that ran

12 of 16 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, 1 violated it and 3 have no contract verdict; 8 failures of our instrument; 4 no recorded run); 1 of them was also run on the host, not in the jail, by the peer-agreement lane that set its level, 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/2407.02013.json · badge: /api/ran/2407.02013.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
ipsitmantri/digraf canonical (classifier label)
classifier basis: classifier_2025
2 ran · 0 no recorded run
ipsitmantri/DiTASK community (classifier label)
classifier basis not recorded on the link
10 ran · 4 no recorded run
FunctionStatusWhere it lives
window_partition Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
ipsitmantri/DiTASK/models/swin_transformer_ditask.py
code served (permissive licence) · get_code("144d10b49baeb8a6")
How it ran

Ran in Syntology's jail on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1) and returned Tensor, ndim 4, dtype family float, shape (8, 4, 4, 4) as a later run recorded it. The image it ran in was not recorded. The comparison behind this sample's level is a different run: the peer-agreement lane ran it again on the host, not in the jail (report dated 2026-09-04T22:38:58Z). 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 a tensor with shape (B, H, W, C)
# B=2 (batch), H=8 (height), W=8 (width), C=4 (channels)
# Using distinct sizes: 2, 8, 8, 4
x = torch.randn(2, 8, 8, 4)

# window_size must divide both H and W evenly
# H=8, W=8, so window_size=4 works (8 // 4 = 2)
window_size = 4

ARGS = {
    "x": x,
    "window_size": window_size,
}
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 4, dtype family float, shape (8, 4, 4, 4) — shape (8, 4, 4, 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
build_scheduler Ran
ran on a synthesized input
ipsitmantri/DiTASK/lr_scheduler.py
code served (permissive licence) · get_code("eca7452105889f50")
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 CosineLRScheduler. 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.optim as optim

torch.manual_seed(0)

# Build a minimal config object with all required attributes
class Config:
    def __init__(self):
        self.TRAIN = TrainConfig()

class TrainConfig:
    def __init__(self):
        self.EPOCHS = 100
        self.WARMUP_EPOCHS = 5
        self.MIN_LR = 1e-5
        self.WARMUP_LR = 1e-4
        self.LR_SCHEDULER = LRSchedulerConfig()

class LRSchedulerConfig:
    def __init__(self):
        self.NAME = 'cosine'
        self.WARMUP_PREFIX = True
        self.DECAY_EPOCHS = 10
        self.DECAY_RATE = 0.1
        self.MULTISTEPS = [30, 60, 90]
        self.GAMMA = 0.1
        self.PATIENCE = 5

# Create a simple model and optimizer
model = nn.Linear(4, 3)
optimizer = optim.SGD(model.parameters(), lr=0.1)

# Create config
config = Config()

# n_iter_per_epoch represents iterations per epoch
n_iter_per_epoch = 10

ARGS = {
    'config': config,
    'optimizer': optimizer,
    'n_iter_per_epoch': n_iter_per_epoch,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
timm, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type CosineLRScheduler — a CosineLRScheduler output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a CosineLRScheduler 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
conv3x3 Ran
ran; our contract draft was wrong, not the code
ipsitmantri/DiTASK/models/seg_hrnet.py
pointer only (licence: MIT); the stored copy get_code serves, from lixiaotong97/DSU, is pointer only (licence: NONE) · get_code("fac5364e2f53c6db")
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 lixiaotong97/DSU, 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.

create_logger Ran
ran; our contract draft was wrong, not the code
ipsitmantri/DiTASK/logger.py
code served (permissive licence) · get_code("299f2d40c6a8adc7")
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 os
import sys
import logging
import tempfile
from termcolor import colored

# Create a temporary directory for logging
temp_dir = tempfile.mkdtemp()

ARGS = {
    'output_dir': temp_dir,
    'dist_rank': 0,
    'name': 'test_logger'
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
termcolor — 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
get_loss Ran
ran; our contract draft was wrong, not the code
ipsitmantri/DiTASK/mtl_loss_schemes.py
code served (permissive licence) · get_code("80c0c9e218ee946c")
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 BalancedCrossEntropyLoss. 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 numpy as np

torch.manual_seed(0)

class MockTaskConfig(dict):
    """Mock task config that supports .get() method"""
    def __init__(self, *args, **kwargs):
        super().__init__(*args, **kwargs)
    
    def get(self, key, default=None):
        return super().get(key, default)

# Create task configs for different tasks
task_cfg_edge = MockTaskConfig({'edge_w': 0.95})
task_cfg_semseg = MockTaskConfig({})
task_cfg_normals = MockTaskConfig({})

# Create config dict
config = {
    'DATA': {}
}

ARGS = {
    'task_cfg': task_cfg_edge,
    'task': 'edge',
    'config': config
}
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 BalancedCrossEntropyLoss — a BalancedCrossEntropyLoss output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a BalancedCrossEntropyLoss 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
interpolate_linear_1d Ran
ran; our contract draft was wrong, not the code
ipsitmantri/digraf/src/activations.py
code served (permissive licence) · get_code("16acc4b4a9200198")
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 1, dtype family int, shape (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)

# Create small 1D tensors for x coordinates (sorted ascending)
x = torch.tensor([1.0, 2.0, 3.0, 4.0, 5.0])

# Create corresponding y coordinates
y = torch.tensor([2.0, 4.0, 6.0, 8.0, 10.0])

# Create query points for interpolation
x_query = torch.tensor([1.5, 2.5, 3.5, 4.5])

ARGS = {
    "x": x,
    "y": y,
    "x_query": x_query,
}
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 1, dtype family int, shape (4,) — shape (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
interpolate_to_support Ran
ran; our contract draft was wrong, not the code
ipsitmantri/digraf/src/activations.py
code served (permissive licence) · get_code("88ee397c7c5a7a3d")
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 1, dtype family float, shape (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)

# Create small tensors for interpolation
# x: original coordinates (must be sorted)
x = torch.tensor([0.0, 1.0, 2.0, 3.0])

# y: original values corresponding to x
y = torch.tensor([0.0, 2.0, 1.0, 3.0])

# support: points where we want to interpolate
support = torch.tensor([0.5, 1.5, 2.5, 3.5])

ARGS = {
    "x": x,
    "y": y,
    "support": support,
}
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 1, dtype family float, shape (4,) — shape (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
lora_filter Ran
ran, violated the contract we drafted
ipsitmantri/DiTASK/models/lora.py
code served (permissive licence) · get_code("7c89e5e716dec3fc")
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 bool, 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)

# The function lora_filter takes two parameters:
# - key: str
# - value: Any
# It checks if 'lora_' is in the key string and returns a boolean.

# Construct arguments that would be used in a typical filter scenario
key = "module.lora_weight"
value = torch.randn(2, 4)

ARGS = {
    "key": key,
    "value": value
}
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 bool, 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
map_old_state_dict_weights Ran
ran on a synthesized input
ipsitmantri/DiTASK/models/lora.py
code served (permissive licence) · get_code("94066f7cf06fd028")
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
from typing import Mapping

torch.manual_seed(0)

# Construct state_dict with some sample weights
state_dict = {
    'module.layer1.weight': torch.randn(3, 4),
    'module.layer1.bias': torch.randn(3),
    'module.attn.qkv.linear.weight': torch.randn(12, 4),  # 3x split into q,k,v
    'module.attn.qkv.linear.bias': torch.randn(12),
    'module.layer2.weight': torch.randn(5, 3),
}

# Construct mapping from checkpoint names to attribute names
mapping = {
    'layer1.weight': 'layer1.weight',
    'layer1.bias': 'layer1.bias',
    'attn.qkv.linear.weight': 'attn.qkv.linear.weight',
    'attn.qkv.linear.bias': 'attn.qkv.linear.bias',
    'layer2.weight': 'layer2.weight',
}

# Define prefix to be added to checkpoint names
prefix = 'module.'

# Test both with and without split_qkv
split_qkv = True

ARGS = {
    'state_dict': state_dict,
    'mapping': mapping,
    'prefix': prefix,
    'split_qkv': split_qkv,
}
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
opts_to_key_value_list Ran
ran on a synthesized input
ipsitmantri/DiTASK/config.py
code served (permissive licence) · get_code("e6ea4b62b01edfb7")
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

def opts_to_key_value_list(opts_list):
    result = []
    for arg in opts_list:
        key, value = arg.split('=', 1)
        result.extend([key, value])
    return result

# The function takes a list of strings in "key=value" format
# and splits them into alternating keys and values
opts_list = [
    "learning_rate=0.001",
    "batch_size=32",
    "epochs=10",
    "model_name=bert"
]

ARGS = {
    "opts_list": opts_list
}
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 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
resize Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
ipsitmantri/DiTASK/models/segformer.py
code served (permissive licence) · get_code("368118c367337eb7")
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 4, dtype family float, shape (2, 3, 8, 10) 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)

# Create a small input tensor: batch_size=2, channels=3, height=4, width=5
input_tensor = torch.randn(2, 3, 4, 5)

# Test case 1: resize with explicit size
size = (8, 10)

# scale_factor can be None or a float/tuple
scale_factor = None

# mode options: 'nearest', 'linear', 'bilinear', 'bicubic', 'trilinear', 'area', 'nearest-exact'
mode = 'nearest'

# align_corners: None or bool (used in interpolate, relevant for some modes)
align_corners = None

# warning: whether to issue warnings about alignment
warning = False

ARGS = {
    'input': input_tensor,
    'size': size,
    'scale_factor': scale_factor,
    'mode': mode,
    'align_corners': align_corners,
    'warning': warning
}
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 4, dtype family float, shape (2, 3, 8, 10) — shape (2, 3, 8, 10) 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
window_reverse Ran
ran; our contract draft was wrong, not the code
ipsitmantri/DiTASK/models/swin_transformer_ditask.py
code served (permissive licence) · get_code("61bf152e6a42a184")
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 4, dtype family float, shape (2, 8, 12, 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)

# Parameters for window_reverse
# windows: (num_windows*B, window_size, window_size, C)
# The function expects windows to be partitioned from an image of size (B, H, W, C)
# where the image is divided into non-overlapping windows of size window_size x window_size

B = 2  # batch size
H = 8  # image height
W = 12  # image width
window_size = 4  # window size
C = 3  # number of channels

# Calculate number of windows
num_windows_h = H // window_size  # 2
num_windows_w = W // window_size  # 3
num_windows = num_windows_h * num_windows_w  # 6

# windows shape: (num_windows*B, window_size, window_size, C)
# = (6*2, 4, 4, 3) = (12, 4, 4, 3)
windows = torch.randn(num_windows * B, window_size, window_size, C)

ARGS = {
    "windows": windows,
    "window_size": window_size,
    "H": H,
    "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 4, dtype family float, shape (2, 8, 12, 3) — shape (2, 8, 12, 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
build_model Not yet run
unverified (harvested, no recorded run)
ipsitmantri/DiTASK/models/build.py
code served (permissive licence) · get_code("c38f2ce46b296240")
How it ran

no invocation recorded.

build_mtl_model Not yet run
unverified (harvested, no recorded run)
ipsitmantri/DiTASK/models/build.py
code served (permissive licence) · get_code("e16d8a6cf1158855")
How it ran

no invocation recorded.

mark_only_lora_as_trainable Not yet run
unverified (harvested, no recorded run)
ipsitmantri/DiTASK/models/lora.py
code served (permissive licence) · get_code("f3788eeccc68b1f0")
How it ran

no invocation recorded.

resize Not yet run
unverified (harvested, no recorded run)
ipsitmantri/DiTASK/models/base_decode_head.py
code served (permissive licence) · get_code("5ebb5fe1837669a8")
How it ran

no invocation recorded.

Also present in other papers' code

Of 16 samples lifted from this paper's linked repositories, 16 carry a function identity and 0 do not. Of the 16 distinct functions with an identity, 9 are also present in other papers whose code we hold (9 with at least one paper dated earlier, 3 the same month, 5 later) and 7 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
conv3x3 686 other papers
603 dated earlier, 14 the same month, 52 later, 17 same year, order not determinable · 31 only as an assembly brick
1406.2661 (2014-06)
Generative Adversarial Networks
1409.0575 (2014-09)
ImageNet Large Scale Visual Recognition Challenge
1412.6572 (2014-12)
Explaining and Harnessing Adversarial Examples
and 683 more not named here
window_reverse 227 other papers
181 dated earlier, 3 the same month, 34 later, 9 same year, order not determinable · 34 only as an assembly brick
1608.03983 (2016-08)
SGDR: Stochastic Gradient Descent with Warm Restarts
1711.10925 (2017-11)
Deep Image Prior
2003.13678 (2020-03)
Designing Network Design Spaces
and 224 more not named here
window_partition 223 other papers
177 dated earlier, 3 the same month, 34 later, 9 same year, order not determinable · 32 only as an assembly brick
1706.03762 (2017-06)
Attention Is All You Need
1711.10925 (2017-11)
Deep Image Prior
2003.13678 (2020-03)
Designing Network Design Spaces
and 220 more not named here
resize 9 other papers
8 dated earlier, 1 later
2203.01502 (2022-03)
Neural Window Fully-connected CRFs for Monocular Depth Estimation
2208.03792 (2022-08)
Domain Randomization-Enhanced Depth Simulation and Restoration for Perceiving and Grasping Specular and Transparent Objects
2210.09071 (2022-10)
Attention Attention Everywhere: Monocular Depth Prediction with Skip Attention
and 6 more not named here
lora_filter 3 other papers
2 dated earlier, 1 later
2401.02385 (2024-01)
TinyLlama: An Open-Source Small Language Model
2403.20320 (2024-03)
MTLoRA: A Low-Rank Adaptation Approach for Efficient Multi-Task Learning
2503.15450 (2025-03)
SkyLadder: Better and Faster Pretraining via Context Window Scheduling
create_logger 1 other paper
1 dated earlier
2403.20320 (2024-03)
MTLoRA: A Low-Rank Adaptation Approach for Efficient Multi-Task Learning
get_loss 1 other paper
1 dated earlier
2403.20320 (2024-03)
MTLoRA: A Low-Rank Adaptation Approach for Efficient Multi-Task Learning
mark_only_lora_as_trainable 1 other paper
1 dated earlier
2403.20320 (2024-03)
MTLoRA: A Low-Rank Adaptation Approach for Efficient Multi-Task Learning
resize 1 other paper
1 dated earlier
2403.20320 (2024-03)
MTLoRA: A Low-Rank Adaptation Approach for Efficient Multi-Task Learning

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

In this paper, we propose a novel activation function tailored specifically for graph data in Graph Neural Networks (GNNs). Motivated by the need for graph-adaptive and flexible activation functions, we introduce DIGRAF, leveraging Continuous Piecewise-Affine Based (CPAB) transformations, which we augment with an additional GNN to learn a graph-adaptive diffeomorphic activation function in an end-to-end manner. In addition to its graph-adaptivity and flexibility, DIGRAF also possesses properties that are widely recognized as desirable for activation functions, such as differentiability, boundness within the domain, and computational efficiency. We conduct an extensive set of experiments across diverse datasets and tasks, demonstrating a consistent and superior performance of DIGRAF compared to traditional and graph-specific activation functions, highlighting its effectiveness as an activation function for GNNs. Our code is available at https://github.com/ ipsitmantri/DiGRAF.

For agents

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

get_harvested_code_for_paper("2407.02013")
get_code_for_paper("2407.02013")
have("2407.02013")

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

curl https://syntology.ai/api/ran/2407.02013.json

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

[![Syntology run record](https://syntology.ai/api/ran/2407.02013.svg)](https://syntology.ai/paper/2407.02013)

Connect an agent — have() is free.