As systems based on opaque Artificial Intelligence (AI) continue to flourish in diverse real-world applications, understanding these black box models has become paramount. In response, Explainable AI (XAI) has emerged as a field of research with practical and ethical benefits across various domains. This paper not only highlights the advancements in XAI and its application in real-world scenarios but also addresses the ongoing challenges within XAI, emphasizing the need for broader perspectives and collaborative efforts. We bring together experts from diverse (...) fields to identify open problems, striving to synchronize research agendas and accelerate XAI in practical applications. By fostering collaborative discussion and interdisciplinary cooperation, we aim to propel XAI forward, contributing to its continued success. Our goal is to put forward a comprehensive proposal for advancing XAI. To achieve this goal, we present a manifesto of 27 open problems categorized into nine categories. These challenges encapsulate the complexities and nuances of XAI and offer a road map for future research. For each problem, we provide promising research directions in the hope of harnessing the collective intelligence of interested stakeholders. (shrink)

We introduce and discuss a knowledge-driven distillation approach to explaining black-box models by means of two kinds of interpretable models. The first is perceptron (or threshold) connectives, which enrich knowledge representation languages such as Description Logics with linear operators that serve as a bridge between statistical learning and logical reasoning. The second is Trepan Reloaded, an ap- proach that builds post-hoc explanations of black-box classifiers in the form of decision trees enhanced by domain knowledge. Our aim is, firstly, to target (...) a model-agnostic distillation approach exemplified with these two frameworks, secondly, to study how these two frameworks interact on a theoretical level, and, thirdly, to investigate use-cases in ML and AI in a comparative manner. Specifically, we envision that user-studies will help determine human understandability of explanations generated using these two frameworks. (shrink)

Axiom weakening is a technique that allows for a fine-grained repair of inconsistent ontologies. Its main advantage is that it repairs on- tologies by making axioms less restrictive rather than by deleting them, employing the use of refinement operators. In this paper, we build on pre- viously introduced axiom weakening for ALC, and make it much more irresistible by extending its definitions to deal with SROIQ, the expressive and decidable description logic underlying OWL 2 DL. We extend the definitions of (...) refinement operator to deal with SROIQ constructs, in particular with role hierarchies, cardinality constraints and nominals, and illustrate its application. Finally, we discuss the problem of termi- nation of an iterated weakening procedure. (shrink)

We often effortlessly take the perceptual perspective of others: we represent some aspect of the environment that others currently perceive. However, taking someone's perspective can interfere with one's perceptual processing: another person's gaze can spontaneously affect our ability to detect stimuli in a scene. But it is still unclear whether our cognitive evaluation of those judgements is also affected. In this study, we investigated whether social perspective-taking can influence participants' metacognitive judgements about their perceptual responses. Participants performed a contrast detection (...) task with a task-irrelevant avatar oriented either congruently or incongruently to the stimulus location. By “blindfolding” the avatar, we tested the influence of social perspective-taking versus domain-general directional orienting. Participants had higher accuracy and perceptual sensitivity with a congruent avatar regardless of the blindfold, suggesting a directional cueing effect. However, their metacognitive efficiency was modulated only by the congruency of a seeing avatar. These results suggest that perceptual metacognitive ability can be socially enhanced by sharing perception of the same objects with others. (shrink)

We present epistemic multilateral logic, a general logical framework for reasoning involving epistemic modality. Standard bilateral systems use propositional formulae marked with signs for assertion and rejection. Epistemic multilateral logic extends standard bilateral systems with a sign for the speech act of weak assertion (Incurvati and Schlöder 2019) and an operator for epistemic modality. We prove that epistemic multilateral logic is sound and complete with respect to the modal logic S5 modulo an appropriate translation. The logical framework developed provides the (...) basis for a novel, proof-theoretic approach to the study of epistemic modality. To demonstrate the fruitfulness of the approach, we show how the framework allows us to reconcile classical logic with the contradictoriness of so-called Yalcin sentences and to distinguish between various inference patterns on the basis of the epistemic properties they preserve. (shrink)

Translation of Aristotle's Physics I-II into Portuguese, with commentaries. Tradução para o português dos livros I e II da Física de Aristóteles, com comentários.

This is an introductory handbook for some of the main themes around the notion of predication in Aristotle. It does not aim at being exhaustive, but only sketches some important lines about the subject; it contains an introductory essay, besides the translation (into Portuguese) and commentary of basic texts (such as Posterior Analytics I-22, Categories 1-5, Interpretation 1-6 etc.).

I discuss the argument Aristotle ascribes to Parmenides at Physics 186a23-32. I discuss (i) the reasons why Aristotle considers it as eristic and inconclusive and (i) the solution (lusis) Aristotle proposes against it.

What are words and how should we individuate them? There are two main answers on the philosophical market. For some, words are bundles of structural-functional features defining a unique performance profile. For others, words are non-eternal continuants individuated by their causal-historical ancestry. These conceptions offer competing views of the nature of words, and it seems natural to assume that at most one of them can capture the essence of wordhood. This paper makes a case for pluralism about wordhood: the view (...) that there is a plurality of acceptable conceptions of the nature of words, none of which is uniquely entitled to inform us as to what wordhood consists in. (shrink)

This book discusses Aristotle’s notions of essence and substance as they are developed in Metaphysics ZH. I examine Aristotle's argument at length and defends an unorthodox interpretation according to which his motivation is to provide an answer against a conflation between criteria for existential priority (delivering substances as primary beings) and criteria for explanatory priority (delivering essences as primary principles).

In Posterior Analytics 71b9 12, we find Aristotle’s definition of scientific knowledge. The definiens is taken to have only two informative parts: scientific knowledge must be knowledge of the cause and its object must be necessary. However, there is also a contrast between the definiendum and a sophistic way of knowing, which is marked by the expression “kata sumbebekos”. Not much attention has been paid to this contrast. In this paper, I discuss Aristotle’s definition paying due attention to this contrast (...) and to the way it interacts with the two conditions presented in the definiens. I claim that the “necessity” condition ammounts to explanatory appropriateness of the cause. (shrink)

Tradução preliminar em pré-print. A Tradução definitiva é a de 2009.

Constitutivism argues that the source of the categorical force of the norms of rationality and morality lies in the constitutive features of agency. A systematic failure to be guided by these norms would amount to a loss or lack of agency. Since we cannot but be agents, we cannot but be unconditionally guided by these norms. The constitutivist strategy has been challenged by David Enoch. He argues that our participation in agency is optional and thus cannot be a source of (...) categorical demands. In this paper, I defend the viability of constitutivism by showing that agency is indeed a special ‘inescapable’ enterprise. Agency has the largest jurisdiction, and it is closed under rational assessment. This inescapability does not exempt constitutivism from raising the question whether agents have reason to be agents, but this question has to be taken up within agency. If this question is answered affirmatively, then—I argue—the criteria of practical correctness are self-ratifying in a non-circular way. This is sufficient to show the viability of the constitutivist strategy. Whether agents have conclusive reasons to be agents, however, is a matter to be addressed in the terms of particular versions of constitutivism. (shrink)

My object is Aristotle's discussion of principle of non-contradiction in the first stretch of Metaphysics IV.4. My main focus rests on the connections between Aristotle's discussion of the principle and some key notions of his (explicit or implied) semantics.

I discuss what Aristotle means when he say that scientific demonstration must proceed from necessary principles. I argue that, for Aristotle, scientific demonstration should not be reduced to sound deduction with necessary premises. Scientific demonstration ultimately depends on the fully appropriate explanatory factor for a given explanandum. This explanatory factor is what makes the explanandum what it is. Consequently, this factor is also unique. When Aristotle says that demonstration must proceed from necessary principles, he means that each demonstration requires the (...) principle that is the necessary one for the fully appropriate explanation of its explanandum. This picture also provides a key to understand Aristotle's thesis that scientific explanation depends on essences: it is the essence of the attribute to be explained that should be stated as the fully appropriate explanatory factor. (shrink)

In Prior Analytics I.30, Aristotle seems too much optmistic about finding out the principles of sciences. For he seems to say that, if our empirical collection of facts in a given domain is exhaustive or sufficient, it will be easy for us to find out the explanatory principles in the domain. However, there is a distance between collecting facts and finding out the explanatory principles in a given domain. In this paper, I discuss how the key expression in the sentence (...) at 46a25 should be interpreted: “the true characteristics of things” (“τῶν ἀληθῶς ὑπαρχόντων τοῖς πράγμασιν”). I argue that, on a more accurate interpretation of the expression, Aristotle’s point would cease to look like a piece of naïve or even silly optimism. (shrink)

Affective experiences such as pains, pleasures, and emotions have affective phenomenology: they feel pleasant. This type of phenomenology has a loopy regulatory profile: it often motivates us to act a certain way, and these actions typically end up regulating our affective experiences back. For example, the pleasure you get by tasting your morning coffee motivates you to drink more of it, and this in turn results in you obtaining another pleasant gustatory experience. In this article, we argue that reflexive imperativism (...) is the only intentionalist account of affective phenomenology—probably, the only account at all—that is able to make sense of its loopy regulatory profile. (shrink)

These are commentaries to the translation into Portuguese of Nicomachean Ethics VI, found in the same volume of Dissertatio.

According to Jim Pryor’s dogmatism, when you have an experience with content p, you often have prima facie justification for believing p that doesn’t rest on your independent justification for believing any proposition. Although dogmatism has an intuitive appeal and seems to have an antisceptical bite, it has been targeted by various objections. This paper principally aims to answer the objections by Roger White according to which dogmatism is inconsistent with the Bayesian account of how evidence affects our rational credences. (...) If this were true, the rational acceptability of dogmatism would be seriously questionable. I respond that these objections don’t get off the ground because they assume that our experiences and our introspective beliefs that we have experiences have the same evidential force, whereas the dogmatist is uncommitted to this assumption. I also consider the question whether dogmatism has an antisceptical bite. I suggest that the answer turns on whether or not the Bayesian can determine the priors of hypotheses and conjectures on the grounds of their extra-empirical virtues. If the Bayesian can do so, the thesis that dogmatism has an antisceptical bite is probably false. (shrink)

Translation of Aristotle's Posterior Analytics I into Portuguese, with a few notes, experimental glossary and introduction. The translation, which was made at 2003/4, was preliminary and its publication was intended to provide a didactic tool for courses as well as a provisional resource in research seminars. It needs some revision. I am currently working (slowly...) on the revision of the translation and a new revised one will surely appear at some point.

The notion of strength has featured prominently in recent debates about abductivism in the epistemology of logic. Following Williamson and Russell, we distinguish between logical and scientific strength and discuss the limits of the characterizations they employ. We then suggest understanding logical strength in terms of interpretability strength and scientific strength as a special case of logical strength. We present applications of the resulting notions to comparisons between logics in the traditional sense and mathematical theories.

Tradução para o Português de Ethica Nicomachea VI.

Translation of Aristotle's Metaphysics IV and VI, with notes. The translation is preliminary and intended as a provisional teaching tool to be also used in seminars and discussions with peers in order to reach a more elaborated version.

I have two aims in this paper. First, I argue that, in Aristotle’s theory of the four causes, there is a basic and common feature by which all causes are causes: they all work in a triadic framework in which they explain why a given attribute holds of a given underlying thing. Secondly, I argue against a version of “compatibilism” according to which each kind of cause is complete in its own domain and does not compete with any other kind. (...) I claim that there are priority relations according to which some kinds of cause are subordinated to others, even if these relations do not hold in every cases. (shrink)

I discuss in this paper the six requirements Aristotle advances at Posterior Analytics A-2, 71b20-33, for the premisses of a scientific demonstration. I argue that the six requirements give no support for an intepretation in terms of “axiomatization”. Quite on the contrary, the six requirements can be consistently understood in a very different picture, according to which the most basic feature of a scientific demonstration is to explain a given proposition by its appropriate cause.

I discuss Aristotle's treatment of essence and definition in Metaphysics VII.4. I argue that it is coherent and perfectly in accord with its broader context. His discussion in VII.4 offers, on the one hand, minimal criteria for what counts as definition and essence for whatever kind of object, but also, on the other hand, stronger criteria for a primary sort of definition and essence—and thereby it serves the interest of book VII in pointing to the explanatory power of the essence (...) of composite substances. (shrink)

Collective volume with papers by alumni and students from the Campinas Aristotle Group.

Ontologies represent principled, formalised descriptions of agents’ conceptualisations of a domain. For a community of agents, these descriptions may differ among agents. We propose an aggregative view of the integration of ontologies based on Judgement Aggregation (JA). Agents may vote on statements of the ontologies, and we aim at constructing a collective, integrated ontology, that reflects the individual conceptualisations as much as possible. As several results in JA show, many attractive and widely used aggregation procedures are prone to return inconsistent (...) collective ontologies. We propose to solve the possible inconsistencies in the collective ontology by applying suitable weakenings of axioms that cause inconsistencies. (shrink)

We discuss a well-known puzzle about the lexicalization of logical operators in natural language, in particular connectives and quantifiers. Of the many logically possible operators, only few appear in the lexicon of natural languages: the connectives in English, for example, are conjunction _and_, disjunction _or_, and negated disjunction _nor_; the lexical quantifiers are _all, some_ and _no_. The logically possible nand (negated conjunction) and Nall (negated universal) are not expressed by lexical entries in English, nor in any natural language. Moreover, (...) the lexicalized operators are all upward or downward monotone, an observation known as the Monotonicity Universal. We propose a logical explanation of lexical gaps and of the Monotonicity Universal, based on the dynamic behaviour of connectives and quantifiers. We define update potentials for logical operators as procedures to modify the context, under the assumption that an update by \( \phi \) depends on the logical form of \( \phi \) and on the speech act performed: assertion or rejection. We conjecture that the adequacy of update potentials determines the limits of lexicalizability for logical operators in natural language. Finally, we show that on this framework the Monotonicity Universal follows from the logical properties of the updates that correspond to each operator. (shrink)

I review recent work on Phenomenal Conservatism, the position introduced by Michael Huemer according to which if it seems that P to a subject S, in the absence of defeaters S has thereby some degree of justification for believing P.

Experiences like pains, pleasures, and emotions have affective phenomenal character: they feel pleasant or unpleasant. Imperativism proposes to explain affective phenomenal character by appeal to imperative content, a kind of intentional content that directs rather than describes. We argue that imperativism is on the right track, but has been developed in the wrong way. There are two varieties of imperativism on the market: first-order and higher-order. We show that neither is successful, and offer in their place a new theory: reflexive (...) imperativism. Our proposal is that an experience P feels pleasant in virtue of being constituted by a Command with reflexive imperative content, while an experience U feels unpleasant in virtue of being constituted by a Command with reflexive imperative content : More of P!Less of U! If you need a slogan: experiences have affective phenomenal character in virtue of commanding us Get more of me! Get less of me! (shrink)

In this paper, I discuss whether there are genuinely *diachronic* constraints of practical rationality, that is, pressures on combinations of practical attitudes over time, which are not reducible to mere synchronic rational pressures. Michael Bratman has recently argued that there is at least one such diachronic rational constraint that governs the stability of intentions over time. *Pace* Bratman, I argue that there are no genuinely diachronic constraints on intentions that meet the stringent desiderata set by him. But I show that (...) there are at least two synchronic rational constraints with distinctive and important, although only indirect, diachronic dimensions. Neither of them, however, supports the practical conservatism in the face of normative underdetermination that, according to Bratman, is part and parcel of the diachronic rationality of intention stability. (shrink)

In this paper, I will discuss the various ways in which intentions can be said to be conditional, with particular attention to the internal conditions on the intentions’ content. I will first consider what it takes to carry out a conditional intention. I will then discuss how the distinctive norms of intention apply to conditional intentions and whether conditional intentions are a weaker sort of commitments than the unconditional ones. This discussion will lead to the idea of what I call (...) the ‘deep structure’ of intentions. Roughly, this is the idea that the conditional nature of our intentions is only partially made explicit in the expressions we use to communicate our intentions and in the explicit form of our thinking about and reasoning with them. Most conditions that qualify our intentions are part of a deep functional structure that can be evinced by observing the actual psychological functioning of intentions and by considering the rational requirements that they engage. I will argue that the deep structure of intentions is characteristically conditional. Genuinely unconditional intentions are only limiting instances of conditional intentions and their contribution to agency can only be understood in light of this fact. I will conclude by showing that the characteristic conditional structure of intentions is intimately related to distinctive features of human agency, especially to its unity over time. (shrink)

Evaluativism (Carruthers 2018) and reflexive imperativism (Barlassina and Hayward 2019) agree that valence—the (un)pleasantness of experiences—is a natural kind shared across all affective states. But they disagree about what valence is. For evaluativism, an experience is pleasant/unpleasant in virtue of representing its worldly object as good/bad; for reflexive imperativism, an experience is pleasant/unpleasant in virtue of commanding its subject to get more/less of itself. I argue that reflexive imperativism is superior to evaluativism according to Carruthers’s own standards. He maintains that (...) a theory of valence should account for its phenomenology and role in imagination-based decision-making. I show that it is reflexive imperativism, rather than evaluativism, that fits this explanatory bill. (shrink)

Translation of Aristotle's Parts of Animals Book I into Portuguese, with full commentaries.

ABSTRACTLinguistic evidence supports the claim that certain, weak rejections are less specific than assertions. On the basis of this evidence, it has been argued that rejected sentences cannot be premisses and conclusions in inferences. We give examples of inferences with weakly rejected sentences as premisses and conclusions. We then propose a logic of weak rejection which accounts for the relevant phenomena and is motivated by principles of coherence in dialogue. We give a semantics for which this logic is sound and (...) complete, show that it axiomatizes the modal logic KD45 and prove that it still derives classical logic on its asserted fragment. Finally, we defend previous logics of strong rejection as being about the linguistically preferred interpretations of weak rejections. (shrink)

In this paper, we develop an impure somatic theory of emotion, according to which emotions are constituted by the integration of bodily perceptions with representations of external objects, events, or states of affairs. We put forward our theory by contrasting it with Prinz's pure somatic theory, according to which emotions are entirely constituted by bodily perceptions. After illustrating Prinz's theory and discussing the evidence in its favor, we show that it is beset by serious problems—i.e., it gets the neural correlates (...) of emotion wrong, it isn't able to distinguish emotions from bodily perceptions that aren't emotions, it cannot account for emotions being directed towards particular objects, and it mischaracterizes emotion phenomenology. We argue that our theory accounts for the empirical evidence considered by Prinz and solves the problems faced by his theory. In particular, we maintain that our theory gives a unified and principled account of the relation between emotions and bodily perceptions, the intentionality of emotions, and emotion phenomenology. (shrink)

These are the commentaries (or notes) for Aristotle's Metaphysics V (Delta) 18-30. This file must be read together with the translation into Portuguese, which has been published as a different item, with a different DOI. In the Introduction, I discuss many issues about Aristotle's jargon, Aristotle's style and Aristotle's awareness of many philosophical problems that nowadays we locate within the branch Philosophy of Language.

Translation of Aristotle's Metaphysics I-III into Portuguese, with a few notes and introduction. The translation, which was made at 2007, is preliminary and its publication was intended to provide a didactic tool for courses as well as a provisional resource in research seminars. It needs some revision. I am currently working (slowly...) on the revision of the translation and a new revised one will surely appear at some point.

I discuss Aristotle's anomalous terminology in Physics A.1 (involving "universals" and "particulars") and its coherence with Aristotle's notion of scientific demonstration.

It is often argued that future-directed decisions are effective at shaping our future conduct because they give rise, at the time of action, to a decisive reason to act as originally decided. In this paper, I argue that standard accounts of decision-based reasons are unsatisfactory. For they focus either on tie-breaking scenarios or cases of self-directed distal manipulation. I argue that future-directed decisions are better understood as tools for the non-manipulative, intrapersonal division of deliberative labor over time. A future-directed decision (...) to ϕ gives rise to a defeasible exclusionary reason to ϕ. This reason is grounded on the default authority that is normally granted to one’s prior self as an “expert” deliberator. I argue that this kind of exclusionary reason is the only one that can account for the effectiveness of future-directed decisions at shaping our diachronic agency without violating our autonomy over time. (shrink)

From playing basketball to ordering at a food counter, we frequently and effortlessly coordinate our attention with others towards a common focus: we look at the ball, or point at a piece of cake. This non-verbal coordination of attention plays a fundamental role in our social lives: it ensures that we refer to the same object, develop a shared language, understand each other’s mental states, and coordinate our actions. Models of joint attention generally attribute this accomplishment to gaze coordination. But (...) are visual attentional mechanisms sufficient to achieve joint attention, in all cases? Besides cases where visual information is missing, we show how combining it with other senses can be helpful, and even necessary to certain uses of joint attention. We explain the two ways in which non-visual cues contribute to joint attention: either as enhancers, when they complement gaze and pointing gestures in order to coordinate joint attention on visible objects, or as modality pointers, when joint attention needs to be shifted away from the whole object to one of its properties, say weight or texture. This multisensory approach to joint attention has important implications for social robotics, clinical diagnostics, pedagogy and theoretical debates on the construction of a shared world. (shrink)

This chapter argues in favour of three interrelated points. First, I argue that demonstration (as expression of scientific knowledge) is fundamentally defined as knowledge of the appropriate cause for a given explanandum: to have scientific knowledge of the explanandum is to explain it through its fully appropriate cause. Secondly, I stress that Aristotle’s notion of cause has a “triadic” structure, which fundamentally depends on the predicative formulation (or “regimentation”) of the explanandum. Thirdly, I argue that what has motivated Aristotle to (...) choose the syllogism as a demonstrative tool was precisely the fact that syllogisms are apt to express causal relations in their triadic structure. Instead of complaining against Aristotle’s preference for the syllogisms as demonstrative tools, I argue that Aristotle was fully aware of the advantages of regimenting the explanandum into a predication. One of these advantages is to abandon a purely extensional standpoint and to highlight the importance of the notion of relevancy in explanation. (shrink)

I examine Aristotle’s definition of scientific knowledge in Posterior Analytics 71b 9-12 and try to understand how it relates to the sophistical way of knowing and to "kata sumbebekos knowledge". I claim that scientific knowledge of p requires knowing p by its appropriate cause, and that this appropriate cause is a universal (katholou) in the restricted sense Aristotle proposes in 73b 26-27 ff., i.e., an attribute coextensive with the subject (an extensional feature) and predicated of the subject in itself (an (...) intensional feature). Kata sumbebekos knowledge, on the other hand, can occur even when the predicate of a conclusion is coextensive with its subject and is proved by a convertible meson which is not the most appropriate from an explanatory standpoint. (shrink)

In this paper we focus on transmission and failure of transmission of warrant. We identify three individually necessary and jointly sufficient conditions for transmission of warrant, and we show that their satisfaction grounds a number of interesting epistemic phenomena that have not been sufficiently appreciated in the literature. We then scrutinise Wright’s analysis of transmission failure and improve on extant readings of it. Nonetheless, we present a Bayesian counterexample that shows that Wright’s analysis is partially incoherent with our analysis of (...) warrant transmission and prima facie defective. We conclude exploring three alternative lines of reply: developing a more satisfactory account of transmission failure, which we outline; dismissing the Bayesian counterexample by rejecting some of its assumptions; reinterpreting Wright’s analysis to make it immune to the counterexample. (shrink)

I show that Mizrahi’s argument against Phenomenal Conservatism is fallacious.

In this paper, I argue against the popular philosophical thesis---aka the ‘own action condition’---that an agent can only intend one’s own actions. I argue that the own action condition does not hold for any executive attitude, intentions included. The proper object of intentions is propositional rather than agential (‘I intend that so-and-so be the case’ rather than ‘I intend to do such-and-such’). I show that, although there are some essential de se components in intending, they do not restrict the content (...) of intentions to one’s own actions. I then discuss the special way in which one’s own actions can figure in the content of one’s intentions, which shows that the distinction between intending and acting is less stark than it appears at first. This is a conclusion that many defenders of the own action condition might find appealing but which, I argue, is better supported by rejecting the own action condition. (shrink)

Joint attention customarily refers to the coordinated focus of attention between two or more individuals on a common object or event, where it is mutually “open” to all attenders that they are so engaged. We identify two broad approaches to analyse joint attention, one in terms of cognitive notions like common knowledge and common awareness, and one according to which joint attention is fundamentally a primitive phenomenon of sensory experience. John Campbell’s relational theory is a prominent representative of the latter (...) approach, and the main focus of this paper. We argue that Campbell’s theory is problematic for a variety of reasons, through which runs a common thread: most of the problems that the theory is faced with arise from the relational view of perception that he endorses, and, more generally, they suggest that perceptual experience is not sufficient for an analysis of joint attention. (shrink)