Initial paper intro and thoughts

docs/paper/BUILD.sh

@@ -0,0 +1,9 @@
+#!/bin/bash
+
+bibtex paper
+
+bibtex paper
+
+pdflatex paper.tex
+
+

docs/paper/paper.tex

@@ -0,0 +1,219 @@
+%%
+%% This is file `sample-sigconf.tex',
+%% generated with the docstrip utility.
+%%
+%% The original source files were:
+%%
+%% samples.dtx  (with options: `sigconf')
+%% 
+%% IMPORTANT NOTICE:
+%% 
+%% For the copyright see the source file.
+%% 
+%% Any modified versions of this file must be renamed
+%% with new filenames distinct from sample-sigconf.tex.
+%% 
+%% For distribution of the original source see the terms
+%% for copying and modification in the file samples.dtx.
+%% 
+%% This generated file may be distributed as long as the
+%% original source files, as listed above, are part of the
+%% same distribution. (The sources need not necessarily be
+%% in the same archive or directory.)
+%%
+%%
+%% Commands for TeXCount
+%TC:macro \cite [option:text,text]
+%TC:macro \citep [option:text,text]
+%TC:macro \citet [option:text,text]
+%TC:envir table 0 1
+%TC:envir table* 0 1
+%TC:envir tabular [ignore] word
+%TC:envir displaymath 0 word
+%TC:envir math 0 word
+%TC:envir comment 0 0
+%%
+%%
+%% The first command in your LaTeX source must be the \documentclass command.
+\documentclass[sigconf]{acmart}
+
+%%
+%% \BibTeX command to typeset BibTeX logo in the docs
+\AtBeginDocument{%
+  \providecommand\BibTeX{{%
+    Bib\TeX}}}
+
+%% Rights management information.  This information is sent to you
+%% when you complete the rights form.  These commands have SAMPLE
+%% values in them; it is your responsibility as an author to replace
+%% the commands and values with those provided to you when you
+%% complete the rights form.
+\setcopyright{acmcopyright}
+\copyrightyear{2023}
+\acmYear{2023}
+\acmDOI{XXXXXXX.XXXXXXX}
+
+%% These commands are for a PROCEEDINGS abstract or paper.
+\acmConference[ICCDA '23]{}{July, 2023}{GuiYang, CN}
+\acmPrice{15.00}
+\acmISBN{978-1-4503-XXXX-X/23/07}
+
+%%
+%% Submission ID.
+%% Use this when submitting an article to a sponsored event. You'll
+%% receive a unique submission ID from the organizers
+%% of the event, and this ID should be used as the parameter to this command.
+%%\acmSubmissionID{123-A56-BU3}
+
+%%
+%% For managing citations, it is recommended to use bibliography
+%% files in BibTeX format.
+%%
+%% You can then either use BibTeX with the ACM-Reference-Format style,
+%% or BibLaTeX with the acmnumeric or acmauthoryear sytles, that include
+%% support for advanced citation of software artefact from the
+%% biblatex-software package, also separately available on CTAN.
+%%
+%% Look at the sample-*-biblatex.tex files for templates showcasing
+%% the biblatex styles.
+%%
+
+%%
+%% The majority of ACM publications use numbered citations and
+%% references.  The command \citestyle{authoryear} switches to the
+%% "author year" style.
+%%
+%% If you are preparing content for an event
+%% sponsored by ACM SIGGRAPH, you must use the "author year" style of
+%% citations and references.
+%% Uncommenting
+%% the next command will enable that style.
+%%\citestyle{acmauthoryear}
+
+%%
+%% end of the preamble, start of the body of the document source.
+\begin{document}
+
+%%
+%% The "title" command has an optional parameter,
+%% allowing the author to define a "short title" to be used in page headers.
+\title{Decoupled Data Science - Tools for flexible, reproducible eScience}
+
+%%
+%% The "author" command and its associated commands are used to define
+%% the authors and their affiliations.
+%% Of note is the shared affiliation of the first two authors, and the
+%% "authornote" and "authornotemark" commands
+%% used to denote shared contribution to the research.
+\author{John Hawkins}
+\email{[email protected]}
+\orcid{1234-5678-9012}
+\affiliation{%
+  \institution{Getting-Data-Science-Done.com}
+  \city{Sydney}
+  \state{NSW}
+  \country{Australia}
+  \postcode{2000}
+}
+
+\renewcommand{\shortauthors}{Hawkins}
+
+\begin{abstract}
+\end{abstract}
+
+%% The code below is generated by the tool at http://dl.acm.org/ccs.cfm.
+%% Please copy and paste the code instead of the example below.
+
+\begin{CCSXML}
+<ccs2012>
+<concept>
+<concept_id>10002951.10003260.10003261</concept_id>
+<concept_desc>Information systems~Web searching and information discovery</concept_desc>
+<concept_significance>500</concept_significance>
+</concept>
+<concept>
+<concept_id>10002951.10003260.10003277.10003280</concept_id>
+<concept_desc>Information systems~Web log analysis</concept_desc>
+<concept_significance>500</concept_significance>
+</concept>
+<concept>
+<concept_id>10010147.10010257</concept_id>
+<concept_desc>Computing methodologies~Machine learning</concept_desc>
+<concept_significance>500</concept_significance>
+</concept>
+</ccs2012>
+\end{CCSXML}
+
+\ccsdesc[500]{Information systems~Web searching and information discovery}
+\ccsdesc[500]{Information systems~Web log analysis}
+\ccsdesc[500]{Computing methodologies~Machine learning}
+
+\keywords{Data Science, Experiment Tracking, Reproducible Science, Metadata Tracking}
+
+\maketitle
+
+\section{Introduction}
+
+Progress in scientific research depends heavily on accurate record keeping of previous
+experimental approaches and results. Failure to maintain these records impedes progress
+by making it difficult to reproduce work, or imposing the costs of repeatedly testing 
+failed lines of experimentation. This cost becomes particularly high in the age of the
+reproducibility crisis, as a many teams running the same experiments in parallel, without
+knowledge of each others work, has produced a factory line of un-reproducible results.
+
+Many Machine Learning experimentation frameworks focus on the task of making experiments
+easier to execute and deploy into production systems\cite{Alberti:2018,MolnerDomenech:2020}. 
+To do so they are often constructed for specific combinations of technology. This is a necessary limitation 
+to enable efficiency, but has the effect of limiting general applicability.
+Many other eScience frameworks focus on the lineage and management of data, referred to as 
+the so-called provenance problem \cite{Sahoo:2008,Conquest:2021}
+The goal of the provenance frameworks is sufficient auditibiliy of data sources that will 
+render eScience transparent and repeatable.
+
+Other frameworks and approaches focus on understanding how to do large scale collaborative science, or
+facilitate meta-level learning of various kinds\cite{Hunter:2005,Liu:2023}. The better we track the
+process of science as a whole, the better we can understand both how to improve scientific processes
+as well as data mine the history of science for phenomena that were difficult to detect.
+
+\section{Methodology}
+
+We begin by discussing all desirable elements required of an open science framework. These are drawn
+from observations of both how collabroative science works and the successful components of distributed
+scientific endeavours. These requirements are drawn from both sciences that are typically dependent
+on computational frameworks (computer science, bioinformatics, physics) and those that generally are not
+(social science, psychology).
+
+The key elements are as follows:
+
+\begin{itemize}
+ \item Provenance of Data Sources
+ \item Record of Data Processing
+ \item Reuse of Datasets
+ \item Tracking of Experiments and Results
+ \item Comparison of Methods and Results
+ \item Generation of Documentation
+ \item Reproducibility of Projects
+ \item Facilitation of Meta-Analysis
+\end{itemize}
+
+\subsection{Data}
+
+\subsection{Features}
+
+\subsection{Feature Importance}
+
+
+\section{Results}
+
+
+
+\section{Conclusion}
+
+
+\section{Acknowledgments}
+
+\bibliographystyle{ACM-Reference-Format}
+\bibliography{refs}
+
+\end{document}
+\endinput

docs/paper/refs.bib

@@ -0,0 +1,74 @@
+@article{MolnerDomenech:2020,
+  doi = {10.1088/1742-6596/1603/1/012025},
+  url = {https://dx.doi.org/10.1088/1742-6596/1603/1/012025},
+  year = {2020},
+  month = {sep},
+  publisher = {IOP Publishing},
+  volume = {1603},
+  number = {1},
+  pages = {012025},
+  author = {Antonio Molner Domenech and Alberto Guillén},
+  title = {ml-experiment: A Python framework for reproducible data science},
+  journal = {Journal of Physics: Conference Series},
+}
+
+@INPROCEEDINGS{Conquest:2021,
+  author={Conquest, Joseph and Stiber, Michael},
+  booktitle={2021 IEEE 17th International Conference on eScience (eScience)}, 
+  title={Software and Data Provenance as a Basis for eScience Workflow}, 
+  year={2021},
+  volume={},
+  number={},
+  pages={245-246},
+  doi={10.1109/eScience51609.2021.00043}
+}
+
+@article{Alberti:2018,
+  author = {Alberti, Michele and Pondenkandath, Vinaychandran and Gygli, Marcel and Ingold, Rolf and Liwicki, Marcus},
+  year = {2018},
+  month = {04},
+  pages = {},
+  title = {DeepDIVA: A Highly-Functional Python Framework for Reproducible Experiments}
+}
+
+@article{Miksa:2017,
+  author = {Miksa, Tomasz and Rauber, Andreas},
+  year = {2017},
+  month = {01},
+  pages = {},
+  title = {Using ontologies for verification and validation of workflow-based experiments},
+  volume = {43},
+  journal = {Web Semantics: Science, Services and Agents on the World Wide Web},
+  doi = {10.1016/j.websem.2017.01.002}
+}
+
+@article{Sahoo:2008,
+  author = {Sahoo, Satya and Sheth, Amit and Henson, Cory},
+  year = {2008},
+  month = {08},
+  pages = {46 - 54},
+  title = {Semantic Provenance for eScience: Managing the Deluge of Scientific Data},
+  volume = {12},
+  journal = {Internet Computing, IEEE},
+  doi = {10.1109/MIC.2008.86}
+}
+
+@article{Hunter:2005,
+  author = {Hunter, Jane and Cheung, Kwok},
+  year = {2005},
+  month = {01},
+  pages = {},
+  title = {Generating eScience Workflows from Statistical Analysis of Prior Data}
+}
+
+@article{Liu:2023,
+  author = {Liu, Lu and Jones, Benjamin F. and Uzzi, Brian and Wang, Dashun},
+  year = {2023},
+  month = {06},
+  pages = {2397-3374},
+  title = {Data, measurement and empirical methods in the science of science},
+  journal = {Nature Human Behaviour},
+  doi = {10.1038/s41562-023-01562-4}
+}
+
+