An occasion to demonstrate Guix for reproducible research

An occasion to demonstrate Guix for reproducible research

[Konrad Hinsen]

Hi Guix,

For those of you working in scientific research, here's an occasion
to show the utility of Guix to the world: the ten-year reproducibility
challenge run by the journal ReScience. You can find the announcement
below.

The main role I see for Guix in this challenge is to ensure
reproducibility for the future, possibly resurrecting old versions of
packages in the process. I proposed two reproduction attempts myself for
this challenge, and I intend to package all dependencies in Guix
and add instructions to my code on how to reproduce it exactly
using "guix time-machine".

Cheers,
  Konrad


Did you ever try to run an old code that you wrote for a scientific
article you published years ago? Did you encounter any problems? Were
you successful? We are curious to hear your story. This is the reason
why we are editing a special issue of ReScience to collect these
stories.

The Ten Years Reproducibility Challenge is an invitation for researchers
to try to run the code they’ve created for a scientific publication that
was published more than ten years ago . This code can be anything
(statistical analysis, numerical simulation, data processing, etc.), can
be written in any language and can address any scientific domain. The
only mandatory condition to enter the challenge is to have published a
scientific article before 2010 , in a journal or a conference with
proceedings, which contains results produced by code, irrespectively of
whether this code was published in some form at the time or not.

Note that we do not ask you to write a new version of your old code. We
ask you instead to try to make your old code to run on modern
hardware/software (with minimal modifications) in order to check if you
can obtain the exact same results that were publised at least ten years
ago.

Sounds easy? We have good reasons to think this might be more difficult
than you think. And maybe the first problem you’ll have to solve is to
find your own source code.

More information at: http://rescience.github.io/ten-years/ 

Re: An occasion to demonstrate Guix for reproducible research

[brettg]

On 24.11.2019 19:53, Konrad Hinsen wrote:
> Hi Guix,
> 
> For those of you working in scientific research, here's an occasion
> to show the utility of Guix to the world: the ten-year reproducibility
> challenge run by the journal ReScience. You can find the announcement
> below.
> 
> The main role I see for Guix in this challenge is to ensure
> reproducibility for the future, possibly resurrecting old versions of
> packages in the process. I proposed two reproduction attempts myself 
> for
> this challenge, and I intend to package all dependencies in Guix
> and add instructions to my code on how to reproduce it exactly
> using "guix time-machine".
> 
> Cheers,
>   Konrad
> 
> 
> Did you ever try to run an old code that you wrote for a scientific
> article you published years ago? Did you encounter any problems? Were
> you successful? We are curious to hear your story. This is the reason
> why we are editing a special issue of ReScience to collect these
> stories.
> 
> The Ten Years Reproducibility Challenge is an invitation for 
> researchers
> to try to run the code they’ve created for a scientific publication 
> that
> was published more than ten years ago . This code can be anything
> (statistical analysis, numerical simulation, data processing, etc.), 
> can
> be written in any language and can address any scientific domain. The
> only mandatory condition to enter the challenge is to have published a
> scientific article before 2010 , in a journal or a conference with
> proceedings, which contains results produced by code, irrespectively of
> whether this code was published in some form at the time or not.
> 
> Note that we do not ask you to write a new version of your old code. We
> ask you instead to try to make your old code to run on modern
> hardware/software (with minimal modifications) in order to check if you
> can obtain the exact same results that were publised at least ten years
> ago.
> 
> Sounds easy? We have good reasons to think this might be more difficult
> than you think. And maybe the first problem you’ll have to solve is to
> find your own source code.
> 
> More information at: http://rescience.github.io/ten-years/


Great share! Thank you!

Brett Gilio