SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2401.02683 · AAAI · 2024

Geometric-Facilitated Denoising Diffusion Model for 3D Molecule Generation

Can Xu, Pengfei Zheng, Hongyang Chen, Haosen Wang, Weigang Wang

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; 5 honoured the contract we drafted, 1 violated it and 0 have no contract verdict; 7 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/2401.02683.json · badge: /api/ran/2401.02683.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
LEOXC1571/GFMDiff canonical (classifier label)
classifier basis: census
13 ran · 0 no recorded run
FunctionStatusWhere it lives
cdf_standard_gaussian Ran
ran; our contract draft was wrong, not the code
LEOXC1571/GFMDiff/models/diff/loss.py
code served (permissive licence) · get_code("89618950bbce6adb")
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, 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 math
import torch

torch.manual_seed(0)

# The function cdf_standard_gaussian takes a single parameter x
# and applies torch.erf to it, so x must be a tensor
x = torch.randn(2, 4)

ARGS = {
    "x": x
}
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 (2, 4) — shape (2, 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
clip_noise_schedule Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
LEOXC1571/GFMDiff/models/diff/noise.py
code served (permissive licence) · get_code("761b3c71b3bd357b")
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 1, dtype family float, shape (5,) 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

# The function takes:
# 1. alphas2: a numpy array of shape (N,) - the cumulative product schedule to clip
# 2. clip_value: a float - the minimum clipping value (default 0.001)

# Create a small noise schedule array
alphas2 = np.array([0.9999, 0.9998, 0.9997, 0.9996, 0.9995], dtype=np.float32)

ARGS = {
    "alphas2": alphas2,
    "clip_value": 0.001
}
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 1, dtype family float, shape (5,) — shape (5,) 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
gaussian_kl Ran
ran; our contract draft was wrong, not the code
LEOXC1571/GFMDiff/models/diff/loss.py
code served (permissive licence) · get_code("5f1c82e11edc1360")
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

torch.manual_seed(0)

# Create small tensors with distinct dimensions
# Batch size: 2, Feature dimension: 4
batch_size = 2
feature_dim = 4

q_mu = torch.randn(batch_size, feature_dim)
q_sigma = torch.abs(torch.randn(batch_size, feature_dim)) + 0.1  # ensure positive
p_mu = torch.randn(batch_size, feature_dim)
p_sigma = torch.abs(torch.randn(batch_size, feature_dim)) + 0.1  # ensure positive

# node_mask: binary mask with same shape as the tensors
node_mask = torch.ones(batch_size, feature_dim)

# d: optional scalar dimension parameter
d = None

ARGS = {
    "q_mu": q_mu,
    "q_sigma": q_sigma,
    "p_mu": p_mu,
    "p_sigma": p_sigma,
    "node_mask": node_mask,
    "d": d,
}
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_adj_matrix Ran
ran, honoured the contract we drafted
LEOXC1571/GFMDiff/models/egnn.py
code served (permissive licence) · get_code("5e3638e42354c03e")
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 2, dtype family int; no output shape is stated. The image it ran in was not recorded. If your copy returns the same type and ndim on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch

torch.manual_seed(0)

# Analyzing the function:
# - n_nodes: int, used in dictionary keys and range() calls
# - batch_size: int, used in dictionary keys and range() calls
# - device: torch device, passed to .to(device) method

ARGS = {
    "n_nodes": 4,
    "batch_size": 2,
    "device": torch.device("cpu")
}
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 2, dtype family int — 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
get_angle Ran
ran; our contract draft was wrong, not the code
LEOXC1571/GFMDiff/models/diff/utils.py
code served (permissive licence) · get_code("56a63de1e5c2817f")
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 (2,) 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)

vec1 = torch.randn(2, 4)
vec2 = torch.randn(2, 4)
keepdim = False

ARGS = {
    "vec1": vec1,
    "vec2": vec2,
    "keepdim": keepdim,
}
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 (2,) — shape (2,) 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_bond Ran
ran, honoured the contract we drafted
LEOXC1571/GFMDiff/models/diff/utils.py
code served (permissive licence) · get_code("5080c95ebb45608e")
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 4, dtype family float; no output shape is stated. The image it ran in was not recorded. If your copy returns the same type and ndim on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch

torch.manual_seed(0)

ARGS = {
    "name": "qm9"
}
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 4, 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
polynomial_schedule Ran
ran, honoured the contract we drafted
LEOXC1571/GFMDiff/models/diff/noise.py
code served (permissive licence) · get_code("1b8c89dc79f7924f")
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 1, dtype family float, shape (11,) 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

ARGS = {
    "timesteps": 10,
    "s": 0.0001,
    "power": 3.0,
}
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 1, dtype family float, shape (11,) — shape (11,) 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
read_discrete_feat Ran
ran; our contract draft was wrong, not the code
LEOXC1571/GFMDiff/models/diff/utils.py
code served (permissive licence) · get_code("57ff3eabc890edf3")
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)

# The function reads dataset_config['discrete_info']
# It iterates over keys in feat_dict
# For each key, it accesses feat_dict[key] and calls len() on it
# Then it converts feat_dict[key] to a tensor, unsqueezes twice
# So feat_dict[key] should be a list or sequence of values

dataset_config = {
    'discrete_info': {
        'color': [0, 1, 2],
        'size': [5, 10, 15, 20]
    }
}

ARGS = {
    'dataset_config': dataset_config
}
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
sigmoid Ran
ran, violated the contract we drafted
LEOXC1571/GFMDiff/models/diff/noise.py
code served (permissive licence) · get_code("152398a541d26c5a")
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 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 numpy as np

def sigmoid(x):
    return 1 / (np.exp(-x) + 1)

# Create a small numpy array to pass as input
x_input = np.array([0.0, 1.0, -1.0, 2.0])

ARGS = {
    "x": x_input
}
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 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
train_classifier Ran
ran, honoured the contract we drafted
LEOXC1571/GFMDiff/sample_eval.py
code served (permissive licence) · get_code("9d71ad8e980762c7")
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 float, 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
from torch.optim import SGD
from torch.optim.lr_scheduler import StepLR

torch.manual_seed(0)

# Create a simple classifier model
class SimpleClassifier(nn.Module):
    def __init__(self):
        super().__init__()
        self.linear = nn.Linear(4, 1)
    
    def forward(self, batch):
        return self.linear(batch.x).squeeze()

# Create a simple batch class that mimics torch_geometric style
class SimpleBatch:
    def __init__(self, x, y):
        self.x = x
        self.y = y
    
    def to(self, device):
        self.x = self.x.to(device)
        self.y = self.y.to(device)
        return self

# Create tiny batches (batch_size=2, feature_dim=4)
batch1_x = torch.randn(2, 4)
batch1_y = torch.randn(2, 5)
batch1 = SimpleBatch(batch1_x, batch1_y)

batch2_x = torch.randn(2, 4)
batch2_y = torch.randn(2, 5)
batch2 = SimpleBatch(batch2_x, batch2_y)

# Create a data loader (list of batches)
loader = [batch1, batch2]

# Create optimizer
classifier = SimpleClassifier()
optimizer = SGD(classifier.parameters(), lr=0.01)

# Create scheduler
scheduler = StepLR(optimizer, step_size=1, gamma=0.1)

# Create criterion (MSE loss)
criterion = nn.MSELoss()

# Create model config
model_config = {
    'context_col': 2,
    'class_batch_size': 2
}

# Mean and std for normalization
mean = torch.tensor(0.5)
std = torch.tensor(0.2)

# Device
device = 'cpu'

ARGS = {
    'classifier': classifier,
    'loader': loader,
    'optimizer': optimizer,
    'scheduler': scheduler,
    'criterion': criterion,
    'model_config': model_config,
    'mean': mean,
    'std': std,
    'device': device
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch, tqdm — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type float, 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
unsorted_segment_mean Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
LEOXC1571/GFMDiff/models/egnn.py
code served (permissive licence) · get_code("bc66f19be57720e7")
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, 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 sample data tensor with shape (batch_size, feature_dim)
# Using distinct sizes: 2 for batch, 4 for features
data = torch.randn(2, 4)

# Create segment_ids tensor that maps each data point to a segment
# Values should be in range [0, num_segments)
segment_ids = torch.tensor([0, 1])

# Number of segments to aggregate into
num_segments = 2

ARGS = {
    "data": data,
    "segment_ids": segment_ids,
    "num_segments": num_segments,
}
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 (2, 4) — shape (2, 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
unsorted_segment_sum Ran
ran; our contract draft was wrong, not the code
LEOXC1571/GFMDiff/models/egnn.py
code served (permissive licence) · get_code("dfdf6dc1a0720e57")
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 (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
import numpy as np

torch.manual_seed(0)

# Create tiny tensors for testing
# data: shape (batch_size, feature_dim) - the values to sum
# segment_ids: shape (batch_size,) - which segment each row belongs to
# num_segments: int - total number of segments

batch_size = 2
feature_dim = 4
num_segments = 3

data = torch.randn(batch_size, feature_dim)
segment_ids = torch.tensor([0, 2], dtype=torch.long)

ARGS = {
    "data": data,
    "segment_ids": segment_ids,
    "num_segments": num_segments,
}
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 (3, 4) — shape (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
valid_classifier Ran
ran, honoured the contract we drafted
LEOXC1571/GFMDiff/sample_eval.py
code served (permissive licence) · get_code("b218d1742958d078")
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 float, 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)

# Build a minimal classifier that works with the function
class MinimalClassifier(nn.Module):
    def __init__(self):
        super().__init__()
        self.linear = nn.Linear(4, 1)
    
    def forward(self, batch, gen_eval=False):
        # The function calls classifier(batch, gen_eval=gen_eval)
        # batch should have some structure; we'll return a single tensor
        return self.linear(batch.x)

# Build a minimal batch class
class MinimalBatch:
    def __init__(self, x, y):
        self.x = x
        self.y = y
    
    def to(self, device):
        self.x = self.x.to(device)
        self.y = self.y.to(device)
        return self

# Create sample data
x_sample = torch.randn(2, 4)
y_sample = torch.randn(2, 3)
batch1 = MinimalBatch(x_sample, y_sample)
batch2 = MinimalBatch(torch.randn(2, 4), torch.randn(2, 3))

# Create loader (simple list of batches)
loader = [batch1, batch2]

# Build classifier
classifier = MinimalClassifier()

# Build criterion (MSE loss)
criterion = nn.MSELoss()

# Build model config
model_config = {
    'context_col': 1,
    'class_batch_size': 2
}

# Normalization parameters
mean = torch.tensor(0.5)
std = torch.tensor(0.2)

# Device
device = torch.device('cpu')

ARGS = {
    'classifier': classifier,
    'loader': loader,
    'criterion': criterion,
    'model_config': model_config,
    'mean': mean,
    'std': std,
    'device': device,
    'gen_eval': False
}
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 float, 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, 2 the same month, 3 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
unsorted_segment_mean 20 other papers
11 dated earlier, 2 the same month, 7 later · 1 only as an assembly brick
1810.04805 (2018-10)
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
2102.09844 (2021-02)
E(n) Equivariant Graph Neural Networks
2110.14811 (2021-10)
SE(3) Equivariant Graph Neural Networks with Complete Local Frames
and 17 more not named here
unsorted_segment_sum 19 other papers
13 dated earlier, 1 the same month, 5 later · 2 only as an assembly brick
1810.04805 (2018-10)
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
1906.02547 (2019-06)
Combining Generative and Discriminative Models for Hybrid Inference
2102.09844 (2021-02)
E(n) Equivariant Graph Neural Networks
and 16 more not named here
clip_noise_schedule 4 other papers
2 dated earlier, 2 later
2306.16819 (2023-06)
Graph Denoising Diffusion for Inverse Protein Folding
2311.13466 (2023-11)
Accelerating Inference in Molecular Diffusion Models with Latent Representations of Protein Structure
2404.12141 (2024-04)
MolCRAFT: Structure-Based Drug Design in Continuous Parameter Space
and 1 more not named here
polynomial_schedule 1 other paper
1 dated earlier
2311.13466 (2023-11)
Accelerating Inference in Molecular Diffusion Models with Latent Representations of Protein Structure
sigmoid 1 other paper
1 dated earlier
2209.14687 (2022-09)
Diffusion Posterior Sampling for General Noisy Inverse Problems

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

Denoising diffusion models have shown great potential in multiple research areas. Existing diffusion-based generative methods on de novo 3D molecule generation face two major challenges. Since majority heavy atoms in molecules allow connections to multiple atoms through single bonds, solely using pair-wise distance to model molecule geometries is insufficient. Therefore, the first one involves proposing an effective neural network as the denoising kernel that is capable to capture complex multi-body interatomic relationships and learn high-quality features. Due to the discrete nature of graphs, mainstream diffusion-based methods for molecules heavily rely on predefined rules and generate edges in an indirect manner. The second challenge involves accommodating molecule generation to diffusion and accurately predicting the existence of bonds. In our research, we view the iterative way of updating molecule conformations in diffusion process is consistent with molecular dynamics and introduce a novel molecule generation method named Geometric-Facilitated Molecular Diffusion (GFMDiff). For the first challenge, we introduce a Dual-Track Transformer Network (DTN) to fully excevate global spatial relationships and learn high quality representations which contribute to accurate predictions of features and geometries. As for the second challenge, we design Geometric-Facilitated Loss (GFLoss) which intervenes the formation of bonds during the training period, instead of directly embedding edges into the latent space. Comprehensive experiments on current benchmarks demonstrate the superiority of GFMDiff.

For agents

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

get_harvested_code_for_paper("2401.02683")
get_code_for_paper("2401.02683")
have("2401.02683")

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

curl https://syntology.ai/api/ran/2401.02683.json

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

[![Syntology run record](https://syntology.ai/api/ran/2401.02683.svg)](https://syntology.ai/paper/2401.02683)

Connect an agent — have() is free.