SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2211.16486 · 2022

AdsorbML: A Leap in Efficiency for Adsorption Energy Calculations using Generalizable Machine Learning Potentials

arXiv · PDF · Open in the Atlas

Code that ran

3 of 3 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, 1 violated it and 0 have no contract verdict; 2 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/2211.16486.json · badge: /api/ran/2211.16486.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
open-catalyst-project/adsorbml canonical (classifier label)
classifier basis: classifier_2025
3 ran · 0 no recorded run
FunctionStatusWhere it lives
get_dft_data Ran
ran; our contract draft was wrong, not the code
open-catalyst-project/adsorbml/adsorbml/2023_neurips_challenge/challenge_eval.py
code served (permissive licence) · get_code("29317f450da71bc5")
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) and returned defaultdict. 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 numpy as np
from collections import defaultdict

# Construct valid arguments for get_dft_data
# The function expects 'targets' which is a dict where:
# - keys are system_ids (strings)
# - values are iterables of [config_id, dft_ads_energy] pairs

targets = {
    'system_id_1': [
        ['config_id_1', 1.5],
        ['config_id_2', 2.3],
        ['config_id_3', 1.8],
    ],
    'system_id_2': [
        ['config_id_1', 3.2],
        ['config_id_2', 2.9],
    ],
    'system_id_3': [
        ['config_id_1', 0.5],
    ],
}

ARGS = {
    'targets': targets,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
numpy, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type defaultdict — a defaultdict output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a defaultdict 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
is_successful Ran
ran, violated the contract we drafted
open-catalyst-project/adsorbml/adsorbml/2023_neurips_challenge/challenge_eval.py
code served (permissive licence) · get_code("95112aaef5df6a05")
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) and returned bool, ndim 0, dtype family float, 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
import numpy as np

torch.manual_seed(0)

# The function takes three parameters:
# - best_pred_energy: a scalar (predicted energy value)
# - best_dft_energy: a scalar (ground truth DFT energy value)
# - SUCCESS_THRESHOLD: a float threshold (default 0.1)

# The function computes the difference and checks if it's within threshold
# All parameters are simple scalars/floats

ARGS = {
    "best_pred_energy": 0.05,
    "best_dft_energy": 0.0,
    "SUCCESS_THRESHOLD": 0.1
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
numpy, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type bool, ndim 0, dtype family float, 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
process_ml_data Ran
ran; our contract draft was wrong, not the code
open-catalyst-project/adsorbml/adsorbml/2023_neurips_challenge/challenge_eval.py
code served (permissive licence) · get_code("6c4d6f362a7d72a6")
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) and returned defaultdict. 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 tempfile
import os

# Create a temporary numpy file with predictions
temp_dir = tempfile.mkdtemp()
results_file = os.path.join(temp_dir, "results.npz")

# Create sample prediction data
pred_ids = np.array(['0_config1', '0_config2', '1_config1'])
pred_energies = np.array([1.5, 2.3, 3.1])
np.savez(results_file, ids=pred_ids, energy=pred_energies)

# Create metadata mapping
metadata = {
    0: {'system_id': 'sys_A', 'config_id': 'cfg_1'},
    1: {'system_id': 'sys_A', 'config_id': 'cfg_2'},
    2: {'system_id': 'sys_B', 'config_id': 'cfg_1'},
}

# Create ml_dft_targets
ml_dft_targets = {
    'model_v1': {
        'sys_A': {
            'cfg_1': 1.2,
            'cfg_2': 2.1,
        },
        'sys_B': {
            'cfg_1': 3.0,
            'cfg_2': 4.5,
        },
    }
}

# Create dft_data
dft_data = {
    'sys_A': {
        'cfg_1': None,
        'cfg_2': None,
    },
    'sys_B': {
        'cfg_1': None,
        'cfg_2': None,
    },
}

# Model parameter (not actually used in the function body)
model = 'model_v1'

ARGS = {
    'results_file': results_file,
    'model': model,
    'metadata': metadata,
    'ml_dft_targets': ml_dft_targets,
    'dft_data': dft_data,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type defaultdict — a defaultdict output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a defaultdict 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 3 samples lifted from this paper's linked repositories, 3 carry a function identity and 0 do not. Of the 3 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 3 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

Computational catalysis is playing an increasingly significant role in the design of catalysts across a wide range of applications. A common task for many computational methods is the need to accurately compute the adsorption energy for an adsorbate and a catalyst surface of interest. Traditionally, the identification of low energy adsorbate-surface configurations relies on heuristic methods and researcher intuition. As the desire to perform high-throughput screening increases, it becomes challenging to use heuristics and intuition alone. In this paper, we demonstrate machine learning potentials can be leveraged to identify low energy adsorbate-surface configurations more accurately and efficiently. Our algorithm provides a spectrum of trade-offs between accuracy and efficiency, with one balanced option finding the lowest energy configuration 87.36% of the time, while achieving a 2000x speedup in computation. To standardize benchmarking, we introduce the Open Catalyst Dense dataset containing nearly 1,000 diverse surfaces and 100,000 unique configurations.

For agents

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

get_harvested_code_for_paper("2211.16486")
get_code_for_paper("2211.16486")
have("2211.16486")

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

curl https://syntology.ai/api/ran/2211.16486.json

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

[![Syntology run record](https://syntology.ai/api/ran/2211.16486.svg)](https://syntology.ai/paper/2211.16486)

Connect an agent — have() is free.