SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2202.08450 · 2022

Design-Bench: Benchmarks for Data-Driven Offline Model-Based Optimization

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; 0 honoured the contract we drafted, 3 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/2202.08450.json · badge: /api/ran/2202.08450.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
rail-berkeley/design-bench canonical (classifier label)
classifier basis not recorded on the link
6 ran · 2 no recorded run
FunctionStatusWhere it lives
default_linear_distribution Ran
ran, violated the contract we drafted
rail-berkeley/design-bench/design_bench/datasets/dataset_builder.py
code served (permissive licence) · get_code("97d1dadc0092cddc")
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 (5,) 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

# Create a small ranks array for testing
# This represents the rank order of designs in a dataset
ranks = np.array([0, 1, 2, 3, 4], dtype=np.int64)

ARGS = {
    "ranks": ranks
}
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 (5,) — shape (5,) 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
default_quadratic_distribution Ran
ran, violated the contract we drafted
rail-berkeley/design-bench/design_bench/datasets/dataset_builder.py
code served (permissive licence) · get_code("cd881bdf30de1f0a")
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 (6,) 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
import torch

np.random.seed(0)
torch.manual_seed(0)

# Create a sample ranks array
# This represents the rank order of designs, typically integers from 0 to n-1
ranks = np.array([0, 1, 2, 3, 4, 5], dtype=np.int32)

ARGS = {
    "ranks": ranks
}
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 ndarray, ndim 1, dtype family float, shape (6,) — shape (6,) 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
default_uniform_distribution Ran
ran, violated the contract we drafted
rail-berkeley/design-bench/design_bench/datasets/dataset_builder.py
code served (permissive licence) · get_code("7dbee57a564eced6")
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 (8,) 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

# Create a sample ranks array
# The function expects a numpy array representing rank order of designs
# It simply returns an array of ones with the same shape
ranks = np.array([3, 1, 4, 1, 5, 9, 2, 6], dtype=np.int32)

ARGS = {
    "ranks": ranks
}
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 (8,) — shape (8,) 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
get_confirm_token Ran
ran; our contract draft was wrong, not the code
rail-berkeley/design-bench/design_bench/disk_resource.py
code served (permissive licence) · get_code("fb3792dae3b52c70")
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.

from unittest.mock import Mock

# Create a mock response object with cookies attribute
# The function iterates over response.cookies.items() and checks if key.startswith('download_warning')
mock_response = Mock()

# Create a cookies dict with a download_warning key
mock_cookies = {
    'download_warning': 'token_value_123',
    'other_cookie': 'some_value'
}

mock_response.cookies = mock_cookies

ARGS = {
    'response': mock_response
}
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
import_name Ran
ran; our contract draft was wrong, not the code
rail-berkeley/design-bench/design_bench/task.py
code served (permissive licence) · get_code("9bdda179859c7e1c")
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 type. 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 importlib
import sys

# Create a simple module and attribute to import
class DummyClass:
    value = "test_value"

# Add a dummy module to sys.modules so we can import it
import types
dummy_module = types.ModuleType('dummy_module')
dummy_module.DummyClass = DummyClass
sys.modules['dummy_module'] = dummy_module

# Define the arguments
ARGS = {
    'name': 'dummy_module:DummyClass'
}
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 type — a type output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a type 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
one_hot Ran
ran; our contract draft was wrong, not the code
rail-berkeley/design-bench/design_bench/datasets/discrete_dataset.py
code served (permissive licence) · get_code("9254b9a1999e5ab9")
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 3, dtype family float, shape (2, 3, 5) 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

# Analyze the function:
# - 'a' is used with: .size, .ravel(), .shape attributes
# - 'num_classes' is used as an integer for np.zeros shape and indexing
# 
# The function converts integer class indices to one-hot representation
# So 'a' should be a numpy array of integers (class indices)
# 'num_classes' should be the total number of classes

# Create a small integer array with class indices
a = np.array([[0, 1, 2], [1, 0, 3]], dtype=np.int64)

# Number of classes should be greater than max index in 'a'
num_classes = 5

ARGS = {
    "a": a,
    "num_classes": num_classes,
}
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 3, dtype family float, shape (2, 3, 5) — shape (2, 3, 5) 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
direct_download Not yet run
unverified (harvested, no recorded run)
rail-berkeley/design-bench/design_bench/disk_resource.py
code served (permissive licence) · get_code("bee40bc7b8e40002")
How it ran

no invocation recorded.

google_drive_download Not yet run
unverified (harvested, no recorded run)
rail-berkeley/design-bench/design_bench/disk_resource.py
code served (permissive licence) · get_code("0508c25f44e088dc")
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, 8 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 8 later) and 0 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
default_linear_distribution 1 other paper
1 later
2410.11502 (2024-10)
Offline Model-Based Optimization by Learning to Rank
default_quadratic_distribution 1 other paper
1 later
2410.11502 (2024-10)
Offline Model-Based Optimization by Learning to Rank
default_uniform_distribution 1 other paper
1 later
2410.11502 (2024-10)
Offline Model-Based Optimization by Learning to Rank
direct_download 1 other paper
1 later
2410.11502 (2024-10)
Offline Model-Based Optimization by Learning to Rank
get_confirm_token 1 other paper
1 later
2410.11502 (2024-10)
Offline Model-Based Optimization by Learning to Rank
google_drive_download 1 other paper
1 later
2410.11502 (2024-10)
Offline Model-Based Optimization by Learning to Rank
import_name 1 other paper
1 later
2410.11502 (2024-10)
Offline Model-Based Optimization by Learning to Rank
one_hot 1 other paper
1 later
2410.11502 (2024-10)
Offline Model-Based Optimization by Learning to Rank

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

Black-box model-based optimization (MBO) problems, where the goal is to find a design input that maximizes an unknown objective function, are ubiquitous in a wide range of domains, such as the design of proteins, DNA sequences, aircraft, and robots. Solving model-based optimization problems typically requires actively querying the unknown objective function on design proposals, which means physically building the candidate molecule, aircraft, or robot, testing it, and storing the result. This process can be expensive and time consuming, and one might instead prefer to optimize for the best design using only the data one already has. This setting -- called offline MBO -- poses substantial and different algorithmic challenges than more commonly studied online techniques. A number of recent works have demonstrated success with offline MBO for high-dimensional optimization problems using high-capacity deep neural networks. However, the lack of standardized benchmarks in this emerging field is making progress difficult to track. To address this, we present Design-Bench, a benchmark for offline MBO with a unified evaluation protocol and reference implementations of recent methods. Our benchmark includes a suite of diverse and realistic tasks derived from real-world optimization problems in biology, materials science, and robotics that present distinct challenges for offline MBO. Our benchmark and reference implementations are released at github.com/rail-berkeley/design-bench and github.com/rail-berkeley/design-baselines.

For agents

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

get_harvested_code_for_paper("2202.08450")
get_code_for_paper("2202.08450")
have("2202.08450")

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

curl https://syntology.ai/api/ran/2202.08450.json

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

[![Syntology run record](https://syntology.ai/api/ran/2202.08450.svg)](https://syntology.ai/paper/2202.08450)

Connect an agent — have() is free.