SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2106.02190 · 2021

Spatial Graph Attention and Curiosity-driven Policy for Antiviral Drug Discovery

arXiv · PDF · Open in the Atlas

Code that ran

9 of 14 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, 0 violated it and 9 have no contract verdict; 0 failures of our instrument; 5 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/2106.02190.json · badge: /api/ran/2106.02190.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
njchoma/DGAPN canonical (classifier label)
classifier basis: census
6 ran · 2 no recorded run
yulun-rayn/dgapn canonical (classifier label)
classifier basis: census
3 ran · 3 no recorded run
FunctionStatusWhere it lives
batched_expand Ran
ran on a synthesized input
njchoma/DGAPN/src/dgapn/gapn_policy.py
code served (permissive licence) · get_code("4e566ed17e45c6b6")
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 (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 torch

torch.manual_seed(0)

# Create a small embedding tensor (batch_size=2, embedding_dim=4)
emb = torch.randn(2, 4)

# Create a batch tensor with indices indicating which sample each element belongs to
# This should have values that correspond to valid indices in the embedding
batch = torch.tensor([0, 1, 0, 1])

ARGS = {
    "emb": emb,
    "batch": batch,
}
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 (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
batched_expand Ran
ran on a synthesized input
yulun-rayn/dgapn/dgapn/model/gapn_policy.py
code served (permissive licence) · get_code("9e6703e2b65561b1")
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 (6, 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)

# emb: a tensor to be repeated/expanded
# batch: a tensor of batch indices used to determine repetition counts via bincount
emb = torch.randn(3, 4)  # 3 embeddings, 4 dimensions
batch = torch.tensor([0, 0, 1, 2, 2, 2])  # batch assignments for 6 items

ARGS = {
    "emb": emb,
    "batch": batch,
}
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 (6, 4) — shape (6, 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
batched_softmax Ran
ran on a synthesized input
njchoma/DGAPN/src/dgapn/gapn_policy.py
code served (permissive licence) · get_code("feafdd257791f6d0")
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 (6, 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 torch_geometric as pyg

torch.manual_seed(0)

# Create logits tensor: shape (6, 4) - 6 nodes with 4-dimensional logits
logits = torch.randn(6, 4)

# Create batch tensor: shape (6,) - assigns each node to a batch
# Values indicate which batch each node belongs to (0 or 1)
batch = torch.tensor([0, 0, 0, 1, 1, 1], dtype=torch.long)

ARGS = {
    "logits": logits,
    "batch": batch,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch, torch_geometric — 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 (6, 4) — shape (6, 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
batched_softmax Ran
ran on a synthesized input
yulun-rayn/dgapn/dgapn/model/gapn_policy.py
code served (permissive licence) · get_code("1f76293ee65bdb43")
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 (6, 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 torch_geometric as pyg

torch.manual_seed(0)

# Create small tensors for testing
# logits: shape (6, 4) - 6 nodes with 4 classes
logits = torch.randn(6, 4)

# batch: shape (6,) - assigns each node to a batch
# Values 0 and 1 indicate two separate graphs in the batch
batch = torch.tensor([0, 0, 0, 1, 1, 1])

ARGS = {
    "logits": logits,
    "batch": batch,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch, torch_geometric — 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 (6, 4) — shape (6, 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
main Ran
ran on a synthesized input
njchoma/DGAPN/src/dataset/preprocess.py
code served (permissive licence) · get_code("f050755aee6bf591")
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.

import csv
import tempfile
import os

# Create a temporary CSV file with 2 columns (score, smiles)
temp_dir = tempfile.mkdtemp()
csv_2col_path = os.path.join(temp_dir, "test_2col.csv")

with open(csv_2col_path, 'w', newline='') as f:
    writer = csv.writer(f)
    writer.writerow(['0.5', 'CCO'])
    writer.writerow(['0.8', 'CC(C)O'])
    writer.writerow(['0.3', 'c1ccccc1'])

ARGS = {
    'dataset_path': csv_2col_path
}
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 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
read_2col Ran
ran on a synthesized input
njchoma/DGAPN/src/dataset/preprocess.py
code served (permissive licence) · get_code("cf327c9b704f12fd")
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.

import torch
import numpy as np

# Create a simple reader that yields (score, smiles) tuples
class SimpleReader:
    def __init__(self, data):
        self.data = data
    
    def __iter__(self):
        return iter(self.data)

# Create sample data with score and SMILES strings
reader_data = [
    ("0.85", "CCO"),
    ("0.92", "CC(C)O"),
    ("0.45", "c1ccccc1"),
    ("0.78", None),  # Test None handling
    ("invalid", "CC"),  # Test exception handling
    ("0.65", "CCCC"),
]

reader = SimpleReader(reader_data)

ARGS = {
    "reader": reader
}
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 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
read_4col Ran
ran on a synthesized input
njchoma/DGAPN/src/dataset/preprocess.py
code served (permissive licence) · get_code("ff8edfb59d13caa6")
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.

import torch
import numpy as np
from collections.abc import Iterable

torch.manual_seed(0)

class MockReader:
    """A mock reader that yields 4-tuples of (index, smiles, unused, score)"""
    def __init__(self):
        self.data = [
            (0, "CC(C)Cc1ccc(cc1)C(C)C(O)=O", "unused1", "7.2"),
            (1, "c1ccccc1", "unused2", "5.1"),
            (2, None, "unused3", "3.4"),
            (3, "CCO", "unused4", "8.9"),
        ]
    
    def __iter__(self):
        return iter(self.data)

reader = MockReader()

ARGS = {
    "reader": reader
}
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 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
read_data Ran
ran on a synthesized input
yulun-rayn/dgapn/dgapn/dataset/preprocess.py
code served (permissive licence) · get_code("c38a474680f6cdd6")
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.

import csv
import tempfile
import os

# Create a temporary CSV file with 2 columns (score, smiles)
temp_dir = tempfile.mkdtemp()
csv_2col_path = os.path.join(temp_dir, "test_2col.csv")

with open(csv_2col_path, 'w', newline='') as f:
    writer = csv.writer(f)
    writer.writerow(['0.5', 'CCO'])
    writer.writerow(['0.8', 'c1ccccc1'])
    writer.writerow(['0.3', 'CC'])

ARGS = {
    'dataset_path': csv_2col_path
}
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 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
unpack_dataset Ran
ran on a synthesized input
njchoma/DGAPN/src/dataset/get_dataset.py
code served (permissive licence) · get_code("2a4bfb02209e2e2f")
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 str. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import os
import gzip
import shutil
import tempfile

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

# Create a small test file and gzip it
test_content = b"This is test dataset content"
packed_name = "dataset.gz"
unpacked_name = "dataset.txt"

packed_filepath = os.path.join(temp_dir, packed_name)
with gzip.open(packed_filepath, 'wb') as f:
    f.write(test_content)

ARGS = {
    "storage_path": temp_dir,
    "packed_name": packed_name,
    "unpacked_name": unpacked_name,
}
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 str — a str output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a str output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
batched_sample Not yet run
unverified (harvested, no recorded run)
njchoma/DGAPN/src/dgapn/gapn_policy.py
code served (permissive licence) · get_code("1a487a9d169c71fa")
How it ran

no invocation recorded.

batched_sample Not yet run
unverified (harvested, no recorded run)
yulun-rayn/dgapn/dgapn/model/gapn_policy.py
code served (permissive licence) · get_code("c5018328336db254")
How it ran

no invocation recorded.

get_largest_ring_size Not yet run
unverified (harvested, no recorded run)
yulun-rayn/dgapn/dgapn/reward/logp/get_score.py
code served (permissive licence) · get_code("4291ed1c781509d8")
How it ran

no invocation recorded.

get_main_reward Not yet run
unverified (harvested, no recorded run)
njchoma/DGAPN/src/reward/get_main_reward.py
code served (permissive licence) · get_code("afb1971c85947f64")
How it ran

no invocation recorded.

get_reward Not yet run
unverified (harvested, no recorded run)
yulun-rayn/dgapn/dgapn/reward/get_reward.py
code served (permissive licence) · get_code("d7caa82df22437b8")
How it ran

no invocation recorded.

Also present in other papers' code

Of 14 samples lifted from this paper's linked repositories, 14 carry a function identity and 0 do not. Of the 14 distinct functions with an identity, 0 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 0 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.

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

We developed Distilled Graph Attention Policy Network (DGAPN), a reinforcement learning model to generate novel graph-structured chemical representations that optimize user-defined objectives by efficiently navigating a physically constrained domain. The framework is examined on the task of generating molecules that are designed to bind, noncovalently, to functional sites of SARS-CoV-2 proteins. We present a spatial Graph Attention (sGAT) mechanism that leverages self-attention over both node and edge attributes as well as encoding the spatial structure -- this capability is of considerable interest in synthetic biology and drug discovery. An attentional policy network is introduced to learn the decision rules for a dynamic, fragment-based chemical environment, and state-of-the-art policy gradient techniques are employed to train the network with stability. Exploration is driven by the stochasticity of the action space design and the innovation reward bonuses learned and proposed by random network distillation. In experiments, our framework achieved outstanding results compared to state-of-the-art algorithms, while reducing the complexity of paths to chemical synthesis.

For agents

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

get_harvested_code_for_paper("2106.02190")
get_code_for_paper("2106.02190")
have("2106.02190")

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

curl https://syntology.ai/api/ran/2106.02190.json

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

[![Syntology run record](https://syntology.ai/api/ran/2106.02190.svg)](https://syntology.ai/paper/2106.02190)

Connect an agent — have() is free.