We envisioned this focus group as more of a creative jam session than a traditional research activity. Laughter mixed with curiosity as participants imagined AI not as a tool, but as a bandmate offering melodies, suggesting rhythms, even challenging their musical instincts. Through spontaneous brainstorming and hands-on exercises, they explored how AI might co-create with artists. This playful experimentation echoed the spirit of the larger EuroPLoP conference, which centered on pattern recognition and collaborative learning fields where structure meets improvisation, and insight emerges from interaction. As AI is still scaling, there are “unknown unknowns” that need to be addressed as soon as possible. Our workshop explored these issues with AI-themed discussions (rather than being tied to any specific AI product). AI is frequently employed to grab attention, suggest innovation, or make something seem more advanced or futuristic than it may be. We wanted to engage participants in creative and critical thinking about such issues. The session concluded with a group reflection using the Project Action Review (PAR) technique, where participants reviewed personal insights and identified alternative research directions. Outcomes included the documentation of group reflections, a playful investigation of complex ideas, and the discovery of new connections among media, learning, and technology. We conducted a short pre- and post- survey, an analysis of which is included in our results.

This monograph reports a multi-agent proof sprint on ten research-level problems, combining rapid draft generation with adversarial verification, targeted repair, and explicit provenance. The workflow uses wiring-diagram decompositions of claim dependencies to localize gaps and coordinate reviewer-driven revisions. Final outcomes are heterogeneous but explicit: the manuscript distinguishes mathematical status from QC-validation status. Mathematically, Problem 3 has a validation-complete existence path under the scoped criterion used here (uniqueness/irreducibility treated as optional), Problem 5 is solved in a scope-limited form for F_O-local connective spectra, Problem 10 is conditional under clearly stated assumptions (with explicit necessity counterexamples when assumptions are dropped), and Problems 4 and 6 are partial with named remaining obligations in the general case (including an unconditional K_n result for Problem 6 with c_0 = 1/3). Problem 7 is treated as provisionally closed via the rotation-route theorem chain, pending independent ledger re-check. At the QC layer, Problems 7 and 9 have node-level validation artifacts but still contain unresolved verifier gaps. The main methodological result is that structure-aware verification and layer-switching strategies improve reliability and calibration in compressed proof sprints.

Our earlier paper "Patterns of Patterns" combined three techniques from training, futures studies, and design in a design pattern called PLACARD that helps groups of people work together effectively. We used that pattern in five hands-on workshop case studies which took place at various locations in the US and the UK. This experience report documents what we learned, including the way our thinking about PLACARD evolved, together with additional patterns our work generated. We evaluate the reproducibility of our methods and results, and consider the broader economic implications of this way of working. We discuss implications of our prototyping work for the design of future platforms, drawing connections with recent developments in cognitive science and artificial intelligence. This positions our patterns of patterns as a toolkit for the design and governance of systems that combine social dynamics with technical components.

Design patterns have been used in various fields of inquiry and endeavour to externalize procedural knowledge in a form that supports human reasoning and coordination. In this paper, we show that contemporary Large Language Model (LLM)-based systems can also read, generate, and reason with design patterns written in a structured template. We describe an experimental workflow in which patterns function as shared priors for action selection, reflection, and revision in hybrid human/agent settings. Drawing on the Active Inference Framework, we illustrate how patterns can guide agent behavior without fully prescribing it. This provides a proof of concept that pattern-capable agents can be created using now-standard software tools. We discuss implications for software development, education, business, and AI governance.

At EuroPLoP 2024 Mary Tedeschi led the “AI Future Envisioning with PLACARD” focus group in Germany. Three conference attendees joined in the room while Sridevi, Paola, and Charles co-facilitated remotely via a web conference. The participants were introduced to a Futures Studies technique with the goal of capturing envisionments of Artificial Intelligence (AI) going forward. To set an atmosphere a technology focused card game was used to make the session more interactive. To close everyone co-created a Project Action Review to recap of the event to capture learnings that has been summarized in this paper. The Focus Group was structured based on lessons learned over six earlier iterations.

We sketch the process of creating a novel video game by blending two video games specified in the Video Game Description Language (VGDL), following the COINVENT computational model of conceptual blending. We highlight the choices that need to be made in this process, and discuss the prospects for a computational game designer based on blending.

The purpose of this paper is to show how we can combine and adapt methods from elite training, future studies, and collaborative design, and apply them to address significant problems in social networks. We focus on three such methods: we use Project Action Reviews to implement social perception, Causal Layered Analysis to implement social cognition, and Design Pattern Languages to implement social action. We present the results of two studies: firstly, we use Causal Layered Analysis to explore the ways in which the design pattern discourse has been evolving. Secondly, to illustrate the three methods in combination, we develop a case study, showing how we applied the methods to bootstrap a distributed cross-disciplinary research seminar. Building on these analyses, we elaborate several scenarios for the future use of design patterns in large-scale distributed collaboration. Our case study suggests ways in which progress could be made towards realizing these scenarios. We conclude that the combination of methods is robust to uncertainty, insofar as they support adaptations as circumstances change, and incorporate diverse perspectives. In particular, we show how methods drawn from other domains enrich and are enriched by design patterns; we believe the analysis will be of interest to all of the communities whose methods we draw upon.

VirtuosA ('virtuous algorithm') is introduced, a model in which artificial intelligence (AI) systems learn ethical behaviour based on a framework adapted from Christian philosopher Dallas Willard and brought together with associated neurobiological structures and broader systems thinking. To make the inquiry concrete, the authors present a simple example scenario that illustrates how a robot might acquire behaviour akin to the virtue of kindness that can be attributed to humans. References to philosophical work by Peter Sloterdijk help contextualise Willard's virtue ethics framework. The VirtuosA architecture can be implemented using state-of-the-art computing practices and plausibly redescribes several concrete scenarios implemented from the computing literature and exhibits broad coverage relative to other work in ethical AI. Strategies are described for using the model for systems evaluation —particularly the role of 'embedded evaluation' within the system—and its broader application as a meta-ethical device is discussed.

This paper shows how we combine and adapt methods from elite training, future studies, and collaborative design, and apply them to address significant problems in social networks. We focus on three such methods: we use Project Action Reviews to implement social perception, Causal Layered Analysis to implement social cognition, and Design Pattern Languages to implement social action. We present the results of two studies: firstly, we use Causal Layered Analysis to explore the ways in which the design pattern discourse has been evolving. Secondly, to illustrate the three methods in combination, we develop a case study, showing how we applied the methods to bootstrap a distributed cross-disciplinary research seminar. Building on these analyses, we elaborate several scenarios for the future use of design patterns in large-scale distributed collaboration. Our case study suggests ways in which progress could be made towards realizing these scenarios. We conclude that the combination of methods is robust to uncertainty, insofar as they support adaptations as circumstances change, and incorporate diverse perspectives. In particular, we show how methods drawn from other domains enrich and are enriched by design patterns; we believe the analysis will be of interest to all of the communities whose methods we draw upon.

Patterns embody repeating phenomena, and, as such, they are partly but not fully detachable from their context. 'Design patterns' and 'pattern languages' are established methods for working with patterns. They have been applied in architecture, software engineering, and other design fields, but have so far seen little application in the field of future studies. We reimagine futures discourse and anticipatory practices using pattern methods. We focus specifically on processes for coordinating distributed projects, integrating multiple voices, and on play that builds capability to face what's yet to come. One of the advantages of the method as a whole is that it deals with local knowledge and does not subsume everything within one overall 'global' strategy, while nevertheless offering a way to communicate between contexts and disciplines.

To adequately model mathematical arguments the analyst must be able to represent the mathematical objects under discussion and the relationships between them, as well as inferences drawn about these objects and relationships as the discourse unfolds. We introduce a framework with these properties, which has been used to analyse mathematical dialogues and expository texts. The framework can recover salient elements of discourse at, and within, the sentence level, as well as the way mathematical content connects to form larger argumentative structures. We show how the framework might be used to support computational reasoning, and argue that it provides a more natural way to examine the process of proving theorems than do Lamport’s structured proofs.

This chapter develops a meta-evaluation of progress markers in Computational Creativity. We rely on an analysis of interview data with people who have applied several standard metrics. We use an existing meta-evaluation framework to distil findings in a format that will support comparison with future research on this topic.

This chapter surveys frameworks that describe social creativity. It focuses on mathematics, but includes work which heads in a more general direction: first, by examining social creativity in music, and then turning to a description of several new results that use formal, qualitative, and simulation techniques to theorise social creativity on computers. The chapter includes a pilot study examining the salience of various frameworks for the analysis of mathematical text.

In a straightforward meta-level shift of focus, we use design patterns as a medium and process for capturing insight about the process of design. We survey mainstream design genres, and draw conclusions about how they can help inform the design of intelligent systems.

The simulation of mathematical reasoning has been a driving force throughout the history of Artificial Intelligence research. However, despite significant successes in computer mathematics, computers are not widely used by mathematicians apart from their quotidian applications. An oft-cited reason for this is that current computational systems cannot do mathematics in the way that humans do. We draw on two areas in which Automated Theorem Proving (ATP) is currently unlike human mathematics: firstly in a focus on soundness, rather than understandability of proof, and secondly in social aspects. Employing techniques and tools from argumentation to build a framework for mixed-initiative collaboration, we develop three complementary arcs. In the first arc – our theoretical model – we interpret the informal logic of mathematical discovery proposed by Lakatos, a philosopher of mathematics, through the lens of dialogue game theory and in particular as a dialogue game ranging over structures of argumentation. In our second arc – our abstraction level – we develop structured arguments, from which we induce abstract argumentation systems and compute the argumentation semantics to provide labelings of the acceptability status of each argument. The output from this stage corresponds to a final, or currently accepted proof artefact, which can be viewed alongside its historical development. Finally, in the third arc – our computational model – we show how each of these formal steps is available in implementation. In an appendix, we demonstrate our approach with a formal, implemented example of real-world mathematical collaboration. We conclude the paper with reflections on our mixed-initiative collaborative approach.

Whereas formal mathematical theories are well studied, computers cannot yet adequately represent and reason about mathematical dialogues and other informal texts. To address this gap, we have developed a representation and reasoning strategy that draws on contemporary argumentation theory and classic AI techniques for representing and querying narratives and dialogues. In order to make the structures that these modelling tools produce accessible to computational reasoning, we encode representations in a higherorder nested semantic network. This system, for which we have developed a preliminary prototype in LISP, can represent both the content of what people say, and the dynamic reasoning steps that move from one step to the next. CCS Concepts • Computing methodologies → Philosophical/theoretical foundations of artificial intelligence;