Emergent communication enables agents to develop bespoke languages that improve communication efficiency. Despite the known importance of temporal structure in natural language, there is no existing evidence of temporal references in emergent communication. This paper addresses this gap, by exploring how agents communicate about temporal relationships. We analyse three potential factors for the emergence of temporal references: environmental, external, and architectural. Our experiments demonstrate that altering the loss function is insufficient for temporal references to emerge; rather, architectural changes are necessary. A minimal change in agent architecture, using a different batching method, allows the emergence of temporal references. This modified design is compared with the standard architecture in a temporal referential games environment, which emphasises temporal relationships. The analysis shows that over 95% of the agents with the modified batching method develop temporal references, without changes to their loss function. We consider temporal referencing necessary for future improvements to the agents’ communication efficiency, enabling future agents to use a closer to optimal coding as compared to purely compositional languages. These insights provide the basis for incorporation of temporal references into other emergent communication settings, and investigation of other aspects of language.

We propose a neuro-symbolic approach for learning causal complex event models from multi-source data, integrating causal discovery and temporal logic. Given resource constraints, we employ signal-level fusion by averaging the data from different antennas of the same WiFi receiver, followed by downsampling to reduce computational overhead. We consider a dataset of WiFi Channel State Information capturing human activities alongside video data from which we extract atomic symbolic activities such as “moving the upper arm.” The extracted symbolic information is processed through LPCMCI (Latent PCMCI). This causal discovery method extends PCMCI (Peter and Clark Momentary Conditional Independence) to handle latent dependencies across multiple time steps while mitigating false discoveries due to auto-correlations. The resulting causal structure is then translated into a temporal logic formula, which serves as a symbolic constraint in a neuro-symbolic learning pipeline. To efficiently process and learn from these structured constraints under resource limitations, we leverage Spiking Neural Networks, which offer energy-efficient computation while preserving temporal dynamics.

Autonomous and semi-autonomous systems are using deep learning models to improve decision-making. However, deep classifiers can be overly confident in their incorrect predictions, a major issue especially in safety-critical domains. The present study introduces three foundational desiderata for developing real-world risk-aware classification systems. Expanding upon the previously proposed Evidential Deep Learning ( EDL ), we demonstrate the unity between these principles and EDL ’s operational attributes. We then augment EDL empowering autonomous agents to exercise discretion during structured decision-making when uncertainty and risks are inherent. We rigorously examine empirical scenarios to substantiate these theoretical innovations. In contrast to existing risk-aware classifiers, our proposed methodologies consistently exhibit superior performance, underscoring their transformative potential in risk-conscious classification strategies. • Evidential deep learning uses Dirichlet distributions to represent the predictive uncertainty of neural classifiers. • Pignistic probabilities can be used to model rational decision-making under uncertainty. • Risk awareness can be integrated into evidential classifiers using pignistic Dirichlet priors.

We investigate the computational problem of determining the set of acceptable arguments in abstract argumentation wrt. credulous and skeptical reasoning under grounded, complete, stable, and preferred semantics. In particular, we investigate the computational complexity of that problem and its verification variant, and develop several algorithms for all problem variants, including two baseline approaches based on iterative acceptability queries and extension enumeration, and some optimised versions. We experimentally compare the runtime performance of these algorithms: our results show that our newly optimised algorithms significantly outperform the baseline algorithms in most cases.

Teams of embodied AI-enabled agents are critical for applications in extreme and highly dynamic environments. Developing robust controllers for such agents requires a deep understanding of the challenges encountered when attempting to coordinate and synchronize their individual perception-cognition-communication-action (PCCA) loops for team-wide mission objectives. We introduce a framework to explore the coordination of the PCCA loops across multiple agents in a new simulated physical environment designed to explore collaboration in each PCCA stage. This environment tasks teams of agents with the correct disposal of dangerous objects in an area and forces careful coordination of sensing, communication, movement, and manipulation actions by providing spatially-bounded communication, incorporating situations that require concerted effort by groups of agents, and introducing uncertainty into agents’ sensing capabilities. We provide a set of heuristic controllers, an offline oracle model, and an initial exploration of a Reward Machine-based controller that learns its policies from training. Together these approaches serve to provide insights into the complexity of the multi-agent PCCA loop coordination problem. The multiagent PCCA simulation environment, which supports AI and human-controlled agents, and the code for various agent controllers are available at https://github.com/nesl/AI-Collab.

Wi-Fi devices, akin to passive radars, can discern human activities within indoor settings due to the human body’s interaction with electromagnetic signals. Current Wi-Fi sensing applications predominantly employ data-driven learning techniques to associate the fluctuations in the physical properties of the communication channel with the human activity causing them. However, these techniques often lack the desired flexibility and transparency. This paper introduces DeepProbHAR, a neuro-symbolic architecture for Wi-Fi sensing, providing initial evidence that Wi-Fi signals can differentiate between simple movements, such as leg or arm movements, which are integral to human activities like running or walking. The neuro-symbolic approach affords gathering such evidence without needing additional specialised data collection or labelling. The training of DeepProbHAR is facilitated by declarative domain knowledge obtained from a camera feed and by fusing signals from various antennas of the Wi-Fi receivers. DeepProbHAR achieves results comparable to the state-of-the-art in human activity recognition. Moreover, as a by-product of the learning process, DeepProbHAR generates specialised classifiers for simple movements that match the accuracy of models trained on finely labelled datasets, which would be particularly costly.

We propose R-latplan, a system that learns reliable symbolic (PDDL) representations of an agent's actions from noisy visual observations, and without explicit human expert knowledge. R-latplan builds upon Latplan, a model that also learns PDDL representations of actions from images. However, Latplan does not ensure that the learned actions correspond to the actual agent's actions and does not map the learned actions to the agent's actual capabilities. There is, therefore, a substantial risk that a learned action could be impossible due to the domain's physics or the agent's capability. R-latplan receives input pairs of (noisy) images representing the states before/after the agent's action is performed in the domain. Contrary to Latplan, it uses a transition identifier function that identifies the class of a transition and associates it as an action label for the pair of images. Our experimental analysis shows that: (1) R-latplan produces reliable PDDL models in which each action can be directly connected to an agent's high level actuators and lead to visually correct states (the agent does not hallucinate), (2) R-latplan generated PDDL models lead to a domain-independent planner to find optimal plans on each benchmarks considered, (3) R-latplan is robust against mislabeled transitions, i.e. if errors are introduced in the transition identifier function.

This paper presents PROB-IRM, an approach that learns robust reward machines (RMs) for reinforcement learning (RL) agents from noisy execution traces. The key aspect of RM-driven RL is the exploitation of a finite-state ma- chine that decomposes the agent’s task into different sub- tasks. PROB-IRM uses a state-of-the-art inductive logic pro- gramming framework robust to noisy examples to learn RMs from noisy traces using the Bayesian posterior degree of be- liefs, thus ensuring robustness against inconsistencies. Piv- otal for the results is the interleaving between RM learning and policy learning: a new RM is learned whenever the RL agent generates a trace that is believed not to be accepted by the current RM. To speed up the training of the RL agent, PROB-IRM employs a probabilistic formulation of reward shaping that uses the posterior Bayesian beliefs derived from the traces. Our experimental analysis shows that PROB-IRM can learn (potentially imperfect) RMs from noisy traces and exploit them to train an RL agent to solve its tasks success- fully. Despite the complexity of learning the RM from noisy traces, agents trained with PROB-IRM perform comparably to agents provided with handcrafted RMs.

Effective communication requires the ability to refer to specific parts of an observation in relation to others. While emergent communication literature shows success in developing various language properties, no research has shown the emergence of such positional references. This paper demonstrates how agents can communicate about spatial relationships within their observations. The results indicate that agents can develop a language capable of expressing the relationships between parts of their observation, achieving over 90% accuracy when trained in a referential game which requires such communication. Using a collocation measure, we demonstrate how the agents create such references. This analysis suggests that agents use a mixture of non-compositional and compositional messages to convey spatial relationships. We also show that the emergent language is interpretable by humans. The translation accuracy is tested by communicating with the receiver agent, where the receiver achieves over 78% accuracy using parts of this lexicon, confirming that the interpretation of the emergent language was successful.

We present a conceptualization providing an original domain-independent perspective on two crucial properties in reasoning: consistency and reinstatement. They emerge as a pair of dual characteristics, representing complementary requirements on the outcomes of reasoning processes. Central to our formalization are two underlying parametric relations: incompatibility and reinstatement violation. Different instances of these relations give rise to a spectrum of consistency and reinstatement scenarios. As a demonstration of versatility and expressive power of our approach we provide a characterization of various abstract argumentation semantics which are expressed as combinations of distinct consistency and reinstatement constraints. Moreover, we conduct an investigation into preserving these essential properties across different reasoning stages. Specifically, we delve into scenarios where a labelling is derived from other labellings through a synthesis function, using the synthesis of argument justification as an illustrative instance. We achieve a general characterization of consistency preservation synthesis functions, while we unveil an impossibility result concerning reinstatement preservation, leading us to explore an alternative notion to ensure feasibility. Our exploration reveals a weakness in the traditional definition of argument justification, for which we propose a refined version overcoming this limitation.

Sound-squatting is a squatting technique that exploits similarities in word pronunciation to trick users into accessing malicious resources. It is an understudied threat that has gained traction with the popularity of smart speakers and audio-only content, such as podcasts. The picture gets even more complex when multiple languages are involved. We here introduce X-squatter, a multi- and cross-language AI-based system that relies on a Transformer Neural Network for generating high-quality sound-squatting candidates. We illustrate the use of X-squatter by searching for domain name squatting abuse across hundreds of millions of issued TLS certificates, alongside other squatting types. Key findings unveil that approximately 15% of generated sound-squatting candidates have associated TLS certificates, well above the prevalence of other squatting types (7%). Furthermore, we employ X-squatter to assess the potential for abuse in PyPI packages, revealing the existence of hundreds of candidates within a 3-year package history. Notably, our results suggest that the current platform checks cannot handle sound-squatting attacks, calling for better countermeasures. We believe X-squatter uncovers the usage of multilingual sound-squatting phenomena on the Internet and it is a crucial asset for proactive protection against the threat.

Wi-Fi sensing applications have achieved remarkable results over the last decade, offering accurate device-free localization and gesture recognition capabilities. Indeed, Wi-Fi sensing has quickly become a critical field of research for future communication systems under the paradigm known as joint communication and sensing. However, device-free wireless sensing can also be exploited for malign purposes against unaware victims, and the omnipresence of Wi-Fi transceivers poses a significant threat to people’s privacy. Therefore, it is essential to develop functional solutions that can effectively thwart wireless sensing. All the current attempts to hinder illegitimate wireless sensing rely on specialized hardware deployed in the environment, but their cost and complexity can undermine widespread deployment. In this paper, we explore the possibility of using native capabilities of Wi-Fi systems, namely beamforming, to thwart wireless sensing. To this end, we propose for the first time a solution that enables complete control over the beamforming in commercial Wi-Fi devices. On top of that, we build BeamDancer, which randomizes beamforming vectors to inhibit channel fingerprinting. We empirically demonstrate the effectiveness of the proposed solution against three different wireless sensing techniques, both data-driven and model-based, while preserving almost entirely the legitimate Wi-Fi traffic at the same time.

Wi-Fi devices can effectively be used as passive radar systems that sense what happens in the surroundings and can even discern human activity. We propose, for the first time, a principled architecture which employs Variational Auto-Encoders for estimating a latent distribution responsible for generating the data, and Evidential Deep Learning for its ability to sense out-of-distribution activities. We verify that the fused data processed by different antennas of the same Wi-Fi receiver results in increased accuracy of human activity recognition compared with the most recent benchmarks, while still being informative when facing out-of-distribution samples and enabling semantic interpretation of latent variables in terms of physical phenomena. The results of this paper are a first contribution toward the ultimate goal of providing a flexible, semantic characterisation of black-swan events, i.e., events for which we have limited to no training data.

Detecting complex events from subsymbolic data streams (such as images, audio recordings or videos) is a challenging problem, as traditional symbolic approaches cannot be used to process subsymbolic data, and neural-only approaches usually require larger amounts of training data than available. In this paper, we present DeepProbCEP, a Complex Event Processing (CEP) approach designed with four objectives: (i) allowing the use of subsymbolic data as an input, (ii) retaining flexibility and modularity in the definition of complex event rules, (iii) limiting the cost of obtaining training data and (iv) being robust against adversarial conditions. DeepProbCEP archives this by using a neuro-symbolic approach, which combines the neural and symbolic approaches to allow training with sparse data. This is made possible through the injection of human knowledge. In this paper, we demonstrate that DeepProbCEP outperforms other state-of-the-art approaches when training using sparse data. We also show that DeepProbCEP is robust in different adversarial settings. Finally, DeepProbCEP’s flexibility is demonstrated by showing it can be used to process both images and audio as input.

We propose a generic notion of consistency in an abstract labelling setting, based on two relations: one of intolerance between the labelled elements and one of incompatibility between the labels assigned to them, thus allowing a spectrum of consistency requirements depending on the actual choice of these relations. As a first application to formal argumentation, we show that traditional Dung’s semantics can be put in correspondence with different consistency requirements in this context. We consider then the issue of consistency preservation when a labelling is obtained as a synthesis of a set of labellings, as is the case for the traditional notion of argument justification. In this context we provide a general characterization of consistency-preserving synthesis functions and analyze the case of argument justification in this respect.

When collaborating with an artificial intelligence (AI) system, we need to assess when to trust its recommendations. Suppose we mistakenly trust it in regions where it is likely to err. In that case, catastrophic failures may occur, hence the need for Bayesian approaches for reasoning and learning to determine the confidence (or epistemic uncertainty) in the probabilities of the queried outcome. Pure Bayesian methods, however, suffer from high computational costs. To overcome them, we revert to efficient and effective approximations. In this paper, we focus on techniques that take the name of evidential reasoning and learning from the process of Bayesian update of given hypotheses based on additional evidence. This paper provides the reader with a gentle introduction to the area of investigation, the up-to-date research outcomes, and the open questions still left unanswered.

We address the problem of deciding skeptical acceptance wrt. preferred semantics of an argument in abstract argumentation frameworks, i.e., the problem of deciding whether an argument is contained in all maximally admissible sets, a.k.a. preferred extensions. State-of-the-art algorithms solve this problem with iterative calls to an external SAT-solver to determine preferred extensions. We provide a new characterisation of skeptical acceptance wrt. preferred semantics that does not involve the notion of a preferred extension. We then develop a new algorithm that also relies on iterative calls to an external SAT-solver but avoids the costly part of maximising admissible sets. We present the results of an experimental evaluation that shows that this new approach significantly outperforms the state of the art. We also apply similar ideas to develop a new algorithm for computing the ideal extension.

Deep neural networks are often ignorant about what they do not know and overconfident when they make uninformed predictions. Some recent approaches quantify classification uncertainty directly by training the model to output high uncertainty for the data samples close to class boundaries or from the outside of the training distribution. These approaches use an auxiliary data set during training to represent out-of-distribution samples. However, selection or creation of such an auxiliary data set is non-trivial, especially for high dimensional data such as images. In this work we develop a novel neural network model that is able to express both aleatoric and epistemic uncertainty to distinguish decision boundary and out-of-distribution regions of the feature space. To this end, variational autoencoders and generative adversarial networks are incorporated to automatically generate out-of-distribution exemplars for training. Through extensive analysis, we demonstrate that the proposed approach provides better estimates of uncertainty for in- and out-of-distribution samples, and adversarial examples on well-known data sets against state-of-the-art approaches including recent Bayesian approaches for neural networks and anomaly detection methods.

We investigate the computational problem of determining the set of acceptable arguments in abstract argumentation wrt. credulous and skeptical reasoning under grounded, complete, stable, and preferred semantics. In particular, we investigate the computational complexity of that problem and its verification variant, and develop four SAT-based algorithms for the case of credulous reasoning under complete semantics, two baseline approaches based on iterative acceptability queries and extension enumeration and two optimised algorithms.

Efficient second-order probabilistic inference in uncertain Bayesian networks was recently introduced. However, such second -order inference methods presume training over complete training data. While the expectation-maximization framework is well-established for learning Bayesian network parameters for incomplete training data, the framework does not determine the covariance of the parameters. This paper introduces two methods to compute the covariances for the parameters of Bayesian networks or Markov random fields due to incomplete data for two-node networks. The first method computes the covariances directly from the posterior distribution of parameters, and the second method more efficiently estimates the covariances from the Fisher information matrix. Finally, the implications and effectiveness of these covariances is theoretically and empirically evaluated.

Despite the remarkable success in a broad set of sensing applications, state-of-the-art deep learning techniques struggle with complex reasoning tasks across a distributed set of sensors. Unlike recognizing transient complex activities (e.g., human activities such as walking or running) from a single sensor, detecting more complex events with larger spatial and temporal dependencies across multiple sensors is extremely difficult, e.g., utilizing a hospital's sensor network to detect whether a nurse is following a sanitary protocol as they traverse from patient to patient. Training a more complicated model requires a larger amount of data-which is unrealistic considering complex events rarely happen in nature. Moreover, neural networks struggle with reasoning about serial, aperiodic events separated by large quantities in the spatial-temporal dimensions.

We enable aProbLog—a probabilistic logical programming approach—to reason in presence of uncertain probabilities represented as Beta-distributed random variables. We achieve the same performance of state-of-the-art algorithms for highly specified and engineered domains, while simultaneously we maintain the flexibility offered by aProbLog in handling complex relational domains. Our motivation is that faithfully capturing the distribution of probabilities is necessary to compute an expected utility for effective decision making under uncertainty: unfortunately, these probability distributions can be highly uncertain due to sparse data. To understand and accurately manipulate such probability distributions we need a well-defined theoretical framework that is provided by the Beta distribution, which specifies a distribution of probabilities representing all the possible values of a probability when the exact value is unknown.

Deep learning models typically make inferences over transient features of the latent space, i.e., they learn data representations to make decisions based on the current state of the inputs over short periods of time. Such models would struggle with state-based events, or complex events, that are composed of simple events with complex spatial and temporal dependencies. In this paper, we propose DeepCEP, a framework that integrates the concepts of deep learning models with complex event processing engines to make inferences across distributed, multimodal information streams with complex spatial and temporal dependencies. DeepCEP utilizes deep learning to detect primitive events. A user can define a complex event to be detected as a particular sequence or pattern of primitive events as well as any other logical predicates that constrain the definition of such an event. The integration of human logic not only increases robustness and interpretability, but also greatly reduces the amount of training data required. Further, we demonstrate how the uncertainty of a model can be propagated throughout the complex event detection pipeline. Finally, we enumerate the future directions of research enabled by DeepCEP. In particular, we detail how an end-to-end training model for complex event processing with deep learning may be realized.

This paper briefly describes the solver ASPrMin, which enumerates preferred extensions and scored first in the Extension Enumeration problem—the only one implemented—of the Preferred Semantics Track of the Second International Competition on Computational Models of Argumentation, ICCMA17.

We introduce CISpaces.org, a tool to support situational understanding in intelligence analysis that complements but not replaces human expertise. The system combines natural language processing, argumentation-based reasoning, and natural language generation to produce intelligence reports from social media data, and to record the process of forming hypotheses from relationships among information. In this paper, we show how CISpaces.org meets the desirable requirements elicited from senior professionals, and demonstrate its usage and capabilities to support analysts in delivering effective and tailored intelligence to decision makers.

This paper briefly describes AIF-EL, an OWL2-EL compliant ontology for the Argument Interchange Format.

We propose a new graded semantics for abstract argumentation frameworks that is based on the constellations approach to probabilistic argumentation. Given an abstract argumentation framework, our approach assigns uniform probability to all arguments and then ranks arguments according to the probability of acceptance wrt. some classical semantics. Albeit relying on a simple idea this approach (1) is based on the solid theoretical foundations of probability theory, and (2) complies with many rationality postulates proposed for graded semantics. We also investigate an application of our approach for inconsistency measurement in argumentation frameworks and show that the measure induced by the probabilistic graded semantics also complies with the basic rationality postulates from that area.

In this paper we provide a critical analysis with metrics that will inform guidelines for designing distributed systems for Collective Situational Understanding (CSU). CSU requires both collective insight-i.e., accurate and deep understanding of a situation derived from uncertain and often sparse data and collective foresight-i.e., the ability to predict what will happen in the future. When it comes to complex scenarios, the need for a distributed CSU naturally emerges, as a single monolithic approach not only is unfeasible: it is also undesirable. We therefore propose a principled, critical analysis of AI techniques that can support specific tasks for CSU to derive guidelines for designing distributed systems for CSU.

In this paper we propose a computational methodology for assessing the impact of trust associated to sources of information in scientific enquiry activities building upon recent proposals of an ontology for situational understanding and results in computational argumentation. Often trust in the source of information serves as a proxy for evaluating the quality of the information itself, especially in the cases of information overhead. We show how our computational methodology, composed of an ontology for representing uncertain information and sources, as well as an argumentative process of conjecture and refutation, support human analysts in scientific enquiry, as well as highlighting issues that demand further investigation.

We demonstrate CISpaces.org, a tool to support situational understanding in intelligence analysis that complements but not replaces human expertise, for the first time applied to a judicial context. The system combines argumentation-based reasoning and natural language generation to support the creation of analysis and summary reports, and to record the process of forming hypotheses from relationships among information.

In this paper we describe AFBenchGen2, which allows to randomised argumentation frameworks for testing purposes with a large variety of structures.

In this paper we investigate the impact of automated configuration techniques on the ArgSemSAT solver—runner-up of the ICCMA 2015—for solving the enumeration of preferred extensions. Moreover, we introduce a fully automated method for varying how argumentation frameworks are represented in the input file, and evaluate how the joint configuration of frameworks and ArgSemSAT parameters can have a remarkable impact on performance. Our findings suggest that automated configuration techniques lead to improved performances in argumentation solvers, an important message for participants to the forthcoming competition.

We evaluate the state of the art of solvers for hard argumentation problems—the enumeration of preferred and stable extensions—to envisage future trends based on evidence collected as part of an extensive empirical evaluation. In the last international competition on computational models of argumentation a general impression was that reduction-based systems (either SAT-based or ASP-based) are the most efficient.

jArgSemSAT is a Java re-implementation of ArgSemSAT—a SAT-based solver for abstract argumentation problems—that can be easily integrated in existing argumentation systems (1) as an off-the-shelf, standalone, library; (2) as a Tweety compatible library; and (3) as a fast and robust web service freely available on the Web. Despite being written in Java, jArgSemSAT is very efficient.

Optimization—minimization or maximization—in the lattice of subsets is a frequent operation in Artificial Intelligence tasks. Examples are subset-minimal model-based diagnosis, nonmonotonic reasoning by means of circumscription, or preferred extensions in abstract argumentation. Finding the optimum among many admissible solutions is often harder than finding admissible solutions with respect to both computational complexity and methodology. This paper addresses the former issue by means of an effective method for finding subset-optimal solutions. It is based on the relationship between cardinality-optimal and subset-optimal solutions, and the fact that many logic-based declarative programming systems provide constructs for finding cardinality-optimal solutions, for example maximum satisfiability (MaxSAT) or weak constraints in Answer Set Programming (ASP). Clearly each cardinality-optimal solution is also a subset-optimal one, and if the language also allows for the addition of particular restricting constructs (both MaxSAT and ASP do) then all subset-optimal solutions can be found by an iterative computation of cardinality-optimal solutions. As a showcase, the computation of preferred extensions of abstract argumentation frameworks using the proposed method is studied.

Abstract argumentation framework (AF) is a unifying framework able to encompass a variety of nonmonotonic reasoning approaches, logic programming and computational argumentation. Yet, efficient approaches for most of the decision and enumeration problems associated to AFs are missing, thus limiting the efficacy of argumentation-based approaches in real domains. In this paper, we present an algorithm for enumerating the preferred extensions of abstract argumentation frameworks which exploits parallel computation. To this purpose, the SCC-recursive semantics definition schema is adopted, where extensions are defined at the level of specific sub-frameworks. The algorithm shows significant performance improvements in large frameworks, in terms of number of solutions found and speedup.

Enumerating semantics extensions in abstract argumentation is generally an intractable problem. For preferred semantics four algorithms have been recently proposed, AspartixM, NAD-Alg, PrefSAT and SCC-P, with significant runtime variations. This work is a first comprehensive exploration of the graph features and of their impact on the execution time of state-of-the-art preferred extensions enumeration algorithms. Following other areas of AI, we exploit empirical performance models, predictive models that relate instance features and algorithms performance. The result is an approach able to select the “best” algorithm for any Dung's argumentation framework with an accuracy, on the average, of the 80%. Moreover, we show that an algorithm selection approach based on classification can select the fastest algorithm in about the double of the number of cases where the most efficient algorithm outperforms the other ones (SCC-P), and about three times the number of cases of the second most efficient algorithm (PrefSAT).

In this paper we describe the system ArgSemSAT which includes algorithms which we proved to overcome current state-of-the-art performances in enumerating preferred extensions.

In this paper we describe the AFBenchGen system, which allows to automatically generate randomised argumentation frameworks for testing purposes.

We introduce probo, a general benchmark framework for comparing abstract argumentation solvers. probo is intended to act as the core of an argumentation competition intended to run in 2015.

It has been claimed that computational models of argumentation provide support for complex decision making activities in part due to the close alignment between their semantics and human intuition. In this paper we assess this claim by means of an experiment: people's evaluation of formal arguments — presented in plain English — is compared to the conclusions obtained from argumentation semantics. Our results show a correspondence between the acceptability of arguments by human subjects and the justification status prescribed by the formal theory in the majority of the cases. However, post-hoc analyses show that there are some significant deviations, which appear to arise from implicit knowledge regarding the domains in which evaluation took place. We argue that in order to create argumentation systems, designers must take implicit domain specific knowledge into account.

Semantics extensions are the outcome of the argumentation reasoning process: enumerating them is generally an intractable problem. For preferred semantics two efficient algorithms have been recently proposed, PrefSAT and SCC-P, with significant runtime variations. This preliminary work aims at investigating the reasons (argumentation framework features) for such variations. Remarkably, we observed that few features have a strong impact, and those exploited by the most performing algorithm are not the most relevant.

This paper introduces Input/Output Argumentation Frameworks, a novel approach to characterize the behavior of an argumentation framework as a sort of black box exposing a well-defined external interface. As a starting point, we define the novel notion of semantics decomposability and analyze complete, stable, grounded and preferred semantics in this respect. Then we show as a main result that, under grounded, complete, stable and credulous preferred semantics, Input/Output Argumentation Frameworks with the same behavior can be interchanged without affecting the result of semantics evaluation of other arguments interacting with them.

This extended research abstract describes an argumentation-based approach to modelling articulated decision making contexts. The approach encompasses a variety of argument and attack schemes aimed at representing basic knowledge and reasoning patterns for decision support.