<?xml version="1.0" encoding="utf-8"?>
<export-example>
  <doc>
    <id>3100</id>
    <completedYear/>
    <publishedYear>2014</publishedYear>
    <thesisYearAccepted/>
    <language>deu</language>
    <pageFirst>131</pageFirst>
    <pageLast>134</pageLast>
    <pageNumber/>
    <edition/>
    <issue>2</issue>
    <volume>14</volume>
    <type>article</type>
    <publisherName>Springer Nature</publisherName>
    <publisherPlace/>
    <creatingCorporation/>
    <contributingCorporation/>
    <belongsToBibliography>0</belongsToBibliography>
    <completedDate>--</completedDate>
    <publishedDate>--</publishedDate>
    <thesisDateAccepted>--</thesisDateAccepted>
    <title language="deu">Cloud-Technologien in der Hochschullehre – Pflicht oder Kür?</title>
    <abstract language="deu">Ein eigenes Themenheft zum Datenmanagement in der Cloud dient uns als Anlass, die Präsenz von Cloud-Themen in der akademischen Datenbanklehre zu erfassen. In diesem Artikel geben wir die Ergebnisse einer Umfrage innerhalb der Fachgruppe Datenbanksysteme durch den Arbeitskreis Datenmanagement in der Cloud wieder. Dozentinnen und Dozenten von über zwanzig Hochschulen nahmen an der Umfrage teil. Es zeigt sich deutlich, dass sich das Thema „Cloud“ in der Hochschullehre zunehmend etabliert, jedoch überwiegend als ergänzendes Angebot, und seltener in der grundständigen Lehre verankert. Wir fassen die Ergebnisse unserer Umfrage zusammen und wagen Deutungsversuche.</abstract>
    <parentTitle language="deu">Datenbank-Spektrum</parentTitle>
    <identifier type="doi">10.1007/s13222-014-0161-2</identifier>
    <enrichment key="opus.import.date">2022-03-17T06:05:16+00:00</enrichment>
    <enrichment key="opus.source">sword</enrichment>
    <enrichment key="opus.import.user">importuser</enrichment>
    <enrichment key="BegutachtungStatus">peer-reviewed</enrichment>
    <licence>Keine Lizenz - Es gilt das deutsche Urheberrecht: § 53 UrhG</licence>
    <author>Stefanie Scherzinger</author>
    <author>Andreas Thor</author>
    <subject>
      <language>deu</language>
      <type>uncontrolled</type>
      <value>Cloud Computing</value>
    </subject>
    <subject>
      <language>deu</language>
      <type>uncontrolled</type>
      <value>Hochschullehre</value>
    </subject>
    <collection role="institutes" number="FakIM">Fakultät Informatik und Mathematik</collection>
    <collection role="othforschungsschwerpunkt" number="16315">Information und Kommunikation</collection>
  </doc>
  <doc>
    <id>2603</id>
    <completedYear/>
    <publishedYear>2019</publishedYear>
    <thesisYearAccepted/>
    <language>eng</language>
    <pageFirst>33</pageFirst>
    <pageLast>38</pageLast>
    <pageNumber/>
    <edition/>
    <issue>2</issue>
    <volume>48</volume>
    <type>article</type>
    <publisherName>ACM</publisherName>
    <publisherPlace/>
    <creatingCorporation/>
    <contributingCorporation/>
    <belongsToBibliography>0</belongsToBibliography>
    <completedDate>--</completedDate>
    <publishedDate>--</publishedDate>
    <thesisDateAccepted>--</thesisDateAccepted>
    <title language="eng">Build your own SQL-on-Hadoop Query Engine A Report on a Term Project in a Master-level Database Course</title>
    <abstract language="eng">This is a report on a course taught at OTH Regensburg in the summer term of 2018. The students in this course built their own SQL-on-Hadoop engine as a term project in just 8 weeks. miniHive is written in Python and compiles SQL queries into MapReduce workflows. These are then executed on Hadoop. miniHive performs generic query optimizations (selection and projection pushdown, or cost-based join reordering), as well as MapReduce-specific optimizations.&#13;
The course was taught in English, using a flipped classroom model. The course material was mainly compiled from third-party teaching videos. This report describes the course setup, the miniHive milestones, and gives a short review of the most successful student projects.</abstract>
    <parentTitle language="eng">ACM SIGMOD Record</parentTitle>
    <identifier type="doi">10.1145/3377330.3377336</identifier>
    <enrichment key="opus.import.date">2022-01-27T15:41:12+00:00</enrichment>
    <enrichment key="opus.source">sword</enrichment>
    <enrichment key="opus.import.user">importuser</enrichment>
    <enrichment key="BegutachtungStatus">peer-reviewed</enrichment>
    <enrichment key="opus.doi.autoCreate">false</enrichment>
    <enrichment key="opus.urn.autoCreate">false</enrichment>
    <licence>Keine Lizenz - Es gilt das deutsche Urheberrecht: § 53 UrhG</licence>
    <author>Stefanie Scherzinger</author>
    <collection role="institutes" number="FakIM">Fakultät Informatik und Mathematik</collection>
    <collection role="othforschungsschwerpunkt" number="16314">Lebenswissenschaften und Ethik</collection>
  </doc>
  <doc>
    <id>2696</id>
    <completedYear/>
    <publishedYear>2019</publishedYear>
    <thesisYearAccepted/>
    <language>eng</language>
    <pageFirst>1620</pageFirst>
    <pageLast>1629</pageLast>
    <pageNumber/>
    <edition/>
    <issue/>
    <volume/>
    <type>conferenceobject</type>
    <publisherName>IEEE</publisherName>
    <publisherPlace/>
    <creatingCorporation/>
    <contributingCorporation/>
    <belongsToBibliography>0</belongsToBibliography>
    <completedDate>--</completedDate>
    <publishedDate>--</publishedDate>
    <thesisDateAccepted>--</thesisDateAccepted>
    <title language="eng">The Best of Both Worlds: Challenges in Linking Provenance and Explainability in Distributed Machine Learning</title>
    <abstract language="eng">Machine learning experts prefer to think of their input as a single, homogeneous, and consistent data set. However, when analyzing large volumes of data, the entire data set may not be manageable on a single server, but must be stored on a distributed file system instead. Moreover, with the pressing demand to deliver explainable models, the experts may no longer focus on the machine learning algorithms in isolation, but must take into account the distributed nature of the data stored, as well as the impact of any data pre-processing steps upstream in their data analysis pipeline. In this paper, we make the point that even basic transformations during data preparation can impact the model learned, and that this is exacerbated in a distributed setting. We then sketch our vision of end-to-end explainability of the model learned, taking the pre-processing into account. In particular, we point out the potentials of linking the contributions of research on data provenance with the efforts on explainability in machine learning. In doing so, we highlight pitfalls we may experience in a distributed system on the way to generating more holistic explanations for our machine learning models.</abstract>
    <parentTitle language="eng">2019 IEEE 39th International Conference on Distributed Computing Systems (ICDCS), 7-10 July 2019, Dallas, TX, USA</parentTitle>
    <identifier type="doi">10.1109/ICDCS.2019.00161</identifier>
    <enrichment key="opus.import.date">2022-02-04T08:58:18+00:00</enrichment>
    <enrichment key="opus.source">sword</enrichment>
    <enrichment key="opus.import.user">importuser</enrichment>
    <enrichment key="BegutachtungStatus">peer-reviewed</enrichment>
    <licence>Keine Lizenz - Es gilt das deutsche Urheberrecht: § 53 UrhG</licence>
    <author>Stefanie Scherzinger</author>
    <author>Christin Seifert</author>
    <author>Lena Wiese</author>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>Computational modeling</value>
    </subject>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>Data models</value>
    </subject>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>Decision trees</value>
    </subject>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>distributed computing</value>
    </subject>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>Distributed databases</value>
    </subject>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>explainable machine learning</value>
    </subject>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>Machine learning</value>
    </subject>
    <collection role="institutes" number="FakIM">Fakultät Informatik und Mathematik</collection>
    <collection role="othforschungsschwerpunkt" number="16311">Digitalisierung</collection>
  </doc>
  <doc>
    <id>3460</id>
    <completedYear/>
    <publishedYear>2021</publishedYear>
    <thesisYearAccepted/>
    <language>eng</language>
    <pageFirst>2697</pageFirst>
    <pageLast>2700</pageLast>
    <pageNumber/>
    <edition/>
    <issue/>
    <volume/>
    <type>conferenceobject</type>
    <publisherName>IEEE</publisherName>
    <publisherPlace>Piscataway, NJ</publisherPlace>
    <creatingCorporation/>
    <contributingCorporation/>
    <belongsToBibliography>0</belongsToBibliography>
    <completedDate>--</completedDate>
    <publishedDate>--</publishedDate>
    <thesisDateAccepted>--</thesisDateAccepted>
    <title language="eng">DeBinelle: Semantic Patches for Coupled Database-Application Evolution</title>
    <abstract language="eng">Databases are at the core of virtually any software product. Changes to database schemas cannot be made in isolation, as they are intricately coupled with application code. Such couplings enforce collateral evolution, which is a recognised, important research problem. In this demonstration, we show a new dimension to this problem, in software that supports alternative database backends: vendor-specific SQL dialects necessitate a simultaneous evolution of both, database schema and program code, for all supported DB variants. These near-same changes impose substantial manual effort for software developers. We introduce DeBinelle, a novel framework and domain-specific language for semantic patches that abstracts DB-variant schema changes and coupled program code into a single, unified representation. DeBinelle further offers a novel alternative to manually evolving coupled schemas and code. DeBinelle considerably extends established, seminal results in software engineering research, supporting several programming languages, and the many dialects of SQL. It effectively eliminates the need to perform vendor-specific changes, replacing them with intuitive semantic patches. Our demo of DeBinelle is based on real-world use cases from reference systems for schema evolution.</abstract>
    <parentTitle language="eng">2021 IEEE 37th International Conference on Data Engineering (ICDE 2021): 19-22 April 2021, Chania, Greece</parentTitle>
    <identifier type="isbn">978-1-7281-9184-3</identifier>
    <identifier type="doi">10.1109/ICDE51399.2021.00307</identifier>
    <enrichment key="opus.import.date">2022-04-10T09:34:41+00:00</enrichment>
    <enrichment key="opus.source">sword</enrichment>
    <enrichment key="opus.import.user">importuser</enrichment>
    <enrichment key="BegutachtungStatus">peer-reviewed</enrichment>
    <licence>Keine Lizenz - Es gilt das deutsche Urheberrecht: § 53 UrhG</licence>
    <author>Stefanie Scherzinger</author>
    <author>Wolfgang Mauerer</author>
    <author>Haridimos Kondylakis</author>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>database management systems</value>
    </subject>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>databases</value>
    </subject>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>evolution</value>
    </subject>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>programming language semantics</value>
    </subject>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>semantic patches</value>
    </subject>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>software product lines</value>
    </subject>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>specification languages</value>
    </subject>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>SQL</value>
    </subject>
    <collection role="institutes" number="FakIM">Fakultät Informatik und Mathematik</collection>
    <collection role="othforschungsschwerpunkt" number="16311">Digitalisierung</collection>
    <collection role="institutes" number="">Labor für Digitalisierung (LFD)</collection>
  </doc>
  <doc>
    <id>3465</id>
    <completedYear/>
    <publishedYear>2022</publishedYear>
    <thesisYearAccepted/>
    <language>eng</language>
    <pageFirst>119</pageFirst>
    <pageLast>134</pageLast>
    <pageNumber/>
    <edition/>
    <issue/>
    <volume/>
    <type>conferenceobject</type>
    <publisherName>Springer</publisherName>
    <publisherPlace>Cham, Switzerland</publisherPlace>
    <creatingCorporation/>
    <contributingCorporation/>
    <belongsToBibliography>0</belongsToBibliography>
    <completedDate>--</completedDate>
    <publishedDate>--</publishedDate>
    <thesisDateAccepted>--</thesisDateAccepted>
    <title language="eng">Tell-Tale Tail Latencies: Pitfalls and Perils in Database Benchmarking</title>
    <abstract language="eng">The performance of database systems is usually characterised by their average-case (i.e., throughput) behaviour in standardised or de-facto standard benchmarks like TPC-X or YCSB. While tails of the latency (i.e., response time) distribution receive considerably less attention, they have been identified as a threat to the overall system performance: In large-scale systems, even a fraction of requests delayed can build up into delays perceivable by end users. To eradicate large tail latencies from database systems, the ability to faithfully record them, and likewise pinpoint them to the root causes, is imminently required. In this paper, we address the challenge of measuring tail latencies using standard benchmarks, and identify subtle perils and pitfalls. In particular, we demonstrate how Java-based benchmarking approaches can substantially distort tail latency observations, and discuss how the discovery of such problems is inhibited by the common focus on throughput performance. We make a case for purposefully re-designing database benchmarking harnesses based on these observations to arrive at faithful characterisations of database performance from multiple important angles.</abstract>
    <parentTitle language="eng">Performance evaluation and benchmarking, 13th TPC Technology Conference (TPCTC 2021): Copenhagen, Denmark, August 20, 2021, Revised Selected Papers</parentTitle>
    <identifier type="isbn">9783030944377</identifier>
    <identifier type="doi">10.1007/978-3-030-94437-7_8</identifier>
    <enrichment key="opus.import.date">2022-04-10T09:34:41+00:00</enrichment>
    <enrichment key="opus.source">sword</enrichment>
    <enrichment key="opus.import.user">importuser</enrichment>
    <enrichment key="BegutachtungStatus">peer-reviewed</enrichment>
    <enrichment key="OtherSeries">Lecture Notes in Computer Science; vol 13169</enrichment>
    <licence>Keine Lizenz - Es gilt das deutsche Urheberrecht: § 53 UrhG</licence>
    <author>Michael Fruth</author>
    <author>Stefanie Scherzinger</author>
    <author>Wolfgang Mauerer</author>
    <author>Ralf Ramsauer</author>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>Benchmark harness</value>
    </subject>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>Database benchmarks</value>
    </subject>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>Tail latencies</value>
    </subject>
    <collection role="institutes" number="FakIM">Fakultät Informatik und Mathematik</collection>
    <collection role="othforschungsschwerpunkt" number="16311">Digitalisierung</collection>
    <collection role="institutes" number="">Labor für Digitalisierung (LFD)</collection>
  </doc>
  <doc>
    <id>3468</id>
    <completedYear/>
    <publishedYear>2022</publishedYear>
    <thesisYearAccepted/>
    <language>eng</language>
    <pageFirst>1247</pageFirst>
    <pageLast>1248</pageLast>
    <pageNumber/>
    <edition/>
    <issue/>
    <volume/>
    <type>conferenceobject</type>
    <publisherName>IEEE</publisherName>
    <publisherPlace/>
    <creatingCorporation/>
    <contributingCorporation/>
    <belongsToBibliography>0</belongsToBibliography>
    <completedDate>--</completedDate>
    <publishedDate>--</publishedDate>
    <thesisDateAccepted>--</thesisDateAccepted>
    <title language="eng">1-2-3 Reproducibility for Quantum Software Experiments</title>
    <abstract language="eng">Various fields of science face a reproducibility crisis. For quantum software engineering as an emerging field, it is therefore imminent to focus on proper reproducibility engineering from the start. Yet the provision of reproduction packages is almost universally lacking. Actionable advice on how to build such packages is rare, particularly unfortunate in a field with many contributions from researchers with backgrounds outside computer science. In this article, we argue how to rectify this deficiency by proposing a 1-2-3~approach to reproducibility engineering for quantum software experiments: Using a meta-generation mechanism, we generate DOI-safe, long-term functioning and dependency-free reproduction packages. They are designed to satisfy the requirements of professional and learned societies solely on the basis of project-specific research artefacts (source code, measurement and configuration data), and require little temporal investment by researchers. Our scheme ascertains long-term traceability even when the quantum processor itself is no longer accessible. By drastically lowering the technical bar, we foster the proliferation of reproduction packages in quantum software experiments and ease the inclusion of non-CS researchers entering the field.</abstract>
    <parentTitle language="eng">2022 IEEE International Conference on Software Analysis, Evolution and Reengineering (SANER), Honolulu, HI, USA, 15-18 March 2022</parentTitle>
    <identifier type="doi">10.1109/SANER53432.2022.00148</identifier>
    <enrichment key="opus.import.date">2022-04-10T09:34:41+00:00</enrichment>
    <enrichment key="opus.source">sword</enrichment>
    <enrichment key="opus.import.user">importuser</enrichment>
    <enrichment key="BegutachtungStatus">peer-reviewed</enrichment>
    <licence>Creative Commons - CC BY - Namensnennung 4.0 International</licence>
    <licence>Keine Lizenz - Es gilt das deutsche Urheberrecht: § 53 UrhG</licence>
    <author>Wolfgang Mauerer</author>
    <author>Stefanie Scherzinger</author>
    <subject>
      <language>deu</language>
      <type>uncontrolled</type>
      <value>Computer Science</value>
    </subject>
    <subject>
      <language>deu</language>
      <type>uncontrolled</type>
      <value>Quantum Physics</value>
    </subject>
    <subject>
      <language>deu</language>
      <type>uncontrolled</type>
      <value>Software Engineering</value>
    </subject>
    <collection role="institutes" number="FakIM">Fakultät Informatik und Mathematik</collection>
    <collection role="othforschungsschwerpunkt" number="16311">Digitalisierung</collection>
    <collection role="institutes" number="">Labor für Digitalisierung (LFD)</collection>
  </doc>
  <doc>
    <id>3464</id>
    <completedYear/>
    <publishedYear>2020</publishedYear>
    <thesisYearAccepted/>
    <language>eng</language>
    <pageFirst>210</pageFirst>
    <pageLast>219</pageLast>
    <pageNumber/>
    <edition/>
    <issue/>
    <volume>12584</volume>
    <type>conferenceobject</type>
    <publisherName>Springer</publisherName>
    <publisherPlace>Cham</publisherPlace>
    <creatingCorporation/>
    <contributingCorporation/>
    <belongsToBibliography>0</belongsToBibliography>
    <completedDate>--</completedDate>
    <publishedDate>--</publishedDate>
    <thesisDateAccepted>--</thesisDateAccepted>
    <title language="eng">Replicability and Reproducibility of a Schema Evolution Study in Embedded Databases</title>
    <abstract language="eng">Ascertaining the feasibility of independent falsification or repetition of published results is vital to the scientific process, and replication or reproduction experiments are routinely performed in many disciplines. Unfortunately, such studies are only scarcely available in database research, with few papers dedicated to re-evaluating published results. In this paper, we conduct a case study on replicating and reproducing a study on schema evolution in embedded databases. We can exactly repeat the outcome for one out of four database applications studied, and come close in two further cases. By reporting results, efforts, and obstacles encountered, we hope to increase appreciation for the substantial efforts required to ensure reproducibility. By discussing minutiae details required to ascertain reproducible work, we argue that such important, but often ignored aspects of scientific work should receive more credit in the evaluation of future research.</abstract>
    <parentTitle language="eng">Advances in conceptual modeling: ER 2020 Workshops CMAI, CMLS, CMOMM4FAIR, CoMoNoS, EmpER, Vienna, Austria, November 3-6, 2020, Proceedings</parentTitle>
    <identifier type="isbn">978-3-030-65846-5</identifier>
    <identifier type="doi">10.1007/978-3-030-65847-2_19</identifier>
    <enrichment key="opus.import.date">2022-04-10T09:34:41+00:00</enrichment>
    <enrichment key="opus.source">sword</enrichment>
    <enrichment key="opus.import.user">importuser</enrichment>
    <enrichment key="OtherSeries">Lecture Notes in Computer Science ; 12584</enrichment>
    <enrichment key="BegutachtungStatus">peer-reviewed</enrichment>
    <licence>Keine Lizenz - Es gilt das deutsche Urheberrecht: § 53 UrhG</licence>
    <author>Dimitri Braininger</author>
    <author>Wolfgang Mauerer</author>
    <author>Stefanie Scherzinger</author>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>replicability</value>
    </subject>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>reproducibility</value>
    </subject>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>schema evolution</value>
    </subject>
    <collection role="institutes" number="FakIM">Fakultät Informatik und Mathematik</collection>
    <collection role="othforschungsschwerpunkt" number="16311">Digitalisierung</collection>
    <collection role="institutes" number="">Labor für Digitalisierung (LFD)</collection>
  </doc>
  <doc>
    <id>3637</id>
    <completedYear/>
    <publishedYear>2021</publishedYear>
    <thesisYearAccepted/>
    <language>deu</language>
    <pageFirst>816</pageFirst>
    <pageLast>817</pageLast>
    <pageNumber/>
    <edition/>
    <issue>10</issue>
    <volume>28</volume>
    <type>article</type>
    <publisherName>Zentrum für Wissenschaftsmanagement e.V. (ZWM) </publisherName>
    <publisherPlace/>
    <creatingCorporation>Deutscher Hochschullehrerverband</creatingCorporation>
    <contributingCorporation/>
    <belongsToBibliography>0</belongsToBibliography>
    <completedDate>--</completedDate>
    <publishedDate>--</publishedDate>
    <thesisDateAccepted>--</thesisDateAccepted>
    <title language="deu">Digitale Forschungswerkzeuge : Nachhaltigkeit für Software und Daten</title>
    <abstract language="deu">Die wissenschaftliche Reproduktionskrise hat den Blick auf digitale Forschungswerkzeuge intensiviert. Auch wenn der Mehraufwand für Reproduzierbarkeit und Zugänglichkeit zunehmend anerkannt wird, existieren noch Defizite in der Umsetzung, wenn es darum geht, die Datenbasis und Forschungswerkzeuge verfügbar zu machen</abstract>
    <parentTitle language="deu">Forschung &amp; Lehre (Forschung und Lehre)</parentTitle>
    <identifier type="url">https://www.wissenschaftsmanagement-online.de/system/files/downloads-wimoarticle/2021-10_WIMO_Digitale_Forschungswerkzeuge_Mauerer_Scherzinger.pdf</identifier>
    <enrichment key="opus.import.date">2022-04-28T11:07:17+00:00</enrichment>
    <enrichment key="opus.source">sword</enrichment>
    <enrichment key="opus.import.user">importuser</enrichment>
    <enrichment key="BegutachtungStatus">peer-reviewed</enrichment>
    <licence>Keine Lizenz - Es gilt das deutsche Urheberrecht: § 53 UrhG</licence>
    <author>Wolfgang Mauerer</author>
    <author>Stefanie Scherzinger</author>
    <collection role="institutes" number="FakIM">Fakultät Informatik und Mathematik</collection>
    <collection role="othforschungsschwerpunkt" number="16311">Digitalisierung</collection>
    <collection role="institutes" number="">Labor für Digitalisierung (LFD)</collection>
  </doc>
  <doc>
    <id>3707</id>
    <completedYear/>
    <publishedYear>2016</publishedYear>
    <thesisYearAccepted/>
    <language>eng</language>
    <pageFirst>33</pageFirst>
    <pageLast>36</pageLast>
    <pageNumber/>
    <edition/>
    <issue/>
    <volume/>
    <type>conferenceobject</type>
    <publisherName>ACM</publisherName>
    <publisherPlace/>
    <creatingCorporation/>
    <contributingCorporation/>
    <belongsToBibliography>0</belongsToBibliography>
    <completedDate>--</completedDate>
    <publishedDate>--</publishedDate>
    <thesisDateAccepted>--</thesisDateAccepted>
    <title language="eng">Data Model Evolution Using Object-NoSQL Mappers: Folklore or State-of-the-Art?</title>
    <abstract language="eng">In big data software engineering, the schema flexibility of NoSQL document stores is a major selling point: When the document store itself does not actively manage a schema, the data model is maintained within the application. Just like object-relational mappers for relational databases, object-NoSQL mappers are part of professional software development with NoSQL document stores. Some mappers go beyond merely loading and storing Java objects: Using dedicated evolution annotations, developers may conveniently add, remove, or rename attributes from stored objects, and also conduct more complex transformations. In this paper, we analyze the dissemination of this technology in Java open source projects. While we find evidence on GitHub that evolution annotations are indeed being used, developers do not employ them so much for evolving the data model, but to solve different tasks instead. Our observations trigger interesting questions for further research.</abstract>
    <parentTitle language="eng">2016 IEEE/ACM 2nd International Workshop on Big Data Software Engineering (BIGDSE), 16 May 2016, Austin, TX, USA</parentTitle>
    <identifier type="doi">10.1145/2896825.2896827</identifier>
    <enrichment key="opus.import.date">2022-04-28T18:45:44+00:00</enrichment>
    <enrichment key="opus.source">sword</enrichment>
    <enrichment key="opus.import.user">importuser</enrichment>
    <enrichment key="BegutachtungStatus">peer-reviewed</enrichment>
    <licence>Keine Lizenz - Es gilt das deutsche Urheberrecht: § 53 UrhG</licence>
    <author>Andreas Ringlstetter</author>
    <author>Stefanie Scherzinger</author>
    <author>Tegawendé F. Bissyandé</author>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>Big data</value>
    </subject>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>data model evolution</value>
    </subject>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>Data models</value>
    </subject>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>Java</value>
    </subject>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>Loading</value>
    </subject>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>Object-NoSQL mappers</value>
    </subject>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>Software</value>
    </subject>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>Software engineering</value>
    </subject>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>Transient analysis</value>
    </subject>
    <collection role="institutes" number="FakIM">Fakultät Informatik und Mathematik</collection>
    <collection role="othforschungsschwerpunkt" number="16311">Digitalisierung</collection>
  </doc>
  <doc>
    <id>3726</id>
    <completedYear/>
    <publishedYear>2015</publishedYear>
    <thesisYearAccepted/>
    <language>eng</language>
    <pageFirst>15</pageFirst>
    <pageLast>16</pageLast>
    <pageNumber/>
    <edition/>
    <issue/>
    <volume/>
    <type>conferenceobject</type>
    <publisherName>ACM</publisherName>
    <publisherPlace>New York, NY, USA</publisherPlace>
    <creatingCorporation/>
    <contributingCorporation/>
    <belongsToBibliography>0</belongsToBibliography>
    <completedDate>--</completedDate>
    <publishedDate>--</publishedDate>
    <thesisDateAccepted>--</thesisDateAccepted>
    <title language="eng">ControVol: Let Yesterday's Data Catch Up with Today's Application Code</title>
    <abstract language="eng">In building software-as-a-service applications, a flexible development environment is key to shipping early and often. Therefore, schema-flexible data stores are becoming more and more popular. They can store data with heterogeneous structure, allowing for new releases to be pushed frequently, without having to migrate legacy data first. However, the current application code must continue to work with any legacy data that has already been persisted in production. To let legacy data structurally "catch up" with the latest application code, developers commonly employ object mapper libraries with life-cycle annotations. Yet when used without caution, they can cause runtime errors and even data loss. We present ControVol, an IDE plugin that detects evolutionary changes to the application code that are incompatible with legacy data. ControVol warns developers already at development time, and even suggests automatic fixes for lazily migrating legacy data when it is loaded into the application. Thus, ControVol ensures that the structure of legacy data can catch up with the structure expected by the latest software release.</abstract>
    <parentTitle language="eng">Proceedings of the 24th International Conference on World Wide Web (WWW '15) ; Florence Italy, 18.05.2015 - 22.0.2015</parentTitle>
    <identifier type="isbn">9781450334730</identifier>
    <identifier type="doi">10.1145/2740908.2742719</identifier>
    <enrichment key="opus.import.date">2022-04-28T18:57:25+00:00</enrichment>
    <enrichment key="opus.source">sword</enrichment>
    <enrichment key="opus.import.user">importuser</enrichment>
    <enrichment key="BegutachtungStatus">peer-reviewed</enrichment>
    <licence>Keine Lizenz - Es gilt das deutsche Urheberrecht: § 53 UrhG</licence>
    <author>Thomas Cerqueus</author>
    <author>Eduardo Cunha de Almeida</author>
    <author>Stefanie Scherzinger</author>
    <collection role="institutes" number="FakIM">Fakultät Informatik und Mathematik</collection>
    <collection role="othforschungsschwerpunkt" number="16311">Digitalisierung</collection>
  </doc>
  <doc>
    <id>3734</id>
    <completedYear/>
    <publishedYear>2015</publishedYear>
    <thesisYearAccepted/>
    <language>eng</language>
    <pageFirst>4</pageFirst>
    <pageLast>10</pageLast>
    <pageNumber/>
    <edition/>
    <issue/>
    <volume/>
    <type>conferenceobject</type>
    <publisherName>IEEE</publisherName>
    <publisherPlace/>
    <creatingCorporation/>
    <contributingCorporation/>
    <belongsToBibliography>0</belongsToBibliography>
    <completedDate>--</completedDate>
    <publishedDate>--</publishedDate>
    <thesisDateAccepted>--</thesisDateAccepted>
    <title language="eng">Safely Managing Data Variety in Big Data Software Development</title>
    <abstract language="eng">We consider the task of building Big Data software systems, offered as software-as-a-service. These applications are commonly backed by NoSQL data stores that address the proverbial Vs of Big Data processing: NoSQL data stores can handle large volumes of data and many systems do not enforce a global schema, to account for structural variety in data. Thus, software engineers can design the data model on the go, a flexibility that is particularly crucial in agile software development. However, NoSQL data stores commonly do not yet account for the veracity of changes when it comes to changes in the structure of persisted data. Yet this is an inevitable consequence of agile software development. In most NoSQL-based application stacks, schema evolution is completely handled within the application code, usually involving object mapper libraries. Yet simple code refactorings, such as renaming a class attribute at the source code level, can cause data loss or runtime errors once the application has been deployed to production. We address this pain point by contributing type checking rules that we have implemented within an IDE plug in. Our plug in ControVol statically type checks the object mapper class declarations against the code release history. ControVol is thus capable of detecting common yet risky cases of mismatched data and schema, and can even suggest automatic fixes.</abstract>
    <parentTitle language="eng">2015 IEEE/ACM 1st International Workshop on Big Data Software Engineering, 23-23 May 2015, Florence, Italy</parentTitle>
    <identifier type="doi">10.1109/BIGDSE.2015.9</identifier>
    <enrichment key="opus.import.date">2022-04-28T18:57:25+00:00</enrichment>
    <enrichment key="opus.source">sword</enrichment>
    <enrichment key="opus.import.user">importuser</enrichment>
    <enrichment key="BegutachtungStatus">peer-reviewed</enrichment>
    <enrichment key="opus.doi.autoCreate">false</enrichment>
    <enrichment key="opus.urn.autoCreate">false</enrichment>
    <licence>Keine Lizenz - Es gilt das deutsche Urheberrecht: § 53 UrhG</licence>
    <author>Thomas Cerqueus</author>
    <author>Eduardo Cunha de Almeida</author>
    <author>Stefanie Scherzinger</author>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>Big data</value>
    </subject>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>history</value>
    </subject>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>Java</value>
    </subject>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>Loading</value>
    </subject>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>NoSQL data stores</value>
    </subject>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>object mapping</value>
    </subject>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>Production</value>
    </subject>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>Runtime</value>
    </subject>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>schema evolution</value>
    </subject>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>Software</value>
    </subject>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>type checking</value>
    </subject>
    <collection role="institutes" number="FakIM">Fakultät Informatik und Mathematik</collection>
    <collection role="othforschungsschwerpunkt" number="16311">Digitalisierung</collection>
  </doc>
</export-example>
