diff options
| -rw-r--r-- | paper.tex | 1000 | ||||
| -rwxr-xr-x | project | 8 | ||||
| -rw-r--r-- | reproduce/analysis/make/paper.mk | 17 | ||||
| -rw-r--r-- | reproduce/software/config/texlive-packages.conf | 3 | ||||
| -rw-r--r-- | tex/src/preamble-biblatex.tex | 145 | ||||
| -rw-r--r-- | tex/src/preamble-project.tex | 19 | ||||
| -rw-r--r-- | tex/src/preamble-style.tex | 156 | ||||
| -rw-r--r-- | tex/src/references.tex | 10 |
8 files changed, 1044 insertions, 314 deletions
@@ -19,7 +19,7 @@ %% you need to distribute drafts that is undergoing revision and you want %% to highlight to your colleagues which parts are new and which parts are %% only for discussion. -%\newcommand{\highlightchanges}{} +\newcommand{\highlightchanges}{} %% Import necessary packages \input{tex/build/macros/project.tex} @@ -274,7 +274,7 @@ This allows accurate post-publication provenance \emph{and} automatic updates to Through the latter, manual updates by authors are by-passed, which are prone to errors, thus discouraging improvements after writing the first draft. Acting as a link, the macro files build the core skeleton of Maneage. -For example, during the software building phase, each software package is identified by a \LaTeX{} file, containing its official name, version and possible citation.. +For example, during the software building phase, each software package is identified by a \LaTeX{} file, containing its official name, version and possible citation.. These are combined at the end to generate precise software acknowledgment and citation (see \cite{akhlaghi19, infante20}), which are excluded here because of the strict word limit. Furthermore, machine related specifications including hardware name and byte-order are also collected and cited, as a reference point if they were needed for \emph{root cause analysis} of observed differences/issues in the execution of the wokflow on different machines. The macro files also act as Make \emph{targets} and \emph{prerequisites} to allow accurate dependency tracking and optimized execution (in parallel, no redundancies), for any level of complexity (e.g., Maneage builds Matplotlib if requested; see Figure~1 of \cite{alliez19}). @@ -532,7 +532,7 @@ The Pozna\'n Supercomputing and Networking Center (PSNC) computational grant 314 -%% Bibliography +%% Bibliography of main body \bibliographystyle{IEEEtran_openaccess} \bibliography{IEEEabrv,references} @@ -575,6 +575,1000 @@ The Pozna\'n Supercomputing and Networking Center (PSNC) computational grant 314 Contact him at rbaena@iac.es. \end{IEEEbiographynophoto} \vfill + + + + + + + + + + + + + + + + + + + + +%% Appendix (only build if 'noappendix' has not been given). So in default, +%% the appendix is built. +\ifdefined\noappendix +\else +\newpage +\appendices +\section{Survey of existing tools for various phases} +\label{appendix:existingtools} + +Computational workflows are commonly high-level tools which employ various lower-level components to acheive their goal. +To help in analysing existing reproducible workflow solutions in the next appendix, the most commonly employed lower-level tools are surveyed with a focus on reproducibility and the proposed criteria. + +\subsection{Independent environment} +\label{appendix:independentenvironment} + +The lowest-level challenge of any reproducible solution is to avoid the differences between systems that are running it. +For example a differing operating system, different versions of installed components, and etc. +Any reasonable attempt at providing a reproducible workflow therefore has to star with a way to isolate its running envionment from the host. +There are three general technologies that are used by workflow solutions: 1) Virtual machines, 2) Containers, 3) Controlled build and environment. +Below, a short description of each solution is provided. + +\subsubsection{Virtual machines} +\label{appendix:virtualmachines} +Virtual machines (VMs) keep a copy of a full operating system that can be run on other operating systems. +This includes the lowest-level kernel which connects to the hardware. +VMs thus provide the ultimate control one can have over the run-time environment of an analysis. +However, the VM's kernel does not talk directly to the hardware that is doing the analysis, it talks to a simulated hardware that is provided by the operating system's kernel. +Therefore, a process that is run inside a virtual machine can be much slower than one that is run on a native kernel. +VMs are used by cloud providers, enabling them to sell fully independent operating systems on their large servers, to their customers (where the customer can have root access). +But because of all the overhead, they aren't used often used for reproducing individual processes. + +\subsubsection{Containers} +Containers are higher-level constructs that don't have their own kernel, they talk directly with the host operating system kernel, but have their own independent software for everything else. +Therefore, they have much less overhead in storage, and hardware/CPU access. +Users often choose an operating system for the container's independent operating system (most commonly GNU/Linux distributions which are free software). + +Below we'll review some of the most common container solutions: Docker and Singularity. + +\begin{itemize} +\item {\bf\small Docker containers:} Docker is one of the most popular tools today for keeping an independent analysis environment. + It is primarily driven by the need of software developers: they need to be able to reproduce a bug on the ``cloud'' (which is just a remote VM), where they have root access. + A Docker container is composed of independent Docker ``images'' that are built with Dockerfiles. + It is possible to precisely version/tag the images that are imported (to avoid downloading the latest/different version in a future build). + To have a reproducible Docker image, it must be ensured that all the imported Docker images check their dependency tags down to the initial image which contains the C library. + + Another important drawback of Docker for scientific applications is that it runs as a daemon (a program that is always running in the background) with root permissions. + This is a major security flaw that discourages many high performance computing (HPC) facilities from installing it. + +\item {\bf\small Singularity:} Singularity is a single-image container (unlike Docker which is composed of modular/independent images). + Although it needs root permissions to be installed on the system (once), it doesn't require root permissions every time it is run. + Its main program is also not a daemon, but a normal program that can be stopped. + These features make it much easier for HPC administrators to install Docker. + However, the fact that it requires root access for initial install is still a hindrance for a random project: if its not present on the HPC, the project can't be run as a normal user. + +\item {\bf\small Virtualenv:} \tonote{Discuss it later.} +\end{itemize} + +When the installed software within VMs or containers is precisely under control, they are good solutions to reproducibly ``running''/repeating an analysis. +However, because they store the already-built software environment, they are not good for ``studying'' the analysis (how the environment was built). +Currently, the most common practice to install software within containers is to use the package manager of the operating system within the image, usually a minimal Debian-based GNU/Linux operating system. +For example the Dockerfile\footnote{\url{https://github.com/benmarwick/1989-excavation-report-Madjedbebe/blob/master/Dockerfile}} in the reproducible scripts of \citeappendix{clarkso15}, which uses \inlinecode{sudo apt-get install r-cran-rjags -y} to install the R interface to the JAGS Bayesian statistics (rjags). +However, the operating system package managers aren't static. +Therefore the versions of the downloaded and used tools within the Docker image will change depending when it was built. +At the time \citeappendix{clarkso15} was published (June 2015), the \inlinecode{apt} command above would download and install rjags 3-15, but today (January 2020), it will install rjags 4-10. +Such problems can be corrected with robust/reproducible package managers like Nix or GNU Guix within the docker image (see Appendix \ref{appendix:packagemanagement}), but this is rarely practiced today. + +\subsubsection{Package managers} +\label{appendix:packagemanagersinenv} +The virtual machine and container solutions mentioned above, install software in standard Unix locations (for example \inlinecode{/usr/bin}), but in their own independent operating systems. +But if software are built in, and used from, a non-standard, project specific directory, we can have an independent build and run-time environment without needing root access, or the extra layers of the container or VM. +This leads us to the final method of having an independent environment: a controlled build of the software and its run-time environment. +Because this is highly intertwined with the way software are installed, we'll describe it in more detail in Section \ref{appendix:packagemanagement} where package managers are reviewed. + + + + + +\subsection{Package management} +\label{appendix:packagemanagement} + +Package management is the process of automating the installation of software. +A package manager thus contains the following information on each software package that can be run automatically: the URL of the software's tarball, the other software that it possibly depends on, and how to configure and build it. + +Here some of package management solutions that are used by the reviewed reproducibility solutions of Appendix \ref{appendix:existingsolutions} are reviewed\footnote{For a list of existing package managers, please see \url{https://en.wikipedia.org/wiki/List_of_software_package_management_systems}}. +Note that we are not including package manager that are only limited to one language, for example \inlinecode{pip} (for Python) or \inlinecode{tlmgr} (for \LaTeX). + + + +\subsubsection{Operating system's package manager} +The most commonly used package managers are those of the host operating system, for example \inlinecode{apt} or \inlinecode{yum} respectively on Debian-based, or RedHat-based GNU/Linux operating systems (among many others). + +These package managers are tightly intertwined with the operating system. +Therefore they require root access, and arbitrary control (for different projects) of the versions and configuration options of software within them is not trivial/possible: for example a special version of a software that may be necessary for a project, may conflict with an operating system component, or another project. +Furthermore, in many operating systems it is only possible to have one version of a software at any moment (no including Nix or GNU Guix which can also be independent of the operating system, described below). +Hence if two projects need different versions of a software, it is not possible to work on them at the same time. + +When a full container or virtual machine (see Appendix \ref{appendix:independentenvironment}) is used for each project, it is common for projects to use the containerized operating system's package manager. +However, it is important to remember that operating system package managers are not static: software are updated on their servers. +For example, simply adding \inlinecode{apt install gcc} to a \inlinecode{Dockerfile} will install different versions of GCC based on when the Docker image is created. +Requesting a special version also doesn't fully address the problem because the package managers also download and install its dependencies. +Hence a fixed version of the dependencies must also be included. + +In summary, these package managers are primarily meant for the operating system components. +Hence, many robust reproducible analysis solutions (reviewed in Appendix \ref{appendix:existingsolutions}) don't use the host's package manager, but an independent package manager, like the ones below. + +\subsubsection{Conda/Anaconda} +\label{appendix:conda} +Conda is an independent package manager that can be used on GNU/Linux, macOS, or Windows operating systems, although all software packages are not available in all operating systems. +Conda is able to maintain an approximately independent environment on an operating system without requiring root access. + +Conda tracks the dependencies of a package/environment through a YAML formatted file, where the necessary software and their acceptable versions are listed. +However, it is not possible to fix the versions of the dependencies through the YAML files alone. +This is thoroughly discussed under issue 787 (in May 2019) of \inlinecode{conda-forge}\footnote{\url{https://github.com/conda-forge/conda-forge.github.io/issues/787}}. +In that discussion, the authors of \citeappendix{uhse19} report that the half-life of their environment (defined in a YAML file) is 3 months, and that at least one of their their dependencies breaks shortly after this period. +The main reply they got in the discussion is to build the Conda environment in a container, which is also the suggested solution by \citeappendix{gruning18}. +However, as described in Appendix \ref{appendix:independentenvironment} containers just hide the reproducibility problem, they don't fix it: containers aren't static and need to evolve (i.e., re-built) with the project. +Given these limitations, \citeappendix{uhse19} are forced to host their conda-packaged software as tarballs on a separate repository. + +Conda installs with a shell script that contains a binary-blob (+500 mega bytes, embedded in the shell script). +This is the first major issue with Conda: from the shell script, it is not clear what is in this binary blob and what it does. +After installing Conda in any location, users can easily activate that environment by loading a special shell script into their shell. +However, the resulting environment is not fully independent of the host operating system as described below: + +\begin{itemize} +\item The Conda installation directory is present at the start of environment variables like \inlinecode{PATH} (which is used to find programs to run) and other such environment variables. + However, the host operating system's directories are also appended afterwards. + Therefore, a user, or script may not notice that a software that is being used is actually coming from the operating system, not the controlled Conda installation. + +\item Generally, by default Conda relies heavily on the operating system and doesn't include core analysis components like \inlinecode{mkdir}, \inlinecode{ls} or \inlinecode{cp}. + Although they are generally the same between different Unix-like operating systems, they have their differences. + For example \inlinecode{mkdir -p} is a common way to build directories, but this option is only available with GNU Coreutils (default on GNU/Linux systems). + Running the same command within a Conda environment on a macOS for example, will crash. + Important packages like GNU Coreutils are available in channels like conda-forge, but they are not the default. + Therefore, many users may not recognize this, and failing to account for it, will cause unexpected crashes. + +\item Many major Conda packaging ``channels'' (for example the core Anaconda channel, or very popular conda-forge channel) don't include the C library, that a package was built with, as a dependency. + They rely on the host operating system's C library. + C is the core language of most modern operating systems and even higher-level languages like Python or R are written in it, and need it to run. + Therefore if the host operating system's C library is different from the C library that a package was built with, a Conda-packaged program will crash and the project will not be executable. + Theoretically, it is possible to define a new Conda ``channel'' which includes the C library as a dependency of its software packages, but it will take too much time for any individual team to practically implement all their necessary packages, up to their high-level science software. + +\item Conda does allow a package to depend on a special build of its prerequisites (specified by a checksum, fixing its version and the version of its dependencies). + However, this is rarely practiced in the main Git repositories of channels like Anaconda and conda-forge: only the name of the high-level prerequisite packages is listed in a package's \inlinecode{meta.yaml} file, which is version-controlled. + Therefore two builds of the package from the same Git repository will result in different tarballs (depending on what prerequisites were present at build time). + In the Conda tarball (that contains the binaries and is not under version control) \inlinecode{meta.yaml} does include the exact versions of most build-time dependencies. + However, because the different software of one project may have been built at different times, if they depend on different versions of a single software there will be a conflict and the tarball can't be rebuilt, or the project can't be run. +\end{itemize} + +As reviewed above, the low-level dependence of Conda on the host operating system's components and build-time conditions, is the primary reason that it is very fast to install (thus making it an attractive tool to software developers who just need to reproduce a bug in a few minutes). +However, these same factors are major caveats in a scientific scenario, where long-term archivability, readability or usability are important. % alternative to `archivability`? + + + +\subsubsection{Nix or GNU Guix} +\label{appendix:nixguix} +Nix \citeappendix{dolstra04} and GNU Guix \citeappendix{courtes15} are independent package managers that can be installed and used on GNU/Linux operating systems, and macOS (only for Nix, prior to macOS Catalina). +Both also have a fully functioning operating system based on their packages: NixOS and ``Guix System''. +GNU Guix is based on Nix, so we'll focus the review here on Nix. + +The Nix approach to package management is unique in that it allows exact dependency tracking of all the dependencies, and allows for multiple versions of a software, for more details see \citeappendix{dolstra04}. +In summary, a unique hash is created from all the components that go into the building of the package. +That hash is then prefixed to the software's installation directory. +For example \citeappendix[from][]{dolstra04} if a certain build of GNU C Library 2.3.2 has a hash of \inlinecode{8d013ea878d0}, then it is installed under \inlinecode{/nix/store/8d013ea878d0-glibc-2.3.2} and all software that are compiled with it (and thus need it to run) will link to this unique address. +This allows for multiple versions of the software to co-exist on the system, while keeping an accurate dependency tree. + +As mentioned in \citeappendix{courtes15}, one major caveat with using these package managers is that they require a daemon with root privileges. +This is necessary ``to use the Linux kernel container facilities that allow it to isolate build processes and maximize build reproducibility''. + +\tonote{While inspecting the Guix build instructions for some software, I noticed they don't actually mention the version names. This creates a similar issue withe Conda example above (how to regenerate the software with a given hash, given that its dependency versions aren't explicitly mentioned. Ask Ludo' about this.} + + +\subsubsection{Spack} +Spack is a package manager that is also influenced by Nix (similar to GNU Guix), see \citeappendix{gamblin15}. + But unlike Nix or GNU Guix, it doesn't aim for full, bit-wise reproducibility and can be built without root access in any generic location. + It relies on the host operating system for the C library. + + Spack is fully written in Python, where each software package is an instance of a class, which defines how it should be downloaded, configured, built and installed. + Therefore if the proper version of Python is not present, Spack cannot be used and when incompatibilities arise in future versions of Python (similar to how Python 3 is not compatible with Python 2), software building recipes, or the whole system, have to be upgraded. + Because of such bootstrapping problems (for example how Spack needs Python to build Python and other software), it is generally a good practice to use simpler, lower-level languages/systems for a low-level operation like package management. + + +\subsection{Package management conclusion} +There are two common issues regarding generic package managers that hinders their usage for high-level scientific projects, as listed below: +\begin{itemize} +\item {\bf\small Pre-compiled/binary downloads:} Most package managers (excluding Nix or its derivatives) only download the software in a binary (pre-compiled) format. + This allows users to download it very fast and almost instantaneously be able to run it. + However, to provide for this, servers need to keep binary files for each build of the software on different operating systems (for example Conda needs to keep binaries for Windows, macOS and GNU/Linux operating systems). + It is also necessary for them to store binaries for each build, which includes different versions of its dependencies. + This will take major space on the servers, therefore once the shelf-life of a binary has expired, it will not be easy to reproduce a project that depends on it . + + For example Debian's Long Term Support is only valid for 5 years. + Pre-built binaries of the ``Stable'' branch will only be kept during this period and this branch only gets updated once every two years. + However, scientific software commonly evolve on much faster rates. + Therefore scientific projects using Debian often use the ``Testing'' branch which has more up to date features. + The problem is that binaries on the Testing branch are immediately removed when no other package depends on it, and a newer version is available. + This is not limited to operating systems, similar problems are also reported in Conda for example, see the discussion of Conda above for one real-world example. + + +\item {\bf\small Adding high-level software:} Packaging new software is not trivial and needs a good level of knowledge/experience with that package manager. +For example each has its own special syntax/standards/languages, with pre-defined variables that must already be known to someone packaging new software. +However, in many scenarios, the most high-level software of a research project are written and used only by the team that is doing the research, even when they are distributed with free licenses on open repositories. +Although active package manager members are commonly very supportive in helping to package new software, many teams may not take that extra effort/time. +They will thus manually install their high-level software in an uncontrolled, or non-standard way, thus jeopardizing the reproducibility of the whole work. + +\item {\bf\small Built for a generic scenario} All the package managers above are built for one full system, that can possibly be run by multiple projects. + This can result in not fully documenting the process that each package was built (for example the versions of the dependent libraries of a package). +\end{itemize} + +Addressing these issues has been the basic reason d'\^etre of the proposed template's approach to package management strategy: instructions to download and build the packages are included within the actual science project (thus fully customizable) and no special/new syntax/language is used: software download, building and installation is done with the same language/syntax that researchers manage their research: using the shell (GNU Bash) and Make (GNU Make). + + + +\subsection{Version control} +\label{appendix:versioncontrol} +A scientific project is not written in a day. +It commonly takes more than a year (for example a PhD project is 3 or 4 years). +During this time, the project evolves significantly from its first starting date and components are added or updated constantly as it approaches completion. +Added with the complexity of modern projects, is not trivial to manually track this evolution, and its affect of on the final output: files produced in one stage of the project may be used at later stages (where the project has evolved). +Furthermore, scientific projects do not progress linearly: earlier stages of the analysis are often modified after later stages are written. +This is a natural consequence of the scientific method; where progress is defined by experimentation and modification of hypotheses (earlier phases). + +It is thus very important for the integrity of a scientific project that the state/version of its processing is recorded as the project evolves for example better methods are found or more data arrive. +Any intermediate dataset that is produced should also be tagged with the version of the project at the time it was created. +In this way, later processing stages can make sure that they can safely be used, i.e., no change has been made in their processing steps. + +Solutions to keep track of a project's history have existed since the early days of software engineering in the 1970s and they have constantly improved over the last decades. +Today the distributed model of ``version control'' is the most common, where the full history of the project is stored locally on different systems and can easily be integrated. +There are many existing version control solutions, for example CVS, SVN, Mercurial, GNU Bazaar, or GNU Arch. +However, currently, Git is by far the most commonly used in individual projects and long term archival systems like Software Heritage \citeappendix{dicosmo18}, it is also the system that is used in the proposed template, so we'll only review it here. + +\subsubsection{Git} +With Git, changes in a project's contents are accurately identified by comparing them with their previous version in the archived Git repository. +When the user decides the changes are significant compared to the archived state, they can ``commit'' the changes into the history/repository. +The commit involves copying the changed files into the repository and calculating a 40 character checksum/hash that is calculated from the files, an accompanying ``message'' (a narrative description of the project's state), and the previous commit (thus creating a ``chain'' of commits that are strongly connected to each other). +For example \inlinecode{f4953cc\-f1ca8a\-33616ad\-602ddf\-4cd189\-c2eff97b} is a commit identifier in the Git history that this paper is being written in. +Commits are is commonly summarized by the checksum's first few characters, for example \inlinecode{f4953cc}. + +With Git, making parallel ``branches'' (in the project's history) is very easy and its distributed nature greatly helps in the parallel development of a project by a team. +The team can host the Git history on a webpage and collaborate through that. +There are several Git hosting services for example \href{http://github.com}{github.com}, \href{http://gitlab.com}{gitlab.com}, or \href{http://bitbucket.org}{bitbucket.org} (among many others). + + + + + +\subsection{Job management} +\label{appendix:jobmanagement} +Any analysis will involve more than one logical step. +For example it is first necessary to download a dataset, then to do some preparations on it, then to actually use it, and finally to make visualizations/tables that can be imported into the final report. +Each one of these is a logically independent step which needs to be run before/after the others in a specific order. +There are many tools for managing the sequence of jobs, below we'll review the most common ones that are also used in the proposed template, or the existing reproducibility solutions of Appendix \ref{appendix:existingsolutions}. + +\subsubsection{Scripts} +\label{appendix:scripts} +Scripts (in any language, for example GNU Bash, or Python) are the most common ways of organizing a series of steps. +They are primarily designed execute each step sequentially (one after another), making them also very intuitive. +However, as the series of operations become complex and large, managing the workflow in a script will become highly complex. +For example if 90\% of a long project is already done and a researcher wants to add a followup step, a script will go through all the previous steps (which can take significant time). +Also, if a small step in the middle of an analysis has to be changed, the full analysis needs to be re-run: scripts have no concept of dependencies (so only the steps that are affected by that change are run). +Such factors discourage experimentation, which is a critical component of the scientific method. +It is possible to manually add conditionals all over the script to add dependencies, but they just make it harder to read, and introduce many bugs themselves. +Parallelization is another drawback of using scripts. +While its not impossible, because of the high-level nature of scripts, it is not trivial and parallelization can also be very inefficient or buggy. + + +\subsubsection{Make} +\label{appendix:make} +Make was originally designed to address the problems mentioned in Appendix \ref{appendix:scripts} for scripts \citeappendix{feldman79}. +In particular this motivation arose from management issues related to program compilation with many source code files. +With Make, the various source files of a program that haven't been changed, wouldn't be recompiled. +Also, when two source files didn't depend on each other, and both needed to be rebuilt, they could be built in parallel. +This greatly helped in debugging of software projects, and speeding up test builds, giving Make a core place in software building tools since then. +The most common implementation of Make, since the early 1990s, is GNU Make \citeappendix[\url{http://www.gnu.org/s/make}]{stallman88}. +The proposed solution uses Make to organize its workflow, see Section \ref{sec:usingmake}. +Here, we'll complement that section with more technical details on Make. + +Usually, the top-level Make instructions are placed in a file called Makefile, but it is also common to use the \inlinecode{.mk} suffix for custom file names. +Each stage/step in the analysis is defined through a \emph{rule}. +Rules define \emph{recipes} to build \emph{targets} from \emph{pre-requisites}. +In POSIX operating systems (Unix-like), everything is a file, even directories and devices. +Therefore all three components in a rule must be files on the running filesystem. +Figure \ref{fig:makeexample} demonstrates a hypothetical Makefile with the targets, prerequisites and recipes highlighted. + +To decide which operation should be re-done when executed, Make compares the time stamp of the targets and prerequisites. +When any of the prerequisite(s) is newer than a target, the recipe is re-run to re-build the target. +When all the prerequisites are older than the target, that target doesn't need to be rebuilt. +The recipe can contain any number of commands, they should just all start with a \inlinecode{TAB}. +Going deeper into the syntax of Make is beyond the scope of this paper, but we recommend interested readers to consult the GNU Make manual\footnote{\url{http://www.gnu.org/software/make/manual/make.pdf}}. + +\subsubsection{SCons} +Scons (\url{https://scons.org}) is a Python package for managing operations outside of Python (in contrast to CGAT-core, discussed below, which only organizes Python functions). +In many aspects it is similar to Make, for example it is managed through a `SConstruct' file. +Like a Makefile, SConstruct is also declarative: the running order is not necessarily the top-to-bottom order of the written operations within the file (unlike the imperative paradigm which is common in languages like C, Python, or FORTRAN). +However, unlike Make, SCons doesn't use the file modification date to decide if it should be remade. +SCons keeps the MD5 hash of all the files (in a hidden binary file) to check if the contents has changed. + +SCons thus attempts to work on a declarative file with an imperative language (Python). +It also goes beyond raw job management and attempts to extract information from within the files (for example to identify the libraries that must be linked while compiling a program). +SCons is therefore more complex than Make: its manual is almost double that of GNU Make. +Besides added complexity, all these ``smart'' features decrease its performance, especially as files get larger and more numerous: on every call, every file's checksum has to be calculated, and a Python system call has to be made (which is computationally expensive). + +Finally, it has the same drawback as any other tool that uses high-level languages, see Section \ref{appendix:highlevelinworkflow}. +We encountered such a problem while testing SCons: on the Debian-10 testing system, the \inlinecode{python} program pointed to Python 2. +However, since Python 2 is now obsolete, SCons was built with Python 3 and our first run crashed. +To fix it, we had to either manually change the core operating system path, or the SCons source hashbang. +The former will conflict with other system tools that assume \inlinecode{python} points to Python-2, the latter may need root permissions for some systems. +This can also be problematic when a Python analysis library, may require a Python version that conflicts with the running SCons. + +\subsubsection{CGAT-core} +CGAT-Core (\url{https://cgat-core.readthedocs.io/en/latest}) is a Python package for managing workflows, see \citeappendix{cribbs19}. +It wraps analysis steps in Python functions and uses Python decorators to track the dependencies between tasks. +It is used papers like \citeappendix{jones19}, but as mentioned in \citeappendix{jones19} it is good for managing individual outputs (for example separate figures/tables in the paper, when they are fully created within Python). +Because it is primarily designed for Python tasks, managing a full workflow (which includes many more components, written in other languages) is not trivial in it. +Another drawback with this workflow manager is that Python is a very high-level language where future versions of the language may no longer be compatible with Python 3, that CGAT-core is implemented in (similar to how Python 2 programs are not compatible with Python 3). + +\subsubsection{Guix Workflow Language (GWL)} +GWL (\url{https://www.guixwl.org}) GWL is based on the declarative language that GNU Guix uses for package management (see Appendix \ref{appendix:packagemanagement}), which is itself based on the general purpose Scheme language. +It is closely linked with GNU Guix and can even install the necessary software needed for each individual process. +Hence in the GWL paradigm, software installation and usage doesn't have to be separated. +GWL has two high-level concepts called ``processes'' and ``workflows'' where the latter defines how multiple processes should be executed together. + +As described above shell scripts and Make are a common and highly used system that have existed for several decades and many researchers are already familiar with them and have already used them. +The list of necessary software solutions for the various stages of a research project (listed in the subsections of Appendix \ref{appendix:existingtools}), is already very large, and each software has its own learning curve (which is a heavy burden for a natural or social scientist for example). +The other workflow management tools are too specific to a special paradigm, for example CGAT-core is written for Python, or GWL is intertwined with GNU Guix. +Therefore their generalization into any kind of problem is not trivial. + +Also, high-level and specific solutions will evolve very fast, for example the Popper solution to reproducible research (see Appendix \ref{appendix:popper}) organized its workflow through the HashiCorp configuration language (HCL) because it was the default in GitHub. +However, in September 2019, GitHub dropped HCL as its default configuration language and is now using its own custom YAML-based language. +Using such high-level, or provider-specific solutions also has the problem that it makes them hard, or impossible, to use in any generic system. +Therefore a robust solution would avoid designing their low-level processing steps in these languages and only use them for the highest-level layer of their project, depending on which provider they want to run their project on. + + + +\subsection{Editing steps and viewing results} +\label{appendix:editors} +In order to later reproduce a project, the analysis steps must be stored in files. +For example Shell, Python or R scripts, Makefiles, Dockerfiles, or even the source files of compiled languages like C or FORTRAN. +Given that a scientific project does not evolve linearly and many edits are needed as it evolves, it is important to be able to actively test the analysis steps while writing the project's source files. +Here we'll review some common methods that are currently used. + +\subsubsection{Text editors} +The most basic way to edit text files is through simple text editors which just allow viewing and editing such files, for example \inlinecode{gedit} on the GNOME graphic user interface. +However, working with simple plain text editors like \inlinecode{gedit} can be very frustrating since its necessary to save the file, then go to a terminal emulator and execute the source files. +To solve this problem there are advanced text editors like GNU Emacs that allow direct execution of the script, or access to a terminal within the text editor. +However, editors that can execute or debug the source (like GNU Emacs), just run external programs for these jobs (for example GNU GCC, or GNU GDB), just as if those programs was called from outside the editor. + +With text editors, the final edited file is independent of the actual editor and can be further edited with another editor, or executed without it. +This is a very important feature that is not commonly present for other solutions mentioned below. +Another very important advantage of advanced text editors like GNU Emacs or Vi(m) is that they can also be run without a graphic user interface, directly on the command-line. +This feature is critical when working on remote systems, in particular high performance computing (HPC) facilities that don't provide a graphic user interface. + +\subsubsection{Integrated Development Environments (IDEs)} +To facilitate the development of source files, IDEs add software building and running environments as well as debugging tools to a plain text editor. +Many IDEs have their own compilers and debuggers, hence source files that are maintained in IDEs are not necessarily usable/portable on other systems. +Furthermore, they usually require a graphic user interface to run. +In summary IDEs are generally very specialized tools, for special projects and are not a good solution when portability (the ability to run on different systems) is required. + +\subsubsection{Jupyter} +Jupyter \citeappendix[initially IPython,][]{kluyver16} is an implementation of Literate Programming \citeappendix{knuth84}. +The main user interface is a web-based ``notebook'' that contains blobs of executable code and narrative. +Jupyter uses the custom built \inlinecode{.ipynb} format\footnote{\url{https://nbformat.readthedocs.io/en/latest}}. +Jupyter's name is a combination of the three main languages it was designed for: Julia, Python and R. +The \inlinecode{.ipynb} format, is a simple, human-readable (can be opened in a plain-text editor) file, formatted in JavaScript Object Notation (JSON). +It contains various kinds of ``cells'', or blobs, that can contain narrative description, code, or multi-media visualizations (for example images/plots), that are all stored in one file. +The cells can have any order, allowing the creation of a literal programming style graphical implementation, where narrative descriptions and executable patches of code can be intertwined. +For example to have a paragraph of text about a patch of code, and run that patch immediately in the same page. + +The \inlinecode{.ipynb} format does theoretically allow dependency tracking between cells, see IPython mailing list (discussion started by Gabriel Becker from July 2013\footnote{\url{https://mail.python.org/pipermail/ipython-dev/2013-July/010725.html}}). +Defining dependencies between the cells can allow non-linear execution which is critical for large scale (thousands of files) and complex (many dependencies between the cells) operations. +It allows automation, run-time optimization (deciding not to run a cell if its not necessary) and parallelization. +However, Jupyter currently only supports a linear run of the cells: always from the start to the end. +It is possible to manually execute only one cell, but the previous/next cells that may depend on it, also have to be manually run (a common source of human error, and frustration for complex operations). +Integration of directional graph features (dependencies between the cells) into Jupyter has been discussed, but as of this publication, there is no plan to implement it (see Jupyter's GitHub issue 1175\footnote{\url{https://github.com/jupyter/notebook/issues/1175}}). + +The fact that the \inlinecode{.ipynb} format stores narrative text, code and multi-media visualization of the outputs in one file, is another major hurdle: +The files can easy become very large (in volume/bytes) and hard to read from source. +Both are critical for scientific processing, especially the latter: when a web-browser with proper JavaScript features isn't available (can happen in a few years). +This is further exacerbated by the fact that binary data (for example images) are not directly supported in JSON and have to be converted into much less memory-efficient textual encodings. + +Finally, Jupyter has an extremely complex dependency graph: on a clean Debian 10 system, Pip (a Python package manager that is necessary for installing Jupyter) required 19 dependencies to install, and installing Jupyter within Pip needed 41 dependencies! +\citeappendix{hinsen15} reported such conflicts when building Jupyter into the Active Papers framework (see Appendix \ref{appendix:activepapers}). +However, the dependencies above are only on the server-side. +Since Jupyter is a web-based system, it requires many dependencies on the viewing/running browser also (for example special JavaScript or HTML5 features, which evolve very fast). +As discussed in Appendix \ref{appendix:highlevelinworkflow} having so many dependencies is a major caveat for any system regarding scientific/long-term reproducibility (as opposed to industrial/immediate reproducibility). +In summary, Jupyter is most useful in manual, interactive and graphical operations for temporary operations (for example educational tutorials). + + + + + + +\subsection{Project management in high-level languages} +\label{appendix:highlevelinworkflow} + +Currently the most popular high-level data analysis language is Python. +R is closely tracking it, and has superseded Python in some fields, while Julia \citeappendix[with its much better performance compared to R and Python, in a high-level structure, see][]{bezanson17} is quickly gaining ground. +These languages have themselves superseded previously popular languages for data analysis of the previous decades, for example Java, Perl or C++. +All are part of the C-family programming languages. +In many cases, this means that the tools to use that language are written in C, which is the language of the operating system. + +Scientists, or data analysts, mostly use these higher-level languages. +Therefore they are naturally drawn to also apply the higher-level languages for lower-level project management, or designing the various stages of their workflow. +For example Conda or Spack (Appendix \ref{appendix:packagemanagement}), CGAT-core (Appendix \ref{appendix:jobmanagement}), Jupyter (Appendix \ref{appendix:editors}) or Popper (Appendix \ref{appendix:popper}) are written in Python. +The discussion below applies to both the actual analysis software and project management software. +In this context, its more focused on the latter. + +Because of their nature, higher-level languages evolve very fast, creating incompatibilities on the way. +The most prominent example is the transition from Python 2 (released in 2000) to Python 3 (released in 2008). +Python 3 was incompatible with Python 2 and it was decided to abandon the former by 2015. +However, due to community pressure, this was delayed to January 1st, 2020. +The end-of-life of Python 2 caused many problems for projects that had invested heavily in Python 2: all their previous work had to be translated, for example see \citeappendix{jenness17} or Appendix \ref{appendix:sciunit}. +Some projects couldn't make this investment and their developers decided to stop maintaining it, for example VisTrails (see Appendix \ref{appendix:vistrails}). + +The problems weren't just limited to translation. +Python 2 was still actively being actively used during the transition period (and is still being used by some, after its end-of-life). +Therefore, developers of packages used by others had to maintain (for example fix bugs in) both versions in one package. +This isn't particular to Python, a similar evolution occurred in Perl: in 2000 it was decided to improve Perl 5, but the proposed Perl 6 was incompatible with it. +However, the Perl community decided not to abandon Perl 5, and Perl 6 was eventually defined as a new language that is now officially called ``Raku'' (\url{https://raku.org}). + +It is unreasonably optimistic to assume that high-level languages won't undergo similar incompatible evolutions in the (not too distant) future. +For software developers, this isn't a problem at all: non-scientific software, and the general population's usage of them, evolves extremely fast and it is rarely (if ever) necessary to look into codes that are more than a couple of years old. +However, in the sciences (which are commonly funded by public money) this is a major caveat for the longer-term usability of solutions that are designed. + +In summary, in this section we are discussing the bootstrapping problem as regards scientific projects: the workflow/pipeline can reproduce the analysis and its dependencies, but the dependencies of the workflow itself cannot not be ignored. +The most robust way to address this problem is with a workflow management system that ideally doesn't need any major dependencies: tools that are already part of the operating system. + +Beyond technical, low-level, problems for the developers mentioned above, this causes major problems for scientific project management as listed below: + +\subsubsection{Dependency hell} +The evolution of high-level languages is extremely fast, even within one version. +For example packages that are written in Python 3 often only work with a special interval of Python 3 versions (for example newer than Python 3.6). +This isn't just limited to the core language, much faster changes occur in their higher-level libraries. +For example version 1.9 of Numpy (Python's numerical analysis module) discontinued support for Numpy's predecessor (called Numeric), causing many problems for scientific users \citeappendix[see][]{hinsen15}. + +On the other hand, the dependency graph of tools written in high-level languages is often extremely complex. +For example see Figure 1 of \citeappendix{alliez19}, it shows the dependencies and their inter-dependencies for Matplotlib (a popular plotting module in Python). + +Acceptable dependency intervals between the dependencies will cause incompatibilities in a year or two, when a robust package manager is not used (see Appendix \ref{appendix:packagemanagement}). +Since a domain scientist doesn't always have the resources/knowledge to modify the conflicting part(s), many are forced to create complex environments with different versions of Python and pass the data between them (for example just to use the work of a previous PhD student in the team). +This greatly increases the complexity of the project, even for the principal author. +A good reproducible workflow can account for these different versions. +However, when the actual workflow system (not the analysis software) is written in a high-level language this will cause a major problem. + +For example, merely installing the Python installer (\inlinecode{pip}) on a Debian system (with \inlinecode{apt install pip2} for Python 2 packages), required 32 other packages as dependencies. +\inlinecode{pip} is necessary to install Popper and Sciunit (Appendices \ref{appendix:popper} and \ref{appendix:sciunit}). +As of this writing, the \inlinecode{pip3 install popper} and \inlinecode{pip2 install sciunit2} commands for installing each, required 17 and 26 Python modules as dependencies. +It is impossible to run either of these solutions if there is a single conflict in this very complex dependency graph. +This problem actually occurred while we were testing Sciunit: even though it installed, it couldn't run because of conflicts (its last commit was only 1.5 years old), for more see Appendix \ref{appendix:sciunit}. +\citeappendix{hinsen15} also report a similar problem when attempting to install Jupyter (see Appendix \ref{appendix:editors}). +Of course, this also applies to tools that these systems use, for example Conda (which is also written in Python, see Appendix \ref{appendix:packagemanagement}). + + + + + +\subsubsection{Generational gap} +This occurs primarily for domain scientists (for example astronomers, biologists or social sciences). +Once they have mastered one version of a language (mostly in the early stages of their career), they tend to ignore newer versions/languages. +The inertia of programming languages is very strong. +This is natural, because they have their own science field to focus on, and re-writing their very high-level analysis toolkits (which they have curated over their career and is often only readable/usable by themselves) in newer languages requires too much investment and time. + +When this investment is not possible, either the mentee has to use the mentor's old method (and miss out on all the new tools, which they need for the future job prospects), or the mentor has to avoid implementation details in discussions with the mentee, because they don't share a common language. +The authors of this paper have personal experiences in both mentor/mentee relational scenarios. +This failure to communicate in the details is a very serious problem, leading to the loss of valuable inter-generational experience. + + + + + + + + + + + + + + + + + + + + +\section{Survey of common existing reproducible workflows} +\label{appendix:existingsolutions} + +As reviewed in the introduction (Section \ref{sec:introduction}), the problem of reproducibility has received a lot of attention over the last three decades and various solutions have already been proposed. +In this appendix, some of the solutions are reviewed. +The solutions are based on an evolving software landscape, therefore they are ordered by date\footnote{When the project has a webpage, the year of its first release is used, otherwise their paper's publication year is used.}. +For each solution, we summarize its methodology and discuss how it relates to the principles in Section \ref{sec:principles}. +Freedom of the software/method is a core concept behind scientific reproducibility, as opposed to industrial reproducibility where a black box is acceptable/desirable. +Therefore proprietary solutions like Code Ocean (\url{https://codeocean.com}) or Nextjournal (\url{https://nextjournal.com}) will not be reviewed here. + +\begin{itemize} +\item \citeappendix{konkol20} have also done a review of some tools from various points of view. +\end{itemize} + + + + +\subsection{Reproducible Electronic Documents, RED (1992)} +\label{appendix:red} + +Reproducible Electronic Documents (\url{http://sep.stanford.edu/doku.php?id=sep:research:reproducible}) is the first attempt that we could find on doing reproducible research \citeappendix{claerbout1992,schwab2000}. +It was developed within the Stanford Exploration Project (SEP) for Geophysics publications. +Their introductions on the importance of reproducibility, resonate a lot with today's environment in computational sciences. +In particular the heavy investment one has to make in order to re-do another scientist's work, even in the same team. +RED also influenced other early reproducible works, for example \citeappendix{buckheit1995}. + +To orchestrate the various figures/results of a project, from 1990, they used ``Cake'' \citeappendix[]{somogyi87}, a dialect of Make, for more on Make, see Appendix \ref{appendix:jobmanagement}. +As described in \citeappendix{schwab2000}, in the latter half of that decade, moved to GNU Make \citeappendix{stallman88}, which was much more commonly used, developed and came with a complete and up-to-date manual. +The basic idea behind RED's solution was to organize the analysis as independent steps, including the generation of plots, and organizing the steps through a Makefile. +This enabled all the results to be re-executed with a single command. +Several basic low-level Makefiles were included in the high-level/central Makefile. +The reader/user of a project had to manually edit the central Makefile and set the variable \inlinecode{RESDIR} (result dir), this is the directory where built files are kept. +Afterwards, the reader could set which figures/parts of the project to reproduce by manually adding its name in the central Makefile, and running Make. + +At the time, Make was already practiced by individual researchers and projects as a job orchestration tool, but SEP's innovation was to standardize it as an internal policy, and define conventions for the Makefiles to be consistent across projects. +This enabled new members to benefit from the already existing work of previous team members (who had graduated or moved to other jobs). +However, RED only used the existing software of the host system, it had no means to control them. +Therefore, with wider adoption, they confronted a ``versioning problem'' where the host's analysis software had different versions on different hosts, creating different results, or crashing \citeappendix{fomel09}. +Hence in 2006 SEP moved to a new Python-based framework called Madagascar, see Appendix \ref{appendix:madagascar}. + + + + + +\subsection{Apache Taverna (2003)} +\label{appendix:taverna} +Apache Taverna (\url{https://taverna.incubator.apache.org}) is a workflow management system written in Java with a graphical user interface, see \citeappendix[still being actively developed]{oinn04}. +A workflow is defined as a directed graph, where nodes are called ``processors''. +Each Processor transforms a set of inputs into a set of outputs and they are defined in the Scufl language (an XML-based language, were each step is an atomic task). +Other components of the workflow are ``Data links'' and ``Coordination constraints''. +The main user interface is graphical, where users place processors in a sheet and define links between their inputs outputs. +\citeappendix{zhao12} have studied the problem of workflow decays in Taverna. +In many aspects Taverna is like VisTrails, see Appendix \ref{appendix:vistrails} [Since kepler is older, it may be better to bring the VisTrails features here.] + + + + + +\subsection{Madagascar (2003)} +\label{appendix:madagascar} +Madagascar (\url{http://ahay.org}) is a set of extensions to the SCons job management tool \citeappendix{fomel13}. +For more on SCons, see Appendix \ref{appendix:jobmanagement}. +Madagascar is a continuation of the Reproducible Electronic Documents (RED) project that was discussed in Appendix \ref{appendix:red}. + +Madagascar does include project management tools in the form of SCons extensions. +However, it isn't just a reproducible project management tool, it is primarily a collection of analysis programs, tools to interact with RSF files, and plotting facilities. +For example in our test of Madagascar 3.0.1, it installed 855 Madagascar-specific analysis programs (\inlinecode{PREFIX/bin/sf*}). +The analysis programs mostly target geophysical data analysis, including various project specific tools: more than half of the total built tools are under the \inlinecode{build/user} directory which includes names of Madagascar users. +Following the Unix spirit of modularized programs that communicating through text-based pipes, Madagascar's core is the custom Regularly Sampled File (RSF) format\footnote{\url{http://www.ahay.org/wiki/Guide\_to\_RSF\_file\_format}}. +RSF is a plain-text file that points to the location of the actual data files on the filesystem, but it can also keep the raw binary dataset within same plain-text file. + +Besides the location or contents of the data, RSF also contains name/value pairs that can be used as options to Madagascar programs, which are built with inputs and outputs of this format. +Since RSF contains program options also, the inputs and outputs of Madagascar's analysis programs are read from, and written to, standard input and standard output. + +Madagascar has been used in the production of hundreds of research papers or book chapters\footnote{\url{http://www.ahay.org/wiki/Reproducible_Documents}} \citeappendix[120 prior to][]{fomel13}. + + +\subsection{GenePattern (2004)} +\label{appendix:genepattern} +GenePattern (\url{https://www.genepattern.org}) is a client-server software containing many common analysis functions/modules, primarily focused for Gene studies \citeappendix[first released in 2004]{reich06}. +Although its highly focused to a special research field, it is reviewed here because its concepts/methods are generic, and in the context of this paper. + +Its server-side software is installed with fixed software packages that are wrapped into GenePattern modules. +The modules are used through a web interface, the modern implementation is GenePattern Notebook \citeappendix{reich17}. +It is an extension of the Jupyter notebook (see Appendix \ref{appendix:editors}), which also has a special ``GenePattern'' cell that will connect to GenePattern servers for doing the analysis. +However, the wrapper modules just call an existing tool on the host system. +Given that each server may have its own set of installed software, the analysis may differ (or crash) when run on different GenePattern servers, hampering reproducibility. + +The primary GenePattern server was active since 2008 and had 40,000 registered users with 2000 to 5000 jobs running every week \citeappendix{reich17}. +However, it was shut down on November 15th 2019 due to end of funding\footnote{\url{https://www.genepattern.org/blog/2019/10/01/the-genomespace-project-is-ending-on-november-15-2019}}. +All processing with this sever has stopped, and any archived data on it has been deleted. +Since GenePattern is free software, there are alternative public servers to use, so hopefully work on it will continue. +However, funding is limited and those servers may face similar funding problems. +This is a very nice example of the fragility of solutions that depend on archiving and running high-level research products (including data, binary/compiled code). + + + + + +\subsection{Kepler (2005)} +Kepler (\url{https://kepler-project.org}) is a Java-based Graphic User Interface workflow management tool \citeappendix{ludascher05}. +Users drag-and-drop analysis components, called ``actors'', into a visual, directional graph, which is the workflow (similar to Figure \ref{fig:analysisworkflow}). +Each actor is connected to others through the Ptolemy approach \citeappendix{eker03}. +In many aspects Kepler is like VisTrails, see Appendix \ref{appendix:vistrails}. +\tonote{Since kepler is older, it may be better to bring the VisTrails features here.} + + + + + +\subsection{VisTrails (2005)} +\label{appendix:vistrails} + +VisTrails (\url{https://www.vistrails.org}) was a graphical workflow managing system that is described in \citeappendix{bavoil05}. +According to its webpage, VisTrails maintainance has stopped since May 2016, its last Git commit, as of this writing, was in November 2017. +However, given that it was well maintained for over 10 years is an achievement. + +VisTrails (or ``visualization trails'') was initially designed for managing visualizations, but later grew into a generic workflow system with meta-data and provenance features. +Each analysis step, or module, is recorded in an XML schema, which defines the operations and their dependencies. +The XML attributes of each module can be used in any XML query language to find certain steps (for example those that used a certain command). +Since the main goal was visualization (as images), apparently its primary output is in the form of image spreadsheets. +Its design is based on a change-based provenance model using a custom VisTrails provenance query language (vtPQL), for more see \citeappendix{scheidegger08}. +Since XML is a plane text format, as the user inspects the data and makes changes to the analysis, the changes are recorded as ``trails'' in the project's VisTrails repository that operates very much like common version control systems (see Appendix \ref{appendix:versioncontrol}). + +With respect to keeping the history/provenance of the final dataset, VisTrails is very much like the template introduced in this paper. +However, even though XML is in plain text, it is very hard to edit manually. +VisTrails therefore provides a graphic user interface with a visual representation of the project's inter-dependent steps (similar to Figure \ref{fig:analysisworkflow}). +Besides the fact that it is no longer maintained, the conceptual differences with the proposed template are substantial. +The most important is that VisTrails doesn't control the software that is run, it only controls the sequence of steps that they are run in. +This template also defines dependencies and operations based on the very standard and commonly known Make system, not a custom XML format. +Scripts can easily be written to generate an XML-formatted output from Makefiles. + + + + + +\subsection{Galaxy (2010)} +\label{appendix:galaxy} + +Galaxy (\url{https://galaxyproject.org}) is a web-based Genomics workbench \citeappendix{goecks10}. +The main user interface are ``Galaxy Pages'', which doesn't require any programming: users simply use abstract ``tools'' which are a wrappers over command-line programs. +Therefore the actual running version of the program can be hard to control across different Galaxy servers \tonote{confirm this}. +Besides the automatically generated metadata of a project (which include version control, or its history), users can also tag/annotate each analysis step, describing its intent/purpose. +Besides some small differences, this seems to be very similar to GenePattern (Appendix \ref{appendix:genepattern}). + + + + + +\subsection{Image Processing On Line journal, IPOL (2010)} +The IPOL journal (\url{https://www.ipol.im}) attempts to publish the full implementation details of proposed image processing algorithm as a scientific paper \citeappendix[first published article in July 2010]{limare11}. +An IPOL paper is a traditional research paper, but with a focus on implementation. +The published narrative description of the algorithm must be detailed to a level that any specialist can implement it in their own programming language (extremely detailed). +The author's own implementation of the algorithm is also published with the paper (in C, C++ or MATLAB), the code must be commented well enough and link each part of it with the relevant part of the paper. +The authors must also submit several example datasets/scenarios. +The referee actually inspects the code and narrative, confirming that they match with each other, and with the stated conclusions of the published paper. +After publication, each paper also has a ``demo'' button on its webpage, allowing readers to try the algorithm on a web-interface and even provide their own input. + +The IPOL model is indeed the single most robust model of peer review and publishing computational research methods/implementations. +It has grown steadily over the last 10 years, publishing 23 research articles in 2019 alone. +We encourage the reader to visit its webpage and see some of its recent papers and their demos. +It can be so thorough and complete because it has a very narrow scope (image processing), and the published algorithms are highly atomic, not needing significant dependencies (beyond input/output), allowing the referees to go deep into each implemented algorithm. +In fact, high-level languages like Perl, Python or Java are not acceptable precisely because of the additional complexities/dependencies that they require. + +Ideally (if any referee/reader was inclined to do so), the proposed template of this paper allows for a similar level of scrutiny, but for much more complex research scenarios, involving hundreds of dependencies and complex processing on the data. + + + +\subsection{WINGS (2010)} +\label{appendix:wings} + +WINGS (\url{https://wings-workflows.org}) is an automatic workflow generation algorithm \citeappendix{gil10}. +It runs on a centralized web server, requiring many dependencies (such that it is recommended to download Docker images). +It allows users to define various workflow components (for example datasets, analysis components and etc), with high-level goals. +It then uses selection and rejection algorithms to find the best components using a pool of analysis components that can satisfy the requested high-level constraints. +\tonote{Read more about this} + + + + + +\subsection{Active Papers (2011)} +\label{appendix:activepapers} +Active Papers (\url{http://www.activepapers.org}) attempts to package the code and data of a project into one file (in HDF5 format). +It was initially written in Java because its compiled byte-code outputs in JVM are portable on any machine \citeappendix[see][]{hinsen11}. +However, Java is not a commonly used platform today, hence it was later implemented in Python \citeappendix{hinsen15}. + +In the Python version, all processing steps and input data (or references to them) are stored in a HDF5 file. +However, it can only account for pure-Python packages using the host operating system's Python modules \tonote{confirm this!}. +When the Python module contains a component written in other languages (mostly C or C++), it needs to be an external dependency to the Active Paper. + +As mentioned in \citeappendix{hinsen15}, the fact that it relies on HDF5 is a caveat of Active Papers, because many tools are necessary to access it. +Downloading the pre-built HDF View binaries (provided by the HDF group) is not possible anonymously/automatically (login is required). +Installing it using the Debian or Arch Linux package managers also failed due to dependencies. +Furthermore, as a high-level data format HDF5 evolves very fast, for example HDF5 1.12.0 (February 29th, 2020) is not usable with older libraries provided by the HDF5 team. % maybe replace with: February 29\textsuperscript{th}, 2020? + +While data and code are indeed fundamentally similar concepts technically \tonote{cite Konrad's paper on this}, they are used by humans differently. +This becomes a burden when large datasets are used, this was also acknowledged in \citeappendix{hinsen15}. +If the data are proprietary (for example medical patient data), the data must not be released, but the methods they were produced can. +Furthermore, since all reading and writing is done in the HDF5 file, it can easily bloat the file to very large sizes due to temporary/reproducible files, and its necessary to remove/dummify them, thus complicating the code, making it hard to read. +For example the Active Papers HDF5 file of \citeappendix[in \href{https://doi.org/10.5281/zenodo.2549987}{zenodo.2549987}]{kneller19} is 1.8 giga-bytes. + +In many scenarios, peers just want to inspect the processing by reading the code and checking a very special part of it (one or two lines), not necessarily needing to run it, or obtaining the datasets. +Hence the extra volume for data, and obscure HDF5 format that needs special tools for reading plain text code is a major burden. + + + + + +\subsection{Collage Authoring Environment (2011)} +\label{appendix:collage} +The Collage Authoring Environment \citeappendix{nowakowski11} was the winner of Elsevier Executable Paper Grand Challenge \citeappendix{gabriel11}. +It is based on the GridSpace2\footnote{\url{http://dice.cyfronet.pl}} distributed computing environment\tonote{find citation}, which has a web-based graphic user interface. +Through its web-based interface, viewers of a paper can actively experiment with the parameters of a published paper's displayed outputs (for example figures). +\tonote{See how it containerizes the software environment} + + + + + +\subsection{SHARE (2011)} +\label{appendix:SHARE} +SHARE (\url{https://is.ieis.tue.nl/staff/pvgorp/share}) is a web portal that hosts virtual machines (VMs) for storing the environment of a research project, for more, see \citeappendix{vangorp11}. +The top project webpage above is still active, however, the virtual machines and SHARE system have been removed since 2019. + +SHARE was recognized as second position in the Elsevier Executable Paper Grand Challenge \citeappendix{gabriel11}. +Simply put, SHARE is just a VM that users can download and run. +The limitations of VMs for reproducibility were discussed in Appendix \ref{appendix:virtualmachines}, and the SHARE system does not specify any requirements on making the VM itself reproducible. + + + + + +\subsection{Verifiable Computational Result, VCR (2011)} +\label{appendix:verifiableidentifier} +A ``verifiable computational result'' (\url{http://vcr.stanford.edu}) is an output (table, figure, or etc) that is associated with a ``verifiable result identifier'' (VRI), see \citeappendix{gavish11}. +It was awarded the third prize in the Elsevier Executable Paper Grand Challenge \citeappendix{gabriel11}. + +A VRI is created using tags within the programming source that produced that output, also recording its version control or history. +This enables exact identification and citation of results. +The VRIs are automatically generated web-URLs that link to public VCR repositories containing the data, inputs and scripts, that may be re-executed. +According to \citeappendix{gavish11}, the VRI generation routine has been implemented in MATLAB, R and Python, although only the MATLAB version was available during the writing of this paper. +VCR also has special \LaTeX{} macros for loading the respective VRI into the generated PDF. + +Unfortunately most parts of the webpage are not complete at the time of this writing. +The VCR webpage contains an example PDF\footnote{\url{http://vcr.stanford.edu/paper.pdf}} that is generated with this system, however, the linked VCR repository (\inlinecode{http://vcr-stat.stanford.edu}) does not exist at the time of this writing. +Finally, the date of the files in the MATLAB extension tarball are set to 2011, hinting that probably VCR has been abandoned soon after the publication of \citeappendix{gavish11}. + + + + + +\subsection{SOLE (2012)} +\label{appendix:sole} +SOLE (Science Object Linking and Embedding) defines ``science objects'' (SOs) that can be manually linked with phrases of the published paper \citeappendix[for more, see ][]{pham12,malik13}. +An SO is any code/content that is wrapped in begin/end tags with an associated type and name. +For example special commented lines in a Python, R or C program. +The SOLE command-line program parses the tagged file, generating metadata elements unique to the SO (including its URI). +SOLE also supports workflows as Galaxy tools \citeappendix{goecks10}. + +For reproducibility, \citeappendix{pham12} suggest building a SOLE-based project in a virtual machine, using any custom package manager that is hosted on a private server to obtain a usable URI. +However, as described in Appendices \ref{appendix:independentenvironment} and \ref{appendix:packagemanagement}, unless virtual machines are built with robust package managers, this is not a sustainable solution (the virtual machine itself is not reproducible). +Also, hosting a large virtual machine server with fixed IP on a hosting service like Amazon (as suggested there) will be very expensive. +The manual/artificial definition of tags to connect parts of the paper with the analysis scripts is also a caveat due to human error and incompleteness (tags the authors may not consider important, but may be useful later). +The solution of the proposed template (where anything coming out of the analysis is directly linked to the paper's contents with \LaTeX{} elements avoids these problems. + + + + + +\subsection{Sumatra (2012)} +Sumatra (\url{http://neuralensemble.org/sumatra}) attempts to capture the environment information of a running project \citeappendix{davison12}. +It is written in Python and is a command-line wrapper over the analysis script, by controlling its running, its able to capture the environment it was run in. +The captured environment can be viewed in plain text, a web interface. +Sumatra also provides \LaTeX/Sphinx features, which will link the paper with the project's Sumatra database. +This enables researchers to use a fixed version of a project's figures in the paper, even at later times (while the project is being developed). + +The actual code that Sumatra wraps around, must itself be under version control, and it doesn't run if there is non-committed changes (although its not clear what happens if a commit is amended). +Since information on the environment has been captured, Sumatra is able to identify if it has changed since a previous run of the project. +Therefore Sumatra makes no attempt at storing the environment of the analysis as in Sciunit (see Appendix \ref{appendix:sciunit}), but its information. +Sumatra thus needs to know the language of the running program. + + + + + +\subsection{Research Object (2013)} +\label{appendix:researchobject} + +The Research object (\url{http://www.researchobject.org}) is collection of meta-data ontologies, to describe aggregation of resources, or workflows, see \citeappendix{bechhofer13} and \citeappendix{belhajjame15}. +It thus provides resources to link various workflow/analysis components (see Appendix \ref{appendix:existingtools}) into a final workflow. + +\citeappendix{bechhofer13} describes how a workflow in Apache Taverna (Appendix \ref{appendix:taverna}) can be translated into research objects. +The important thing is that the research object concept is not specific to any special workflow, it is just a metadata bundle which is only as robust in reproducing the result as the running workflow. +For example, Apache Taverna cannot guarantee exact reproducibility as described in Appendix \ref{appendix:taverna}. +But when a translator is written to convert the proposed template into research objects, they can do this. + + + + + +\subsection{Sciunit (2015)} +\label{appendix:sciunit} +Sciunit (\url{https://sciunit.run}) defines ``sciunit''s that keep the executed commands for an analysis and all the necessary programs and libraries that are used in those commands. +It automatically parses all the executables in the script, and copies them, and their dependency libraries (down to the C library), into the sciunit. +Because the sciunit contains all the programs and necessary libraries, its possible to run it readily on other systems that have a similar CPU architecture. +For more, please see \citeappendix{meng15}. + +In our tests, Sciunit installed successfully, however we couldn't run it because of a dependency problem with the \inlinecode{tempfile} package (in the standard Python library). +Sciunit is written in Python 2 (which reached its end-of-life in January 1st, 2020) and its last Git commit in its main branch is from June 2018 (+1.5 years ago). +Recent activity in a \inlinecode{python3} branch shows that others are attempting to translate the code into Python 3 (the main author has graduated and apparently not working on Sciunit anymore). + +Because we weren't able to run it, the following discussion will just be theoretical. +The main issue with Sciunit's approach is that the copied binaries are just black boxes. +Therefore, its not possible to see how the used binaries from the initial system were built, or possibly if they have security problems. +This is a major problem for scientific projects, in principle (not knowing how they programs were built) and practice (archiving a large volume sciunit for every step of an analysis requires a lot of space). + + + + + +\subsection{Binder (2017)} +Binder (\url{https://mybinder.org}) is a tool to containerize already existing Jupyter based processing steps. +Users simply add a set of Binder-recognized configuration files to their repository. +Binder will build a Docker image and install all the dependencies inside of it with Conda (the list of necessary packages comes from Conda). +One good feature of Binder is that the imported Docker image must be tagged (something like a checksum). +This will ensure that future/latest updates of the imported Docker image are not mistakenly used. +However, it does not make sure that the dockerfile used by the imported Docker image follows a similar convention also. +Binder is used by \citeappendix{jones19}. + + + + + +\subsection{Gigantum (2017)} +Gigantum (\url{https://gigantum.com}) is a client/server system, in which the client is a web-based (graphical) interface that is installed as ``Gigantum Desktop'' within a Docker image and is free software (MIT License). +\tonote{I couldn't find the license to the server software yet, but it says that 20GB is provided for ``free'', so it is a little confusing if anyone can actually run the server.} +\tonote{I took the date from their PiPy page, where the first version 0.1 was published in November 2016.} + +Gigantum uses Docker containers for an independent environment, Conda (or Pip) to install packages, Jupyter notebooks to edit and run code, and Git to store its history. +Simply put, its a high-level wrapper for combining these components. +Internally, a Gigantum project is organized as files in a directory that can be opened without their own client. +The file structure (which is under version control) includes codes, input data and output data. +As acknowledged on their own webpage, this greatly reduces the speed of Git operations, transmitting, or archiving the project. +Therefore there are size limits on the dataset/code sizes. +However, there is one directory which can be used to store files that must not be tracked. + + + + + +\subsection{Popper (2017)} +\label{appendix:popper} +Popper (\url{https://falsifiable.us}) is a software implementation of the Popper Convention \citeappendix{jimenez17}. +The Convention is a set of very generic conditions that are also applicable to the template proposed in this paper. +For a discussion on the convention, please see Section \ref{sec:principles}, in this section we'll review their software implementation. + +The Popper team's own solution is through a command-line program called \inlinecode{popper}. +The \inlinecode{popper} program itself is written in Python, but job management is with the HashiCorp configuration language (HCL). +HCL is primarily aimed at running jobs on HashiCorp's ``infrastructure as a service'' (IaaS) products. +Until September 30th, 2019\footnote{\url{https://github.blog/changelog/2019-09-17-github-actions-will-stop-running-workflows-written-in-hcl}}, HCL was used by ``GitHub Actions'' to manage workflows. % maybe use the \textsuperscript{th} with dates? + +To start a project, the \inlinecode{popper} command-line program builds a template, or ``scaffold'', which is a minimal set of files that can be run. +The scaffold is very similar to the raw template of that is proposed in this paper. +However, as of this writing, the scaffold isn't complete. +It lacks a manuscript and validation of outputs (as mentioned in the convention). +By default Popper runs in a Docker image (so root permissions are necessary), but Singularity is also supported. +See Appendix \ref{appendix:independentenvironment} for more on containers, and Appendix \ref{appendix:highlevelinworkflow} for using high-level languages in the workflow. + + + + + +\subsection{Whole Tale (2019)} +\label{appendix:wholetale} + +Whole Tale (\url{https://wholetale.org}) is a web-based platform for managing a project and organizing data provenance, see \citeappendix{brinckman19} +It uses online editors like Jupyter or RStudio (see Appendix \ref{appendix:editors}) that are encapsulated in a Docker container (see Appendix \ref{appendix:independentenvironment}). + +The web-based nature of Whole Tale's approach, and its dependency on many tools (which have many dependencies themselves) is a major limitation for future reproducibility. +For example, when following their own tutorial on ``Creating a new tale'', the provided Jupyter notebook could not be executed because of a dependency problem. +This has been reported to the authors as issue 113\footnote{\url{https://github.com/whole-tale/wt-design-docs/issues/113}}, but as all the second-order dependencies evolve, its not hard to envisage such dependency incompatibilities being the primary issue for older projects on Whole Tale. +Furthermore, the fact that a Tale is stored as a binary Docker container causes two important problems: 1) it requires a very large storage capacity for every project that is hosted there, making it very expensive to scale if demand expands. 2) It is not possible to see how the environment was built accurately (when the Dockerfile uses \inlinecode{apt}), for more on this, please see Appendix \ref{appendix:packagemanagement}. + + + + + +\subsection{Things to add} +\url{https://sites.nationalacademies.org/cs/groups/pgasite/documents/webpage/pga_180684.pdf}, does the following classification of tools: + \begin{itemize} + \item Research environments: \href{http://vcr.stanford.edu}{Verifiable computational research} (discussed above), \href{http://www.sciencedirect.com/science/article/pii/S1877050911001207}{SHARE} (a Virtual Machine), \href{http://www.codeocean.com}{Code Ocean} (discussed above), \href{http://jupyter.org}{Jupyter} (discussed above), \href{https://yihui.name/knitr}{knitR} (based on Sweave, dynamic report generation with R), \href{https://cran.r-project.org}{Sweave} (Function in R, for putting R code within \LaTeX), \href{http://www.cyverse.org}{Cyverse} (proprietary web tool with servers for bioinformatics), \href{https://nanohub.org}{NanoHUB} (collection of Simulation Programs for nanoscale phenomena that run in the cloud), \href{https://www.elsevier.com/about/press-releases/research-and-journals/special-issue-computers-and-graphics-incorporates-executable-paper-grand-challenge-winner-collage-authoring-environment}{Collage Authoring Environment} (discussed above), \href{https://osf.io/ns2m3}{SOLE} (discussed above), \href{https://osf.io}{Open Science framework} (a hosting webpage), \href{https://www.vistrails.org}{VisTrails} (discussed above), \href{https://pypi.python.org/pypi/Sumatra}{Sumatra} (discussed above), \href{http://software.broadinstitute.org/cancer/software/genepattern}{GenePattern} (reviewed above), Image Processing On Line (\href{http://www.ipol.im}{IPOL}) journal (publishes full analysis scripts, but doesn't deal with dependencies), \href{https://github.com/systemslab/popper}{Popper} (reviewed above), \href{https://galaxyproject.org}{Galaxy} (reviewed above), \href{http://torch.ch}{Torch.ch} (finished project for neural networks on images), \href{http://wholetale.org/}{Whole Tale} (discussed above). + \item Workflow systems: \href{http://www.taverna.org.uk}{Taverna}, \href{http://www.wings-workflows.org}{Wings}, \href{https://pegasus.isi.edu}{Pegasus}, \href{http://www.pgbovine.net/cde.html}{CDE}, \href{http://binder.org}{Binder}, \href{http://wiki.datakurator.org/wiki}{Kurator}, \href{https://kepler-project.org}{Kepler}, \href{https://github.com/everware}{Everware}, \href{http://cds.nyu.edu/projects/reprozip}{Reprozip}. + \item Dissemination platforms: \href{http://researchcompendia.org}{ResearchCompendia}, \href{https://datacenterhub.org/about}{DataCenterHub}, \href{http://runmycode.org}, \href{https://www.chameleoncloud.org}{ChameleonCloud}, \href{https://occam.cs.pitt.edu}{Occam}, \href{http://rcloud.social/index.html}{RCloud}, \href{http://thedatahub.org}{TheDataHub}, \href{http://www.ahay.org/wiki/Package_overview}{Madagascar}. + \end{itemize} + + + + + + + + + + + + + + + + + + + + +\newpage +\section{Things remaining to add} +\begin{itemize} +\item Special volume on ``Reproducible research'' in the Computing in Science Engineering \citeappendix{fomel09}. +\item ``I’ve learned that interactive programs are slavery (unless they include the ability to arrive in any previous state by means of a script).'' \citeappendix{fomel09}. +\item \citeappendix{fomel09} discuss the ``versioning problem'': on different systems, programs have different versions. +\item \citeappendix{fomel09}: a C program written 20 years ago was still usable. +\item \citeappendix{fomel09}: ``in an attempt to increase the size of the community, Matthias Schwab and I submitted a paper to Computers in Physics, one of CiSE’s forerunners. It was rejected. The editors said if everyone used Microsoft computers, everything would be easily reproducible. They also predicted the imminent demise of Fortran''. +\item \citeappendix{alliez19}: Software citation, with a nice dependency plot for matplotlib. + \item SC \href{https://sc19.supercomputing.org/submit/reproducibility-initiative}{Reproducibility Initiative} for mandatory Artifact Description (AD). + \item \href{https://www.acm.org/publications/policies/artifact-review-badging}{Artifact review badging} by the Association of computing machinery (ACM). + \item eLife journal \href{https://elifesciences.org/labs/b521cf4d/reproducible-document-stack-towards-a-scalable-solution-for-reproducible-articles}{announcement} on reproducible papers. \citeappendix{lewis18} is their first reproducible paper. + \item The \href{https://www.scientificpaperofthefuture.org}{Scientific paper of the future initiative} encourages geoscientists to include associate metadata with scientific papers \citeappendix{gil16}. + \item Digital objects: \url{http://doi.org/10.23728/b2share.b605d85809ca45679b110719b6c6cb11} and \url{http://doi.org/10.23728/b2share.4e8ac36c0dd343da81fd9e83e72805a0} + \item \citeappendix{mesirov10}, \citeappendix{casadevall10}, \citeappendix{peng11}: Importance of reproducible research. + \item \citeappendix{sandve13} is an editorial recommendation to publish reproducible results. + \item \citeappendix{easterbrook14} Free/open software for open science. + \item \citeappendix{peng15}: Importance of better statistical education. + \item \citeappendix{topalidou16}: Failed attempt to reproduce a result. + \item \citeappendix{hutton16} reproducibility in hydrology, criticized in \citeappendix{melson17}. + \item \citeappendix{fomel09}: Editorial on reproducible research. + \item \citeappendix{munafo17}: Reproducibility in social sciences. + \item \citeappendix{stodden18}: Effectiveness of journal policy on computational reproducibility. + \item \citeappendix{fanelli18} is critical of the narrative that there is a ``reproducibility crisis'', and that its important to empower scientists. + \item \citeappendix{burrell18} open software (in particular Python) in heliophysics. + \item \citeappendix{allen18} show that many papers don't cite software. + \item \citeappendix{zhang18} explicity say that they won't release their code: ``We opt not to make the code used for the chemical evo-lution modeling publicly available because it is an important asset of the re-searchers’ toolkits'' + \item \citeappendix{jones19} make genuine effort at reproducing every number in the paper (using Docker, Conda, and CGAT-core, and Binder), but they can ultimately only release scripts. They claim its not possible to reproduce that level of reproducibility, but here we show it is. + \item LSST uses Kubernetes and docker for reproducibility \citeappendix{banek19}. + \item Interesting survey/paper on the importance of coding in science \citeappendix{merali10}. + \item Discuss the Provenance challenge \citeappendix{moreau08}, showing the importance of meta data and provenance tracking. + Especially that it is organized by teh medical scientists. + Its webpage (for latest challenge) has a nice intro: \url{https://www.cccinnovationcenter.com/challenges/provenance-challenge}. + \item In discussion: The XML provenance system is very interesting, scripts can be written to parse the Makefiles within this template to generate such XML outputs for easy standard metadata parsing. + The XML that contains a log of the outputs is also interesting. + \item \citeappendix{becker17} Discuss reproducibility methods in R. + \item Elsevier Executable Paper Grand Challenge\footnote{\url{https://shar.es/a3dgl2}} \citeappendix{gabriel11}. + \item \citeappendix{menke20} show how software identifability has seen the best improvement, so there is hope! + \item Nature's collection on papers about reproducibility: \url{https://www.nature.com/collections/prbfkwmwvz}. + \item Nice links for applying FAIR principles in research software: \url{https://www.rd-alliance.org/group/software-source-code-ig/wiki/fair4software-reading-materials} + \item Jupyter Notebooks and problems with reproducibility: \citeappendix{rule18} and \citeappendix{pimentel19}. + \item Reproducibility certification \url{https://www.cascad.tech}. + \item \url{https://plato.stanford.edu/entries/scientific-reproducibility}. + \item +Modern analysis tools are almost entirely implemented as software packages. +This has lead many scientists to adopt solutions that software developers use for reproducing software (for example to fix bugs, or avoid security issues). +These tools and how they are used are thorougly reviewed in Appendices \ref{appendix:existingtools} and \ref{appendix:existingsolutions}. +However, the problem of reproducibility in the sciences is more complicated and subtle than that of software engineering. +This difference can be broken up into the following categories, which are described more fully below: +1) Reading vs. executing, 2) Archiving how software is used and 3) Citation of the software/methods used for scientific credit. + +The first difference is because in the sciences, reproducibility is not merely a problem of re-running a research project (where a binary blob like a container or virtual machine is sufficient). +For a scientist it is more important to read/study a method of a paper that is 1, 10, or 100 years old. +The hardware to execute the code may have become obsolete, or it may require too much processing power, storage, or time for another random scientist to execute. +Another scientist just needs to be assured that the commands they are reading is exactly what was (and can potentially be) executed. + +On the second point, scientists are devoting a smaller fraction of their papers to the technical aspects of the work because they are done increasingly by pre-written software programs and libraries. +Therefore, scientific papers are no longer a complete repository for preserving and archiving very important aspects of the scientific endeavor and hard gained experience. +Attempts such as Software Heritage\footnote{\url{https://www.softwareheritage.org}} \citeappendix{dicosmo18} do a wonderful job at long term preservation and archival of the software source code. +However, preservation of the software's raw code is only part of the process, it is also critically important to preserve how the software was used: with what configuration or run-time options, for what kinds of problems, in conjunction with which other software tools and etc. + +The third major difference was scientific credit, which is measured in units of citations, not dollars. +As described above, scientific software are playing an increasingly important role in modern science. +Because of the domain-specific knowledge necessary to produce such software, they are mostly written by scientists for scientists. +Therefore a significant amount of effort and research funding has gone into producing scientific software. +Atleast for the software that do have an accompanying paper, it is thus important that those papers be cited when they are used. +\end{itemize} + + + + +%% Bibliography of appendix +\bibliographystyleappendix{IEEEtran_openaccess} +\bibliographyappendix{IEEEabrv,references} +\fi \end{document} %% This file is free software: you can redistribute it and/or modify it @@ -36,6 +36,7 @@ host_cc=0 operation= build_dir= input_dir= +noappendix=0 check_config= make_targets= software_dir= @@ -119,6 +120,7 @@ Configure and Make options: -?, --help Print this help list. Make options: + --no-appendix Don't include the appendix in the final paper. -d, --debug=FLAGS Print various types of debugging information. -p, --prepare-redo Re-do preparation (only done automatically once). @@ -205,6 +207,8 @@ do # # Note that Make's `debug' can take values, but when called without any # value, it is like giving it a value of `a'): + --no-appendix) noappendix=1; shift;; + --no-appendix=*) on_off_option_error --no-appendix;; -d|--debug) if [ x"$2" = x ]; then debug=a; shift; else debug="$2"; check_v debug "$debug"; shift;shift; fi;; -d=*|--debug=*) debug="${1#*=}"; check_v debug "$debug"; shift;; @@ -370,8 +374,8 @@ controlled_env() { # Remove all existing environment variables (with `env -i') and only # use some pre-defined environment variables, then build the project. envmake=".local/bin/env -i HOME=$bdir sys_rm=$(which rm) $gopt" - envmake="$envmake .local/bin/make --no-builtin-rules" - envmake="$envmake --no-builtin-variables -f $1" + envmake="$envmake noappendix=$noappendix .local/bin/make" + envmake="$envmake --no-builtin-rules --no-builtin-variables -f $1" if ! [ x"$debug" = x ]; then envmake="$envmake --debug=$debug"; fi # Set the number of jobs. Note that for the `configure.sh' script the diff --git a/reproduce/analysis/make/paper.mk b/reproduce/analysis/make/paper.mk index f363b6f..29a1ea0 100644 --- a/reproduce/analysis/make/paper.mk +++ b/reproduce/analysis/make/paper.mk @@ -48,10 +48,18 @@ $(mtexdir)/project.tex: $(mtexdir)/verify.tex # Put a LaTeX input command for all the necessary macro files. # 'hardware-parameters.tex' is created in 'configure.sh'. - rm -f $(mtexdir)/project.tex + projecttex=$(mtexdir)/project.tex + rm -f $$projecttex for t in $(subst paper,,$(makesrc)) hardware-parameters; do - echo "\input{tex/build/macros/$$t.tex}" >> $(mtexdir)/project.tex + echo "\input{tex/build/macros/$$t.tex}" >> $$projecttex done + + # Add the necessary macro to include appendix or not. + if [ x"$(noappendix)" = x1 ]; then + echo "\newcommand{\noappendix}{}" >> $$projecttex + fi + + # The paper shouldn't be built. else echo echo "-----" @@ -129,7 +137,12 @@ $(texbdir)/paper.bbl: tex/src/references.tex $(mtexdir)/dependencies-bib.tex \ # option for better security. See # https://savannah.nongnu.org/task/?15694 for details. latex -shell-escape -halt-on-error "$$p"/paper.tex + + # Since we have multiple bibliographies (one for the main body, + # and one for the appendix), we use 'multibib'. Multibib creates + # a separate '.aux' file for each bibliography. bibtex paper + bibtex appendix # Hack: tidy up eprint+doi style that didn't work in .bst file. # TODO (better): read Part 4 of diff --git a/reproduce/software/config/texlive-packages.conf b/reproduce/software/config/texlive-packages.conf index d88a0bf..fd66da9 100644 --- a/reproduce/software/config/texlive-packages.conf +++ b/reproduce/software/config/texlive-packages.conf @@ -18,4 +18,5 @@ # want their versions. texlive-typewriter-pkgs = courier inconsolata xkeyval upquote texlive-packages = times IEEEtran cite xcolor pgfplots ps2eps \ - listings ulem etoolbox $(texlive-typewriter-pkgs) + listings ulem etoolbox multibib \ + $(texlive-typewriter-pkgs) diff --git a/tex/src/preamble-biblatex.tex b/tex/src/preamble-biblatex.tex deleted file mode 100644 index 0561d1c..0000000 --- a/tex/src/preamble-biblatex.tex +++ /dev/null @@ -1,145 +0,0 @@ -%% Biblatex settings. -%% -%% Settings necessary to make the bibliography with Biblatex. Keeping all -%% BibLaTeX settings in a separate preamble was done in the spirit of -%% modularity to 1) easily managable, 2) If a similar BibLaTeX -%% configuration is necessary in another LaTeX compilation, this file can -%% just be copied there and used. -%% -%% USAGE: -%% - `tex/src/references.tex': the file containing Bibtex source of each -%% reference. The file suffix doesn't have to be `.bib'. This naming -%% helps in clearly identifying the files and avoiding places that -%% complain about `.bib' files. -% -%% Copyright (C) 2018-2020 Mohammad Akhlaghi <mohammad@akhlaghi.org> -% -%% This LaTeX file is part of Maneage. Maneage is free software: you can -%% redistribute it and/or modify it under the terms of the GNU General -%% Public License as published by the Free Software Foundation, either -%% version 3 of the License, or (at your option) any later version. -% -%% Maneage is distributed in the hope that it will be useful, but WITHOUT -%% ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or -%% FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License -%% for more details. See <http://www.gnu.org/licenses/>. - - - - -%% To break up highlighted text (for example texttt when some it is on the -%% line break) and also to no underline emphasized words (like journal -%% titles in the references). -\usepackage[normalem]{ulem} - - - - - -%% For quotation signs (sometimes used by BibLaTeX) -\usepackage{csquotes} - - - - - -%% To define colors -\usepackage{xcolor} - - - - - -% Basic BibLaTeX settings -\usepackage[ - doi=false, - url=false, - dashed=false, - eprint=false, - maxbibnames=10, - minbibnames=4, - hyperref=true, - maxcitenames=2, - mincitenames=1, - giveninits=true, - style=authoryear, - uniquelist=false, - backend=biber,natbib]{biblatex} -\DeclareFieldFormat[article]{pages}{#1} -\DeclareFieldFormat{pages}{\mkfirstpage[{\mkpageprefix[bookpagination]}]{#1}} -\addbibresource{tex/src/references.tex} -\addbibresource{tex/build/macros/dependencies-bib.tex} -\renewbibmacro{in:}{} -\AtEveryBibitem{\clearfield{month}} -\renewcommand*{\bibfont}{\normalsize} -\DefineBibliographyStrings{english}{references = {References}} - -%% Include the adsurl field key into those that are recognized: -\DeclareSourcemap{ - \maps[datatype=bibtex]{ - \map{ - \step[fieldsource=adsurl,fieldtarget=iswc] - \step[fieldsource=gbkurl,fieldtarget=iswc] - } - } -} - -%% Set the color of the doi link to mymg (magenta) and the ads links -%% to mypurp (or purple): -\definecolor{mypurp}{cmyk}{0.75,1,0,0} -\definecolor{myblue}{rgb}{0,0.669,0.885} -\newcommand{\doihref}[2]{\href{#1}{\color{myblue}{#2}}} -\newcommand{\adshref}[2]{\href{#1}{\color{mypurp}{#2}}} -\newcommand{\blackhref}[2]{\href{#1}{\color{black}{#2}}} - -%% Define a format for the printtext commands in -%% DeclareBibliographyDriver to make links for the doi, ads link and -%% arxiv link: -\DeclareFieldFormat{doilink}{ - \iffieldundef{doi}{#1}{\doihref{http://dx.doi.org/\thefield{doi}}{#1}}} -\DeclareFieldFormat{adslink}{ - \iffieldundef{iswc}{#1}{\adshref{\thefield{iswc}}{#1}}} -\DeclareFieldFormat{arxivlink}{ - \iffieldundef{eprint}{#1}{\href{http://arxiv.org/abs/\thefield{eprint}}{#1}}} - -\DeclareListFormat{doiforbook}{ - \iffieldundef{doi}{#1}{\doihref{http://dx.doi.org/\thefield{doi}}{#1}}} -\DeclareFieldFormat{googlebookslink}{ - \iffieldundef{iswc}{#1}{\adshref{\thefield{iswc}}{#1}}} - -%% Set the formatting to make the last three values into the -%% appropriate link. Note that the % signs are necessary. Without -%% them, the items will be indented. -\DeclareBibliographyDriver{article}{% - \usebibmacro{bibindex}% - \usebibmacro{begentry}% - \usebibmacro{author/translator+others}% - \newunit% - \printtext{\usebibmacro{title}}% - \newunit% - \printtext[doilink]{\usebibmacro{journal}}% - \addcomma% - \printtext[adslink]{\printfield{volume}}% - \addcomma% - \printtext[arxivlink]{\printfield{pages}}% - \addperiod% -} - -\DeclareBibliographyDriver{book}{% - \usebibmacro{bibindex}% - \usebibmacro{begentry}% - \usebibmacro{author/translator+others}% - \newunit% - \printtext{\usebibmacro{title}}% - \addperiod% - \addspace% - \printlist[doiforbook]{publisher}% - \addcomma% - \addspace% - \printfield[googlebookslink]{edition}% - \printtext{ ed.}% - \addperiod% -} - -%% In order to have et al. instead of et al.,: -\renewcommand*{\nameyeardelim}{\addspace} diff --git a/tex/src/preamble-project.tex b/tex/src/preamble-project.tex index 16a9ddc..b4fd764 100644 --- a/tex/src/preamble-project.tex +++ b/tex/src/preamble-project.tex @@ -5,6 +5,12 @@ %% \cite{} output to follow that of the IEEE. \usepackage{cite} +%% To have multiple bibliographies (one for the main paper, one for the +%% appendix). With 'multibib' we need to specify a name for each +%% bibliography. +\usepackage{multibib} +\newcites{appendix}{Bibliography} + %% For the `\url' command. \usepackage{url} @@ -51,6 +57,19 @@ +%% Maneage feature for highlighting updates. When this is set, text marked +%% as \new will be colored in dark green and text that is marked +%% wtih \tonote will be marked in dark red. +\ifdefined\highlightchanges +\newcommand{\new}[1]{\textcolor{green!60!black}{#1}} +\newcommand{\tonote}[1]{\textcolor{red!60!black}{[#1]}} +\else +\newcommand{\new}[1]{\textcolor{black}{#1}} +\newcommand{\tonote}[1]{{}} +\fi + + + %% Custom macros \newcommand{\inlinecode}[1]{\textcolor{blue!35!black}{\texttt{#1}}} diff --git a/tex/src/preamble-style.tex b/tex/src/preamble-style.tex deleted file mode 100644 index f8b95d6..0000000 --- a/tex/src/preamble-style.tex +++ /dev/null @@ -1,156 +0,0 @@ -%% Set the page margins (use `showframe' to see the sides). -%% A4 is 210mm x 297mm -\usepackage[a4paper]{geometry} - -%% Horizontal space of text: total is 210mm -\setlength{\hoffset}{0mm} % remaining: 190mm -\setlength{\textwidth}{155mm} % remaining: 160mm -\setlength{\marginparsep}{0pt} -\setlength{\marginparwidth}{0pt} -\setlength{\oddsidemargin}{0pt} - -%% Vertical space of text: total is 297mm. -\setlength{\voffset}{-15.4mm} % remaining: 287mm (== 10mm (1 inch + \hoffset). -\setlength{\topmargin}{0mm} % remaining: 287mm. -\setlength{\headheight}{10mm} % remaining: 277mm. -\setlength{\headsep}{10mm} % remaining: 272mm. -\setlength{\textheight}{245mm} % remaining: 22mm. -\setlength{\footskip}{7mm} % remaining: 10mm. - -%% To see the layout, add a `\layout' right after `\begin{document}'. -\usepackage{layout} - -%% To display codes. -\usepackage{listings} -\input{listings-bash.prf} -\lstset{ - frame=none, - commentstyle=\color{gray}, - basicstyle=\small\ttfamily, -} - -%% To allow a prefix to the enumeration. -\usepackage{enumitem} -\setlist{nolistsep} % No space before `\begin{itemize}' - -%% Horizontal line with spacing -\newcommand{\horizontalline}{\vspace{3mm}\hrule\vspace{3mm}} - -%% Custom title format -\usepackage{setspace} -\makeatletter -\renewcommand{\maketitle}{\bgroup\setlength{\parindent}{0pt} - \begin{flushleft} - {\mpbold RESEARCH PAPER} - - \vspace{3mm} - {\LARGE\mpmedium \@title} - - \vspace{2mm} - \@author - \end{flushleft}\egroup - \horizontalline -} -\makeatother - -%% For authors and affiliations -\newcommand{\authoraffil}[2]{#1\textsuperscript{\mplight#2}} - -%% Spacing before and after section titles. -%% Format: \titlespacing*{<command>}{<left>}{<before-sep>}{<after-sep>} -\usepackage{titlesec} -\titlespacing*{\section} {0pt}{10pt plus 0pt minus 0pt}{0pt plus 0pt minus 0pt} -\titlespacing*{\subsection} {0pt}{7pt plus 0pt minus 0pt} {0pt plus 0pt minus 0pt} -\titlespacing*{\subsubsection}{0pt}{4pt plus 0pt minus 0pt} {0pt plus 0pt minus 0pt} -\titleformat{\section}{\Large\scshape\bf}{\thesection.{ }}{0pt}{} -\titleformat{\subsection}{\large\bfseries\itshape}{\thesubsection.{ }}{0pt}{} -\titleformat{\subsubsection}{\bfseries\itshape}{\thesubsubsection.{ }}{0pt}{} - -%% Set the font. -%% After downloading, put the font in `/usr/share/fonts/TTF'. -%% https://www.fontspace.com/m-fonts/m-2p -%% Also for M+: https://mplus-fonts.osdn.jp/about-en.html -%% https://www.fontpalace.com/font-download/Memento/ -\usepackage{fontspec} -\usepackage[T1]{fontenc} -\usepackage{Alegreya} -\newfontfamily\mplight{AlegreyaSans-Light} -\newfontfamily\mpbold{AlegreyaSans-Bold} -\newfontfamily\mpmedium{AlegreyaSans-Medium} -\newfontfamily\mpregular{AlegreyaSans-Regular} - -%% For highlighting updates. When this is set, text marked as \new -%% will be colored in dark green and text that is marked wtih \tonote -%% will be marked in dark red. -\ifdefined\highlightchanges -\newcommand{\new}[1]{\textcolor{green!60!black}{#1}} -\newcommand{\tonote}[1]{\textcolor{red!60!black}{[#1]}} -\else -\newcommand{\new}[1]{\textcolor{black}{#1}} -\newcommand{\tonote}[1]{{}} -\fi - -%% To print the creation date on the PDF. -\usepackage{datetime} - -%% To have links. -\usepackage[ - colorlinks, - urlcolor=gray, - citecolor=gray, - linkcolor=gray, - linktocpage]{hyperref} -\renewcommand\UrlFont{\rmfamily} - -%% To include figures. -\usepackage{graphicx} - -%% To manage captions. -\usepackage[font={footnotesize}]{caption} - -%% To use colors. -\usepackage{xcolor} - -%% Header and footer style. -\usepackage{lastpage} -\usepackage{fancyhdr} -\pagestyle{fancy} -\lhead{\mplight\footnotesize Art.XX, page {\thepage} of \pageref{LastPage}} -\chead{} -\rhead{\mplight\footnotesize Akhlaghi, et al: Maneage, a Customizable Framework for Managing Data Lineage} -\lfoot{} -\cfoot{} -\rfoot{} -\renewcommand\headrulewidth{0.0pt} -\renewcommand\footrulewidth{0.0pt} -\fancypagestyle{firstpage} { - \lhead{\includegraphics[width=3.5cm]{tex/img/codata.pdf}} - \chead{} - \rhead{\mplight\footnotesize - Akhlaghi, M, et al. 2020. Maneage, a Customizable Framework\\ - for Managing Data Lineage. \emph{Data Science Journal}, VV,\\ - NN, pp.1-\pageref*{LastPage}. DOI: \href{https://doi.org/10.5334/dsj-XXXX-XXX}{\textcolor{black}{https://doi.org/10.5334/dsj-XXXX-XXX}}\\ - PDF created on: \currenttime{}, \today} - \lfoot{} - \cfoot{} - \rfoot{} - \renewcommand\headrulewidth{0.1pt} - \renewcommand\footrulewidth{0.0pt} -} - -%% For creating color boxes -\usepackage[many]{tcolorbox} - -%% Custom macros -\newcommand{\inlinecode}[1]{\textcolor{blue!35!black}{\texttt{#1}}} - -%% To use International Phonetic Alphabet (IPA) -\usepackage{tipa} - -%% Example Makefile macros -\newcommand{\mkcomment}[1]{\textcolor{red!70!white}{\# #1}} -\newcommand{\mkvar}[1]{\textcolor{orange!40!black}{#1}} -\newcommand{\mktarget}[1]{\textcolor{blue!40!black}{#1}} -\newcommand{\mkprog}[1]{\textcolor{green!30!black}{#1}} -\newcommand{\mktab}[1]{\textcolor{black!30!white}{\_\_\_TAB\_\_\_}} -\newcommand{\recipecomment}[1]{{ }{ }{ }{ }{ }{ }{ }{ }{ }\mkcomment{#1}} diff --git a/tex/src/references.tex b/tex/src/references.tex index 3d395ec..992f40f 100644 --- a/tex/src/references.tex +++ b/tex/src/references.tex @@ -171,7 +171,7 @@ archivePrefix = {arXiv}, author = {Roberto {Di Cosmo} and Francois Pellegrini}, title = {Encouraging a wider usage of software derived from research}, year = {2019}, - journal = {\doihref{https://www.ouvrirlascience.fr/wp-content/uploads/2020/02/Opportunity-Note_software-derived-from-research_EN.pdf}{Ouvrir la science}}, + journal = {\doihref{https://www.ouvrirlascience.fr/wp-content/uploads/2020/02/Opportunity-Note\_software-derived-from-research\_EN.pdf}{Ouvrir la science}}, volume = {}, pages = {}, doi = {}, @@ -1031,7 +1031,7 @@ archivePrefix = {arXiv}, archivePrefix = {arXiv}, eprint = {1506.02822}, primaryClass = {cs.DC}, - doi = {10.1007/978-3-319-27308-2_47}, + doi = {10.1007/978-3-319-27308-2\_47}, adsurl = {https://ui.adsabs.harvard.edu/abs/2015arXiv150602822C}, adsnote = {Provided by the SAO/NASA Astrophysics Data System} } @@ -1203,7 +1203,7 @@ archivePrefix = {arXiv}, journal = {Provenance and Annotation of Data and Processes (IPAW)}, year = {2012}, pages = {203}, - doi = {10.1007/978-3-642-34222-6_16}, + doi = {10.1007/978-3-642-34222-6\_16}, } @@ -1307,7 +1307,7 @@ Reproducible Research in Image Processing}, @ARTICLE{nowakowski11, - author = {Piotr Nowakowski and Eryk Ciepiela and Daniel Har\k{e}\.{z}lak and Joanna Kocot and Marek Kasztelnik and Tomasz Barty\'nski and Jan Meizner and Grzegorz Dyk and Maciej Malawski}, + author = {Piotr Nowakowski and Eryk Ciepiela and Daniel Hare\.{z}lak and Joanna Kocot and Marek Kasztelnik and Tomasz Barty\'nski and Jan Meizner and Grzegorz Dyk and Maciej Malawski}, title = {The Collage Authoring Environment}, journal = {Procedia Computer Science}, volume = {4}, @@ -1618,7 +1618,7 @@ Reproducible Research in Image Processing}, journal = {Large Installation System Administration Conference}, year = {2004}, volume = {18}, - pages = {79. \url{https://www.usenix.org/legacy/events/lisa04/tech/full_papers/dolstra/dolstra.pdf}}, + pages = {79. \url{https://www.usenix.org/legacy/events/lisa04/tech/full\_papers/dolstra/dolstra.pdf}}, } |