SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1908.01425 · 2019

ChemBO: Bayesian Optimization of Small Organic Molecules with Synthesizable Recommendations

arXiv · PDF · Open in the Atlas

Code that ran

4 of 6 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 4 have no contract verdict; 0 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/1908.01425.json · badge: /api/ran/1908.01425.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
cyclone923/ChemBo community (classifier label)
classifier basis not recorded on the link
4 ran · 2 no recorded run
FunctionStatusWhere it lives
get_list_from_file Ran
ran on a synthesized input
cyclone923/ChemBo/experiments/compute_experiment_stats.py
code served (permissive licence) · get_code("7c53f35294810f40")
How it ran

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

import tempfile
import os

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

# Create an exp_log file with the expected format
exp_log_path = os.path.join(temp_dir, 'exp_log')
with open(exp_log_path, 'w') as f:
    f.write("# Some header max=0.95)\n")
    f.write("# Another line max=0.87)\n")
    f.write("# Third line max=0.92)\n")

# Create a run_log file that will be replaced with exp_log
run_log_path = os.path.join(temp_dir, 'run_log')
with open(run_log_path, 'w') as f:
    f.write("dummy content\n")

ARGS = {
    'path': run_log_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 list, ndim 1, dtype family float — a list output has no array shape of its own; none is stated
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
get_smiles_list_from_file Ran
ran on a synthesized input
cyclone923/ChemBo/experiments/compute_experiment_stats.py
code served (permissive licence) · get_code("cde312892921c496")
How it ran

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

import tempfile
import os

# Create a temporary file with SMILES data in the expected format
temp_file = tempfile.NamedTemporaryFile(mode='w', delete=False, suffix='.txt')
temp_file.write("some data result: CC(=O)O\n")
temp_file.write("other line result: c1ccccc1\n")
temp_file.write("no result here\n")
temp_file.write("another result: CCO\n")
temp_file.close()

ARGS = {
    'path': temp_file.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 list, ndim 1, dtype family float — a list output has no array shape of its own; none is stated
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
get_worker_manager Ran
ran on a synthesized input
cyclone923/ChemBo/chemist_opt/chemist.py
code served (permissive licence) · get_code("16d7fecc2b1fd69c")
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 WorkerManager. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import torch.nn as nn

torch.manual_seed(0)

class WorkerManager:
    """Stand-in WorkerManager class"""
    def __init__(self, name="default_worker"):
        self.name = name
    
    def __repr__(self):
        return f"WorkerManager(name={self.name})"

# Create a WorkerManager instance
worker_manager_instance = WorkerManager(name="test_worker")

# The function accepts either a WorkerManager instance or a string
# Test with the WorkerManager instance
ARGS = {
    "worker_manager": worker_manager_instance
}
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 WorkerManager — a WorkerManager output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a WorkerManager 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
mol_maximise_acquisition Ran
ran on a synthesized input
cyclone923/ChemBo/chemist_opt/gp_bandit.py
code served (permissive licence) · get_code("f389610d35206a70")
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 torch
import logging
from unittest.mock import Mock, MagicMock

torch.manual_seed(0)

# Create a mock domain object
class MockDomain:
    def __init__(self, domain_type='euclidean'):
        self.domain_type = domain_type
    
    def get_type(self):
        return self.domain_type
    
    def is_a_member(self, points):
        return True

# Create a mock explorer/optimizer
class MockExplorer:
    def __init__(self):
        self.acq_fn = None
        self.capital_type = None
    
    def reset_params(self, acquisition, capital_type):
        self.acq_fn = acquisition
        self.capital_type = capital_type
    
    def run(self, max_evals):
        # Return top_value, top_point, history
        top_point = [0.5, 0.3, 0.2, 0.1]
        top_value = 0.95
        history = []
        return top_value, top_point, history

# Create ancillary data object
class MockAncData:
    def __init__(self):
        self.acq_opt_method = 'rand_explorer'
        self.domain = MockDomain(domain_type='euclidean')
        self.max_evals = 10
        self.capital_type = 'energy'
        self.acq_optimizer = MockExplorer()

# Create acquisition function
def mock_acq_fn(x):
    if isinstance(x, list):
        return torch.tensor([0.9], dtype=torch.float32)
    else:
        x_tensor = torch.tensor(x, dtype=torch.float32)
        return torch.tensor(0.9, dtype=torch.float32)

anc_data = MockAncData()
acq_fn = mock_acq_fn

ARGS = {
    'acq_fn': acq_fn,
    'anc_data': anc_data,
}
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 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_chembl_prop Not yet run
unverified (harvested, no recorded run)
cyclone923/ChemBo/datasets/loaders.py
code served (permissive licence) · get_code("078a8c06e83fe6bb")
How it ran

no invocation recorded.

get_list_from_file Not yet run
unverified (harvested, no recorded run)
cyclone923/ChemBo/experiments/compute_novelty.py
code served (permissive licence) · get_code("ca948737e7b888e1")
How it ran

no invocation recorded.

Also present in other papers' code

Of 6 samples lifted from this paper's linked repositories, 6 carry a function identity and 0 do not. Of the 6 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 6 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

In applications such as molecule design or drug discovery, it is desirable to have an algorithm which recommends new candidate molecules based on the results of past tests. These molecules first need to be synthesized and then tested for objective properties. We describe ChemBO, a Bayesian optimization framework for generating and optimizing organic molecules for desired molecular properties. While most existing data-driven methods for this problem do not account for sample efficiency or fail to enforce realistic constraints on synthesizability, our approach explores the synthesis graph in a sample-efficient way and produces synthesizable candidates. We implement ChemBO as a Gaussian process model and explore existing molecular kernels for it. Moreover, we propose a novel optimal-transport based distance and kernel that accounts for graphical information explicitly. In our experiments, we demonstrate the efficacy of the proposed approach on several molecular optimization problems.

For agents

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

get_harvested_code_for_paper("1908.01425")
get_code_for_paper("1908.01425")
have("1908.01425")

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

curl https://syntology.ai/api/ran/1908.01425.json

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

[![Syntology run record](https://syntology.ai/api/ran/1908.01425.svg)](https://syntology.ai/paper/1908.01425)

Connect an agent — have() is free.