1. the complete title of one (or more) paper(s) published in the open literature describing the work that the author claims describes a human-competitive result; An Evolutionary Approach for Generating Software Models: The case of Kromaia in Game Software Engineering -------------------------------------------------------------------------------------- 2. the name, complete physical mailing address, e-mail address, and phone number of EACH author of EACH paper(s); Daniel Blasco SVIT Research Group Universidad San Jorge Autovía A-23 Zaragoza-Huesca Km. 299 50830 Zaragoza, Spain email: dblasco@usj.es tel: +34 976 060 100 Jaime Font SVIT Research Group Universidad San Jorge Autovía A-23 Zaragoza-Huesca Km. 299 50830 Zaragoza, Spain email: jfont@usj.es tel: +34 976 060 100 Mar Zamorano SVIT Research Group Universidad San Jorge Autovía A-23 Zaragoza-Huesca Km. 299 50830 Zaragoza, Spain email: mzamorano@usj.es tel: +34 976 060 100 Carlos Cetina SVIT Research Group Universidad San Jorge Autovía A-23 Zaragoza-Huesca Km. 299 50830 Zaragoza, Spain email: ccetina@usj.es tel: +34 976 060 100 -------------------------------------------------------------------------------------- 3. the name of the corresponding author (i.e., the author to whom notices will be sent concerning the competition); Jaime Font -------------------------------------------------------------------------------------- 4. the abstract of the paper(s); In the context of Model-Driven Engineering applied to video games, software models are high-level abstractions that represent source code implementations of varied content such as the stages of the game, vehicles, or enemy entities (e.g., final bosses). In this work, we present our Evolutionary Model Generation (EMoGen) approach to generate software models that are comparable in quality to the models created by human developers. Our approach is based on an evolution (mutation and crossover) and assessment cycle to generate the software models. We evaluated the software models generated by EMoGen in the Kromaia video game, which is a commercial video game released on Steam and PlayStation 4. Each model generated by EMoGen has more than 1000 model elements. The results, which compare the software models generated by our approach and those generated by the developers, show that our approach achieves results that are comparable to the ones created manually by the developers in the retail and digital versions of the video game case study. However, our approach only takes five hours of unattended time in comparison to ten months of work by the developers. We perform a statistical analysis, and we make an implementation of EMoGen readily available. -------------------------------------------------------------------------------------- 5. a list containing one or more of the eight letters (A, B, C, D, E, F, G, or H) that correspond to the criteria (see above) that the author claims that the work satisfies; G, E, F -------------------------------------------------------------------------------------- 6. a statement stating why the result satisfies the criteria that the contestant claims (see examples of statements of human-competitiveness as a guide to aid in constructing this part of the submission); (G) The result solves a problem of indisputable difficulty in its field. The complexity of developing video games has reached a point that exceeds the human capacity of developers (endless delays and omnipresent bugs attest to this). The latest video game blockbuster (Cyberpunk 2077) is a good example of this: - The title suffered unnumerable delays throughout its seven years of development. - The title was riddled with bugs upon release, so much so that developers had to release a monstrous 50GB day-one update. - Despite of the update, the title was still so buggy that the development studio offered refunds without having to return the game. - To date, five months after the release date, developers are still working to fix the video game. Actually, the annual surveys of the International Game Developers Association describe unending days and sleepless nights that developers trudged through to bring video games to life. According to these surveys, developers have become severely underweight, slept in their office, and gone weeks without seeing their friends or family just to get a video game out of the door. (E) The result is equal to or better than the most recent human-created solution to a long-standing problem for which there has been a succession of increasingly better human-created solutions. Like most video games, Kromaia is the result of a succession of efforts of the development team to build a video game that delivers the best experience possible when played. However, building a video game is not straightforward, as there are no fixed rules on what makes a video game interesting, fun, addictive, or enjoyable. This results in the need for a series of iterations where the product is tested and evolved several times until the final version, the one that delivers the best experience, is obtained. In particular, Kromaia was developed over five years, although at the end of the first year the team already had an incomplete but playable version of the video game. There has been a succession of solutions, each of them getting closer to the objective of generating a game able to deliver a pleasant experience when played. Once the first playable version was ready, it was presented to competitions at video game events, achieving better results as the video game evolved. It was a finalist at hóPLAY 2010, finalist at Freeplay 2011, finalist at the Indie Developer Burger Awards 2012, finalist at the European Indie Game Days 2013, winner at 3D WIRE 2013, winner at hóPLAY 2014, and winner at GAMELAB 2015. In the presented work, we compare the software models of game bosses generated by our evolutionary approach and those manually produced by the Kromaia development team and released as part of the video game. The comparison is based on a set of metrics widely used in literature to determine and compare the quality of a video game component. The comparison shows that the results of the evolutionary algorithm perform similarly or even better in terms of quality than those manually produced by the development team. (F) The result is equal to or better than a result that was considered an achievement in its field at the time it was first discovered. As pointed out in the previous point, Kromaia was the winner of several awards at different video game events. It is therefore considered by part of the video game community as an achievement at that time. The results of the evolutionary approach presented in our work performed similarly (or even better) to the models of boss enemies used in the commercial release of the video game on six different metrics from literature used to assess the quality of video games. Therefore, the results of our evolutionary approach are equal or better to those from Kromaia, considered as the best at the time by different video game communities. -------------------------------------------------------------------------------------- 7. a full citation of the paper (that is, author names; publication date; name of journal, conference, technical report, thesis, book, or book chapter; name of editors, if applicable, of the journal or edited book; publisher name; publisher city; page numbers, if applicable); Daniel Blasco, Jaime Font, Mar Zamorano, Carlos Cetina, An evolutionary approach for generating software models: The case of Kromaia in Game Software Engineering, Journal of Systems and Software, Volume 171, January 2021, 110804, ISSN 0164-1212, https://doi.org/10.1016/j.jss.2020.110804. -------------------------------------------------------------------------------------- 8. a statement either that "any prize money, if any, is to be divided equally among the co-authors" OR a specific percentage breakdown as to how the prize money, if any, is to be divided among the co-authors; Prize money, if any, is to be divided equally among the co-authors. -------------------------------------------------------------------------------------- 9. a statement stating why the authors expect that their entry would be the "best," and Video games are big: video game industry (160B$) is already bigger than movies industry (96B$) [1]; video game industry is eating sports industry (750B$) by means of e-sports [1]; and video game industry aims to create virtual worlds [2] that will revolutionize the way we work and socialize. However, there is a catch: video game complexity is so big that it puts extreme pressure on video game developers as the International Game Developers Association (IGDA) reports [3]. Every year, IGDA releases the Developer Satisfaction Survey about the well-being and opinions of developers and of the game industry as a whole. Survey after survey [4], IGDA raises concern about how crunch in video game development is affecting small studios as well as giants of the industry. Crunch has become a term to describe unending days and sleepless nights that developers trudged through to bring video games to life. These surveys revealed the horrors of crunch. Developers have become severely underweight, slept in their office, and gone weeks without seeing their friends or family just to get a video game out of the door. Crunch was the response of the industry to tackle the increasing complexity of video games. However, crunch is not sustainable. The latest video game blockbuster (Cyberpunk 2077) is a good example of this [5]. The title suffered unnumerable delays throughout its seven-year development. The title was riddled with bugs upon release, so much so that developers had to release a monstrous 50GB day-one update. Despite the update, the title was still so buggy that the development studio offered refunds without having to return the game. To date, five months after the release date, developers are still crunching to fix the video game. Our evolutionary approach has potential to be a game-changer for video game development. Our approach produced human-competitive video game content (final bosses, the game characters at the end of each stage of the video game) of a commercial video game (Kromaia video game [6]) released worldwide in both physical and digital versions for PlayStation and PC. We state that the video game content was human competitive because we successfully compared it to the video game content produced by human developers by means of fundamental and measurable indicators accepted by the video game community (Completion, Duration, Uncertainty, Killer Moves, Permanence, and Lead Change) [7]. It is worth mentioning that we compared the results of our approach to multi-award-winning video game content (best technology at GAMELAB, best creative design at hóPLAY, and best game at 3D WIRE) [6]. To produce the human-competitive video game content, our approach only took five hours of unattended time in comparison with ten months of work by the video game developers as the version control system shows and it was confirmed by the developers (including the time spent by real players on tests) [8]. The results were so striking that they soon attracted the attention of national (Spain) news [9, 10, 11] and are starting to attract the attention of South American news [12]. Among all of the questions from reporters and audience (which included video game developers), one question prevailed from interview to interview: does this new approach make video game developers redundant? In other words, video game developers, that repeatedly suffer from crunch, started to question their role in video game development because of the results of our approach. We applied for a European patent and extended it to a PCT patent. Our approach also shares another facet with human developers: the capability of making money (in the form of licenses in the case of our approach). Our approach attracted the attention of multi-award-winning video game studios such as Kraken Empire and Tequila Works as well as industry giants as King (the developers of the well-known Candy Crush video game). Our work is a conceptual leap forward for Genetic Programming [13], where programs are evolved to fit a specific task. Our work contributes to the rise of what we named Genetic Modeling [8], where models (higher-level specifications with exponentially less noise than programing languages) are evolved to fit a specific task (models are evolved for video game content in the particular case of our work). The major advantage of modelling languages (e.g., UML) is that models use concepts that are much less bound to the underlying implementation technology (like video game engines such as Unreal or Unity), and are much closer to the problem domain (the content of the video game) related to most popular programming languages (e.g., C++). This notion of ”model” should not be confused with ”mesh” or ”polygon mesh”, which are terms used in computer graphics and video games for the visual representation of 3D shapes/geometry. Automatically generating human-competitive models is a challenging task. Fully achieving it spans the creation of model elements, the initialization of their properties, and their relationships with each other. Moreover, the resulting models must be valid, which includes satisfying modeling constraints. Finally, the human-competitive aspect is only achieved if the resulting models are comparable to those produced by developers for the same task at hand. Our work success at the scale of a multi-award-winning commercial video game such as Kromaia where each generated model has about 1300 model elements, 15000 model properties, and 1000 model relationships. [1] Market Watch, “Videogames are a bigger industry than movies and North American sports combined, thanks to the pandemic,” 2021. https://www.marketwatch.com/story/videogames-are-a-bigger-industry-than-sports-and-movies-combined-thanks-to-the-pandemic-11608654990 (accessed May 13, 2021). [2] The Guardian, “Virtual worlds,” 2021. https://www.theguardian.com/games/virtual-worlds (accessed May 13, 2021). [3] International Game Developers Association, “Developer Satisfaction Survey,” 2020. https://igda-website.s3.us-east-2.amazonaws.com/wp-content/uploads/2020/11/25095744/IGDA-DSS-2019-Industry-Trends-Report_111820.pdf (accessed May 13, 2021). [4] International Game Developers Association, “Developer Satisfaction Survey Repository,” 2021. https://igda.org/resources-tax/dss/ (accessed May 13, 2021). [5] The Guardian, “Cyberpunk 2077: how 2020's biggest video game launch turned into a shambles,” 2020. https://www.theguardian.com/games/2020/dec/18/cyberpunk-2077-how-2020s-biggest-video-game-launch-turned-into-a-shambles (accessed May 13, 2021). [6] Kraken Empire, “Kromai video game,” 2020. http://www.krakenempire.com/kromaia/media.html (accessed May 13, 2021). [7] C. Browne, F. Maire, Evolutionary game design, IEEE Trans. Comput. Intellig. and AI in Games 2 (2010) 1–16. [8] D. Blasco, J. Font, M. Zamorano, C. Cetina, An evolutionary approach for generating software models: The case of Kromaia in Game Software Engineering, Journal of Systems and Software, Volume 171, 2021. [9] ABC, “El invento español que reduce el trabajo de desarrollo de un videojuego de meses a horas,”2021. https://www.abc.es/tecnologia/videojuegos/abci-invento-espanol-reduce-trabajo-desarrollovideojuego-meses-horas-202101282036_noticia.html#vca=rrss-inducido&vmc=abces&vso=tw&vli=noticia.foto (accessed May 13, 2021). [10] HERALDO, “Un motor de sugerencias genera nuevos contenidos para videojuegos en tan solo unas horas,” 2021. https://www.heraldo.es/noticias/aragon/2021/04/09/un-motor-de-sugerencias-generanuevos-contenidos-para-videojuegos-en-tan-solo-unas-horas-1483464.html (accessed May 13, 2021). [11] Cadena SER, “Hora 14 Aragón (03/05/2021),” 2021. https://play.cadenaser.com/audio/ser_aragon_hora14aragon_20210503_140552_143000/ (accessed May 13, 2021). [12] TeraGames, “Un motor de sugerencias genera nuevos contenidos sobre videojuegos,” 2021. https://www.teragames.com.mx/un-motor-de-sugerencias-genera-nuevos-contenidos-sobre-videojuegos/ (accessed May 13, 2021). [13] J. R. Koza, Genetic Programming: On the Programming of Computers by Means of Natural Selection, MIT Press, Cambridge, MA, 1992. -------------------------------------------------------------------------------------- 10. An indication of the general type of genetic or evolutionary computation used, such as GA (genetic algorithms), GP (genetic programming), ES (evolution strategies), EP (evolutionary programming), LCS (learning classifier systems), GE (grammatical evolution), GEP (gene expression programming), DE (differential evolution), etc. Genetic Modeling (see 9.) -------------------------------------------------------------------------------------- 11. The date of publication of each paper. If the date of publication is not on or before the deadline for submission, but instead, the paper has been unconditionally accepted for publication and is “in press” by the deadline for this competition, the entry must include a copy of the documentation establishing that the paper meets the "in press" requirement. Accepted 24 August 2020, Available online 27 August 2020, Published January 2021.