SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1807.05614 · 2018

ANN-Benchmarks: A Benchmarking Tool for Approximate Nearest Neighbor Algorithms

arXiv · PDF · Open in the Atlas

Code that ran

14 of 16 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, 0 violated it and 6 have no contract verdict; 7 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/1807.05614.json · badge: /api/ran/1807.05614.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
erikbern/ann-benchmarks community (classifier label)
classifier basis not recorded on the link
11 ran · 2 no recorded run
maumueller/ann-benchmarks-reproducibility community (classifier label)
classifier basis not recorded on the link
3 ran · 0 no recorded run
FunctionStatusWhere it lives
algorithm_status Ran
ran; our contract draft was wrong, not the code
maumueller/ann-benchmarks-reproducibility/ann_benchmarks/algorithms/definitions.py
code served (permissive licence) · get_code("b78ed1fd13d41cb3")
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 InstantiationStatus. 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
from enum import Enum

class InstantiationStatus(Enum):
    AVAILABLE = 0
    NO_CONSTRUCTOR = 1
    NO_MODULE = 2

# Create a stand-in definition class with module and constructor attributes
class Definition:
    def __init__(self, module, constructor):
        self.module = module
        self.constructor = constructor

# Test case 1: Valid module and constructor
definition = Definition(module="os.path", constructor="join")

ARGS = {
    "definition": definition
}
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 InstantiationStatus — a InstantiationStatus output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a InstantiationStatus 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
algorithm_status Ran
ran on a synthesized input
erikbern/ann-benchmarks/ann_benchmarks/definitions.py
code served (permissive licence) · get_code("b33d2a8b86372d58")
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 InstantiationStatus. 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 dataclasses import dataclass
from typing import Any, List

@dataclass
class Definition:
    algorithm: str
    constructor: str
    module: str
    docker_tag: str
    arguments: List[Any]
    query_argument_groups: List[List[Any]]
    disabled: bool

# Create a valid Definition instance
definition = Definition(
    algorithm="test_algorithm",
    constructor="TestConstructor",
    module="os",
    docker_tag="v1.0",
    arguments=[],
    query_argument_groups=[],
    disabled=False
)

ARGS = {
    "definition": definition
}
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 InstantiationStatus — a InstantiationStatus output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a InstantiationStatus 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
euclidean Ran
ran on a synthesized input
erikbern/ann-benchmarks/ann_benchmarks/distance.py
code served (permissive licence) · get_code("ad492dc47d8560b5")
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 float64, ndim 0, 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 numpy as np

# The euclidean function takes two arguments: a and b
# Both are used with numpy operations (subtraction, exponentiation, summation)
# They should be numpy arrays of compatible shapes

# Create two small numpy arrays
a = np.array([1.0, 2.0, 3.0, 4.0])
b = np.array([5.0, 6.0, 7.0, 8.0])

ARGS = {
    "a": a,
    "b": b
}
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 float64, ndim 0, dtype family float — no output shape is stated: observe_signature.py recorded float ndim 0, which disagrees with the fixture run
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
float_parse_entry Ran
ran, honoured the contract we drafted
erikbern/ann-benchmarks/ann_benchmarks/data.py
code served (permissive licence) · get_code("44fa38f4dba6c740")
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 torch
import numpy as np

def float_parse_entry(line: str) -> list:
    return [float(x) for x in line.strip().split()]

# The function takes a single string parameter 'line'
# It strips whitespace, splits on whitespace, and converts each token to float
# We need to provide a valid string with space-separated numbers

ARGS = {
    "line": "1.5 2.3 3.14 4.0 5.99"
}
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 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
float_unparse_entry Ran
ran; our contract draft was wrong, not the code
erikbern/ann-benchmarks/ann_benchmarks/data.py
code served (permissive licence) · get_code("43546c638e833781")
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
import numpy as np

torch.manual_seed(0)

ARGS = {
    "entry": [1.5, 2.3, 3.14, 4.0, 5.99]
}
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 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
get_bool_env_var Ran
ran on a synthesized input
erikbern/ann-benchmarks/ann_benchmarks/util.py
code served (permissive licence) · get_code("b6d98bf31780fdf9")
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 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 os

# The function takes two parameters:
# 1. env_var_name: str - the name of an environment variable
# 2. default_value: bool - a default boolean value to return if env var is not set

# Set up some test cases by manipulating the environment
os.environ['TEST_VAR_TRUE'] = 'yes'
os.environ['TEST_VAR_FALSE'] = 'no'
os.environ['TEST_VAR_EMPTY'] = ''

ARGS = {
    'env_var_name': 'TEST_VAR_TRUE',
    'default_value': False
}
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 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
get_config_files Ran
ran on a synthesized input
erikbern/ann-benchmarks/ann_benchmarks/definitions.py
code served (permissive licence) · get_code("328aec72f4ecb66d")
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 os
import glob
import tempfile
import shutil

# Create a temporary directory structure that mimics ann_benchmarks/algorithms
temp_base = tempfile.mkdtemp()
base_dir = os.path.join(temp_base, 'ann_benchmarks', 'algorithms')
os.makedirs(base_dir, exist_ok=True)

# Create subdirectories with config.yml files
algorithms = ['faiss', 'annoy', 'hnsw']
for algo in algorithms:
    algo_dir = os.path.join(base_dir, algo)
    os.makedirs(algo_dir, exist_ok=True)
    config_path = os.path.join(algo_dir, 'config.yml')
    with open(config_path, 'w') as f:
        f.write(f"# Config for {algo}\n")

# Create base directory with config.yml (which should be excluded)
base_algo_dir = os.path.join(base_dir, 'base')
os.makedirs(base_algo_dir, exist_ok=True)
base_config_path = os.path.join(base_algo_dir, 'config.yml')
with open(base_config_path, 'w') as f:
    f.write("# Base config\n")

ARGS = {
    'base_dir': base_dir
}
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_dataset Ran
ran on a synthesized input
erikbern/ann-benchmarks/ann_benchmarks/datasets.py
code served (permissive licence) · get_code("311bb1de5567138a")
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 tuple. 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 os
import tempfile
import h5py
import numpy as np

# Create a temporary directory for test data
temp_dir = tempfile.mkdtemp()
os.chdir(temp_dir)

# Create a mock dataset creation function
def create_mock_dataset(hdf5_filename: str) -> None:
    """Create a mock HDF5 dataset for testing"""
    with h5py.File(hdf5_filename, 'w') as f:
        # Create train and test datasets
        f.create_dataset('train', data=np.random.rand(10, 128).astype(np.float32))
        f.create_dataset('test', data=np.random.rand(5, 128).astype(np.float32))
        f.attrs['dimension'] = 128

# Create the DATASETS dict with mock dataset creators
DATASETS = {
    'test-dataset': create_mock_dataset,
    'mock-data': create_mock_dataset,
}

# Pre-create the data directory
if not os.path.exists('data'):
    os.mkdir('data')

# Pre-create a test HDF5 file so the download is skipped
hdf5_test_path = os.path.join('data', 'test-dataset.hdf5')
with h5py.File(hdf5_test_path, 'w') as f:
    f.create_dataset('train', data=np.random.rand(10, 128).astype(np.float32))
    f.create_dataset('test', data=np.random.rand(5, 128).astype(np.float32))
    f.attrs['dimension'] = 128

# Define arguments for get_dataset function
ARGS = {
    'dataset_name': 'test-dataset',
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
h5py, numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type tuple — a tuple output has no array shape of its own; none is 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
get_unique_algorithms Ran
ran; our contract draft was wrong, not the code
maumueller/ann-benchmarks-reproducibility/ann_benchmarks/algorithms/definitions.py
code served (permissive licence) · get_code("15a8353f5fe218be")
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
import yaml

# Create a temporary YAML file with test data
temp_dir = tempfile.mkdtemp()
definition_file = os.path.join(temp_dir, "definitions.yaml")

# Create test definition data matching the nested structure expected by get_unique_algorithms
test_definitions = {
    "point1": {
        "metric1": {
            "algorithm_a": {},
            "algorithm_b": {}
        },
        "metric2": {
            "algorithm_c": {}
        }
    },
    "point2": {
        "metric3": {
            "algorithm_a": {},
            "algorithm_d": {}
        }
    }
}

# Write the YAML file
with open(definition_file, 'w') as f:
    yaml.dump(test_definitions, f)

ARGS = {
    "definition_file": definition_file
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
yaml — 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
instantiate_algorithm Ran
ran; our contract draft was wrong, not the code
maumueller/ann-benchmarks-reproducibility/ann_benchmarks/algorithms/definitions.py
code served (permissive licence) · get_code("a8a893f658ddb978")
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
import importlib
from unittest.mock import Mock

torch.manual_seed(0)

# Create a minimal definition object that has the required attributes:
# - module: string name of a module
# - constructor: string name of a callable in that module
# - arguments: list/tuple of positional arguments to pass to the constructor

definition = Mock()
definition.module = 'os.path'
definition.constructor = 'join'
definition.arguments = ['/tmp', 'file.txt']

ARGS = {
    'definition': definition
}
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
int_parse_entry Ran
ran; our contract draft was wrong, not the code
erikbern/ann-benchmarks/ann_benchmarks/data.py
code served (permissive licence) · get_code("378ed3f6e88f78c2")
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 frozenset. 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 typing import List, Union, Set, FrozenSet

torch.manual_seed(0)

# The function int_parse_entry takes a single parameter 'line' which is a string.
# It strips whitespace, splits by spaces, converts each element to int, and returns a frozenset.
# We need to provide a valid string input that contains space-separated integers.

line = "1 2 3 4 5"

ARGS = {
    "line": line
}
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 frozenset — a frozenset output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a frozenset 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
jaccard Ran
ran; our contract draft was wrong, not the code
erikbern/ann-benchmarks/ann_benchmarks/distance.py
code served (permissive licence) · get_code("df5a5ca06135cc3f")
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 float, 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
from typing import List

# Set seed for reproducibility
torch.manual_seed(0)

# Define test data for the jaccard function
# The function takes two lists of integers and computes Jaccard similarity

# Example 1: Two lists with some overlap
list_a = [1, 2, 3, 4, 5]
list_b = [3, 4, 5, 6, 7]

ARGS = {
    "a": list_a,
    "b": list_b,
}
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 float, 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
norm Ran
ran on a synthesized input
erikbern/ann-benchmarks/ann_benchmarks/distance.py
code served (permissive licence) · get_code("68b87eb6bd321966")
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 float64, ndim 0, 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 numpy as np

# The function 'norm' takes a single parameter 'a' and computes the L2 norm
# It expects an array-like object that supports exponentiation and summation
# We'll pass a numpy array

a = np.array([1.0, 2.0, 3.0, 4.0])

ARGS = {
    "a": a
}
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 float64, ndim 0, dtype family float — no output shape is stated: observe_signature.py recorded float ndim 0, which disagrees with the fixture run
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
train_test_split Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
erikbern/ann-benchmarks/ann_benchmarks/datasets.py
code served (permissive licence) · get_code("762ddcae80faee0b")
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. 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
import numpy as np

# Create a small dataset for testing
# X should be a 2D numpy array with samples as rows
# Using shape (100, 5) - 100 samples with 5 features
X = np.random.randn(100, 5).astype(np.float32)

# Define all arguments for the function
ARGS = {
    'X': X,
    'test_size': 20,
    'dimension': None
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, sklearn — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type list — a list output has no array shape of its own; none is 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
get_dataset_fn Not yet run
unverified (harvested, no recorded run)
erikbern/ann-benchmarks/ann_benchmarks/datasets.py
code served (permissive licence) · get_code("08c7a13d549d2592")
How it ran

no invocation recorded.

load_and_transform_dataset Not yet run
unverified (harvested, no recorded run)
erikbern/ann-benchmarks/ann_benchmarks/runner.py
code served (permissive licence) · get_code("2e5446b131505e9a")
How it ran

no invocation recorded.

Also present in other papers' code

Of 16 samples lifted from this paper's linked repositories, 16 carry a function identity and 0 do not. Of the 16 distinct functions with an identity, 9 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 9 later) and 7 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
algorithm_status 1 other paper
1 later
2409.17424 (2024-09)
Results of the Big ANN: NeurIPS'23 competition
float_parse_entry 1 other paper
1 later
2410.18926 (2024-10)
LoRANN: Low-Rank Matrix Factorization for Approximate Nearest Neighbor Search
float_unparse_entry 1 other paper
1 later
2410.18926 (2024-10)
LoRANN: Low-Rank Matrix Factorization for Approximate Nearest Neighbor Search
get_dataset_fn 1 other paper
1 later
2410.18926 (2024-10)
LoRANN: Low-Rank Matrix Factorization for Approximate Nearest Neighbor Search
get_unique_algorithms 1 other paper
1 later
2409.17424 (2024-09)
Results of the Big ANN: NeurIPS'23 competition
instantiate_algorithm 1 other paper
1 later
2409.17424 (2024-09)
Results of the Big ANN: NeurIPS'23 competition
int_parse_entry 1 other paper
1 later
2410.18926 (2024-10)
LoRANN: Low-Rank Matrix Factorization for Approximate Nearest Neighbor Search
jaccard 1 other paper
1 later
2410.18926 (2024-10)
LoRANN: Low-Rank Matrix Factorization for Approximate Nearest Neighbor Search
train_test_split 1 other paper
1 later
2410.18926 (2024-10)
LoRANN: Low-Rank Matrix Factorization for Approximate Nearest Neighbor Search

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

This paper describes ANN-Benchmarks, a tool for evaluating the performance of in-memory approximate nearest neighbor algorithms. It provides a standard interface for measuring the performance and quality achieved by nearest neighbor algorithms on different standard data sets. It supports several different ways of integrating $k$-NN algorithms, and its configuration system automatically tests a range of parameter settings for each algorithm. Algorithms are compared with respect to many different (approximate) quality measures, and adding more is easy and fast; the included plotting front-ends can visualise these as images, $\LaTeX$ plots, and websites with interactive plots. ANN-Benchmarks aims to provide a constantly updated overview of the current state of the art of $k$-NN algorithms. In the short term, this overview allows users to choose the correct $k$-NN algorithm and parameters for their similarity search task; in the longer term, algorithm designers will be able to use this overview to test and refine automatic parameter tuning. The paper gives an overview of the system, evaluates the results of the benchmark, and points out directions for future work. Interestingly, very different approaches to $k$-NN search yield comparable quality-performance trade-offs. The system is available at http://ann-benchmarks.com .

For agents

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

get_harvested_code_for_paper("1807.05614")
get_code_for_paper("1807.05614")
have("1807.05614")

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

curl https://syntology.ai/api/ran/1807.05614.json

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

[![Syntology run record](https://syntology.ai/api/ran/1807.05614.svg)](https://syntology.ai/paper/1807.05614)

Connect an agent — have() is free.