SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1806.03146 · 2018

Neural Message Passing with Edge Updates for Predicting Properties of Molecules and Materials

arXiv · PDF · Open in the Atlas

Code that ran

20 of 22 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, 1 violated it and 13 have no contract verdict; 4 failures of our instrument; 2 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/1806.03146.json · badge: /api/ran/1806.03146.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
nrel/m2p community (classifier label)
classifier basis not recorded on the link
6 ran · 0 no recorded run
toshi-k/kaggle-champs-scalar-coupling community (classifier label)
classifier basis not recorded on the link
5 ran · 2 no recorded run
toshi-k/kaggle-trends-assessment-prediction community (classifier label)
classifier basis not recorded on the link
5 ran · 0 no recorded run
copy not recorded community
not in the paper's declared repositories
4 ran · 0 no recorded run
FunctionStatusWhere it lives
calc_score Ran
ran on a synthesized input
toshi-k/kaggle-champs-scalar-coupling/source/02_triplet_update/lib/calc_score.py
code served (permissive licence) · get_code("f227691802ff9c3c")
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 float64, ndim 0, 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 numpy as np
import pandas as pd

# Create a small dataframe with the required columns
n_samples = 6
df_truth = pd.DataFrame({
    'type': ['1JHC', '1JHC', '2JHH', '2JHH', '3JHH', '3JHH'],
    'scalar_coupling_constant': np.array([10.5, 11.2, 5.1, 4.9, 3.2, 3.5]),
    'fc': np.array([10.0, 11.0, 0.5, 0.4, 0.1, 0.2]),
    'sd': np.array([0.3, 0.1, 4.0, 4.1, 2.5, 2.8]),
    'pso': np.array([0.1, 0.05, 0.4, 0.3, 0.4, 0.3]),
    'dso': np.array([0.1, 0.05, 0.2, 0.2, 0.2, 0.2])
})

# Create predictions with shape (n_samples, 4)
# Each column corresponds to: fc, sd, pso, dso
pred = np.array([
    [10.1, 0.25, 0.08, 0.12],
    [11.1, 0.05, 0.03, 0.08],
    [0.6, 3.9, 0.35, 0.18],
    [0.5, 4.2, 0.25, 0.22],
    [0.15, 2.4, 0.38, 0.25],
    [0.25, 2.9, 0.28, 0.18]
])

ARGS = {
    'df_truth': df_truth,
    'pred': pred
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, pandas — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type float64, ndim 0, dtype family float — no output shape is stated: observe_signature.py recorded float ndim 0, which disagrees with the fixture run
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
float_or_string Ran
ran, honoured the contract we drafted
this paper's copy was not recorded; identical code first harvested from peterbjorgensen/msgnet
pointer only · get_code("f6861553018d2738")
How it ran

The body of this sample is withheld: this paper's copy of the code was not recorded (its link names no repository or source path), so no licence was read for it. 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.

generate_batches Ran
ran on a synthesized input
toshi-k/kaggle-champs-scalar-coupling/source/02_triplet_update/lib/generate_batches.py
code served (permissive licence) · get_code("b7265a8562acd4a6")
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 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 random
import numpy as np
import pandas as pd

# Create a simple stand-in class for structures_groups
# that has a get_group method
class StructuresGroups:
    def __init__(self, groups_dict):
        self.groups_dict = groups_dict
    
    def get_group(self, mol_name):
        return self.groups_dict.get(mol_name, [])

# Set up test data
random.seed(42)
np.random.seed(42)

# Create mock molecule structures data
# Each molecule has a list of structures (we just care about the length)
structures_groups = StructuresGroups({
    'mol_A': ['struct_1', 'struct_2', 'struct_3'],  # 3 atoms
    'mol_B': ['struct_1', 'struct_2', 'struct_3'],  # 3 atoms
    'mol_C': ['struct_1', 'struct_2', 'struct_3', 'struct_4'],  # 4 atoms
    'mol_D': ['struct_1', 'struct_2', 'struct_3', 'struct_4'],  # 4 atoms
    'mol_E': ['struct_1', 'struct_2', 'struct_3', 'struct_4'],  # 4 atoms
    'mol_F': ['struct_1'],  # 1 atom
})

moles = ['mol_A', 'mol_B', 'mol_C', 'mol_D', 'mol_E', 'mol_F']
batch_size = 2
use_remainder = False

ARGS = {
    'structures_groups': structures_groups,
    'moles': moles,
    'batch_size': batch_size,
    'use_remainder': use_remainder
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, pandas — 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 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
getUA Ran
ran on a synthesized input
toshi-k/kaggle-champs-scalar-coupling/source/01_preprocess/xyz2mol.py
code served (permissive licence) · get_code("268a472f480f137c")
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 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
import numpy as np

torch.manual_seed(0)

# Analyzing the function:
# - maxValence_list: iterated over with zip, elements used in arithmetic (maxValence - valence > 0)
# - valence_list: iterated over with zip, elements used in arithmetic (maxValence - valence)
# Both should be lists of numeric values

maxValence_list = [5, 10, 8, 3]
valence_list = [2, 10, 5, 4]

ARGS = {
    "maxValence_list": maxValence_list,
    "valence_list": valence_list
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type tuple, ndim 2, dtype family int — 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
get_CIP_assignments Ran
ran on a synthesized input
nrel/m2p/m2p/utils.py
code served (permissive licence) · get_code("ba59ef5d8be606b0")
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 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 random
import numpy as np
from math import ceil, floor

# Set seeds for reproducibility
random.seed(42)
np.random.seed(42)

# Define arguments for get_CIP_assignments
ARGS = {
    "n_structures": 5,
    "pm": 0.6,
    "DP": 4
}
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 list, ndim 2, 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
get_arguments Ran
ran; our contract draft was wrong, not the code
this paper's copy was not recorded; identical code first harvested from peterbjorgensen/msgnet
pointer only · get_code("c3c3392a3d0f7172")
How it ran

The body of this sample is withheld: this paper's copy of the code was not recorded (its link names no repository or source path), so no licence was read for it. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

get_atom Ran
ran on a synthesized input
toshi-k/kaggle-champs-scalar-coupling/source/01_preprocess/xyz2mol.py
code served (permissive licence) · get_code("c0e80b5122acc10f")
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 int, ndim 0, dtype family int, 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

ARGS = {
    "atom": "c"
}
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 int, ndim 0, dtype family int, 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_config_from_root Ran
ran on a synthesized input
nrel/m2p/versioneer.py
code served (permissive licence) · get_code("51944f53542b7e19")
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 VersioneerConfig. 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 configparser
import os
import tempfile

class VersioneerConfig:
    """Container for Versioneer configuration parameters."""
    pass

# Create a temporary directory with a setup.cfg file
temp_dir = tempfile.mkdtemp()
setup_cfg_path = os.path.join(temp_dir, 'setup.cfg')

setup_cfg_content = """[versioneer]
VCS = git
style = pep440
versionfile_source = myproject/_version.py
versionfile_build = myproject/_version.py
tag_prefix = v
parentdir_prefix = myproject-
verbose = False
"""

with open(setup_cfg_path, 'w') as f:
    f.write(setup_cfg_content)

ARGS = {
    'root': temp_dir
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
none outside the standard library — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type VersioneerConfig — a VersioneerConfig output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a VersioneerConfig 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_fnc Ran
ran on a synthesized input
toshi-k/kaggle-trends-assessment-prediction/source/02_edge_gnn/lib/fnc.py
code served (permissive licence) · get_code("bc06d832937584f2")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned tuple. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import numpy as np
import pandas as pd
from pathlib import Path
import tempfile

# Create a minimal FNC dataframe with the expected structure
# The FNC data is upper triangular: 53x53 matrix flattened to 1378 values
# which is 52 + 51 + 50 + ... + 1 = 1378

def create_minimal_fnc_csv():
    """Create a minimal FNC CSV with correct structure"""
    n_features = 1378  # Upper triangular of 53x53
    n_samples = 10
    
    data = {
        'Id': [f'sub_{i:02d}' for i in range(n_samples)]
    }
    
    # Add the 1378 FNC features
    for i in range(n_features):
        data[f'FNC_{i}'] = np.random.randn(n_samples)
    
    df = pd.DataFrame(data)
    return df

# Create temporary directory and dataset
temp_dir = tempfile.mkdtemp()
dir_dataset = Path(temp_dir)

# Create FNC CSV file
fnc_df = create_minimal_fnc_csv()
fnc_df.to_csv(dir_dataset / 'fnc.csv', index=False)

# Define split IDs
all_ids = fnc_df['Id'].tolist()
train_ids = all_ids[:4]
valid_ids = all_ids[4:7]
test_ids = all_ids[7:]

ARGS = {
    'dir_dataset': dir_dataset,
    'train_ids': train_ids,
    'valid_ids': valid_ids,
    'test_ids': test_ids,
    'alpha': -1.0,  # Use raw FNC without graphical lasso to avoid computational overhead
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, pandas, sklearn, tqdm — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type tuple — a tuple output has no array shape of its own; none is stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
get_fnc_matrix Ran
ran on a synthesized input
toshi-k/kaggle-trends-assessment-prediction/source/02_edge_gnn/lib/fnc.py
code served (permissive licence) · get_code("62eb0cf7d768ea1a")
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 3, dtype family float, shape (2, 53, 53) as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import numpy as np
import pandas as pd

# Construct a minimal DataFrame that matches what get_fnc_matrix expects
# The function expects fnc to be a DataFrame with:
# - len(fnc) rows (batch dimension)
# - enough columns to fill the upper triangle of a 53x53 matrix
# The upper triangle of a 53x53 matrix has 53*52/2 = 1378 elements

# Create a small example: 2 rows (batch size), 1379 columns (1 for index + 1378 for triangle)
batch_size = 2
num_triangle_elements = 53 * 52 // 2
total_cols = num_triangle_elements + 1

data = np.random.randn(batch_size, total_cols).astype(np.float32)
fnc = pd.DataFrame(data)

ARGS = {
    "fnc": fnc
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, pandas — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type ndarray, ndim 3, dtype family float, shape (2, 53, 53) — shape (2, 53, 53) 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_monomer_sequences Ran
ran on a synthesized input
nrel/m2p/m2p/utils.py
code served (permissive licence) · get_code("d9edcdb08a7a6569")
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 random
import numpy as np

# Set seeds for reproducibility
random.seed(0)
np.random.seed(0)

ARGS = {
    "n_structures": 5,
    "distribution": [1, 2],
    "DP": 10
}
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 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
graphical_lasso_wrap Ran
ran on a synthesized input
toshi-k/kaggle-trends-assessment-prediction/source/02_edge_gnn/lib/fnc.py
code served (permissive licence) · get_code("61b8bc67290ec426")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned ndarray, ndim 2, dtype family float, shape (4, 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
from sklearn.covariance import graphical_lasso

# Create a small empirical covariance matrix
# The function accesses emp_cov[0], so emp_cov must be indexable
# We'll create a list containing one covariance matrix

# Generate a small positive definite matrix for the covariance
np.random.seed(0)
dim = 4
# Create a random matrix and make it symmetric positive definite
A = np.random.randn(dim, dim)
emp_cov_matrix = A @ A.T + np.eye(dim) * 0.1
emp_cov = [emp_cov_matrix]

# Define parameters
alpha = 0.01
max_iter = 100

ARGS = {
    "emp_cov": emp_cov,
    "alpha": alpha,
    "max_iter": max_iter,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, sklearn — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type ndarray, ndim 2, dtype family float, shape (4, 4) — shape (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
init_logger Ran
ran on a synthesized input
toshi-k/kaggle-champs-scalar-coupling/source/02_triplet_update/lib/log.py
code served (permissive licence) · get_code("4190c7c69c0c7bcb")
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 RootLogger. 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 logging
import tempfile
from pathlib import Path

# Create a temporary directory for the log file
temp_dir = tempfile.mkdtemp()
log_file_path = os.path.join(temp_dir, "test.log")

ARGS = {
    'path': log_file_path,
    'name': 'root'
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
none outside the standard library — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type RootLogger — a RootLogger output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a RootLogger 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
init_logger Ran
ran on a synthesized input
toshi-k/kaggle-trends-assessment-prediction/source/02_edge_gnn/lib/log.py
code served (permissive licence) · get_code("0d5a312be60d852c")
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
import tempfile
from pathlib import Path

ARGS = {
    'path': str(Path(tempfile.gettempdir()) / 'test_logger.log'),
    '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
none outside the standard library — 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
list_of_lists Ran
ran, honoured the contract we drafted
this paper's copy was not recorded; identical code first harvested from peterbjorgensen/msgnet
pointer only · get_code("61dc9fc0e2272217")
How it ran

The body of this sample is withheld: this paper's copy of the code was not recorded (its link names no repository or source path), so no licence was read for it. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

load_ids Ran
ran on a synthesized input
toshi-k/kaggle-trends-assessment-prediction/source/01_preprocess/spatial_map.py
code served (permissive licence) · get_code("26b74228db6c7167")
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 2, 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.

from pathlib import Path
import pandas as pd
import tempfile
import os

# Create a temporary directory with the required CSV files
temp_dir = tempfile.mkdtemp()
dir_dataset = Path(temp_dir)

# Create train_scores.csv
train_scores_data = {
    'Id': ['sample_1', 'sample_2', 'sample_3'],
    'Score': [0.8, 0.9, 0.7]
}
train_scores_df = pd.DataFrame(train_scores_data)
train_scores_df.to_csv(dir_dataset / 'train_scores.csv', index=False)

# Create sample_submission.csv
sample_submission_data = {
    'Id': ['00001_extra', '00002_extra', '00003_extra', '00001_other'],
    'Prediction': [0.5, 0.6, 0.7, 0.8]
}
sample_submission_df = pd.DataFrame(sample_submission_data)
sample_submission_df.to_csv(dir_dataset / 'sample_submission.csv', index=False)

ARGS = {
    'dir_dataset': dir_dataset
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
pandas — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type tuple, ndim 2, 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
register_vcs_handler Ran
ran; our contract draft was wrong, not the code
nrel/m2p/m2p/_version.py
code served (permissive licence) · get_code("c55cafde08716f01")
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 function. 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.

# Global HANDLERS dict that the function uses
HANDLERS = {}

# Define arguments for register_vcs_handler
ARGS = {
    "vcs": "git",
    "method": "commit"
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
none outside the standard library — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type function — a function output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a function 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
run_command Ran
ran; our contract draft was wrong, not the code
nrel/m2p/m2p/_version.py
code served (permissive licence) · get_code("dbb37355631dabcf")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned tuple, ndim 1, dtype family float; no output shape is stated. The image it ran in was not recorded. If your copy returns the same type and ndim on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import subprocess
import sys

ARGS = {
    "commands": ["echo"],
    "args": ["hello", "world"],
    "cwd": None,
    "verbose": False,
    "hide_stderr": False,
    "env": None,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
none outside the standard library — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type tuple, ndim 1, dtype family float — a tuple output has no array shape of its own; none is stated
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
species_count_filter Ran
ran, violated the contract we drafted
this paper's copy was not recorded; identical code first harvested from peterbjorgensen/msgnet
pointer only · get_code("6664fee3d8969be5")
How it ran

The body of this sample is withheld: this paper's copy of the code was not recorded (its link names no repository or source path), so no licence was read for it. 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.

versions_from_parentdir Ran
ran; our contract draft was wrong, not the code
nrel/m2p/m2p/_version.py
code served (permissive licence) · get_code("5032e3b81c0fffb3")
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 os
import tempfile

ARGS = {
    'parentdir_prefix': 'myproject-',
    'root': '/tmp/myproject-1.2.3/src',
    'verbose': False
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
none outside the standard library — 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
get_BO Not yet run
unverified (harvested, no recorded run)
toshi-k/kaggle-champs-scalar-coupling/source/01_preprocess/xyz2mol.py
code served (permissive licence) · get_code("6beaa320bb27bc5a")
How it ran

no invocation recorded.

load_dataset Not yet run
unverified (harvested, no recorded run)
toshi-k/kaggle-champs-scalar-coupling/source/02_triplet_update/lib/load_dataset.py
code served (permissive licence) · get_code("b45623a6365e525f")
How it ran

no invocation recorded.

Also present in other papers' code

Of 22 samples lifted from this paper's linked repositories, 22 carry a function identity and 0 do not. Of the 22 distinct functions with an identity, 8 are also present in other papers whose code we hold (4 with at least one paper dated earlier, 1 the same month, 4 later) and 14 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
register_vcs_handler 26 other papers
2 the same month, 24 later
1806.00550 (2018-06)
A Swiss Army Infinitesimal Jackknife
1806.03720 (2018-06)
Stochastic seismic waveform inversion using generative adversarial networks as a geological prior
1812.01719 (2018-12)
Knowing what you know in brain segmentation using Bayesian deep neural networks
and 23 more not named here
versions_from_parentdir 9 other papers
9 later
2104.08691 (2021-04)
The Power of Scale for Parameter-Efficient Prompt Tuning
2204.04516 (2022-04)
Uncertainty-Informed Deep Learning Models Enable High-Confidence Predictions for Digital Histopathology
2205.10242 (2022-05)
EXODUS: Stable and Efficient Training of Spiking Neural Networks
and 6 more not named here
run_command 7 other papers
7 later
2104.08691 (2021-04)
The Power of Scale for Parameter-Efficient Prompt Tuning
2204.04516 (2022-04)
Uncertainty-Informed Deep Learning Models Enable High-Confidence Predictions for Digital Histopathology
2205.10242 (2022-05)
EXODUS: Stable and Efficient Training of Spiking Neural Networks
and 4 more not named here
get_config_from_root 2 other papers
2 later
2104.08691 (2021-04)
The Power of Scale for Parameter-Efficient Prompt Tuning
2207.09250 (2022-07)
Roughness of molecular property landscapes and its impact on modellability
float_or_string 1 other paper
1 dated earlier
1712.06113 (2017-12)
SchNet - a deep learning architecture for molecules and materials
get_arguments 1 other paper
1 dated earlier
1712.06113 (2017-12)
SchNet - a deep learning architecture for molecules and materials
list_of_lists 1 other paper
1 dated earlier
1712.06113 (2017-12)
SchNet - a deep learning architecture for molecules and materials
species_count_filter 1 other paper
1 dated earlier
1712.06113 (2017-12)
SchNet - a deep learning architecture for molecules and materials

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

Neural message passing on molecular graphs is one of the most promising methods for predicting formation energy and other properties of molecules and materials. In this work we extend the neural message passing model with an edge update network which allows the information exchanged between atoms to depend on the hidden state of the receiving atom. We benchmark the proposed model on three publicly available datasets (QM9, The Materials Project and OQMD) and show that the proposed model yields superior prediction of formation energies and other properties on all three datasets in comparison with the best published results. Furthermore we investigate different methods for constructing the graph used to represent crystalline structures and we find that using a graph based on K-nearest neighbors achieves better prediction accuracy than using maximum distance cutoff or the Voronoi tessellation graph.

For agents

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

get_harvested_code_for_paper("1806.03146")
get_code_for_paper("1806.03146")
have("1806.03146")

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

curl https://syntology.ai/api/ran/1806.03146.json

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

[![Syntology run record](https://syntology.ai/api/ran/1806.03146.svg)](https://syntology.ai/paper/1806.03146)

Connect an agent — have() is free.