ground.bib

@misc{basel3,
  title="{The Basel iii Accord}",
  author="{The Basel Committee}",
  key="Basel",
  year=2016,
  note={\url{http://www.basel-iii-accord.com}, retrieved November, 2016.}
}
@book{cheney2009provenance,
  title={Provenance in Databases},
  author={Cheney, James and Chiticariu, Laura and Tan, Wang-Chiew},
  year={2009},
  publisher={Now Publishers Inc}
}
@book{inmon2005building,
  title={Building the data warehouse},
  author={Inmon, William H},
  year={2005},
  publisher={John Wiley \& Sons}
}
@misc{gartner,
  title={Gartner Says Every Budget is Becoming an {IT} Budget},
  author={Gartner},
  month=oct,
  year=2012,
  number=2208015,
  note={\url{http://www.gartner.com/newsroom/id/2208015}
  }
}
@book{patil2012data,
  title={Data Jujitsu: The Art of Turning Data into Product},
  author={Patil, DJ},
  year={2012},
  publisher={O'Reilly Media}
}
@inproceedings{zeldovich2008securing,
  title={Securing Distributed Systems with Information Flow Control.},
  author={Zeldovich, Nickolai and Boyd-Wickizer, Silas and Mazieres, David},
  booktitle={NSDI},
  volume={8},
  pages={293--308},
  year={2008}
}
@misc{starwarskid,
    title="{Star Wars Kid: The Data Dump}",
    key={star wars},
    year=2008,
    note={\url{http://waxy.org/2008/05/star_wars_kid_the_data_dump/}, retrieved June, 2008.}
}
@book{stonebraker1987design,
  title={The design of the {Postgres} storage system},
  author={Stonebraker, Michael},
  year={1987},
  publisher={Morgan Kaufmann Publishers Burlington}
}
@book{loshin2010master,
  title={Master Data Management},
  author={Loshin, David},
  year={2010},
  publisher={Morgan Kaufmann}
}
@book{grades16,
  editor    = {Peter Boncz and Josep{-}Lluis Larriba{-}Pey},
  title={International Workshop on Graph Data Management
               Experiences and Systems {(GRADES)}},
  year=2016,
  publisher={{ACM}}
}

@inproceedings{mcsherry2015scalability,
  title="{Scalability! But at what COST?}",
  author={McSherry, Frank and Isard, Michael and Murray, Derek G},
  booktitle={HotOS XV},
  year={2015}
}

@inproceedings{kandogan2015labbook,
  title={Lab{B}ook: {M}etadata-driven social collaborative data analysis},
  author={Kandogan, Eser and Roth, Mary and Schwarz, Peter and Hui, Joshua and Terrizzano, Ignacio and Christodoulakis, Christina and Miller, Ren{\'e}e J},
  booktitle={Big Data (Big Data), 2015 IEEE International Conference on},
  pages={431--440},
  year={2015},
  organization={IEEE}
}

@article{clio,
  title={The {C}lio project: {M}anaging heterogeneity},
  author={Miller, Ren{\'e}e J and Hern{\'a}ndez, Mauricio A and Haas, Laura M and Yan, Ling-Ling and Ho, CT Howard and Fagin, Ronald and Popa, Lucian},
  journal={SIGMOD Record},
  volume={30},
  number={1},
  pages={78--83},
  year={2001}
}

@inproceedings{goods,
  title={Goods: {O}rganizing {G}oogle's Datasets},
  author={Halevy, Alon and Korn, Flip and Noy, Natalya F and Olston, Christopher and Polyzotis, Neoklis and Roy, Sudip and Whang, Steven Euijong},
  booktitle={Proceedings of the 2016 International Conference on Management of Data},
  pages={795--806},
  year={2016},
  organization={ACM}
}

@inproceedings{vistrails,
  title={Vis{T}rails: {V}isualization meets data management},
  author={Callahan, Steven P and Freire, Juliana and Santos, Emanuele and Scheidegger, Carlos E and Silva, Cl{\'a}udio T and Vo, Huy T},
  booktitle={Proceedings of the 2006 ACM SIGMOD international conference on Management of data},
  pages={745--747},
  year={2006},
  organization={ACM}
}

@inproceedings{datahub,
  title={Data{H}ub: {C}ollaborative data science \& dataset version management at scale},
  author={Bhardwaj, Anant and Bhattacherjee, Souvik and Chavan, Amit and Deshpande, Amol and Elmore, Aaron J and Madden, Samuel and Parameswaran, Aditya G},
  booktitle={CIDR},
  year={2015}
}

@article{decibel,
  title={Decibel: {T}he relational dataset branching system},
  author={Maddox, Michael and Goehring, David and Elmore, Aaron J and Madden, Samuel and Parameswaran, Aditya and Deshpande, Amol},
  journal={Proceedings of the VLDB Endowment},
  volume={9},
  number={9},
  pages={624--635},
  year={2016},
  publisher={VLDB Endowment}
}

@article{provdb,
  title={Prov{DB}: {A} System for Lifecycle Management of Collaborative Analysis Workflows},
  author={Miao, Hui and Chavan, Amit and Deshpande, Amol},
  journal={arXiv preprint arXiv:1610.04963},
  year={2016}
}

@inproceedings{burrito,
  title={{BURRITO}: {W}rapping Your Lab Notebook in Computational Infrastructure.},
  author={Guo, Philip J and Seltzer, Margo},
  booktitle={Workshop on the Theory and Practice of Provenance (TaPP)},
  year={2012}
}

@inproceedings{reprozip,
  author    = {Fernando Seabra Chirigati and
               Dennis E. Shasha and
               Juliana Freire},
  title     = {Repro{Z}ip: {U}sing Provenance to Support Computational Reproducibility},
  booktitle = {Workshop on the Theory and Practice of Provenance (TaPP)},
  year      = {2013},
}

@inproceedings{datatamer,
  title={Data Curation at Scale: {T}he Data Tamer System.},
  author={Stonebraker, Michael and Bruckner, Daniel and Ilyas, Ihab F and Beskales, George and Cherniack, Mitch and Zdonik, Stanley B and Pagan, Alexander and Xu, Shan},
  booktitle={CIDR},
  year={2013}
}

@article{deepdive,
  title={Deep{D}ive: {W}eb-scale Knowledge-base Construction using Statistical Learning and Inference.},
  author={Niu, Feng and Zhang, Ce and R{\'e}, Christopher and Shavlik, Jude W},
  journal={VLDS},
  volume={12},
  pages={25--28},
  year={2012}
}

@inproceedings{yago,
  title={Yago: {A} core of semantic knowledge},
  author={Suchanek, Fabian M and Kasneci, Gjergji and Weikum, Gerhard},
  booktitle={Proceedings of the 16th international conference on World Wide Web},
  pages={697--706},
  year={2007},
  organization={ACM}
}

@inproceedings{myers1999jflow,
  title={J{F}low: {P}ractical mostly-static information flow control},
  author={Myers, Andrew C},
  booktitle={Proceedings of the 26th ACM SIGPLAN-SIGACT symposium on Principles of programming languages},
  pages={228--241},
  year={1999},
  organization={ACM}
}

@article{webtables,
  title={Web{T}ables: {E}xploring the power of tables on the web},
  author={Cafarella, Michael J and Halevy, Alon and Wang, Daisy Zhe and Wu, Eugene and Zhang, Yang},
  journal={Proceedings of the VLDB Endowment},
  volume={1},
  number={1},
  pages={538--549},
  year={2008},
  publisher={VLDB Endowment}
}

@article{adelfio2013schema,
  title={Schema extraction for tabular data on the web},
  author={Adelfio, Marco D and Samet, Hanan},
  journal={Proceedings of the VLDB Endowment},
  volume={6},
  number={6},
  pages={421--432},
  year={2013},
  publisher={VLDB Endowment}
}

@inproceedings{wrangler,
  title={Wrangler: {I}nteractive visual specification of data transformation scripts},
  author={Kandel, Sean and Paepcke, Andreas and Hellerstein, Joseph and Heer, Jeffrey},
  booktitle={Proceedings of the SIGCHI Conference on Human Factors in Computing Systems},
  pages={3363--3372},
  year={2011},
  organization={ACM}
}

@inproceedings{flashextract,
  title={Flash{E}xtract: {A} framework for data extraction by examples},
  author={Le, Vu and Gulwani, Sumit},
  booktitle={ACM SIGPLAN Notices},
  volume={49},
  pages={542--553},
  year={2014},
  organization={ACM}
}

@article{manyeyes,
  title={Many{E}yes: {A} site for visualization at internet scale},
  author={Viegas, Fernanda B and Wattenberg, Martin and Van Ham, Frank and Kriss, Jesse and McKeon, Matt},
  journal={IEEE transactions on visualization and computer graphics},
  volume={13},
  number={6},
  pages={1121--1128},
  year={2007},
  publisher={IEEE}
}

@inproceedings{willett,
  title={Comment{S}pace: {S}tructured support for collaborative visual analysis},
  author={Willett, Wesley and Heer, Jeffrey and Hellerstein, Joseph and Agrawala, Maneesh},
  booktitle={Proceedings of the SIGCHI conference on Human Factors in Computing Systems},
  pages={3131--3140},
  year={2011},
  organization={ACM}
}

@techreport{dresnerdataprep,
  title="{2016 End User Data Preparation Market Study}",
  author={Howard Dresner},
  year={2016},
  institution={Dresner Advisory Services, LLC}
}

@techreport{dresnercollectiveinsights,
  title="{2016 Collective Insights Market Study Report}",
  author={Howard Dresner},
  year={2016},
  institution={Dresner Advisory Services, LLC}
}

@techreport{gartnermetadata,
  title="{Magic Quadrant for Metadata Management Solutions}",
  author={Guido De Simoni and Roxane Edjlali},
  institution={Gartner, Inc.},
  year={2016}
}

@techreport{gartnerdataprep,
  title="{Market Guide for Self-Service Data Preparation}",
  author={Rita L. Sallam and Paddy Forry and Ehtisham Zaidi and Shubhangi Vashisth},
  institution={Gartner, Inc.},
  year={2016}
}

@techreport{gartnerdatacatalog,
  title={How Chief Data Officers Can Use an Information Catalog to Maximize Business Value From Information Assets},
  author={Alan D. Duncan and Douglas Laney and Guido De Simoni},
  institution={Gartner, Inc.},
  year={2016}
}



@inproceedings{sculley2,
title = {Machine Learning: The High Interest Credit Card of Technical Debt},
author  = {D. Sculley and Gary Holt and Daniel Golovin and Eugene Davydov and Todd Phillips and Dietmar Ebner and Vinay Chaudhary and Michael Young},
year  = 2014,
booktitle = {SE4ML: Software Engineering for Machine Learning (NIPS 2014 Workshop)}
}


@inproceedings{Crankshaw15,
  author    = {Daniel Crankshaw and
               Peter Bailis and
               Joseph E. Gonzalez and
               Haoyuan Li and
               Zhao Zhang and
               Michael J. Franklin and
               Ali Ghodsi and
               Michael I. Jordan},
  title     = {The Missing Piece in Complex Analytics: Low Latency, Scalable Model Management and Serving with Velox},
  booktitle = {{CIDR} 2015, Seventh Biennial Conference on Innovative Data Systems},
  year      = {2015}
}

@misc{tfserving,
  title = {{TensorFlow Serving}},
  howpublished = {\url{https://tensorflow.github.io/serving}},
  key = {tfserving},
}

@inproceedings{bernstein1994overview,
  title={An overview of repository technology},
  author={Bernstein, Philip A and Dayal, Umeshwar},
  booktitle={VLDB},
  volume={94},
  pages={705--713},
  year={1994}
}

@article{bernstein1999microsoft,
  title={Microsoft repository version 2 and the open information model},
  author={Bernstein, Philip A and Bergstraesser, Thomas and Carlson, Jason and Pal, Shankar and Sanders, Paul and Shutt, David},
  journal={Information Systems},
  volume={24},
  number={2},
  pages={71--98},
  year={1999},
  publisher={Elsevier}
}