Artefacts in Software Engineering: A Fundamental Positioning

TL;DR

This paper critically examines the concept of artefacts in software engineering, proposing a standardized terminology and a meta model to clarify their definitions and relationships, aiming to unify understanding among researchers and practitioners.

Contribution

It introduces a comprehensive meta model for artefacts in software engineering, clarifying their levels, relations, and definitions to promote terminological standardization.

Findings

Proposes a three-level meta model for artefacts.

Defines relations like related, refined, and equivalent.

Aims to unify terminology in software engineering.

Abstract

Artefacts play a vital role in software and systems development processes. Other terms like documents, deliverables, or work products are widely used in software development communities instead of the term artefact. In the following, we use the term `artefact' including all these other terms. Despite its relevance, the exact denotation of the term `artefact' is still not clear due to a variety of different understandings of the term and to a careless negligent usage. This often leads to approaches being grounded in a fuzzy, unclear understanding of the essential concepts involved. In fact, there does not exist a common terminology. Therefore, it is our goal that the term artefact be standardised so that researchers and practitioners have a common understanding for discussions and contributions. In this position paper, we provide a positioning and critical reflection upon the notion of artefact in software engineering at different levels of perception and how these relate to each other. We further contribute a meta model that provides a description of an artefact that is independent from any underlying process model. This meta model defines artefacts at three levels. Abstraction and refinement relations between these levels allow correlating artefacts to each other and defining the notion of related, refined, and equivalent artefacts. Our contribution shall foster the long overdue and too often underestimated terminological discussion on what artefacts are to provide a common ground with clearer concepts and principles for future software engineering contributions, such as the design of artefact-oriented development processes and tools.