pith. sign in

arxiv: 1907.03877 · v1 · pith:NRWDQ3T2new · submitted 2019-07-08 · 💻 cs.HC · cs.AI· cs.IR

Pitako -- Recommending Game Design Elements in Cicero

Tiago Machado , Dan Gopstein , Andy Nealen , Julian Togelius This is my paper

Pith reviewed 2026-05-25 00:37 UTC · model grok-4.3

classification 💻 cs.HC cs.AIcs.IR
keywords recommender systemsgame designmixed-initiativemechanicsdynamicscreative assistanceAI design tools
0
0 comments X

The pith

Pitako applies recommender systems to suggest mechanics and dynamics from human-designed games.

A machine-rendered reading of the paper's core claim, the machinery that carries it, and where it could break.

The paper introduces Pitako as a recommender system tool embedded in the Cicero game design assistant. It accepts human-designed games as input and generates suggestions for game mechanics and dynamics as output. This setup tests whether patterns from existing games can support new creative work. The authors describe its motivation, implementation details, and example uses. If the approach holds, recommender systems could move from shopping recommendations into everyday creative assistance.

Core claim

Pitako is a recommender system that processes games designed by humans and recommends mechanics and dynamics for new designs, implemented as a component inside the mixed-initiative AI-based Game Design Assistant Cicero.

What carries the argument

The recommender system that takes human-designed games as input and outputs recommended mechanics and dynamics.

If this is right

  • The system can generate mechanics and dynamics suggestions drawn directly from patterns in human games.
  • It supports mixed-initiative design workflows inside Cicero.
  • Recommender systems can be applied to creative tasks beyond e-commerce.
  • Designers receive concrete output examples during the design process.

Where Pith is reading between the lines

These are editorial extensions of the paper, not claims the author makes directly.

  • Similar recommenders could be tested in other creative domains such as level design or narrative construction.
  • Suggestions might surface mechanics from distant genres that a designer would not consider unaided.
  • Long-term use could change the distribution of mechanics that appear in published games.

Load-bearing premise

Patterns extracted from existing human-designed games will produce suggestions that are relevant and helpful for new creative design tasks.

What would settle it

A controlled study in which designers using Pitako produce games rated no more helpful or creative than those produced without the tool.

Figures

Figures reproduced from arXiv: 1907.03877 by Andy Nealen, Dan Gopstein, Julian Togelius, Tiago Machado.

Figure 1
Figure 1. Figure 1: Example of a Space Invaders (Taito, 1978) version written in VGDL. • The Sprite Set - A sprite is any object in the game, including its graphical representation and behavior. In this set the sprites are defined. It is the place to specify if your avatar can shoot and if a non player character (NPC) will move randomly around the level or chase another game element. We stress here that in VGDL a sprite has b… view at source ↗
Figure 2
Figure 2. Figure 2: In the association rule on the top, the presence of a [PITH_FULL_IMAGE:figures/full_fig_p003_2.png] view at source ↗
Figure 3
Figure 3. Figure 3: From left to right, a catalog of game sprite sets with [PITH_FULL_IMAGE:figures/full_fig_p004_3.png] view at source ↗
Figure 4
Figure 4. Figure 4: In this figure (a) is the user’s game’s sprite set. In (b) we look at [PITH_FULL_IMAGE:figures/full_fig_p005_4.png] view at source ↗
Figure 5
Figure 5. Figure 5: For the sprite type RandomNPC in the game Bomberman, its positions in the three first levels are shown in this figure. The association rule is filtering according the heuristics and then suggested to the user. C. Recommending interaction rules In VGDL, an interaction is composed by two sprites and the interaction they activate when colliding. Therefore to [PITH_FULL_IMAGE:figures/full_fig_p005_5.png] view at source ↗
Figure 6
Figure 6. Figure 6: The sprite recommendation component displays which game the sprite [PITH_FULL_IMAGE:figures/full_fig_p006_6.png] view at source ↗
Figure 7
Figure 7. Figure 7: An example of a interaction recommendation component. The avatar [PITH_FULL_IMAGE:figures/full_fig_p006_7.png] view at source ↗
Figure 9
Figure 9. Figure 9: An example of a game designed by a user assisted by our recommender [PITH_FULL_IMAGE:figures/full_fig_p007_9.png] view at source ↗
read the original abstract

Recommender Systems are widely and successfully applied in e-commerce. Could they be used for design? In this paper, we introduce Pitako1, a tool that applies the Recommender System concept to assist humans in creative tasks. More specifically, Pitako provides suggestions by taking games designed by humans as inputs, and recommends mechanics and dynamics as outputs. Pitako is implemented as a new system within the mixed-initiative AI-based Game Design Assistant, Cicero. This paper discusses the motivation behind the implementation of Pitako as well as its technical details and presents usage examples. We believe that Pitako can influence the use of recommender systems to help humans in their daily tasks.

Editorial analysis

A structured set of objections, weighed in public.

Desk editor's note, referee report, simulated authors' rebuttal, and a circularity audit. Tearing a paper down is the easy half of reading it; the pith above is the substance, this is the friction.

Referee Report

1 major / 0 minor

Summary. The paper introduces Pitako, a recommender system integrated into the Cicero mixed-initiative AI-based Game Design Assistant. It takes human-designed games as input and outputs recommended mechanics and dynamics, covering motivation, technical implementation details, and usage examples, with the belief that it can extend recommender systems to creative design tasks.

Significance. If the described functionality holds and the recommendations prove relevant, the work could illustrate a practical application of recommender systems beyond e-commerce into game design assistance, potentially informing mixed-initiative creative tools in HCI.

major comments (1)
  1. [Abstract] Abstract: the manuscript asserts that Pitako 'provides suggestions' to 'assist humans in creative tasks' and 'can influence the use of recommender systems', yet supplies no evaluation, user study, accuracy metrics, or evidence that the extracted patterns yield relevant or helpful outputs for new designs; only usage examples are referenced, leaving the core utility claim unsupported.

Simulated Author's Rebuttal

1 responses · 0 unresolved

We thank the referee for the detailed review. The primary concern is the absence of formal evaluation supporting the utility claims. We address this directly below, noting that the manuscript is a system description paper focused on implementation and illustrative examples rather than empirical validation.

read point-by-point responses

  1. Referee: [Abstract] Abstract: the manuscript asserts that Pitako 'provides suggestions' to 'assist humans in creative tasks' and 'can influence the use of recommender systems', yet supplies no evaluation, user study, accuracy metrics, or evidence that the extracted patterns yield relevant or helpful outputs for new designs; only usage examples are referenced, leaving the core utility claim unsupported.

    Authors: The referee correctly observes that the paper contains no user study, accuracy metrics, or controlled evaluation. The manuscript's scope is limited to describing the motivation for applying recommender systems to game design, the technical integration into Cicero, and usage examples that demonstrate the recommendation process. These examples serve to illustrate how the system operates on human-designed games but do not constitute evidence of relevance or helpfulness for new designs. We do not claim empirical validation of utility; the abstract's phrasing reflects the intended purpose of the tool rather than proven outcomes. If a revision is requested, we can revise the abstract and conclusion to more precisely frame the contribution as a proof-of-concept system description and add an explicit limitations section discussing the need for future evaluation. revision: partial

Circularity Check

0 steps flagged

No significant circularity

full rationale

This is a system-description paper that presents the implementation and usage of Pitako, a recommender tool inside Cicero. The manuscript supplies motivation, technical details, and examples for an input-output mapping (human-designed games → suggested mechanics/dynamics) but contains no equations, derivations, fitted parameters, predictions, or uniqueness theorems. No load-bearing step reduces to its own inputs by construction or self-citation chain. The central claim is realized exactly by the described functionality and requires no external validation that the paper itself supplies.

Axiom & Free-Parameter Ledger

0 free parameters · 0 axioms · 0 invented entities

The paper is a descriptive account of a software tool. It contains no mathematical derivations, fitted parameters, or new postulated entities.

pith-pipeline@v0.9.0 · 5642 in / 958 out tokens · 24235 ms · 2026-05-25T00:37:56.967923+00:00 · methodology

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Reference graph

Works this paper leans on

43 extracted references · 43 canonical work pages

  1. [1]

    The long tail,

    C. Anderson, “The long tail,” Wired magazine, vol. 12, no. 10, p. 107, 2004

    work page 2004

  2. [2]

    Personalizing tags: A folksonomy-like approach for recommending movies,

    A. Said, B. Kille, E. W. De Luca, and S. Albayrak, “Personalizing tags: A folksonomy-like approach for recommending movies,” in Proceedings of the 2Nd International Workshop on Information Heterogeneity and Fusion in Recommender Systems , ser. HetRec ’11. New York, NY , USA: ACM, 2011, pp. 53–56. [Online]. Available: http://doi.acm.org/10.1145/2039320.2039328

    work page doi:10.1145/2039320.2039328 2011

  3. [3]

    How can we help our k-12 teachers?: Using a recommender to make personalized book suggestions,

    M. S. Pera and Y . K. Ng, “How can we help our k-12 teachers?: Using a recommender to make personalized book suggestions,” in Proceedings of the 2014 IEEE/WIC/ACM International Joint Conferences on Web Intelligence (WI) and Intelligent Agent Technologies (IAT) - Volume 02 , ser. WI-IAT ’14. Washington, DC, USA: IEEE Computer Society, 2014, pp. 335–342. [O...

    work page doi:10.1109/wi-iat.2014.116 2014

  4. [4]

    Multi-method evaluation in scientific paper recommender systems,

    A. Sesagiri Raamkumar and S. Foo, “Multi-method evaluation in scientific paper recommender systems,” in Adjunct Publication of the 26th Conference on User Modeling, Adaptation and Personalization , ser. UMAP ’18. New York, NY , USA: ACM, 2018, pp. 179–182. [Online]. Available: http://doi.acm.org/10.1145/3213586.3226215

    work page doi:10.1145/3213586.3226215 2018

  5. [5]

    Movement correction in instructed fitness training: Design recommendations and opportunities,

    L. Turmo Vidal, E. M ´arquez Segura, and A. Waern, “Movement correction in instructed fitness training: Design recommendations and opportunities,” in Proceedings of the 2018 Designing Interactive Systems Conference, ser. DIS ’18. New York, NY , USA: ACM, 2018, pp. 1041–

    work page 2018

  6. [6]

    Available: http://doi.acm.org/10.1145/3196709.3196789

    [Online]. Available: http://doi.acm.org/10.1145/3196709.3196789

    work page doi:10.1145/3196709.3196789

  7. [7]

    Recommending friends in local social networks: An envelope of algorithms,

    Y . Liu, X. Chang, and W. W. Huang, “Recommending friends in local social networks: An envelope of algorithms,” in Proceedings of the 2014 International Conference on Big Data Science and Computing , ser. BigDataScience ’14. New York, NY , USA: ACM, 2014, pp. 35:1–35:3. [Online]. Available: http://doi.acm.org/10.1145/2640087.2644197

    work page doi:10.1145/2640087.2644197 2014

  8. [8]

    Sentient sketchbook: Computer-aided game level authoring

    A. Liapis, G. N. Yannakakis, and J. Togelius, “Sentient sketchbook: Computer-aided game level authoring.” in FDG, 2013, pp. 213–220

    work page 2013

  9. [9]

    Swap adjacent gems to make sets of three: A history of matching tile games,

    J. Juul, “Swap adjacent gems to make sets of three: A history of matching tile games,” Artifact, vol. 1, no. 4, pp. 205–216, 2007

    work page 2007

  10. [10]

    Mechanics automatically recognized via interactive observation: Jumping,

    A. Summerville, J. Osborn, C. Holmg ˚ard, and D. W. Zhang, “Mechanics automatically recognized via interactive observation: Jumping,” in Proceedings of the 12th International Conference on the Foundations of Digital Games , ser. FDG ’17. New York, NY , USA: ACM, 2017, pp. 25:1–25:10. [Online]. Available: http://doi.acm.org/10.1145/3102071.3102104

    work page doi:10.1145/3102071.3102104 2017

  11. [11]

    Creating creativity: user interfaces for support- ing innovation,

    B. Shneiderman, “Creating creativity: user interfaces for support- ing innovation,” ACM Transactions on Computer-Human Interaction (TOCHI), vol. 7, no. 1, pp. 114–138, 2000

    work page 2000

  12. [12]

    The gene: An intimate history,

    M. Siddharta, “The gene: An intimate history,” Scribner, New York, pp. 9–9, 2016

    work page 2016

  13. [13]

    Defining game mechanics,

    M. Sicart, “Defining game mechanics,” Game Studies , vol. 8, no. 2, 2008

    work page 2008

  14. [14]

    Towards minimalist game design,

    A. Nealen, A. Saltsman, and E. Boxerman, “Towards minimalist game design,” in Proceedings of the 6th International Conference on Founda- tions of Digital Games . ACM, 2011, pp. 38–45

    work page 2011

  15. [15]

    Challenges for game designers, charles river media,

    B. Brathwaite and I. Schreiber, “Challenges for game designers, charles river media,” Inc., Rockland, MA , 2008

    work page 2008

  16. [16]

    Schuytema, Game design: A practical approach

    P. Schuytema, Game design: A practical approach . Charles River Media, 2007, no. Sirsi) i9781584504719

    work page 2007

  17. [17]

    Mda: A formal approach to game design and game research,

    R. Hunicke, M. LeBlanc, and R. Zubek, “Mda: A formal approach to game design and game research,” in Proceedings of the AAAI Workshop on Challenges in Game AI , vol. 4, no. 1, 2004, p. 1722

    work page 2004

  18. [18]

    The genetics of drosophila melanogaster,

    T. H. Morgan, C. Bridges, and A. Sturtevant, “The genetics of drosophila melanogaster,” Biblphia genet, vol. 2, pp. 1–262, 1925

    work page 1925

  19. [19]

    Towards a video game description language,

    M. Ebner, J. Levine, S. M. Lucas, T. Schaul, T. Thompson, and J. Togelius, “Towards a video game description language,” 2013

    work page 2013

  20. [20]

    A video game description language for model-based or interactive learning,

    T. Schaul, “A video game description language for model-based or interactive learning,” in Computational Intelligence in Games (CIG), 2013 IEEE Conference on . IEEE, 2013, pp. 1–8

    work page 2013

  21. [21]

    General video game ai: Competition, challenges and opportu- nities,

    D. Perez-Liebana, S. Samothrakis, J. Togelius, T. Schaul, and S. M. Lucas, “General video game ai: Competition, challenges and opportu- nities,” in Thirtieth AAAI Conference on Artificial Intelligence , 2016

    work page 2016

  22. [22]

    The 2014 general video game playing competition,

    D. Perez-Liebana, S. Samothrakis, J. Togelius, T. Schaul, S. M. Lucas, A. Cou ¨etoux, J. Lee, C.-U. Lim, and T. Thompson, “The 2014 general video game playing competition,” IEEE Transactions on Computational Intelligence and AI in Games , vol. 8, no. 3, pp. 229–243, 2016

    work page 2014

  23. [23]

    R. S. Singleton, Film Scheduling, Or, How Long Will it Take to Shoot Your Movie? Lone Eagle New York, 1991

    work page 1991

  24. [24]

    Seekwhence a retrospective analysis tool for general game design,

    T. Machado, A. Nealen, and J. Togelius, “Seekwhence a retrospective analysis tool for general game design,” in Proceedings of the 12th International Conference on the Foundations of Digital Games , ser. FDG ’17. New York, NY , USA: ACM, 2017, pp. 4:1–4:6. [Online]. Available: http://doi.acm.org/10.1145/3102071.3102090

    work page doi:10.1145/3102071.3102090 2017

  25. [25]

    Kwiri-what, when, where and who: Everything you ever wanted to know about your game but didnt know how to ask,

    T. Machado, D. Gopstein, A. Nealen, and J. Togelius, “Kwiri-what, when, where and who: Everything you ever wanted to know about your game but didnt know how to ask,” inKnowledge Extraction From Games Workshop. AAAI, 2019

    work page 2019

  26. [26]

    Ai- assisted game debugging with cicero,

    T. Machado, D. Gopstein, A. Nealen, O. Nov, and J. Togelius, “Ai- assisted game debugging with cicero,” 2018 IEEE Congress on Evolu- tionary Computation (CEC) , pp. 1–8, 2018

    work page 2018

  27. [27]

    Shopping for game mechanics,

    T. Machado, I. Bravi, Z. Wang, A. Nealen, and J. Togelius, “Shopping for game mechanics,” 2016

    work page 2016

  28. [28]

    Hybrid recommender systems: Survey and experiments,

    R. Burke, “Hybrid recommender systems: Survey and experiments,” User modeling and user-adapted interaction, vol. 12, no. 4, pp. 331–370, 2002

    work page 2002

  29. [29]

    Toward the next generation of recommender systems: A survey of the state-of-the-art and possible extensions,

    G. Adomavicius and A. Tuzhilin, “Toward the next generation of recommender systems: A survey of the state-of-the-art and possible extensions,” IEEE Trans. on Knowl. and Data Eng. , vol. 17, no. 6, pp. 734–749, Jun. 2005. [Online]. Available: https://doi.org/10.1109/TKDE.2005.99

    work page doi:10.1109/tkde.2005.99 2005

  30. [30]

    The anatomy of a large-scale hypertextual web search engine,

    S. Brin and L. Page, “The anatomy of a large-scale hypertextual web search engine,” Computer networks and ISDN systems , vol. 30, no. 1-7, pp. 107–117, 1998

    work page 1998

  31. [31]

    User modeling for adaptive news access,

    D. Billsus and M. J. Pazzani, “User modeling for adaptive news access,” User modeling and user-adapted interaction , vol. 10, no. 2-3, pp. 147– 180, 2000

    work page 2000

  32. [32]

    Learning user interests through positive examples using content analysis and collaborative filtering,

    I. Schwab, A. Kobsa, and I. Koychev, “Learning user interests through positive examples using content analysis and collaborative filtering,” Internal Memo, GMD, St. Augustin, Germany , 2001

    work page 2001

  33. [33]

    Amazon. com recommendations: Item-to-item collaborative filtering,

    G. Linden, B. Smith, and J. York, “Amazon. com recommendations: Item-to-item collaborative filtering,” IEEE Internet computing , no. 1, pp. 76–80, 2003

    work page 2003

  34. [34]

    The netflix recommender system: Algorithms, business value, and innovation,

    C. A. Gomez-Uribe and N. Hunt, “The netflix recommender system: Algorithms, business value, and innovation,” ACM Transactions on Management Information Systems (TMIS) , vol. 6, no. 4, p. 13, 2016

    work page 2016

  35. [35]

    Efficient adaptive-support associa- tion rule mining for recommender systems,

    W. Lin, S. A. Alvarez, and C. Ruiz, “Efficient adaptive-support associa- tion rule mining for recommender systems,” Data mining and knowledge discovery, vol. 6, no. 1, pp. 83–105, 2002

    work page 2002

  36. [36]

    Fast algorithms for mining association rules,

    R. Agarwal, R. Srikant et al. , “Fast algorithms for mining association rules,” in Proc. of the 20th VLDB Conference , 1994, pp. 487–499

    work page 1994

  37. [37]

    Mining association rules between sets of items in large databases,

    R. Agrawal, T. Imieli ´nski, and A. Swami, “Mining association rules between sets of items in large databases,” in Acm sigmod record, vol. 22, no. 2. ACM, 1993, pp. 207–216

    work page 1993

  38. [38]

    A suggestive interface for 3d drawing,

    T. Igarashi and J. F. Hughes, “A suggestive interface for 3d drawing,” in Proceedings of the 14th annual ACM symposium on User interface software and technology . ACM, 2001, pp. 173–181

    work page 2001

  39. [39]

    Designscape: Design with interactive layout suggestions,

    P. O’Donovan, A. Agarwala, and A. Hertzmann, “Designscape: Design with interactive layout suggestions,” in Proceedings of the 33rd Annual ACM Conference on Human Factors in Computing Systems , ser. CHI ’15. New York, NY , USA: ACM, 2015, pp. 1221–1224. [Online]. Available: http://doi.acm.org/10.1145/2702123.2702149

    work page doi:10.1145/2702123.2702149 2015

  40. [40]

    The known stranger: Supporting conversations between strangers with personalized topic suggestions,

    T. T. Nguyen, D. T. Nguyen, S. T. Iqbal, and E. Ofek, “The known stranger: Supporting conversations between strangers with personalized topic suggestions,” in Proceedings of the 33rd Annual ACM Conference on Human Factors in Computing Systems , ser. CHI ’15. New York, NY , USA: ACM, 2015, pp. 555–564. [Online]. Available: http://doi.acm.org/10.1145/270212...

    work page doi:10.1145/2702123.2702411 2015

  41. [41]

    Towards pattern-based mixed-initiative dungeon generation,

    A. Baldwin, S. Dahlskog, J. M. Font, and J. Holmberg, “Towards pattern-based mixed-initiative dungeon generation,” in Proceedings of the 12th International Conference on the Foundations of Digital Games , ser. FDG ’17. New York, NY , USA: ACM, 2017, pp. 74:1–74:10. [Online]. Available: http://doi.acm.org/10.1145/3102071.3110572

    work page doi:10.1145/3102071.3110572 2017

  42. [42]

    Fostering creativity in the mixed-initiative evolutionary dungeon designer,

    A. Alvarez, S. Dahlskog, J. Font, J. Holmberg, C. Nolasco, and A. ¨Osterman, “Fostering creativity in the mixed-initiative evolutionary dungeon designer,” in Proceedings of the 13th International Conference on the Foundations of Digital Games , ser. FDG ’18. New York, NY , USA: ACM, 2018, pp. 50:1–50:8. [Online]. Available: http://doi.acm.org/10.1145/3235...

    work page doi:10.1145/3235765.3235815 2018

  43. [43]

    A computational framework for conceptual blending,

    M. Eppe, E. Maclean, R. Confalonieri, O. Kutz, M. Schorlemmer, E. Plaza, and K.-U. K ¨uhnberger, “A computational framework for conceptual blending,” Artificial Intelligence , vol. 256, pp. 105–129, 2018

    work page 2018