@phdthesis{Truemper2014,
  author    = {Tr{\"u}mper, Jonas},
  title     = {Visualization techniques for the analysis of software behavior and related structures},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus-72145},
  school      = {Universit{\"a}t Potsdam},
  year      = {2014},
  abstract  = {Software maintenance encompasses any changes made to a software system after its initial deployment and is thereby one of the key phases in the typical software-engineering lifecycle. In software maintenance, we primarily need to understand structural and behavioral aspects, which are difficult to obtain, e.g., by code reading. Software analysis is therefore a vital tool for maintaining these systems: It provides - the preferably automated - means to extract and evaluate information from their artifacts such as software structure, runtime behavior, and related processes. However, such analysis typically results in massive raw data, so that even experienced engineers face difficulties directly examining, assessing, and understanding these data. Among other things, they require tools with which to explore the data if no clear question can be formulated beforehand. For this, software analysis and visualization provide its users with powerful interactive means. These enable the automation of tasks and, particularly, the acquisition of valuable and actionable insights into the raw data. For instance, one means for exploring runtime behavior is trace visualization. This thesis aims at extending and improving the tool set for visual software analysis by concentrating on several open challenges in the fields of dynamic and static analysis of software systems. This work develops a series of concepts and tools for the exploratory visualization of the respective data to support users in finding and retrieving information on the system artifacts concerned. This is a difficult task, due to the lack of appropriate visualization metaphors; in particular, the visualization of complex runtime behavior poses various questions and challenges of both a technical and conceptual nature. This work focuses on a set of visualization techniques for visually representing control-flow related aspects of software traces from shared-memory software systems: A trace-visualization concept based on icicle plots aids in understanding both single-threaded as well as multi-threaded runtime behavior on the function level. The concept's extensibility further allows the visualization and analysis of specific aspects of multi-threading such as synchronization, the correlation of such traces with data from static software analysis, and a comparison between traces. Moreover, complementary techniques for simultaneously analyzing system structures and the evolution of related attributes are proposed. These aim at facilitating long-term planning of software architecture and supporting management decisions in software projects by extensions to the circular-bundle-view technique: An extension to 3-dimensional space allows for the use of additional variables simultaneously; interaction techniques allow for the modification of structures in a visual manner. The concepts and techniques presented here are generic and, as such, can be applied beyond software analysis for the visualization of similarly structured data. The techniques' practicability is demonstrated by several qualitative studies using subject data from industry-scale software systems. The studies provide initial evidence that the techniques' application yields useful insights into the subject data and its interrelationships in several scenarios.},
  language  = {en}
}
@phdthesis{Tinnefeld2014,
  author    = {Tinnefeld, Christian},
  title     = {Building a columnar database on shared main memory-based storage},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-72063},
  school      = {Universit{\"a}t Potsdam},
  pages     = {175},
  year      = {2014},
  abstract  = {In the field of disk-based parallel database management systems exists a great variety of solutions based on a shared-storage or a shared-nothing architecture. In contrast, main memory-based parallel database management systems are dominated solely by the shared-nothing approach as it preserves the in-memory performance advantage by processing data locally on each server. We argue that this unilateral development is going to cease due to the combination of the following three trends: a) Nowadays network technology features remote direct memory access (RDMA) and narrows the performance gap between accessing main memory inside a server and of a remote server to and even below a single order of magnitude. b) Modern storage systems scale gracefully, are elastic, and provide high-availability. c) A modern storage system such as Stanford's RAMCloud even keeps all data resident in main memory. Exploiting these characteristics in the context of a main-memory parallel database management system is desirable. The advent of RDMA-enabled network technology makes the creation of a parallel main memory DBMS based on a shared-storage approach feasible. This thesis describes building a columnar database on shared main memory-based storage. The thesis discusses the resulting architecture (Part I), the implications on query processing (Part II), and presents an evaluation of the resulting solution in terms of performance, high-availability, and elasticity (Part III). In our architecture, we use Stanford's RAMCloud as shared-storage, and the self-designed and developed in-memory AnalyticsDB as relational query processor on top. AnalyticsDB encapsulates data access and operator execution via an interface which allows seamless switching between local and remote main memory, while RAMCloud provides not only storage capacity, but also processing power. Combining both aspects allows pushing-down the execution of database operators into the storage system. We describe how the columnar data processed by AnalyticsDB is mapped to RAMCloud's key-value data model and how the performance advantages of columnar data storage can be preserved. The combination of fast network technology and the possibility to execute database operators in the storage system opens the discussion for site selection. We construct a system model that allows the estimation of operator execution costs in terms of network transfer, data processed in memory, and wall time. This can be used for database operators that work on one relation at a time - such as a scan or materialize operation - to discuss the site selection problem (data pull vs. operator push). Since a database query translates to the execution of several database operators, it is possible that the optimal site selection varies per operator. For the execution of a database operator that works on two (or more) relations at a time, such as a join, the system model is enriched by additional factors such as the chosen algorithm (e.g. Grace- vs. Distributed Block Nested Loop Join vs. Cyclo-Join), the data partitioning of the respective relations, and their overlapping as well as the allowed resource allocation. We present an evaluation on a cluster with 60 nodes where all nodes are connected via RDMA-enabled network equipment. We show that query processing performance is about 2.4x slower if everything is done via the data pull operator execution strategy (i.e. RAMCloud is being used only for data access) and about 27\% slower if operator execution is also supported inside RAMCloud (in comparison to operating only on main memory inside a server without any network communication at all). The fast-crash recovery feature of RAMCloud can be leveraged to provide high-availability, e.g. a server crash during query execution only delays the query response for about one second. Our solution is elastic in a way that it can adapt to changing workloads a) within seconds, b) without interruption of the ongoing query processing, and c) without manual intervention.},
  language  = {en}
}
@phdthesis{Takouna2014,
  author    = {Takouna, Ibrahim},
  title     = {Energy-efficient and performance-aware virtual machine management for cloud data centers},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus-72399},
  school      = {Universit{\"a}t Potsdam},
  year      = {2014},
  abstract  = {Virtualisierte Cloud Datenzentren stellen nach Bedarf Ressourcen zur Verf{\"u}gu-ng, erm{\"o}glichen agile Ressourcenbereitstellung und beherbergen heterogene Applikationen mit verschiedenen Anforderungen an Ressourcen. Solche Datenzentren verbrauchen enorme Mengen an Energie, was die Erh{\"o}hung der Betriebskosten, der W{\"a}rme innerhalb der Zentren und des Kohlendioxidausstoßes verursacht. Der Anstieg des Energieverbrauches kann durch ein ineffektives Ressourcenmanagement, das die ineffiziente Ressourcenausnutzung verursacht, entstehen. Die vorliegende Dissertation stellt detaillierte Modelle und neue Verfahren f{\"u}r virtualisiertes Ressourcenmanagement in Cloud Datenzentren vor. Die vorgestellten Verfahren ziehen das Service-Level-Agreement (SLA) und die Heterogenit{\"a}t der Auslastung bez{\"u}glich des Bedarfs an Speicherzugriffen und Kommunikationsmustern von Web- und HPC- (High Performance Computing) Applikationen in Betracht. Um die pr{\"a}sentierten Techniken zu evaluieren, verwenden wir Simulationen und echte Protokollierung der Auslastungen von Web- und HPC- Applikationen. Außerdem vergleichen wir unser Techniken und Verfahren mit anderen aktuellen Verfahren durch die Anwendung von verschiedenen Performance Metriken. Die Hauptbeitr{\"a}ge dieser Dissertation sind Folgendes: Ein Proaktives auf robuster Optimierung basierendes Ressourcenbereitstellungsverfahren. Dieses Verfahren erh{\"o}ht die F{\"a}higkeit der Hostes zur Verf{\"u}g-ungsstellung von mehr VMs. Gleichzeitig aber wird der unn{\"o}tige Energieverbrauch minimiert. Zus{\"a}tzlich mindert diese Technik unerw{\"u}nschte {\"A}nde-rungen im Energiezustand des Servers. Die vorgestellte Technik nutzt einen auf Intervall basierenden Vorhersagealgorithmus zur Implementierung einer robusten Optimierung. Dabei werden unsichere Anforderungen in Betracht gezogen. Ein adaptives und auf Intervall basierendes Verfahren zur Vorhersage des Arbeitsaufkommens mit hohen, in k{\"u}rzer Zeit auftretenden Schwankungen. Die Intervall basierende Vorhersage ist implementiert in der Standard Abweichung Variante und in der Median absoluter Abweichung Variante. Die Intervall-{\"A}nderungen basieren auf einem adaptiven Vertrauensfenster um die Schwankungen des Arbeitsaufkommens zu bew{\"a}ltigen. Eine robuste VM Zusammenlegung f{\"u}r ein effizientes Energie und Performance Management. Dies erm{\"o}glicht die gegenseitige Abh{\"a}ngigkeit zwischen der Energie und der Performance zu minimieren. Unser Verfahren reduziert die Anzahl der VM-Migrationen im Vergleich mit den neu vor kurzem vorgestellten Verfahren. Dies tr{\"a}gt auch zur Reduzierung des durch das Netzwerk verursachten Energieverbrauches. Außerdem reduziert dieses Verfahren SLA-Verletzungen und die Anzahl von {\"A}nderungen an Energiezus-t{\"a}nden. Ein generisches Modell f{\"u}r das Netzwerk eines Datenzentrums um die verz{\"o}-gerte Kommunikation und ihre Auswirkung auf die VM Performance und auf die Netzwerkenergie zu simulieren. Außerdem wird ein generisches Modell f{\"u}r ein Memory-Bus des Servers vorgestellt. Dieses Modell beinhaltet auch Modelle f{\"u}r die Latenzzeit und den Energieverbrauch f{\"u}r verschiedene Memory Frequenzen. Dies erlaubt eine Simulation der Memory Verz{\"o}gerung und ihre Auswirkung auf die VM-Performance und auf den Memory Energieverbrauch. Kommunikation bewusste und Energie effiziente Zusammenlegung f{\"u}r parallele Applikationen um die dynamische Entdeckung von Kommunikationsmustern und das Umplanen von VMs zu erm{\"o}glichen. Das Umplanen von VMs benutzt eine auf den entdeckten Kommunikationsmustern basierende Migration. Eine neue Technik zur Entdeckung von dynamischen Mustern ist implementiert. Sie basiert auf der Signal Verarbeitung des Netzwerks von VMs, anstatt die Informationen des virtuellen Umstellung der Hosts oder der Initiierung der VMs zu nutzen. Das Ergebnis zeigt, dass unsere Methode die durchschnittliche Anwendung des Netzwerks reduziert und aufgrund der Reduzierung der aktiven Umstellungen Energie gespart. Außerdem bietet sie eine bessere VM Performance im Vergleich zu der CPU-basierten Platzierung. Memory bewusste VM Zusammenlegung f{\"u}r unabh{\"a}ngige VMs. Sie nutzt die Vielfalt des VMs Memory Zuganges um die Anwendung vom Memory-Bus der Hosts zu balancieren. Die vorgestellte Technik, Memory-Bus Load Balancing (MLB), verteilt die VMs reaktiv neu im Bezug auf ihre Anwendung vom Memory-Bus. Sie nutzt die VM Migration um die Performance des gesamtem Systems zu verbessern. Außerdem sind die dynamische Spannung, die Frequenz Skalierung des Memory und die MLB Methode kombiniert um ein besseres Energiesparen zu leisten.},
  language  = {en}
}
@phdthesis{Steinert2014,
  author    = {Steinert, Bastian},
  title     = {Built-in recovery support for explorative programming},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus-71305},
  school      = {Universit{\"a}t Potsdam},
  year      = {2014},
  abstract  = {This work introduces concepts and corresponding tool support to enable a complementary approach in dealing with recovery. Programmers need to recover a development state, or a part thereof, when previously made changes reveal undesired implications. However, when the need arises suddenly and unexpectedly, recovery often involves expensive and tedious work. To avoid tedious work, literature recommends keeping away from unexpected recovery demands by following a structured and disciplined approach, which consists of the application of various best practices including working only on one thing at a time, performing small steps, as well as making proper use of versioning and testing tools. However, the attempt to avoid unexpected recovery is both time-consuming and error-prone. On the one hand, it requires disproportionate effort to minimize the risk of unexpected situations. On the other hand, applying recommended practices selectively, which saves time, can hardly avoid recovery. In addition, the constant need for foresight and self-control has unfavorable implications. It is exhaustive and impedes creative problem solving. This work proposes to make recovery fast and easy and introduces corresponding support called CoExist. Such dedicated support turns situations of unanticipated recovery from tedious experiences into pleasant ones. It makes recovery fast and easy to accomplish, even if explicit commits are unavailable or tests have been ignored for some time. When mistakes and unexpected insights are no longer associated with tedious corrective actions, programmers are encouraged to change source code as a means to reason about it, as opposed to making changes only after structuring and evaluating them mentally. This work further reports on an implementation of the proposed tool support in the Squeak/Smalltalk development environment. The development of the tools has been accompanied by regular performance and usability tests. In addition, this work investigates whether the proposed tools affect programmers' performance. In a controlled lab study, 22 participants improved the design of two different applications. Using a repeated measurement setup, the study examined the effect of providing CoExist on programming performance. The result of analyzing 88 hours of programming suggests that built-in recovery support as provided with CoExist positively has a positive effect on programming performance in explorative programming tasks.},
  language  = {en}
}
@book{MeyerWeske2014,
  author    = {Meyer, Andreas and Weske, Mathias},
  title     = {Weak conformance between process models and synchronized object life cycles},
  number    = {91},
  publisher = {Universit{\"a}tsverlag Potsdam},
  address   = {Potsdam},
  isbn      = {978-3-86956-303-9},
  issn      = {1613-5652},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus-71722},
  publisher      = {Universit{\"a}t Potsdam},
  pages     = {31},
  year      = {2014},
  abstract  = {Process models specify behavioral execution constraints between activities as well as between activities and data objects. A data object is characterized by its states and state transitions represented as object life cycle. For process execution, all behavioral execution constraints must be correct. Correctness can be verified via soundness checking which currently only considers control flow information. For data correctness, conformance between a process model and its object life cycles is checked. Current approaches abstract from dependencies between multiple data objects and require fully specified process models although, in real-world process repositories, often underspecified models are found. Coping with these issues, we introduce the concept of synchronized object life cycles and we define a mapping of data constraints of a process model to Petri nets extending an existing mapping. Further, we apply the notion of weak conformance to process models to tell whether each time an activity needs to access a data object in a particular state, it is guaranteed that the data object is in or can reach the expected state. Then, we introduce an algorithm for an integrated verification of control flow correctness and weak data conformance using soundness checking.},
  language  = {en}
}
@book{MeinelWillems2014,
  author    = {Meinel, Christoph and Willems, Christian},
  title     = {openHPI : 哈索•普拉特纳研究院的 MOOC（大规模公开在线课）计划},
  number    = {89},
  publisher = {Universit{\"a}tsverlag Potsdam},
  address   = {Potsdam},
  isbn      = {978-3-86956-291-9},
  issn      = {1613-5652},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus-70380},
  publisher      = {Universit{\"a}t Potsdam},
  pages     = {22},
  year      = {2014},
  abstract  = {摘要。哈索•普拉特纳研究院 (HPI) 的新型互动在线教育平台 openHPI (https://openHPI.de) 可以为从事信息技术和信息学领域内容的工作和感兴趣的学员提供可自由访问的、免费的在线课程。与斯坦福大学于 2011 年首推，之后也在美国其他精英大学提供的"网络公开群众课"（简称 MOOC）一样，openHPI 同样在互联网中提供学习视频和阅读材料，其中综合了支持学习的自我测试、家庭作业和社交讨论论坛，并刺激对促进学习的虚拟学习团队的培训。与"传统的"讲座平台，比如 tele-TASK 平台 (http://www.tele-task.de) 不同（在该平台中，可调用以多媒体方式记录的和已准备好的讲座），openHPI 提供的是按教学法准备的在线课程。这些课程的开始时间固定，之后在连续六个课程周稳定的提供以多媒体方式准备的、尽可能可以互动的学习材料。每周讲解课程主题的一章。为此在该周开始前会准备一系列学习视频、文字、自我测试和家庭作业材料，课程学员在该周将精力用于处理这些内容。这些计划与一个社交讨论平台相结合，学员在该平台上可以与课程导师和其他学员交换意见、解答问题和讨论更多主题。当然，学员可以自己决定学习活动的类型和范围。他们可以为课程作出自己的贡献，比如在论坛中引用博文或推文。之后其他学员可以评论、讨论或自己扩展这些博文或推文。这样学员、教师和提供的学习内容就在一个虚拟的团体中与社交学习网络相互结合起来。},
  language  = {de}
}
@book{MeinelSchnjakinMetzkeetal.2014,
  author    = {Meinel, Christoph and Schnjakin, Maxim and Metzke, Tobias and Freitag, Markus},
  title     = {Anbieter von Cloud Speicherdiensten im {\"U}berblick},
  publisher = {Universit{\"a}tsverlag Potsdam},
  address   = {Potsdam},
  isbn      = {978-3-86956-274-2},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus-68780},
  publisher      = {Universit{\"a}t Potsdam},
  pages     = {84},
  year      = {2014},
  abstract  = {Durch die immer st{\"a}rker werdende Flut an digitalen Informationen basieren immer mehr Anwendungen auf der Nutzung von kosteng{\"u}nstigen Cloud Storage Diensten. Die Anzahl der Anbieter, die diese Dienste zur Verf{\"u}gung stellen, hat sich in den letzten Jahren deutlich erh{\"o}ht. Um den passenden Anbieter f{\"u}r eine Anwendung zu finden, m{\"u}ssen verschiedene Kriterien individuell ber{\"u}cksichtigt werden. In der vorliegenden Studie wird eine Auswahl an Anbietern etablierter Basic Storage Diensten vorgestellt und miteinander verglichen. F{\"u}r die Gegen{\"u}berstellung werden Kriterien extrahiert, welche bei jedem der untersuchten Anbieter anwendbar sind und somit eine m{\"o}glichst objektive Beurteilung erlauben. Hierzu geh{\"o}ren unter anderem Kosten, Recht, Sicherheit, Leistungsf{\"a}higkeit sowie bereitgestellte Schnittstellen. Die vorgestellten Kriterien k{\"o}nnen genutzt werden, um Cloud Storage Anbieter bez{\"u}glich eines konkreten Anwendungsfalles zu bewerten.},
  language  = {de}
}
@book{MeinelPlattnerDoellneretal.2014,
  author    = {Meinel, Christoph and Plattner, Hasso and D{\"o}llner, J{\"u}rgen Roland Friedrich and Weske, Mathias and Polze, Andreas and Hirschfeld, Robert and Naumann, Felix and Giese, Holger and Baudisch, Patrick},
  title     = {Proceedings of the 7th Ph.D. Retreat of the HPI Research School on Service-oriented Systems Engineering},
  publisher = {Universit{\"a}tsverlag Potsdam},
  address   = {Potsdam},
  isbn      = {978-3-86956-273-5},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus-63490},
  publisher      = {Universit{\"a}t Potsdam},
  pages     = {ii, 218},
  year      = {2014},
  abstract  = {Design and Implementation of service-oriented architectures imposes a huge number of research questions from the fields of software engineering, system analysis and modeling, adaptability, and application integration. Component orientation and web services are two approaches for design and realization of complex web-based system. Both approaches allow for dynamic application adaptation as well as integration of enterprise application. Commonly used technologies, such as J2EE and .NET, form de facto standards for the realization of complex distributed systems. Evolution of component systems has lead to web services and service-based architectures. This has been manifested in a multitude of industry standards and initiatives such as XML, WSDL UDDI, SOAP, etc. All these achievements lead to a new and promising paradigm in IT systems engineering which proposes to design complex software solutions as collaboration of contractually defined software services. Service-Oriented Systems Engineering represents a symbiosis of best practices in object-orientation, component-based development, distributed computing, and business process management. It provides integration of business and IT concerns. The annual Ph.D. Retreat of the Research School provides each member the opportunity to present his/her current state of their research and to give an outline of a prospective Ph.D. thesis. Due to the interdisciplinary structure of the Research Scholl, this technical report covers a wide range of research topics. These include but are not limited to: Self-Adaptive Service-Oriented Systems, Operating System Support for Service-Oriented Systems, Architecture and Modeling of Service-Oriented Systems, Adaptive Process Management, Services Composition and Workflow Planning, Security Engineering of Service-Based IT Systems, Quantitative Analysis and Optimization of Service-Oriented Systems, Service-Oriented Systems in 3D Computer Graphics sowie Service-Oriented Geoinformatics.},
  language  = {en}
}
@misc{Hildebrandt2014,
  author    = {Hildebrandt, Dieter},
  title     = {A software reference architecture for service-oriented 3D geovisualization systems},
  series = {Postprints der Universit{\"a}t Potsdam : Mathematisch-Naturwissenschaftliche Reihe},
  journal   = {Postprints der Universit{\"a}t Potsdam : Mathematisch-Naturwissenschaftliche Reihe},
  number    = {1131},
  issn      = {1866-8372},
  doi       = {10.25932/publishup-47583},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-475831},
  pages     = {48},
  year      = {2014},
  abstract  = {Modern 3D geovisualization systems (3DGeoVSs) are complex and evolving systems that are required to be adaptable and leverage distributed resources, including massive geodata. This article focuses on 3DGeoVSs built based on the principles of service-oriented architectures, standards and image-based representations (SSI) to address practically relevant challenges and potentials. Such systems facilitate resource sharing and agile and efficient system construction and change in an interoperable manner, while exploiting images as efficient, decoupled and interoperable representations. The software architecture of a 3DGeoVS and its underlying visualization model have strong effects on the system's quality attributes and support various system life cycle activities. This article contributes a software reference architecture (SRA) for 3DGeoVSs based on SSI that can be used to design, describe and analyze concrete software architectures with the intended primary benefit of an increase in effectiveness and efficiency in such activities. The SRA integrates existing, proven technology and novel contributions in a unique manner. As the foundation for the SRA, we propose the generalized visualization pipeline model that generalizes and overcomes expressiveness limitations of the prevalent visualization pipeline model. To facilitate exploiting image-based representations (IReps), the SRA integrates approaches for the representation, provisioning and styling of and interaction with IReps. Five applications of the SRA provide proofs of concept for the general applicability and utility of the SRA. A qualitative evaluation indicates the overall suitability of the SRA, its applications and the general approach of building 3DGeoVSs based on SSI.},
  language  = {en}
}
@phdthesis{Heise2014,
  author    = {Heise, Arvid},
  title     = {Data cleansing and integration operators for a parallel data analytics platform},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-77100},
  school      = {Universit{\"a}t Potsdam},
  pages     = {ii, 179},
  year      = {2014},
  abstract  = {The data quality of real-world datasets need to be constantly monitored and maintained to allow organizations and individuals to reliably use their data. Especially, data integration projects suffer from poor initial data quality and as a consequence consume more effort and money. Commercial products and research prototypes for data cleansing and integration help users to improve the quality of individual and combined datasets. They can be divided into either standalone systems or database management system (DBMS) extensions. On the one hand, standalone systems do not interact well with DBMS and require time-consuming data imports and exports. On the other hand, DBMS extensions are often limited by the underlying system and do not cover the full set of data cleansing and integration tasks. We overcome both limitations by implementing a concise set of five data cleansing and integration operators on the parallel data analytics platform Stratosphere. We define the semantics of the operators, present their parallel implementation, and devise optimization techniques for individual operators and combinations thereof. Users specify declarative queries in our query language METEOR with our new operators to improve the data quality of individual datasets or integrate them to larger datasets. By integrating the data cleansing operators into the higher level language layer of Stratosphere, users can easily combine cleansing operators with operators from other domains, such as information extraction, to complex data flows. Through a generic description of the operators, the Stratosphere optimizer reorders operators even from different domains to find better query plans. As a case study, we reimplemented a part of the large Open Government Data integration project GovWILD with our new operators and show that our queries run significantly faster than the original GovWILD queries, which rely on relational operators. Evaluation reveals that our operators exhibit good scalability on up to 100 cores, so that even larger inputs can be efficiently processed by scaling out to more machines. Finally, our scripts are considerably shorter than the original GovWILD scripts, which results in better maintainability of the scripts.},
  language  = {en}
}