SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1807.10129 · 2018

A Benchmark of Selected Algorithmic Differentiation Tools on Some Problems in Computer Vision and Machine Learning

arXiv · PDF · Open in the Atlas

Code that ran

13 of 13 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 12 have no contract verdict; 1 failure 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/1807.10129.json · badge: /api/ran/1807.10129.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
microsoft/ADBench canonical (classifier label)
classifier basis: classifier_2025
1 ran · 0 no recorded run
awf/ADBench community (classifier label)
classifier basis not recorded on the link
12 ran · 0 no recorded run
FunctionStatusWhere it lives
cap_str Ran
ran on a synthesized input
awf/ADBench/ADBench/utils.py
pointer only (licence: MIT) · get_code("9cefd234c81926f6")
How it ran

The body of this sample is withheld: MIT, as GitHub detects it on this paper's repository, awf/ADBench, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with it. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

filepath_to_basename Ran
ran on a synthesized input
awf/ADBench/src/python/runner/Filepaths.py
pointer only (licence: MIT) · get_code("475acdd13fbe59f5")
How it ran

The body of this sample is withheld: MIT, as GitHub detects it on this paper's repository, awf/ADBench, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with it. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

filepath_to_dirname Ran
ran on a synthesized input
awf/ADBench/src/python/runner/Filepaths.py
pointer only (licence: MIT) · get_code("1b9349bc26fa72ce")
How it ran

The body of this sample is withheld: MIT, as GitHub detects it on this paper's repository, awf/ADBench, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with it. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

find_repeats_for_minimum_measurable_time Ran
ran on a synthesized input
awf/ADBench/src/python/runner/Benchmark.py
pointer only (licence: MIT) · get_code("4ced703c7a310071")
How it ran

The body of this sample is withheld: MIT, as GitHub detects it on this paper's repository, awf/ADBench, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with it. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

get_fn Ran
ran on a synthesized input
awf/ADBench/ADBench/utils.py
pointer only (licence: MIT) · get_code("acc7f1787dc94b66")
How it ran

The body of this sample is withheld: MIT, as GitHub detects it on this paper's repository, awf/ADBench, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with it. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

get_tool Ran
ran on a synthesized input
awf/ADBench/ADBench/utils.py
pointer only (licence: MIT) · get_code("1151cb2d78194e5b")
How it ran

The body of this sample is withheld: MIT, as GitHub detects it on this paper's repository, awf/ADBench, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with it. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

load_matrix Ran
ran on a synthesized input
awf/ADBench/ADBench/check_J.py
pointer only (licence: MIT) · get_code("e9ac370154cec5f8")
How it ran

The body of this sample is withheld: MIT, as GitHub detects it on this paper's repository, awf/ADBench, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with it. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

measure_shortest_time Ran
ran on a synthesized input
awf/ADBench/src/python/runner/Benchmark.py
pointer only (licence: MIT) · get_code("3fdcf207a614916b")
How it ran

The body of this sample is withheld: MIT, as GitHub detects it on this paper's repository, awf/ADBench, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with it. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

module_load Ran
ran on a synthesized input
awf/ADBench/src/python/runner/ModuleLoader.py
pointer only (licence: MIT) · get_code("4f29a61bb2a73796")
How it ran

The body of this sample is withheld: MIT, as GitHub detects it on this paper's repository, awf/ADBench, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with it. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

modulepath_to_basename Ran
ran on a synthesized input
awf/ADBench/src/python/runner/Filepaths.py
pointer only (licence: MIT) · get_code("3bb2c5a077ed30bc")
How it ran

The body of this sample is withheld: MIT, as GitHub detects it on this paper's repository, awf/ADBench, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with it. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

objective_display_name Ran
ran; our contract draft was wrong, not the code
microsoft/ADBench/ADBench/plot_graphs.py
code served (permissive licence) · get_code("74c9da4f6b8b0da0")
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 torch.nn as nn

torch.manual_seed(0)

# The function objective_display_name takes a single parameter 'objective'
# which is a string. It calls .upper() on it, so it must be a string.
# The function returns a transformed version of the string.

objective_value = "lstm"

ARGS = {
    "objective": objective_value
}
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
round_sf Ran
ran on a synthesized input
awf/ADBench/ADBench/check_J.py
pointer only (licence: MIT) · get_code("08deada56461fd30")
How it ran

The body of this sample is withheld: MIT, as GitHub detects it on this paper's repository, awf/ADBench, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with it. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

test_equality Ran
ran on a synthesized input
awf/ADBench/ADBench/check_J.py
pointer only (licence: MIT) · get_code("6696b6fe355729ef")
How it ran

The body of this sample is withheld: MIT, as GitHub detects it on this paper's repository, awf/ADBench, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with it. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

Also present in other papers' code

Of 13 samples lifted from this paper's linked repositories, 13 carry a function identity and 0 do not. Of the 13 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 13 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

Algorithmic differentiation (AD) allows exact computation of derivatives given only an implementation of an objective function. Although many AD tools are available, a proper and efficient implementation of AD methods is not straightforward. The existing tools are often too different to allow for a general test suite. In this paper, we compare fifteen ways of computing derivatives including eleven automatic differentiation tools implementing various methods and written in various languages (C++, F#, MATLAB, Julia and Python), two symbolic differentiation tools, finite differences, and hand-derived computation. We look at three objective functions from computer vision and machine learning. These objectives are for the most part simple, in the sense that no iterative loops are involved, and conditional statements are encapsulated in functions such as {\tt abs} or {\tt logsumexp}. However, it is important for the success of algorithmic differentiation that such `simple' objective functions are handled efficiently, as so many problems in computer vision and machine learning are of this form. Of course, our results depend on programmer skill, and familiarity with the tools. However, we contend that this paper presents an important datapoint: a skilled programmer devoting roughly a week to each tool produced the timings we present. We have made our implementations available as open source to allow the community to replicate and update these benchmarks.

For agents

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

get_harvested_code_for_paper("1807.10129")
get_code_for_paper("1807.10129")
have("1807.10129")

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

curl https://syntology.ai/api/ran/1807.10129.json

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

[![Syntology run record](https://syntology.ai/api/ran/1807.10129.svg)](https://syntology.ai/paper/1807.10129)

Connect an agent — have() is free.