author = {Brachmann, Michael and Spoth, William and Kennedy, Oliver and Glavic, Boris and Mueller, Heiko and Castelo, Sonia and Bautista, Carlos and Freire, Juliana},
title = {Your notebook is not crumby enough, REPLace it},
booktitle = {CIDR},
year = {2020}
}
@inproceedings{brachmann:2019:sigmod:data,
author = {Brachmann, Mike and Bautista, Carlos and Castelo, Sonia and Feng, Su and Freire, Juliana and Glavic, Boris and Kennedy, Oliver and Mueller, Heiko and Rampin, Remi and Spoth, William and Yang, Ying},
title = {Data Debugging and Exploration with Vizier},
booktitle = {SIGMOD-Demo},
year = {2019}
}
@inproceedings{DBLP:conf/tapp/PimentelBMF15,
author = {Jo{\~{a}}o Felipe Pimentel and
Vanessa Braganholo and
Leonardo Murta and
Juliana Freire},
title = {Collecting and Analyzing Provenance on Interactive Notebooks: When
IPython Meets noWorkflow},
booktitle = {TaPP},
publisher = {{USENIX} Association},
year = {2015}
}
@inproceedings{DBLP:conf/ipaw/PimentelFMB16,
author = {Jo{\~{a}}o Felipe Pimentel and
Juliana Freire and
Leonardo Murta and
Vanessa Braganholo},
title = {Fine-Grained Provenance Collection over Scripts Through Program Slicing},
booktitle = {{IPAW}},
series = {Lecture Notes in Computer Science},
volume = {9672},
pages = {199--203},
publisher = {Springer},
year = {2016}
}
@article{DBLP:journals/ese/PimentelMBF21,
author = {Jo{\~{a}}o Felipe Pimentel and
Leonardo Murta and
Vanessa Braganholo and
Juliana Freire},
title = {Understanding and improving the quality and reproducibility of Jupyter
author = {Stephen Macke and Aditya G. Parameswaran and Hongpu Gong and Doris Jung Lin Lee and Doris Xin and Andrew Head},
title = {Fine-Grained Lineage for Safer Notebook Interactions},
pdf = {/Users/lord_pretzel/Documents/PaperGit/Papers/macke-21-fglsnin-2021-Fine-Grained_Lineage_for_Safer_Notebook_Interactions-Macke_Parameswaran.pdf},
author = {Sheeba Samuel and Birgitta K{\"{o}}nig{-}Ries},
title = {ProvBook: Provenance-based Semantic Enrichment of Interactive
Notebooks for Reproducibility},
pdf = {/Users/lord_pretzel/Documents/PaperGit/Papers/samuel-18-p-2018-ProvBook_Provenance-based_Semantic_Enrichment_of_Interactive_Notebooks_for_Reproducibility-Samuel_K_o_nig_-_Rie.pdf},
booktitle = {Proceedings of the {ISWC} 2018 Posters {\&} Demonstrations,
Industry and Blue Sky Ideas Tracks co-located with 17th
International Semantic Web Conference {(ISWC} 2018), Monterey,
author = {Adriane Chapman and Paolo Missier and Giulia Simonelli and Riccardo Torlone},
title = {Capturing and Querying Fine-Grained Provenance of Preprocessing Pipelines in Data Science},
pdf = {/Users/lord_pretzel/Documents/PaperGit/Papers/chapman-20-cqfgppp-2020-Capturing_and_Querying_Fine-Grained_Provenance_of_Preprocessing_Pipelines_in_Data_Science-Chapman_Missier.pdf},
author = {Lukas Rupprecht and James C. Davis and Constantine Arnold and
Yaniv Gur and Deepavali Bhagwat},
title = {Improving Reproducibility of Data Science Pipelines Through
Transparent Provenance Capture},
pdf = {/Users/lord_pretzel/Documents/PaperGit/Papers/rupprecht-20-imrdsptt-2020-Improving_Reproducibility_of_Data_Science_Pipelines_Through_Transparent_Provenance_Capture-Rupprecht_Davis.pdf},
author = {Chapman, Adriane and Sasikant, Abhirami and Simonelli, Giulia
and Missier, Paolo and Torlone, Riccardo},
booktitle = {Provenance in Data Science},
pages = {25--45},
publisher = {Springer},
title = {The Right (Provenance) Hammer for the Job: A Comparison of
Data Provenance Instrumentation},
year = 2021,
}
@inproceedings{namaki-20-v,
author = {Mohammad Hossein Namaki and Avrilia Floratou and Fotis Psallidas and Subru Krishnan and Ashvin Agrawal and Yinghui Wu and Yiwen Zhu and Markus Weimer},
title = {Vamsa: Automated Provenance Tracking in Data Science Scripts},
pdf = {/Users/lord_pretzel/Documents/PaperGit/Papers/namaki-20-v-2020-Vamsa_Automated_Provenance_Tracking_in_Data_Science_Scripts-Namaki_Floratou.pdf},
booktitle = {{KDD} '20: The 26th {ACM} {SIGKDD} Conference on Knowledge Discovery and Data Mining, Virtual Event, CA, USA, August 23-27, 2020},
editor = {Rajesh Gupta and Yan Liu and Jiliang Tang and B. Aditya Prakash},
publisher = {{ACM}},
isbn = {978-1-4503-7998-4},
}
@article{silva-18-d,
author = {V{\'{\i}}tor Silva and Daniel de Oliveira and Marta Mattoso
and Patrick Valduriez},
title = {Dfanalyzer: Runtime Dataflow Analysis of Scientific
Applications Using Provenance},
pdf = {/Users/lord_pretzel/Documents/PaperGit/Papers/silva-18-d-2018-Dfanalyzer_Runtime_Dataflow_Analysis_of_Scientific_Applications_Using_Provenance-Silva_Oliveira.pdf},
author = {Jo{\~{a}}o Felipe Pimentel and Juliana Freire and Leonardo Murta and Vanessa Braganholo},
title = {A Survey on Collecting, Managing, and Analyzing Provenance From Scripts},
pdf = {/Users/lord_pretzel/Documents/PaperGit/Papers/pimentel-19-scmanpfs-2019-A_Survey_on_Collecting_Managing_and_Analyzing_Provenance_From_Scripts-Pimentel_Freire.pdf},
author = {Chris A. Silles and Andrew R. Runnalls},
title = {Provenance-Awareness in {R}},
booktitle = {Provenance and Annotation of Data and Processes - Third International Provenance and Annotation Workshop, {IPAW} 2010, Troy, NY, USA, June 15-16, 2010. Revised Selected Papers},
author = {Jo{\~{a}}o Felipe Pimentel and Leonardo Murta and Vanessa Braganholo and Juliana Freire},
title = {Noworkflow: a Tool for Collecting, Analyzing, and Managing Provenance From Python Scripts},
pdf = {/Users/lord_pretzel/Documents/PaperGit/Papers/pimentel-17-n-2017-Noworkflow_a_Tool_for_Collecting_Analyzing_and_Managing_Provenance_From_Python_Scripts-Pimentel_Murta.pdf},
Author = {Davidson, Susan B. and Cohen-Boulakia, Sarah and Eyal, Anat and Lud{\"a}scher, Bertram and McPhillips, Timothy and Bowers, Shawn and Freire, Juliana},
Date-Added = {2009-11-19 10:26:42 +0100},
pdf = {/Users/lord_pretzel/Documents/PaperGit/Papers/DCELMBF07_Provenance in Scientific Workflow Systems_0.pdf},
Date-Modified = {2013-08-21 01:11:11 +0000},
Journal = {IEEE Data Engineering Bulletin},
Keywords = {provenance; CS595Background},
Number = {4},
Pages = {44--50},
Title = {{Provenance in Scientific Workflow Systems}},