SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2501.02144 · 2025

Establishing baselines for generative discovery of inorganic crystals

arXiv · PDF · Open in the Atlas

Code that ran

4 of 4 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; 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/2501.02144.json · badge: /api/ran/2501.02144.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
bartel-group/matgen_baselines canonical (classifier label)
classifier basis not recorded on the link
4 ran · 0 no recorded run
FunctionStatusWhere it lives
get_task_description Ran
ran on a synthesized input
bartel-group/matgen_baselines/generate.py
code served (permissive licence) · get_code("46f9c50544d05bb2")
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 torch
from dataclasses import dataclass

@dataclass
class GenerationConfig:
    """Configuration for structure generation."""
    method: str
    num_strucs: int
    filepath: str
    filter_type: str = None
    target: float = None
    threshold: float = None
    ml_filter: dict = None

# Test case 1: with ml_filter containing stability
config1 = GenerationConfig(
    method="energy_minimization",
    num_strucs=10,
    filepath="/tmp/structures.txt",
    ml_filter={'type': 'stability', 'target': 0.5}
)

# Test case 2: with ml_filter containing other filter type
config2 = GenerationConfig(
    method="monte_carlo",
    num_strucs=5,
    filepath="/tmp/output.txt",
    ml_filter={'type': 'bandgap', 'target': 2.0}
)

# Test case 3: with filter_type but no ml_filter
config3 = GenerationConfig(
    method="genetic_algorithm",
    num_strucs=20,
    filepath="/tmp/gen.txt",
    filter_type="density"
)

# Test case 4: no filtering at all
config4 = GenerationConfig(
    method="random_search",
    num_strucs=15,
    filepath="/tmp/random.txt"
)

ARGS = {
    "config": config1
}
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 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
load_config Ran
ran on a synthesized input
bartel-group/matgen_baselines/generate.py
code served (permissive licence) · get_code("9f44a3d6c8f1ad85")
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 json
import tempfile
import os

# Create a temporary config file with the required structure
temp_dir = tempfile.mkdtemp()
config_file_path = os.path.join(temp_dir, 'config.json')

config_data = {
    'mp_api_key': 'test_api_key_12345',
    'tasks': [
        {
            'name': 'task1',
            'type': 'classification',
            'batch_size': 32,
            'learning_rate': 0.001,
            'metadata': {
                'num_classes': 10,
                'input_dim': 784
            }
        },
        {
            'name': 'task2',
            'type': 'regression',
            'batch_size': 16,
            'learning_rate': 0.0005,
            'metadata': {
                'output_dim': 1
            }
        }
    ]
}

with open(config_file_path, 'w') as f:
    json.dump(config_data, f)

ARGS = {
    'config_path': config_file_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 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
load_config Ran
ran on a synthesized input
bartel-group/matgen_baselines/generative_models/CDVAE/generate_cdvae.py
code served (permissive licence) · get_code("32867585d66d1238")
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 json
import tempfile
import os

# Create a temporary JSON configuration file
temp_dir = tempfile.mkdtemp()
config_file = os.path.join(temp_dir, "test_config.json")

# Write a valid JSON configuration
test_config = {
    "model": "test_model",
    "learning_rate": 0.001,
    "batch_size": 32,
    "epochs": 10,
    "layers": [64, 128, 256]
}

with open(config_file, 'w') as f:
    json.dump(test_config, f)

ARGS = {
    "config_path": config_file
}
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
load_json Ran
ran on a synthesized input
bartel-group/matgen_baselines/matgen_baselines/utils/helpers.py
code served (permissive licence) · get_code("338377b48a35b40e")
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 json
import tempfile
import os

# Create a temporary JSON file with valid test data
temp_dir = tempfile.mkdtemp()
test_json_file = os.path.join(temp_dir, "test_data.json")

# Write a valid JSON file
test_data = {
    "name": "test",
    "values": [1, 2, 3],
    "nested": {"key": "value"}
}

with open(test_json_file, 'w') as f:
    json.dump(test_data, f)

ARGS = {
    "filename": test_json_file
}
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

Also present in other papers' code

Of 4 samples lifted from this paper's linked repositories, 4 carry a function identity and 0 do not. Of the 4 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 4 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

Generative artificial intelligence offers a promising avenue for materials discovery, yet its advantages over traditional methods remain unclear. In this work, we introduce and benchmark two baseline approaches - random enumeration of charge-balanced prototypes and data-driven ion exchange of known compounds - against four generative techniques based on diffusion models, variational autoencoders, and large language models. Our results show that established methods such as ion exchange are better at generating novel materials that are stable, although many of these closely resemble known compounds. In contrast, generative models excel at proposing novel structural frameworks and, when sufficient training data is available, can more effectively target properties such as electronic band gap and bulk modulus. To enhance the performance of both the baseline and generative approaches, we implement a post-generation screening step in which all proposed structures are passed through stability and property filters from pre-trained machine learning models including universal interatomic potentials. This low-cost filtering step leads to substantial improvement in the success rates of all methods, remains computationally efficient, and ultimately provides a practical pathway toward more effective generative strategies for materials discovery. By establishing baselines for comparison, this work highlights opportunities for continued advancement of generative models, especially for the targeted generation of novel materials that are thermodynamically stable.

For agents

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

get_harvested_code_for_paper("2501.02144")
get_code_for_paper("2501.02144")
have("2501.02144")

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

curl https://syntology.ai/api/ran/2501.02144.json

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

[![Syntology run record](https://syntology.ai/api/ran/2501.02144.svg)](https://syntology.ai/paper/2501.02144)

Connect an agent — have() is free.