WIP: More edits

.github/workflows/publish.yml

@@ -35,11 +35,30 @@ jobs:
             - name: Render Quarto
               uses: quarto-dev/quarto-actions/render@v2
 
+
             - name: Publish to GitHub Pages
               if: github.event_name != 'pull_request'
               uses: quarto-dev/quarto-actions/publish@v2
               with:
                 render: false
                 target: gh-pages
               env:
-                GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+                GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+
+            - name: Commit PDF
+              if: github.event_name != 'pull_request'
+              uses: EndBug/add-and-commit@v9
+              with:
+                add: '_manuscript/index.pdf'
+                author_name: 'GitHub Actions'
+                message: 'Add poster.pdf at ${{ github.sha }}'
+
+
+            - name: Commit DOCX
+              if: github.event_name != 'pull_request'
+              uses: EndBug/add-and-commit@v9
+              with:
+                add: '_manuscript/index.docx'
+                author_name: 'GitHub Actions'
+                message: 'Add poster.pdf at ${{ github.sha }}'
+

_quarto.yml

@@ -10,8 +10,11 @@ format:
       hypothesis: true
     toc: true
 
-  # docx: default
-  # jats: default
+  docx:
+    toc: true
+    number-sections: true
+    highlight-style: github
+
   pdf: default
 
 number-sections: true

index.qmd

@@ -7,16 +7,16 @@ heavy construction.
 
 Recent progress in machine learning and artificial intelligence promises to
 advance research and understanding across a wide range of fields and
-activities. In tandem, an increased awareness of the importance of open data
-for reproducibility and scientific transparency is making inroads in fields
-that have not traditionally produced large publicly available datasets. Data
-sharing requirements from publishers and funders, as well as from other
-stakeholders, have also created pressure to make datasets with research and/or
-public interest value available through digital repositories. However, to make
-the best use of existing data, and facilitate the creation of useful future
+activities. In tandem, increased awareness of the importance of open data for
+reproducibility and scientific transparency is making inroads in fields that
+have not traditionally produced large publicly available datasets. Data sharing
+requirements from publishers and funders, as well as from other stakeholders,
+have also created pressure to make datasets with research and/or public
+interest value available through digital repositories. However, to make the
+best use of existing data, and facilitate the creation of useful future
 datasets, robust, interoperable and usable standards need to evolve and adapt
 over time. The open-source development model provides significant potential
-benefits to the process of standard creation and adaptation. In particular,
+benefits to the process of standard creation and adaptation. In particular, the
 development and adaptation of standards can use long-standing socio-technical
 processes that have been key to managing the development of software, and allow
 incorporating broad community input into the formulation of these standards. By
@@ -26,14 +26,17 @@ validation), processes such as automated testing and continuous integration,
 which have been important in the development of open-source software, can be
 adopted in defining data and metadata standards as well. Similarly, open-source
 governance provides a range of stakeholders a voice in the development of
-standards, potentially enabling use-cases and concerns that would not be taken
+standards, potentially enabling use cases and concerns that would not be taken
 into account in a top-down model of standards development. On the other hand,
 open-source models carry unique risks that need to be incorporated into the
 process.
 
 
 {{< include sections/01-introduction.qmd >}}
 {{< include sections/02-challenges.qmd >}}
+{{< include sections/xx-use-cases.qmd >}}
+{{< include sections/xx-cross-sector.qmd >}}
 {{< include sections/03-recommendations.qmd >}}
+{{< include sections/04-acknowledgments.qmd >}}
 
 

references.bib

@@ -1,3 +1,125 @@
+
+
+@book{Mons2018DataStewardshipBook,
+	address = {Milton},
+	author = {Mons, Barend},
+	date-added = {2024-06-17 11:30:13 -0700},
+	date-modified = {2024-06-17 11:30:13 -0700},
+	doi = {10.1201/9781315380711},
+	edition = {1},
+	id = {cdi{\_}askewsholts{\_}vlebooks{\_}9781315351148},
+	isbn = {9780815348184},
+	keywords = {big data ; Bioinformatics ; Business enterprises ; COMPUTERSCIENCEnetBASE ; data curation ; data formatting ; data integration ; Data Preparation \& Mining ; Data protection ; data publishing ; Database management ; FAIR data ; Information resources management ; Information technology ; INFORMATIONSCIENCEnetBASE ; SCI-TECHnetBASE ; Statistical Computing ; STATSnetBASE ; STMnetBASE},
+	n2 = {Data Stewardship for Open Science: Implementing FAIR Principles has been written with the intention of making scientists, funders, and innovators in all disciplines and stages of their professional activities broadly aware of the need, complexity, and challenges associated with open science, modern science communication, and data stewardship. The FAIR principles are used as a guide throughout the text, and this book should leave experimentalists consciously incompetent about data stewardship and motivated to respect data stewards as representatives of a new profession, while possibly motivating others to consider a career in the field. The ebook, avalable for no additional cost when you buy the paperback, will be updated every 6 months on average (providing that significant updates are needed or avaialble). Readers will have the opportunity to contribute material towards these updates, and to develop their own data management plans, via the free Data Stewardship Wizard .},
+	publisher = {CRC Press},
+	title = {Data Stewardship for Open Science: Implementing FAIR Principles},
+	volume = {1},
+	year = {2018},
+	bdsk-url-1 = {https://doi.org/10.1201/9781315380711}}
+
+
+@MISC{Koch2012-ve,
+  title        = "Observatories of the mind",
+  booktitle    = "Nature Publishing Group {UK}",
+  author       = "Koch, Christof and Clay Reid, R",
+  abstract     = "An ambitious project to map the mouse brain at the Allen
+                  Institute for Brain Science is a huge undertaking that may
+                  unify neuroscience, argue Christof Koch and R. Clay Reid.",
+  month        =  mar,
+  year         =  2012,
+  howpublished = "\url{http://dx.doi.org/10.1038/483397a}",
+  note         = "Accessed: 2024-6-17",
+  language     = "en"
+}
+
+
+
+@ARTICLE{Basaglia2023-dq,
+  title    = "Data preservation in high energy physics",
+  author   = "Basaglia, T and Bellis, M and Blomer, J and Boyd, J and Bozzi, C
+              and Britzger, D and Campana, S and Cartaro, C and Chen, G and
+              Couturier, B and David, G and Diaconu, C and Dobrin, A and
+              Duellmann, D and Ebert, M and Elmer, P and Fernandes, J and
+              Fields, L and Fokianos, P and Ganis, G and Geiser, A and Gheata,
+              M and Lopez, J B Gonzalez and Hara, T and Heinrich, L and
+              Hildreth, M and Herner, K and Jayatilaka, B and Kado, M and
+              Keeble, O and Kohls, A and Naim, K and Lange, C and
+              Lassila-Perini, K and Levonian, S and Maggi, M and Marshall, Z
+              and Vila, P Mato and Me{\v c}ionis, A and Morris, A and Piano, S
+              and Potekhin, M and Schr{\"o}der, M and Schwickerath, U and
+              Sexton-Kennedy, E and {\v S}imko, T and Smith, T and South, D and
+              Verbytskyi, A and Vidal, M and Vivace, A and Wang, L and Watt, G
+              and Wenaus, T and {DPHEP Collaboration}",
+  abstract = "Data preservation is a mandatory specification for any present
+              and future experimental facility and it is a cost-effective way
+              of doing fundamental research by exploiting unique data sets in
+              the light of the continuously increasing theoretical
+              understanding. This document summarizes the status of data
+              preservation in high energy physics. The paradigms and the
+              methodological advances are discussed from a perspective of more
+              than ten years of experience with a structured effort at
+              international level. The status and the scientific return related
+              to the preservation of data accumulated at large collider
+              experiments are presented, together with an account of ongoing
+              efforts to ensure long-term analysis capabilities for ongoing and
+              future experiments. Transverse projects aimed at generic
+              solutions, most of which are specifically inspired by open
+              science and FAIR principles, are presented as well. A prospective
+              and an action plan are also indicated.",
+  journal  = "The European Physical Journal C",
+  volume   =  83,
+  number   =  9,
+  pages    = "795",
+  month    =  sep,
+  year     =  2023
+}
+
+
+
+
+@inproceedings{wells1979fits,
+  title={FITS-a flexible image transport system},
+  author={Wells, Donald Carson and Greisen, Eric W},
+  booktitle={Image processing in astronomy},
+  pages={445},
+  year={1979}
+}
+
+@ARTICLE{Rubel2022NWB,
+  title    = "The Neurodata Without Borders ecosystem for neurophysiological
+              data science",
+  author   = "R{\"u}bel, Oliver and Tritt, Andrew and Ly, Ryan and Dichter,
+              Benjamin K and Ghosh, Satrajit and Niu, Lawrence and Baker,
+              Pamela and Soltesz, Ivan and Ng, Lydia and Svoboda, Karel and
+              Frank, Loren and Bouchard, Kristofer E",
+  abstract = "The neurophysiology of cells and tissues are monitored
+              electrophysiologically and optically in diverse experiments and
+              species, ranging from flies to humans. Understanding the brain
+              requires integration of data across this diversity, and thus
+              these data must be findable, accessible, interoperable, and
+              reusable (FAIR). This requires a standard language for data and
+              metadata that can coevolve with neuroscience. We describe design
+              and implementation principles for a language for neurophysiology
+              data. Our open-source software (Neurodata Without Borders, NWB)
+              defines and modularizes the interdependent, yet separable,
+              components of a data language. We demonstrate NWB's impact
+              through unified description of neurophysiology data across
+              diverse modalities and species. NWB exists in an ecosystem, which
+              includes data management, analysis, visualization, and archive
+              tools. Thus, the NWB data language enables reproduction,
+              interchange, and reuse of diverse neurophysiology data. More
+              broadly, the design principles of NWB are generally applicable to
+              enhance discovery across biology through data FAIRness.",
+  journal  = "Elife",
+  volume   =  11,
+  month    =  oct,
+  year     =  2022,
+  keywords = "FAIR data; Neurophysiology; archive; data ecosystem; data
+              language; data standard; human; mouse; neuroscience; rat",
+  language = "en"
+}
+
+
 @ARTICLE{Gorgolewski2016BIDS,
   title    = "The {Brain} {Imaging} {Data} {Structure}, a format for organizing and
               describing outputs of neuroimaging experiments",