The question “what is an interpretation?” is often intertwined with the perhaps even harder question “what is a scientific theory?”. Given this proximity, we try to clarify the first question to acquire some ground for the latter. The quarrel between the syntactic and semantic conceptions of scientific theories occupied a large part of the scenario of the philosophy of science in the 20th century. For many authors, one of the two currents needed to be victorious. We endorse that such debate, (...) at least in the terms commonly expressed, can be misleading. We argue that the traditional notion of “interpretation” within the syntax/semantic debate is not the same as that of the debate concerning the interpretation of quantum mechanics. As much as the term is the same, the term “interpretation” as employed in quantum mechanics has its meaning beyond (pure) logic. Our main focus here lies on the formal aspects of the solutions to the measurement problem. There are many versions of quantum theory, many of them incompatible with each other. In order to encompass a wider variety of approaches to quantum theory, we propose a different one with an emphasis on pure formalism. This perspective has the intent of elucidating the role of each so-called “interpretation” of quantum mechanics, as well as the precise origin of the need to interpret it. (shrink)

This book shows how research in linguistic pragmatics, philosophy of language, and rhetoric can be connected through argumentation to analyze a recognizably common strategy used in political and everyday conversation, namely the distortion of another’s words in an argumentative exchange. Straw man argumentation refers to the modification of a position by misquoting, misreporting or wrenching the original speaker’s statements from their context in order to attack them more easily or more effectively. Through 63 examples taken from different contexts (including political (...) and forensic discourses and dialogs) and 20 legal cases, the book analyzes the explicit and implicit types of straw man, shows how to assess the correctness of a quote or a report, and illustrates the arguments that can be used for supporting an interpretation and defending against a distortion. The tools of argumentation theory, a discipline aimed at investigating the uses of arguments by combining insights from pragmatics, logic, and communication, are applied to provide an original account of interpretation and reporting, and to describe and illustrate tactics and procedures that can be used and implemented for practical purposes.. This book will appeal to scholars in the fields of political communication, communication in general, argumentation theory, rhetoric and pragmatics, as well as to people working in public speech, speech writing, and discourse analysis. (shrink)

Mechanistic interpretability is the program of explaining what AI systems are doing in terms of their internal mechanisms. I analyze some aspects of the program, along with setting out some concrete challenges and assessing progress to date. I argue for the importance of propositional interpretability, which involves interpreting a system’s mechanisms and behav- ior in terms of propositional attitudes: attitudes (such as belief, desire, or subjective probabil- ity) to propositions (e.g. the proposition that it is hot outside). Propositional attitudes are (...) the central way that we interpret and explain human beings and they are likely to be central in AI too. A central challenge is what I call thought logging: creating systems that log all of the rel- evant propositional attitudes in an AI system over time. I examine currently popular methods of interpretability (such as probing, sparse auto-encoders, and chain of thought methods) as well as philosophical methods of interpretation (including those grounded in psychoseman- tics) to assess their strengths and weaknesses as methods of propositional interpretability. (shrink)

The problem of establishing the best interpretation of a speech act is of fundamental importance in argumentation and communication in general. A party in a dialogue can interpret another’s or his own speech acts in the most convenient ways to achieve his dialogical goals. In defamation law this phenomenon becomes particularly important, as the dialogical effects of a communicative move may result in legal consequences. The purpose of this paper is to combine the instruments provided by argumentation theory with the (...) advances in pragmatics in order to propose an argumentative approach to meaning reconstruction. This theoretical proposal will be applied to and tested against defamation cases at common law. Interpretation is represented as based on a hierarchy of interpretative presumptions. On this view, the development of the logical form of an utterance is regarded as the result of an abductive pattern of reasoning in which various types of presumptions are confronted and the weakest ones are excluded. Conflicts of interpretations and equivocation become essentially interwoven with the dialectical problem of fulfilling the burden of defeating a presumption. The interpreter has a burden of explaining why a given presumption is subject to default, assuming that the speaker is reasonable and acting based on a set of shared expectations. (shrink)

In a recent reply to our article, “What is Interpretability?,” Prasetya argues against our position that artificial neural networks are explainable. It is claimed that our indefeasibility thesis—that adding complexity to an explanation of a phenomenon does not make the phenomenon any less explainable—is false. More precisely, Prasetya argues that unificationist explanations are defeasible to increasing complexity, and thus, we may not be able to provide such explanations of highly complex AI models. The reply highlights an important lacuna in our (...) original paper, the omission of the unificationist account of explanation, and affords us the opportunity to respond. Here, we argue that artificial neural networks are explainable in a way that should satisfy unificationists and that interpretability methods present ways in which ML theories can achieve unification. (shrink)

According to the Principle of Charity, we ought to interpret each other charitably. That is, we ought to adopt the interpretation that shows the interpreted person in the best light. The Principle of Charity is motivated by appealing to a harm asymmetry: it is worse (the thought goes) to mistakenly criticize someone than to fail to rightfully criticize them. This chapter argues that in oppressive contexts, charity is not enough. First, the Principle of Charity is myopic. Charitable interpretation only considers (...) harm to the person being interpreted and ignores third party harms. Second, under conditions of oppression, our conceptual resources and evidential standards will be systematically biased against marginalized perspectives. So charitable interpretations will overlook harm to marginalized persons. Finally, the chapter give a diagnosis of the Principle of Charity: It misunderstands the interpersonal interpretive aim. The interpersonal interpretive aim is to interpret one another in a way that accurately captures the normative features that are crucial to our interpersonal relationships. What we need is not a Principle of Charity, but an Aim of Justice. The chapter’s conclusion explains what an Aim of Justice would require of us, notably, empathetic engagement and intellectual humility. (shrink)

The interpretive-sensory access theory of self-knowledge claims that we come to know our own minds by turning our capacities for knowing other minds onto ourselves. Peter Carruthers argues that two of the theory’s advantages are empirical adequacy and scientific fruitfulness: it leaves few of the old discoveries unexplained and makes new predictions that provide a framework for new discoveries. A decade has now passed since the theory’s introduction. I review the most important developments during this time period regarding the two (...) criteria: whether the theory’s six main predictions were supported, and whether the theory’s predictions contributed to new empirical studies. I argue that the interpretive-sensory access theory of self-knowledge remains empirically adequate and scientifically fruitful. (shrink)

This paper aims at showing that the generative-semantic framework is not essential to the proposal in H.J. Verkuyl On the Compositional Nature of the Aspects Reidel:Dordrecht 1972. Compositionality can be shown to be neutral as to the then-difference between generative-semantic and the interpretive-semantic branch of transformational grammar.

In a beautiful recent essay, the philosopher Walter Sinnott-Armstrong explains the reasons for his departure from evangelical Christianity, the religious culture in which he was brought up. Sinnot-Armstrong contrasts the interpretive methods used by good philosophers and fundamentalist believers: Good philosophers face objections and uncertainties. They follow where arguments lead, even when their conclusions are surprising and disturbing. Intellectual honesty is also required of scholars who interpret philosophical texts. If I had distorted Kant’s view to make him reach a conclusion (...) that I preferred, then my philosophy professor would have failed me. The contrast with religious reasoning is stark. My Christian friends seemed happy to hide serious problems in the Bible and in their arguments. They preferred comfort to intellectual honesty. I couldn’t. To what extent can we, historians of philosophy, claim the virtue of intellectual honesty? Speaking frankly, I do not find the practice criticized by Sinnot-Armstrong’s philosophy professor rare or unusual at all. We very frequently distort the views of past philosophers in order to reach the conclusions we prefer. We just call it “Charitable Interpretation.” In this essay, I discuss and criticize the logic behind so-called charitable interpretations in the history of philosophy. This phenomenon is ubiquitous and is not at all restricted to a particular philosophical strand or ideology. Analytic philosophers and post-modernists, Marxists, liberals, secularists, and fundamentalists, we all engage in the very same domestication project. Even more disturbing than the sheer ideological pervasiveness of this phenomenon is the fact that, on many occasions, superb philosophers and historians take part in this fairly childish endeavor. In the first part of this essay, I discuss the general logic of charitable interpretations in the history of philosophy, mostly by addressing discussions in metaphysics and epistemology. In the second part, I focus on the somewhat less noticed use of charitable interpretations in the study of political philosophy, and point out the quintessential role ideology plays in these discussions. In both parts, I concentrate mostly on the interpretation of Spinoza’s thought. I do so not because I have special fondness for Spinoza (“guilty as charged,” I admit), but because Spinoza is such a beast (and may I add, an enchanting beast) and attracts a disproportionate share of the domestication efforts from historians and philosophers of all creeds and persuasions. In the third and final part of the paper, I will begin to outline an alternative methodology, which suggests that past philosophers can be most relevant to our current philosophical discussion, to the extent that they provide us with well-motivated challenges to our common-sense beliefs. Such challenges have the invaluable virtue of being able to undermine our most fundamental and secure beliefs, and force us to engage with the most fundamental questions. What more can we expect from good philosophy? (shrink)

Statutory interpretation involves the reconstruction of the meaning of a legal statement when it cannot be considered as accepted or granted. This phenomenon needs to be considered not only from the legal and linguistic perspective, but also from the argumentative one - which focuses on the strategies for defending a controversial or doubtful viewpoint. This book draws upon linguistics, legal theory, computing, and dialectics to present an argumentation-based approach to statutory interpretation. By translating and summarizing the existing legal interpretative canons (...) into eleven patterns of natural arguments - called argumentation schemes - the authors offer a system of argumentation strategies for developing, defending, assessing, and attacking an interpretation. Illustrated through major cases from both common and civil law, this methodology is summarized in diagrams and maps for application to computer sciences. These visuals help make the structures, strategies, and vulnerabilities of legal reasoning accessible to both legal professionals and laypeople. (shrink)

This paper takes issue with an influential interpretationist argument for physicalism about intentionality based on the possibility of radical interpretation. The interpretationist defends the physicalist thesis that the intentional truths supervene on the physical truths by arguing that it is possible for a radical interpreter, who knows all of the physical truths, to work out the intentional truths about what an arbitrary agent believes, desires, and means without recourse to any further empirical information. One of the most compelling arguments for (...) the possibility of radical interpretation, associated most closely with David Lewis and Donald Davidson, gives a central role to decision theoretic representation theorems, which demonstrate that if an agent’s preferences satisfy certain constraints, it is possible to deduce probability and utility functions that represent her beliefs and desires. We argue that an interpretationist who wants to rely on existing representation theorems in defence of the possibility of radical interpretation faces a trilemma, each horn of which is incompatible with the possibility of radical interpretation. (shrink)

Davidson has claimed that to conclude that reference is inscrutable, one must assume that "If some theory of truth... is satisfactory in the light of all relevant evidence... then any theory that is generated from the first theory by a permutation will also be satisfactory in the light of all relevant evidence." However, given that theories of truth are not directly read off the world, but rather serve as parts of larger theories of behavior, this assumption is far from self-evident. (...) A proper understanding of the role truth theories play in theories of interpretation makes the inscrutability of reference much less wide-spread than Davidson suggests, and, as a result, the radical interpretation methodology is much less likely to saddle its defenders with counterintuitive cases of indeterminacy than is commonly supposed. (shrink)

A potentially new interpretation of quantum mechanics posits the state of the universe as a consistent set of facts that are instantiated in the correlations among entangled objects. A fact (or event) occurs exactly when the number or density of future possibilities decreases, and a quantum superposition exists if and only if the facts of the universe are consistent with the superposition. The interpretation sheds light on both in-principle and real-world predictability of the universe.

This article probes the question of what interpretations of quantum mechanics actually accomplish. In other domains, which are briefly considered, interpretations serve to make alien systematizations intelligible to us. This often involves clarifying the status of their implicit ontology. A survey of interpretations of non-relativistic quantum mechanics supports the evaluation that these interpretations make a contribution to philosophy, but not to physics. Interpretations of quantum field theory are polarized by the divergence between the Lagrangian field theory that led to the (...) Standard Model of Particle physics and the Algebraic quantum field theory, that discounts an ontology of particles. Ruetsche's interpretation, it is argued, offers a potential for loosening the sharp polarization that presently obtains. A brief evaluation focuses on the functional ontology of quantum field theory considered as an effective theory. (shrink)

Background: Microbiome biomarker discovery for patient diagnosis, prognosis, and risk evaluation is attracting broad interest. Selected groups of microbial features provide signatures that characterize host disease states such as cancer or cardio-metabolic diseases. Yet, the current predictive models stemming from machine learning still behave as black boxes and seldom generalize well. Their interpretation is challenging for physicians and biologists, which makes them difficult to trust and use routinely in the physician-patient decision-making process. Novel methods that provide interpretability and biological insight (...) are needed. Here, we introduce "predomics", an original machine learning approach inspired by microbial ecosystem interactions that is tailored for metagenomics data. It discovers accurate predictive signatures and provides unprecedented interpretability. The decision provided by the predictive model is based on a simple, yet powerful score computed by adding, subtracting, or dividing cumulative abundance of microbiome measurements. -/- Results: Tested on >100 datasets, we demonstrate that predomics models are simple and highly interpretable. Even with such simplicity, they are at least as accurate as state-of-the-art methods. The family of best models, discovered during the learning process, offers the ability to distil biological information and to decipher the predictability signatures of the studied condition. In a proof-of-concept experiment, we successfully predicted body corpulence and metabolic improvement after bariatric surgery using pre-surgery microbiome data. -/- Conclusions: Predomics is a new algorithm that helps in providing reliable and trustworthy diagnostic decisions in the microbiome field. Predomics is in accord with societal and legal requirements that plead for an explainable artificial intelligence approach in the medical field. (shrink)

The conspicuous similarities between interpretive strategies in classical statistical mechanics and in quantum mechanics may be grounded on their employment of common implementations of probability. The objective probabilities which represent the underlying stochasticity of these theories can be naturally associated with three of their common formal features: initial conditions, dynamics, and observables. Various well-known interpretations of the two theories line up with particular choices among these three ways of implementing probability. This perspective has significant application to debates on primitive ontology (...) and to the quantum measurement problem. (shrink)

Metaethical expressivism is typically characterised as the view that normative statements express desire-like attitudes instead of beliefs. However, in this paper I argue that expressivists should claim that normative statements express beliefs in normative propositions, and not merely in some deflationary sense but in a theoretically robust sense explicated by a theory of propositional attitudes. I first argue that this can be achieved by combining an interpretationist understanding of belief with a nonfactualist view of normative belief content. This results in (...) a view I call ‘interpretative expressivism’. I then argue that traditional arguments employed by expressivists that normative statements express noncognitive attitudes can just as well support the claim that normative statements express nonfactual or nonrepresentational beliefs. Finally, I argue that this view has a number of advantages to versions of expressivism that deny that normative statements express non-deflationary normative beliefs. (shrink)

This paper interprets the influential colony management simulator ‘Dwarf Fortress’ existentially, in terms of finitude, absurdity, and narrative. It applies Aarseth/Möring’s proposed method of game interpretation, adopting their definition of ‘cybermedia’ as a generalized game ontology, then providing a specialized ontology of ‘Dwarf Fortress’ which describes its genre and salient gameplay features, incorporating Ian Bogost’s concept of ‘procedural rhetoric’. It then gives an existentialist interpretation of ‘Dwarf Fortress’ which centres on ‘finitude’, ‘absurdity’, and ‘narrative’, showing that ‘Dwarf Fortress’ is a (...) game about the existential tensions involved in being human. We live knowing our lives and civilizations are finite, that there are radical limits on what we can know and do. There is no meaning inherent in the world, or in history, so it is up to us to create our own, and one of our most powerful ways of doing this is narrative. (shrink)

In our paper "Surface and Deep Interpretation," we sought to provide detail and texture to Arthur Danto's views on interpretation, thereby explicating and defending them (as published in Mark Rollins, ed., Danto and His Critics (Blackwell, originally published 1993; second edition 2012). Leddy objects to our views; in the end, Danto's view, given our explication of it, remains tenable.

Quantum Mechanics is a fundamental physical theory about atomic-scale processes. It was built between 1920 and 1940 by the most distinguished physicists of that time. The accordance between the predictions of the theory and experimental results is remarkable. The physical interpretation of its mathematical constructs, however, raised unprecedented controversies. Ontological, semantic, and epistemic vagueness abound in the orthodox interpretations and have resulted in serious misunderstandings that are often repeated in textbooks and elsewhere. In this work, we identify, criticize, and clarify (...) the most spread ones. (shrink)

How do we determine whether individuals accept the actual consistency of a political argument instead of just its rhetorical good looks? This article answers this question by proposing an interpretation of political argument within the constraints of political liberalism. It utilises modern developments in the philosophy of logic and language to reclaim ‘meaningless nonsense’ from use as a partisan war cry and to build up political argument as something more than a power struggle between competing conceptions of the good. Standard (...) solutions for ‘clarifying’ meaning through descriptive definition encounter difficulties with the biases of status quo idioms (long noted by theorists like William Connolly and Quentin Skinner), as well as partisan translations and circularity. Collectively called linguistic gerrymandering, these difficulties threaten political liberalism’s underlying coherency. The proposed interpretation of political argument overcomes this with a new brand of conceptual analysis that can falsifiably determine whether rhetoric has hijacked political argument. (shrink)

Nous proposons dans cet article des éléments nouveaux pour l’interprétation de la doctrine d’Héraclite, concernant en particulier le rôle de l’opposition des contraires en tant que générateur d’harmonie, mentionné dans les Fragments 8 et 51. Cette interprétation est basée sur l’outil conceptuel que constituent les matrices de concepts. Après avoir décrit les éléments fondamentaux qui régissent ces dernières, nous nous attachons à définir dans ce cadre conceptuel les notions d’opposition et de contraire, ainsi que d’harmonie. Cela permet de fournir une (...) interprétation ainsi qu’une justification pour la doctrine spécifique d’Héraclite, selon laquelle l’opposition des contraires est génératrice d’harmonie. (shrink)

Recent breakthroughs in artificial intelligence have primarily resulted from training deep neural networks (DNNs) with vast numbers of adjustable parameters on enormous datasets. Due to their complex internal structure, DNNs are frequently characterized as inscrutable ``black boxes,'' making it challenging to interpret the mechanisms underlying their impressive performance. This opacity creates difficulties for explanation, safety assurance, trustworthiness, and comparisons to human cognition, leading to divergent perspectives on these systems. This chapter examines recent developments in interpretability methods for DNNs, with a (...) focus on interventionist approaches inspired by causal explanation in philosophy of science. We argue that these methods offer a promising avenue for understanding how DNNs process information compared to merely behavioral benchmarking and correlational probing. We review key interventionist methods and illustrate their application through practical case studies. These methods allow researchers to identify and manipulate specific computational components within DNNs, providing insights into their causal structure and internal representations. We situate these approaches within the broader framework of causal abstraction, which aims to align low-level neural computations with high-level interpretable models. While acknowledging current limitations, we contend that interventionist methods offer a path towards more rigorous and theoretically grounded interpretability research, potentially informing both AI development and computational cognitive neuroscience. (shrink)

Researchers have converged on the idea that a pragmatic understanding of communication can shed important light on the evolution of language. Accordingly, animal communication scientists have been keen to adopt insights from pragmatics research. Some authors couple their appeal to pragmatic aspects of communication with the claim that there are fundamental asymmetries between signalers and receivers in non-human animals. For example, in the case of primate vocal calls, signalers are said to produce signals unintentionally and mindlessly, whereas receivers are thought (...) to engage in contextual interpretation to derive the significance of signals. We argue that claims about signaler-receiver asymmetries are often confused. This is partly because their authors conflate two conceptions of pragmatics, which generate different accounts of the explanatory target for accounts of the evolution of language. Here we distinguish these conceptions, in order to help specify more precisely the proper explanatory target for language evolution research. (shrink)

Evolutionary theory (ET) is teeming with probabilities. Probabilities exist at all levels: the level of mutation, the level of microevolution, and the level of macroevolution. This uncontroversial claim raises a number of contentious issues. For example, is the evolutionary process (as opposed to the theory) indeterministic, or is it deterministic? Philosophers of biology have taken different sides on this issue. Millstein (1997) has argued that we are not currently able answer this question, and that even scientific realists ought to remain (...) agnostic concerning the determinism or indeterminism of evolutionary processes. If this argument is correct, it suggests that, whatever we take probabilities in ET to be, they must be consistent with either determinism or indeterminism. This raises some interesting philosophical questions: How should we understand the probabilities used in ET? In other words, what is meant by saying that a certain evolutionary change is more or less probable? Which interpretation of probability is the most appropriate for ET? I argue that the probabilities used in ET are objective in a realist sense, if not in an indeterministic sense. Furthermore, there are a number of interpretations of probability that are objective and would be consistent with ET under determinism or indeterminism. However, I argue that evolutionary probabilities are best understood as propensities of population-level kinds. (shrink)

It is typically assumed that while we know other people’s mental states by observing and interpreting their behavior, we know our own mental states by introspection, i.e., without interpreting ourselves. In his latest book, The opacity of mind: An integrative theory of self-knowledge, Peter Carruthers (2011) argues against this assumption. He holds that findings from across the cognitive sciences strongly suggest that self-knowledge of conscious propositional attitudes such as intentions, judgments, and decisions involves a swift and unconscious process of self-interpretation (...) that utilizes the same sensory channels that we employ when working out other people’s mental states. I provide an overview of Carruthers’ book before discussing a pathological case that challenges his account of self-knowledge and mentioning empirical evidence that undermines his use of a particular kind of data in his case against introspection of conscious attitudes. (shrink)

Arthur C. Danto did not live to witness the proliferation of AI in artistic creation. However, his philosophy of art offers key ideas about art that can provide an interesting perspective on artwork generated by artificial intelligence (AI). In this article, I analyze how his ideas about contemporary art, intention, interpretation, and authorship could be applied to the ongoing debate about AI and artistic creation. At the same time, it is also interesting to consider whether the incorporation of AI into (...) artistic creation marks a new chapter in the narrative, which seems to have reached its end, or if it represents a significant rupture with past artistic traditions. (shrink)

The Philosophy of Psychiatry is a unique area of research because the nature of the subject matter leads to quite distinct methodological issues. Naturalism, Interpretation, and Mental Disorder is an original new work focusing on the challenges we face when trying to interpret and understand mental illness. The book integrates a hermeneutical perspective, and shows how such an approach can reveal important facts about historical sources in psychiatry and the nature of dialogue in the therapeutic encounter. In addition, the book (...) demonstrates how such an approach can be valuable for understanding the concept of mental disorder itself. Naturalism, Interpretation, and Mental Disorder brings fresh thinking to the philosophy of psychiatry, and will be of interest to students and scholars in the fields of Mental Health and Philosophy. (shrink)

In the Inner Chapters, arguments for a variety of different philosophical positions are present, including skepticism, relativism, particularism, and objectivism. Given that these are not all mutually consistent, we are left with the problem of reconciling the tensions among them. The various positions are described and passages from the Inner Chapters are presented illustrating each. A detailed commentary is offered on the opening of the Inner Chapters, arguing that it is best understood in an objectivist fashion. An interpretation is presented (...) of Zhuangzi's view of sagehood that reconciles the various arguments in the text. (shrink)

Artificial intelligence (AI) systems have demonstrated impressive performance across a variety of clinical tasks. However, notoriously, sometimes these systems are 'black boxes'. The initial response in the literature was a demand for 'explainable AI'. However, recently, several authors have suggested that making AI more explainable or 'interpretable' is likely to be at the cost of the accuracy of these systems and that prioritising interpretability in medical AI may constitute a 'lethal prejudice'. In this paper, we defend the value of interpretability (...) in the context of the use of AI in medicine. Clinicians may prefer interpretable systems over more accurate black boxes, which in turn is sufficient to give designers of AI reason to prefer more interpretable systems in order to ensure that AI is adopted and its benefits realised. Moreover, clinicians may be justified in this preference. Achieving the downstream benefits from AI is critically dependent on how the outputs of these systems are interpreted by physicians and patients. A preference for the use of highly accurate black box AI systems, over less accurate but more interpretable systems , may itself constitute a form of lethal prejudice that may diminish the benefits of AI to - and perhaps even harm - patients. (shrink)

The semeiotic of Charles Sanders Peirce is irreducibly triadic, positing that a sign mediates between the object that determines it and the interpretant that it determines. He eventually holds that each sign has two objects and three interpretants, standardizing quickly on immediate and dynamical for the objects but experimenting with a variety of names for the interpretants. The two most prominent terminologies are immediate/dynamical/final and emotional/energetic/logical, and scholars have long debated how they are related to each other. This paper (...) seeks to shed new light on the matter by reviewing the numerous manuscript drafts where Peirce develops the latter nomenclature while attempting to introduce his pragmatism to a general audience. It then goes on to examine an additional set of interpretants, intentional/effectual/communicational, and shows that the three different trichotomies can be understood as complementary, rather than redundant or conflicting. (shrink)

We argue that many intuitions do not have conscious propositional contents. In particular, many of the intuitions had in response to philosophical thought experiments, like Gettier cases, do not have such contents. They are more like hunches, urgings, murky feelings, and twinges. Our view thus goes against the received view of intuitions in philosophy, which we call Mainstream Propositionalism. Our positive view is that many thought-experimental intuitions are conscious, spontaneous, non-theoretical, non-propositional psychological states that often motivate belief revision, but they (...) require interpretation, in light of background beliefs, before a subject can form a propositional judgment as a consequence of them. We call our view Interpretationalism. We argue (i) that Interpretationalism avoids the problems that beset Mainstream Propositionalism and (ii) that our view meshes well with empirical results in contemporary cognitive science. (shrink)

The notions of inference and default are used in pragmatics with different meanings, resulting in theoretical disputes that emphasize the differences between the various pragmatic approaches. This paper is aimed at showing how the terminological and theoretical differences concerning the two aforementioned terms result from taking into account inference and default from different points of view and levels of analysis. Such differences risk making a dialogue between the theories extremely difficult. However, at a functional level of analysis the different theories, (...) definitions, and approaches to interpretation can be compared and integrated. At this level, the standardization of pragmatic inferences can be regarded as the development of a specific type of presumptions, used to draw prima-facie interpretations. (shrink)

We propose a formal framework for interpretable machine learning. Combining elements from statistical learning, causal interventionism, and decision theory, we design an idealised explanation game in which players collaborate to find the best explanation for a given algorithmic prediction. Through an iterative procedure of questions and answers, the players establish a three-dimensional Pareto frontier that describes the optimal trade-offs between explanatory accuracy, simplicity, and relevance. Multiple rounds are played at different levels of abstraction, allowing the players to explore overlapping causal (...) patterns of variable granularity and scope. We characterise the conditions under which such a game is almost surely guaranteed to converge on a optimal explanation surface in polynomial time, and highlight obstacles that will tend to prevent the players from advancing beyond certain explanatory thresholds. The game serves a descriptive and a normative function, establishing a conceptual space in which to analyse and compare existing proposals, as well as design new and improved solutions. (shrink)

'Interpretational' accounts of meaning are frequently treated as incompatible with accounts stressing language's 'social' character. However, this paper argues that one can reconcile interpretational and social accounts by distinguishing "methodological" from "ascriptional" individualism. While methodological individualism requires only that the meaning of one's terms ultimately be grounded in facts about oneself, ascriptional individualism requires that the meaning of one's terms be independent of how others use theirs. Interpretational accounts are committed only to methodological individualism, while arguments for languages social character (...) are best understood as attacks on ascriptional individualism. As a result, one can recognize language's social character and still be an interpretationalist. (shrink)

The aim of this paper is to comprehensively question the validity of the standard way of interpreting Chaitin's famous incompleteness theorem, which says that for every formalized theory of arithmetic there is a finite constant c such that the theory in question cannot prove any particular number to have Kolmogorov complexity larger than c. The received interpretation of theorem claims that the limiting constant is determined by the complexity of the theory itself, which is assumed to be good measure of (...) the strength of the theory. I exhibit certain strong counterexamples and establish conclusively that the received view is false. Moreover, I show that the limiting constants provided by the theorem do not in any way reflect the power of formalized theories, but that the values of these constants are actually determined by the chosen coding of Turing machines, and are thus quite accidental. (shrink)

Philosophers have wanted to work with conceptions of word-competence, or concept-possession, on which being a competent practitioner with a word amounts to being a competent judge of its uses by others. I argue that our implicit conception of competence with a word does not have this presupposition built into it. One implication of this is what I call "modesty" in interpretation: we allow for others, uses of words that we would not allow for ourselves. I develop this point by looking (...) at Saul Kripke's discussion of some famous examples given by Benson Mates, concerning beliefs about beliefs. I defend Mates's point against Kripke's claim that an interpreter who is modest in my sense must be "conceptually confused." . (shrink)

It is often assumed that literary meaning is essentially linguistic in nature and that literary interpretation is therefore a purely linguistic affair. This essay identifies a variety of literary meaning that cannot be reduced to linguistic meaning. Meaning of this sort is generated not by a communicative act so much as through a creative one: the construction of a fictional world. The way in which a fictional world can bear meaning turns out to be strikingly unlike the way a sentence (...) can, and this, I argue, has important implications for the theory of interpretation. (shrink)

Davidson argues that his version of interpretivism entails that sceptical scenarios are impossible, thus offering a response to any sceptical argument that depends upon the possibility of sceptical scenarios. It has been objected that Davidson’s interpretivism does not entail the impossibility of sceptical scenarios due to the possibility that interpreter and speaker are in a shared state of massive error, and so this response to scepticism fails. In this paper I show that the objection from the possibility of shared error (...) rests on a misunderstanding of Davidson’s interpretivist position. Properly understood, Davidson’s view does entail that sceptical scenarios are impossible. I also give a reason independent of its anti-sceptical implications to prefer Davidson’s interpretivism over the version of interpretivism erroneously attributed to him by those who object to his anti-sceptical argument. (shrink)

In this paper I propose an interpretation of classical statistical mechanics that centers on taking seriously the idea that probability measures represent complete states of statistical mechanical systems. I show how this leads naturally to the idea that the stochasticity of statistical mechanics is associated directly with the observables of the theory rather than with the microstates (as traditional accounts would have it). The usual assumption that microstates are representationally significant in the theory is therefore dispensable, a consequence which suggests (...) interesting possibilities for developing non-equilibrium statistical mechanics and investigating inter-theoretic answers to the foundational questions of statistical mechanics. (shrink)

This paper begins with a puzzle regarding Lewis' theory of radical interpretation. On the one hand, Lewis convincingly argued that the facts about an agent's sensory evidence and choices will always underdetermine the facts about her beliefs and desires. On the other hand, we have several representation theorems—such as those of (Ramsey 1931) and (Savage 1954)—that are widely taken to show that if an agent's choices satisfy certain constraints, then those choices can suffice to determine her beliefs and desires. In (...) this paper, I will argue that Lewis' conclusion is correct: choices radically underdetermine beliefs and desires, and representation theorems provide us with no good reasons to think otherwise. Any tension with those theorems is merely apparent, and relates ultimately to the difference between how 'choices' are understood within Lewis' theory and the problematic way that they're represented in the context of the representation theorems. For the purposes of radical interpretation, representation theorems like Ramsey's and Savage's just aren't very relevant after all. (shrink)

This paper applies a pragmatic-retorical theory of explanation and interpretation to understand the methodological perspectivism of the social sciences.

La mécanique quantique est une théorie physique contemporaine réputée pour ses défis au sens commun et ses paradoxes. Depuis bientôt un siècle, plusieurs interprétations de la théorie ont été proposées par les physiciens et les philosophes, offrant des images quantiques du monde, ou des métaphysiques, radicalement différentes. L'existence d'un hasard fondamental, ou d'une multitude de mondes en-dehors du nôtre, dépend ainsi de l'interprétation adoptée. Cet article, en s'appuyant sur le livre Boyer-Kassem (2015), Qu'est-ce que la mécanique quantique ?, présente trois (...) principales interprétations quantiques, empiriquement équivalentes : l'interprétation dite orthodoxe, l'interprétation de Bohm, et l'interprétation des mondes multiples. (shrink)

Aestheticians in the tradition of Critical Theory have claimed that the or a purpose of musical interpretation is somehow to save or salvage or rescue ("retten") the musical work. What sense, if any, can be made of this claim? The notion of salvage or rescue presupposes the concept of danger. Threats to works of art emerge from two sources: from outside and from inside. Whilst the former problem is only touched upon, the latter is discussed in some detail, using the (...) example of Brahms' Alto Rhapsody op. 53. Kathleen Ferrier's and Clemens Krauss' interpretation of 1947 deals with rather than ignores the composer's crumbly attempt at fusing art and religion. Salvage as their attitude vis-a-vis the work is distinguished from cover-up on the one hand and exposure on the other hand. (shrink)

This chapter proposes a dialectical approach to legal interpretation, consisting of three dimensions: a formalization of the canons of interpretation in terms of argumentation schemes; a dialectical classification of interpretive schemes; and a logical and computational model for comparing the arguments pro and contra an interpretation. The traditional interpretive maxims or canons used in both common and civil law are translated into defeasible patterns of arguments, which can be evaluated through sets of corresponding critical questions. These interpretive argumentation schemes are (...) classified in general categories and a distinction is drawn between schemes supporting and rebutting an interpretation. This framework allows conceiving statutory interpretation as a dialectical procedure consisting in weighing arguments pro and contra an interpretation. This procedure is formalized and represented computationally through tools from formal argumentation systems. (shrink)

I propose an account of probability in the Everett interpretation of quantum mechanics. According to the account, probabilities are objective chances of centered propositions. As I show, the account solves a number of problems concerning the role of probability in the Everett interpretation. It also challenges an implicit assumption, concerning the aim and scope of fundamental physical theories, that is made throughout the philosophy of physics literature.

The many worlds interpretation of quantum mechanics (MWI) states that the world we live in is just one among many parallel worlds. It is widely believed that because of this commitment to parallel worlds, the MWI violates common sense. Some go so far as to reject the MWI on this basis. This is despite its myriad of advantages to physics (e.g. consistency with relativity theory, mathematical simplicity, realism, determinism, etc.). Here, we make the case that common sense in fact favors (...) the MWI. We argue that causal explanations are commonsensical only when they are local causal explanations. We present several quantum mechanical experiments that seem to exhibit nonlocal “action at a distance”. Under the assumption that only one world exists, these experiments seem immune to local causal explanation. However, we show that the MWI, by taking all worlds together, can provide local causal explanations of the experiments. The MWI therefore restores common sense to physical explanation. (shrink)

Since its emergence in the 1960s, Artifcial Intelligence (AI) has grown to conquer many technology products and their felds of application. Machine learning, as a major part of the current AI solutions, can learn from the data and through experience to reach high performance on various tasks. This growing success of AI algorithms has led to a need for interpretability to understand opaque models such as deep neural networks. Various requirements have been raised from diferent domains, together with numerous tools (...) to debug, justify outcomes, and establish the safety, fairness and reliability of the models. This variety of tasks has led to inconsistencies in the terminology with, for instance, terms such as interpretable, explainable and transparent being often used interchangeably in methodology papers. These words, however, convey diferent meanings and are “weighted" diferently across domains, for example in the technical and social sciences. In this paper, we propose an overarching terminology of interpretability of AI systems that can be referred to by the technical developers as much as by the social sciences community to pursue clarity and efciency in the defnition of regulations for ethical and reliable AI development. We show how our taxonomy and defnition of interpretable AI difer from the ones in previous research and how they apply with high versatility to several domains and use cases, proposing a—highly needed—standard for the communication among interdisciplinary areas of AI. (shrink)

This chapter is based on a presentation I gave at a conference on General Education. It provides an overview of a course I teach on (Jungian) dream interpretation, focusing especially on the assessment criteria that make it possible to grade students' interpretations of their own dreams in a highly objective manner.