@inproceedings{21d7fe996d4a444a92bf721a7fa03971,
title = "Approximated summarization of data provenance",
abstract = "Many modern applications involve collecting large amounts of data from multiple sources, and then aggregating and manipulating it in intricate ways. The complexity of such applications, combined with the size of the collected data, makes it difficult to understand how the resulting information was derived. Data provenance has proven helpful in this respect, however, maintaining and presenting the full and exact provenance information may be infeasible due to its size and complexity. We therefore introduce the notion of approximated summarized provenance, which provides a compact representation of the provenance at the possible cost of information loss. Based on this notion, we present a novel provenance summarization algorithm which, based on the semantics of the underlying data and the intended use of provenance, outputs a summary of the input provenance. Experiments measure the conciseness and accuracy of the resulting provenance summaries, and improvement in provenance usage time.",
keywords = "Crowd-sourcing applications, Provenance, Provisioning",
author = "Eleanor Ainy and Pierre Bourhis and Davidson, \{Susan B.\} and Daniel Deutch and Tova Milo",
note = "Publisher Copyright: {\textcopyright} 2015 ACM.; 24th ACM International Conference on Information and Knowledge Management, CIKM 2015 ; Conference date: 19-10-2015 Through 23-10-2015",
year = "2015",
month = oct,
day = "17",
doi = "10.1145/2806416.2806429",
language = "الإنجليزيّة",
series = "International Conference on Information and Knowledge Management, Proceedings",
publisher = "Association for Computing Machinery",
pages = "483--492",
booktitle = "CIKM 2015 - Proceedings of the 24th ACM International Conference on Information and Knowledge Management",
address = "الولايات المتّحدة",
}