SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2310.00841 · ICML · 2024

Drug Discovery with Dynamic Goal-aware Fragments

Sung Hwang, Kenji Kawaguchi, Seanie Lee, Seul Lee

arXiv · PDF · Open in the Atlas

Code that ran

6 of 8 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; 1 honoured the contract we drafted, 2 violated it and 0 have no contract verdict; 3 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/2310.00841.json · badge: /api/ran/2310.00841.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
seullee05/geam canonical (classifier label)
classifier basis: census
6 ran · 2 no recorded run
FunctionStatusWhere it lives
choose_parents Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
seullee05/geam/utils_ga/ga.py
code served (permissive licence) · get_code("b17a90a858423da8")
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 (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 numpy as np

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

# population_mol: a list of molecule objects (strings used as stand-ins)
population_mol = ["molecule_A", "molecule_B", "molecule_C", "molecule_D"]

# population_scores: a list of numeric scores
population_scores = [0.5, 0.8, 0.3, 0.9]

ARGS = {
    "population_mol": population_mol,
    "population_scores": population_scores,
}
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 (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
one_of_k_encoding Ran
ran, violated the contract we drafted
seullee05/geam/utils_fgib/data.py
pointer only (licence: MIT); the stored copy get_code serves, from mlvlab/LLaMo, is pointer only (licence: NONE) · get_code("c245ff54c55ec6a1")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from mlvlab/LLaMo, and GitHub detected no licence in that repository when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

one_of_k_encoding_unk Ran
ran, violated the contract we drafted
seullee05/geam/utils_fgib/data.py
pointer only (licence: MIT); the stored copy get_code serves, from mlvlab/LLaMo, is pointer only (licence: NONE) · get_code("5eabfca51d7e1d92")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from mlvlab/LLaMo, and GitHub detected no licence in that repository when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

reduce_mean Ran
ran; our contract draft was wrong, not the code
seullee05/geam/model/ac.py
code served (permissive licence) · get_code("37b5e57246562ac1")
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 expects a 'nodes' object with a mailbox attribute
# The mailbox should be a dict with key 'm' containing a tensor
# The tensor is indexed with [1] to get dimension 1, then torch.mean is applied

class MockNodes:
    def __init__(self):
        self.mailbox = {
            'm': torch.randn(2, 4)  # Shape: (batch=2, features=4)
        }

nodes = MockNodes()

ARGS = {
    'nodes': nodes
}
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
reduce_sum Ran
ran; our contract draft was wrong, not the code
seullee05/geam/model/ac.py
code served (permissive licence) · get_code("65ceccc035ea7b4a")
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)

# Create a mock nodes object that has a mailbox attribute
# The mailbox contains 'm' key with a tensor
# reduce_sum does: torch.sum(nodes.mailbox['m'], 1)
# This means nodes.mailbox['m'] should be a 2D tensor
# sum along dimension 1 reduces it to 1D

class MockNodes:
    def __init__(self):
        # Create a tensor of shape (2, 4) - batch size 2, feature dim 4
        self.mailbox = {
            'm': torch.randn(2, 4)
        }

nodes = MockNodes()

ARGS = {
    'nodes': nodes
}
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
reward_vina Ran
ran, honoured the contract we drafted
seullee05/geam/utils_sac/utils.py
code served (permissive licence) · get_code("ceca25c9f9c313dc")
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 (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 numpy as np

class MockPredictor:
    """Mock predictor that implements the predict method used by reward_vina"""
    def predict(self, smis):
        # Return a dummy prediction array matching the number of SMILES strings
        # Values are negative to test the negation in reward_vina
        return np.array([-2.5, -1.5])

# Create small test data
smis = ["CCO", "CC"]  # Two simple SMILES strings
predictor = MockPredictor()

ARGS = {
    "smis": smis,
    "predictor": predictor,
}
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 (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
adj2sparse Not yet run
unverified (harvested, no recorded run)
seullee05/geam/utils_sac/env.py
code served (permissive licence) · get_code("867aa328c7a38bf2")
How it ran

no invocation recorded.

map_idx Not yet run
unverified (harvested, no recorded run)
seullee05/geam/utils_sac/env.py
code served (permissive licence) · get_code("d6ed86cc24aa07cf")
How it ran

no invocation recorded.

Also present in other papers' code

Of 8 samples lifted from this paper's linked repositories, 8 carry a function identity and 0 do not. Of the 8 distinct functions with an identity, 3 are also present in other papers whose code we hold (3 with at least one paper dated earlier, 0 the same month, 2 later) and 5 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
one_of_k_encoding 3 other papers
2 dated earlier, 1 later
2111.15144 (2021-11)
Decoding the Protein-ligand Interactions Using Parallel Graph Neural Networks
2305.01520 (2023-05)
Conditional Graph Information Bottleneck for Molecular Relational Learning
2411.00871 (2024-11)
LLaMo: Large Language Model-based Molecular Graph Assistant
one_of_k_encoding_unk 2 other papers
1 dated earlier, 1 later
2305.01520 (2023-05)
Conditional Graph Information Bottleneck for Molecular Relational Learning
2411.00871 (2024-11)
LLaMo: Large Language Model-based Molecular Graph Assistant
reduce_mean 1 other paper
1 dated earlier
2110.01219 (2021-10)
Hit and Lead Discovery with Explorative RL and Fragment-based Molecule Generation

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

Fragment-based drug discovery is an effective strategy for discovering drug candidates in the vast chemical space, and has been widely employed in molecular generative models. However, many existing fragment extraction methods in such models do not take the target chemical properties into account or rely on heuristic rules. Additionally, the existing fragment-based generative models cannot update the fragment vocabulary with goal-aware fragments newly discovered during the generation. To this end, we propose a molecular generative framework for drug discovery, named Goal-aware fragment Extraction, Assembly, and Modification (GEAM). GEAM consists of three modules, each responsible for goalaware fragment extraction, fragment assembly, and fragment modification. The fragment extraction module identifies important fragments contributing to the desired target properties with the information bottleneck principle, thereby constructing an effective goal-aware fragment vocabulary. Moreover, GEAM can explore beyond the initial vocabulary with the fragment modification module, and the exploration is further enhanced through the dynamic goal-aware vocabulary update. We experimentally demonstrate that GEAM effectively discovers drug candidates through the generative cycle of the three modules in various drug discovery tasks. Our code is available at https://github.com/ SeulLee05/GEAM.

For agents

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

get_harvested_code_for_paper("2310.00841")
get_code_for_paper("2310.00841")
have("2310.00841")

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

curl https://syntology.ai/api/ran/2310.00841.json

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

[![Syntology run record](https://syntology.ai/api/ran/2310.00841.svg)](https://syntology.ai/paper/2310.00841)

Connect an agent — have() is free.