Tootfinder

From Protoscience to Epistemic Monoculture: How Benchmarking Set the Stage for the Deep Learning Revolution
Bernard J. Koch, David Peterson
https://arxiv.org/abs/2404.06647

From Protoscience to Epistemic Monoculture: How Benchmarking Set the Stage for the Deep Learning Revolution
Over the past decade, AI research has focused heavily on building ever-larger deep learning models. This approach has simultaneously unlocked incredible achievements in science and technology, and hindered AI from overcoming long-standing limitations with respect to explainability, ethical harms, and environmental efficiency. Drawing on qualitative interviews and computational analyses, our three-part history of AI research traces the creation of this "epistemic monoculture" back to a radical r…

This https://arxiv.org/abs/2402.08171 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCY_…

Epistemic Power, Objectivity and Gender in AI Ethics Labor: Legitimizing Located Complaints
What counts as legitimate AI ethics labor, and consequently, what are the epistemic terms on which AI ethics claims are rendered legitimate? Based on 75 interviews with technologists including researchers, developers, open source contributors, and activists, this paper explores the various epistemic bases from which AI ethics is discussed and practiced. In the context of outside attacks on AI ethics as an impediment to ``progress,'' I show how some AI ethics practices have reached toward author…

This https://arxiv.org/abs/2402.08171 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCY_…

Epistemic Power, Objectivity and Gender in AI Ethics Labor: Legitimizing Located Complaints
What counts as legitimate AI ethics labor, and consequently, what are the epistemic terms on which AI ethics claims are rendered legitimate? Based on 75 interviews with technologists including researchers, developers, open source contributors, and activists, this paper explores the various epistemic bases from which AI ethics is discussed and practiced. In the context of outside attacks on AI ethics as an impediment to ``progress,'' I show how some AI ethics practices have reached toward author…

Very interesting looking social analysis of scientists, managing uncertainty, and questionable research practices.
#STS #QRPs #ResearchIntegrity

Navigating the Science System: Research Integrity and Academic Survival Strategies - Science and Engineering Ethics
Research Integrity (RI) is high on the agenda of both institutions and science policy. The European Union as well as national ministries of science have launched ambitious initiatives to combat misconduct and breaches of research integrity. Often, such initiatives entail attempts to regulate scientific behavior through guidelines that institutions and academic communities can use to more easily identify and deal with cases of misconduct. Rather than framing misconduct as a result of an informat…

Epistemic injustice: an invitation to ask new questions – PIRC https://publicinterest.org.uk/epistemic-injustice-an-invitation-to-ask-new-questions/?mc_cid=ea9608deba&mc_eid=fe3615d311

Epistemic injustice: an invitation to ask new questions – PIRC
Who is allowed to know things in our society? Why we need to ensure narrative change is led by those currently excluded from that work.

KI, Du bist so 1 Pimmel: Interview in Ars Technica mit Molly Crockett und Lisa Messeri über das Ratten-Bild, das wir alle nicht mehr vergessen werden und welche Folgen all die KI-Mythen, die z.B. @… generell kritisiert, für die Wissenschaft haben werden: "Producing more but understanding less".

This https://arxiv.org/abs/2404.06647 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCY_…

From Protoscience to Epistemic Monoculture: How Benchmarking Set the Stage for the Deep Learning Revolution
Over the past decade, AI research has focused heavily on building ever-larger deep learning models. This approach has simultaneously unlocked incredible achievements in science and technology, and hindered AI from overcoming long-standing limitations with respect to explainability, ethical harms, and environmental efficiency. Drawing on qualitative interviews and computational analyses, our three-part history of AI research traces the creation of this "epistemic monoculture" back to a radical r…

Very interesting looking social analysis of scientists, managing uncertainty, and questionable research practices.
#STS #QRPs #ResearchIntegrity

Navigating the Science System: Research Integrity and Academic Survival Strategies - Science and Engineering Ethics
Research Integrity (RI) is high on the agenda of both institutions and science policy. The European Union as well as national ministries of science have launched ambitious initiatives to combat misconduct and breaches of research integrity. Often, such initiatives entail attempts to regulate scientific behavior through guidelines that institutions and academic communities can use to more easily identify and deal with cases of misconduct. Rather than framing misconduct as a result of an informat…

Stalnaker's Epistemic Logic in Isabelle/HOL
Laura P. Gamboa Guzman (Iowa State University, Ames, Iowa), Kristin Y. Rozier (Iowa State University, Ames, Iowa)
https://arxiv.org/abs/2404.14919

Stalnaker's Epistemic Logic in Isabelle/HOL
The foundations of formal models for epistemic and doxastic logics often rely on certain logical aspects of modal logics such as S4 and S4.2 and their semantics; however, the corresponding mathematical results are often stated in papers or books without including a detailed proof, or a reference to it, that allows the reader to convince themselves about them. We reinforce the foundations of the epistemic logic S4.2 for countably many agents by formalizing its soundness and completeness results …

Robust Online Epistemic Replanning of Multi-Robot Missions
Lauren Bramblett, Branko Miloradovic, Patrick Sherman, Alessandro V. Papadopoulos, Nicola Bezzo
https://arxiv.org/abs/2403.00641

Robust Online Epistemic Replanning of Multi-Robot Missions
As Multi-Robot Systems (MRS) become more affordable and computing capabilities grow, they provide significant advantages for complex applications such as environmental monitoring, underwater inspections, or space exploration. However, accounting for potential communication loss or the unavailability of communication infrastructures in these application domains remains an open problem. Much of the applicable MRS research assumes that the system can sustain communication through proximity regulat…

Leveraging Active Subspaces to Capture Epistemic Model Uncertainty in Deep Generative Models for Molecular Design
A N M Nafiz Abeer, Sanket Jantre, Nathan M Urban, Byung-Jun Yoon
https://arxiv.org/abs/2405.00202

Leveraging Active Subspaces to Capture Epistemic Model Uncertainty in Deep Generative Models for Molecular Design
Deep generative models have been accelerating the inverse design process in material and drug design. Unlike their counterpart property predictors in typical molecular design frameworks, generative molecular design models have seen fewer efforts on uncertainty quantification (UQ) due to computational challenges in Bayesian inference posed by their large number of parameters. In this work, we focus on the junction-tree variational autoencoder (JT-VAE), a popular model for generative molecular de…

SD: Further points to meet these challenges: think about building open infrastructures, ensure a diversity of voices, and finding local solutions to address epistemic injustices. #ecsa2024

Feminist History of Philosophy || CfA: Women and Epistemic Emotions in the Early Modern Period – McMaster University
https://feministhistoryofphilosophy.wordpress.com/2024/02/22/cfa-women-and-epistemic-emotions-in-the-early-modern-period-mcmaster-university/

From Justin Joque, "Revolutionary Mathematics"

This https://arxiv.org/abs/2310.01046 has been replaced.
initial toot: https://mastoxiv.page/@arX…

Epistemic integration and social segregation of AI in neuroscience
In recent years, Artificial Intelligence (AI) shows a spectacular ability of insertion inside a variety of disciplines which use it for scientific advancements and which sometimes improve it for their conceptual and methodological needs. According to the transverse science framework originally conceived by Shinn and Joerges, AI can be seen as an instrument which is progressively acquiring a universal character through its diffusion across science. In this paper we address empirically one aspect…

From Displacements to Distributions: A Machine-Learning Enabled Framework for Quantifying Uncertainties in Parameters of Computational Models
Taylor Roper, Harri Hakula, Troy Butler
https://arxiv.org/abs/2403.03233

From Displacements to Distributions: A Machine-Learning Enabled Framework for Quantifying Uncertainties in Parameters of Computational Models
This work presents novel extensions for combining two frameworks for quantifying both aleatoric (i.e., irreducible) and epistemic (i.e., reducible) sources of uncertainties in the modeling of engineered systems. The data-consistent (DC) framework poses an inverse problem and solution for quantifying aleatoric uncertainties in terms of pullback and push-forward measures for a given Quantity of Interest (QoI) map. Unfortunately, a pre-specified QoI map is not always available a priori to the coll…

Is Epistemic Uncertainty Faithfully Represented by Evidential Deep Learning Methods?
Mira J\"urgens, Nis Meinert, Viktor Bengs, Eyke H\"ullermeier, Willem Waegeman
https://arxiv.org/abs/2402.09056

Is Epistemic Uncertainty Faithfully Represented by Evidential Deep Learning Methods?
Trustworthy ML systems should not only return accurate predictions, but also a reliable representation of their uncertainty. Bayesian methods are commonly used to quantify both aleatoric and epistemic uncertainty, but alternative approaches, such as evidential deep learning methods, have become popular in recent years. The latter group of methods in essence extends empirical risk minimization (ERM) for predicting second-order probability distributions over outcomes, from which measures of epist…

Leveraging Active Subspaces to Capture Epistemic Model Uncertainty in Deep Generative Models for Molecular Design
A N M Nafiz Abeer, Sanket Jantre, Nathan M Urban, Byung-Jun Yoon
https://arxiv.org/abs/2405.00202

Leveraging Active Subspaces to Capture Epistemic Model Uncertainty in Deep Generative Models for Molecular Design
Deep generative models have been accelerating the inverse design process in material and drug design. Unlike their counterpart property predictors in typical molecular design frameworks, generative molecular design models have seen fewer efforts on uncertainty quantification (UQ) due to computational challenges in Bayesian inference posed by their large number of parameters. In this work, we focus on the junction-tree variational autoencoder (JT-VAE), a popular model for generative molecular de…

Bayesian Learned Models Can Detect Adversarial Malware For Free
Bao Gia Doan, Dang Quang Nguyen, Paul Montague, Tamas Abraham, Olivier De Vel, Seyit Camtepe, Salil S. Kanhere, Ehsan Abbasnejad, Damith C. Ranasinghe
https://arxiv.org/abs/2403.18309

Bayesian Learned Models Can Detect Adversarial Malware For Free
The vulnerability of machine learning-based malware detectors to adversarial attacks has prompted the need for robust solutions. Adversarial training is an effective method but is computationally expensive to scale up to large datasets and comes at the cost of sacrificing model performance for robustness. We hypothesize that adversarial malware exploits the low-confidence regions of models and can be identified using epistemic uncertainty of ML approaches -- epistemic uncertainty in a machine l…

From Displacements to Distributions: A Machine-Learning Enabled Framework for Quantifying Uncertainties in Parameters of Computational Models
Taylor Roper, Harri Hakula, Troy Butler
https://arxiv.org/abs/2403.03233

From Displacements to Distributions: A Machine-Learning Enabled Framework for Quantifying Uncertainties in Parameters of Computational Models
This work presents novel extensions for combining two frameworks for quantifying both aleatoric (i.e., irreducible) and epistemic (i.e., reducible) sources of uncertainties in the modeling of engineered systems. The data-consistent (DC) framework poses an inverse problem and solution for quantifying aleatoric uncertainties in terms of pullback and push-forward measures for a given Quantity of Interest (QoI) map. Unfortunately, a pre-specified QoI map is not always available a priori to the coll…

What is a "bug"? On subjectivity, epistemic power, and implications for software research
David Gray Widder, Claire Le Goues
https://arxiv.org/abs/2402.08165

What is a "bug"? On subjectivity, epistemic power, and implications for software research
Considerable effort in software research and practice is spent on bugs. Finding, reporting, tracking, triaging, attempting to fix them automatically, detecting "bug smells" -these comprise a substantial portion of large projects' time and development cost, and are of significant interest to researchers in Software Engineering, Programming Languages, and beyond. But, what is a bug, exactly? While segmentation faults rarely spark joy, most bugs are not so clear cut. Per the Oxford English Dicti…

On the Meaning of Local Symmetries: Epistemic-Ontological Dialectic
Jordan Fran\c{c}ois, Lucrezia Ravera
https://arxiv.org/abs/2404.17449 https://

On the Meaning of Local Symmetries: Epistemic-Ontological Dialectic
We propose our account of the meaning of local symmetries. We argue that the general covariance principle and gauge principle both are principles of democratic epistemic access to the law of physics, leading to ontological insights about the objective nature of spacetime. We further argue that relationality is a core notion of general-relativistic gauge field theory, tacitly encoded by its (active) local symmetries.

Alexander Pruss's Blog || The epistemic gap and causal closure
http://alexanderpruss.blogspot.com/2024/03/the-epistemic-gap-and-causal-closure.html

AI Model Placement for 6G Networks under Epistemic Uncertainty Estimation
Liming Huang, Yulei Wu, Juan Marcelo Parra-Ullauri, Reza Nejabati, Dimitra Simeonidou
https://arxiv.org/abs/2402.11245

AI Model Placement for 6G Networks under Epistemic Uncertainty Estimation
The adoption of Artificial Intelligence (AI) based Virtual Network Functions (VNFs) has witnessed significant growth, posing a critical challenge in orchestrating AI models within next-generation 6G networks. Finding optimal AI model placement is significantly more challenging than placing traditional software-based VNFs, due to the introduction of numerous uncertain factors by AI models, such as varying computing resource consumption, dynamic storage requirements, and changing model performanc…

Is Epistemic Uncertainty Faithfully Represented by Evidential Deep Learning Methods?
Mira J\"urgens, Nis Meinert, Viktor Bengs, Eyke H\"ullermeier, Willem Waegeman
https://arxiv.org/abs/2402.09056

Is Epistemic Uncertainty Faithfully Represented by Evidential Deep Learning Methods?
Trustworthy ML systems should not only return accurate predictions, but also a reliable representation of their uncertainty. Bayesian methods are commonly used to quantify both aleatoric and epistemic uncertainty, but alternative approaches, such as evidential deep learning methods, have become popular in recent years. The latter group of methods in essence extends empirical risk minimization (ERM) for predicting second-order probability distributions over outcomes, from which measures of epist…

Generalising realisability in statistical learning theory under epistemic uncertainty
Fabio Cuzzolin
https://arxiv.org/abs/2402.14759 https://

Generalising realisability in statistical learning theory under epistemic uncertainty
The purpose of this paper is to look into how central notions in statistical learning theory, such as realisability, generalise under the assumption that train and test distribution are issued from the same credal set, i.e., a convex set of probability distributions. This can be considered as a first step towards a more general treatment of statistical learning under epistemic uncertainty.

This https://arxiv.org/abs/2309.03723 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_qu…

On the optimal error exponents for classical and quantum antidistinguishability
The concept of antidistinguishability of quantum states has been studied to investigate foundational questions in quantum mechanics. It is also called quantum state elimination, because the goal of such a protocol is to guess which state, among finitely many chosen at random, the system is not prepared in (that is, it can be thought of as the first step in a process of elimination). Antidistinguishability has been used to investigate the reality of quantum states, ruling out $ψ$-epistemic onto…

This https://arxiv.org/abs/2404.19623 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_eco…

Level-$k$ Reasoning, Cognitive Hierarchy, and Rationalizability
We use a uniform framework to cognitive hierarchy (CH) solution concepts a decision-theoretical foundation by the epistemic game theoretical solution concept $Δ$-rationalizability (Battigalli and Siniscalchi, 2003). We formulate level-$k$ strategic sophistication as an information type, and, by putting intuitive conditions on the the belief of players with a strategic sophistication, we define a restriction $Δ^κ$, from which the levels of reasoning is endogenously determined. We show that in…

Multivariate Bayesian Last Layer for Regression: Uncertainty Quantification and Disentanglement
Han Wang, Eiji Kawasaki, Guillaume Damblin, Geoffrey Daniel
https://arxiv.org/abs/2405.01761

Multivariate Bayesian Last Layer for Regression: Uncertainty Quantification and Disentanglement
We present new Bayesian Last Layer models in the setting of multivariate regression under heteroscedastic noise, and propose an optimization algorithm for parameter learning. Bayesian Last Layer combines Bayesian modelling of the predictive distribution with neural networks for parameterization of the prior, and has the attractive property of uncertainty quantification with a single forward pass. The proposed framework is capable of disentangling the aleatoric and epistemic uncertainty, and can…

This https://arxiv.org/abs/2404.17449 has been replaced.
initial toot: https://mastoxiv.page/@ar…

On the Meaning of Local Symmetries: Epistemic-Ontological Dialectic
We propose our account of the meaning of local symmetries. We argue that the general covariance principle and gauge principle both are principles of democratic epistemic access to the law of physics, leading to ontological insights about the objective nature of spacetime. We further argue that relationality is a core notion of general-relativistic gauge field theory, tacitly encoded by its (active) local symmetries.

This https://arxiv.org/abs/2205.08010 has been replaced.
link: https://scholar.google.com/scholar?q=a

The e-value and the Full Bayesian Significance Test: Logical Properties and Philosophical Consequences
This article gives a conceptual review of the e-value, ev(H|X) -- the epistemic value of hypothesis H given observations X. This statistical significance measure was developed in order to allow logically coherent and consistent tests of hypotheses, including sharp or precise hypotheses, via the Full Bayesian Significance Test (FBST). Arguments of analysis allow a full characterization of this statistical test by its logical or compositional properties, showing a mutual complementarity betw…

This https://arxiv.org/abs/2404.09037 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_ees…

Intention-Aware Control Based on Belief-Space Specifications and Stochastic Expansion
This paper develops a correct-by-design controller for an autonomous vehicle interacting with opponent vehicles with unknown intentions. We use discrete-valued random variables to model unknown intentions. Based on this, we define an intention-aware control problem for an autonomous vehicle and a collection of opponent agents with epistemic uncertainty. To this end, we focus on a control objective specified in the belief space with temporal logic specifications. From this stochastic control pro…

This https://arxiv.org/abs/2402.00060 has been replaced.
link: https://scholar.google.com/scholar?q=a

Treatment of Epistemic Uncertainty in Conjunction Analysis with Dempster-Shafer Theory
The paper presents an approach to the modelling of epistemic uncertainty in Conjunction Data Messages (CDM) and the classification of conjunction events according to the confidence in the probability of collision. The approach proposed in this paper is based on the Dempster-Shafer Theory (DSt) of evidence and starts from the assumption that the observed CDMs are drawn from a family of unknown distributions. The Dvoretzky-Kiefer-Wolfowitz (DKW) inequality is used to construct robust bounds on su…

A Game-Theoretic Analysis of Auditing Differentially Private Algorithms with Epistemically Disparate Herd
Ya-Ting Yang, Tao Zhang, Quanyan Zhu
https://arxiv.org/abs/2404.16195

A Game-Theoretic Analysis of Auditing Differentially Private Algorithms with Epistemically Disparate Herd
Privacy-preserving AI algorithms are widely adopted in various domains, but the lack of transparency might pose accountability issues. While auditing algorithms can address this issue, machine-based audit approaches are often costly and time-consuming. Herd audit, on the other hand, offers an alternative solution by harnessing collective intelligence. Nevertheless, the presence of epistemic disparity among auditors, resulting in varying levels of expertise and access to knowledge, may impact au…

Epistemic Power, Objectivity and Gender in AI Ethics Labor: Legitimizing Located Complaints
David Gray Widder
https://arxiv.org/abs/2402.08171 https://

Epistemic Power, Objectivity and Gender in AI Ethics Labor: Legitimizing Located Complaints
What counts as legitimate AI ethics labor, and consequently, what are the epistemic terms on which AI ethics claims are rendered legitimate? Based on 75 interviews with technologists including researchers, developers, open source contributors, artists, and activists, this paper explores various epistemic bases from which AI ethics is practiced. In the context of outside attacks on AI ethics as an impediment to "progress," I show how some AI ethics practices have reached toward scholarly authori…

This https://arxiv.org/abs/2311.16570 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_qfi…

Epistemic Limits of Empirical Finance: Causal Reductionism and Self-Reference
The clarion call for causal reduction in the study of capital markets is intensifying. However, in self-referencing and open systems such as capital markets, the idea of unidirectional causation (if applicable) may be limiting at best, and unstable or fallacious at worst. In this research, we critically assess the use of scientific deduction and causal inference within the study of empirical finance and econometrics. We then demonstrate the idea of competing causal chains using a toy model adap…

Level-$k$ Reasoning, Cognitive Hierarchy, and Rationalizability
Shuige Liu
https://arxiv.org/abs/2404.19623 https://arxiv.org/pdf/240…

Level-$k$ Reasoning, Cognitive Hierarchy, and Rationalizability
We use a uniform framework to cognitive hierarchy (CH) solution concepts a decision-theoretical foundation by the epistemic game theoretical solution concept $Δ$-rationalizability (Battigalli and Siniscalchi, 2003). We formulate level-$k$ strategic sophistication as an information type, and, by putting intuitive conditions on the the belief of players with a strategic sophistication, we define a restriction $Δ^κ$, from which the levels of reasoning is endogenously determined. We show that in…

Just caught wind of this initiative: Open Research Community Accelerator (ORCA) https://www.orcaopen.org/
Happy to see that it does seem to have a broader vision of open science, recognizes plurality in epistemic practices, & folds in a concern for equity. Nonetheless, the adoption of the cute & cuddly orc…

This https://arxiv.org/abs/2402.08171 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCY_…

Epistemic Power, Objectivity and Gender in AI Ethics Labor: Legitimizing Located Complaints
What counts as legitimate AI ethics labor, and consequently, what are the epistemic terms on which AI ethics claims are rendered legitimate? Based on 75 interviews with technologists including researchers, developers, open source contributors, and activists, this paper explores the various epistemic bases from which AI ethics is discussed and practiced. In the context of outside attacks on AI ethics as an impediment to ``progress,'' I show how some AI ethics practices have reached toward author…

A computed 95% confidence interval does cover the true value with probability 0.95 if epistemically interpreted
Dan Hedlin
https://arxiv.org/abs/2402.10000

A computed 95% confidence interval does cover the true value with probability 0.95 if epistemically interpreted
Suppose the lifetime of a large sample of batteries in routine use is measured. A confidence interval is computed to 394 plus/minus 1.96 times 4.6 days. The standard interpretation is that if we repeatedly draw samples and compute confidence intervals, about 95% of the intervals will cover the unknown true lifetime. What can be said about the particular interval 394 plus/minus 1.96 times 4.6 has not been clear. We clarify this by using an epistemic interpretation of probability. The conclusion …

This https://arxiv.org/abs/2402.08171 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCY_…

Epistemic Power, Objectivity and Gender in AI Ethics Labor: Legitimizing Located Complaints
What counts as legitimate AI ethics labor, and consequently, what are the epistemic terms on which AI ethics claims are rendered legitimate? Based on 75 interviews with technologists including researchers, developers, open source contributors, and activists, this paper explores the various epistemic bases from which AI ethics is discussed and practiced. In the context of outside attacks on AI ethics as an impediment to ``progress,'' I show how some AI ethics practices have reached toward author…

This https://arxiv.org/abs/2404.09037 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_ees…

Intention-Aware Control Based on Belief-Space Specifications and Stochastic Expansion
This paper develops a correct-by-design controller for an autonomous vehicle interacting with opponent vehicles with unknown intentions. We use discrete-valued random variables to model unknown intentions. Based on this, we define an intention-aware control problem for an autonomous vehicle and a collection of opponent agents with epistemic uncertainty. To this end, we focus on a control objective specified in the belief space with temporal logic specifications. From this stochastic control pro…

A Framework for Variational Inference of Lightweight Bayesian Neural Networks with Heteroscedastic Uncertainties
David J. Schodt, Ryan Brown, Michael Merritt, Samuel Park, Delsin Menolascino, Mark A. Peot
https://arxiv.org/abs/2402.14532

A Framework for Variational Inference of Lightweight Bayesian Neural Networks with Heteroscedastic Uncertainties
Obtaining heteroscedastic predictive uncertainties from a Bayesian Neural Network (BNN) is vital to many applications. Often, heteroscedastic aleatoric uncertainties are learned as outputs of the BNN in addition to the predictive means, however doing so may necessitate adding more learnable parameters to the network. In this work, we demonstrate that both the heteroscedastic aleatoric and epistemic variance can be embedded into the variances of learned BNN parameters, improving predictive perfo…

Ensuring trustworthy and ethical behaviour in intelligent logical agents
Stefania Costantini
https://arxiv.org/abs/2402.07547 https://

Ensuring trustworthy and ethical behaviour in intelligent logical agents
Autonomous Intelligent Agents are employed in many applications upon which the life and welfare of living beings and vital social functions may depend. Therefore, agents should be trustworthy. A priori certification techniques (i.e., techniques applied prior to system's deployment) can be useful, but are not sufficient for agents that evolve, and thus modify their epistemic and belief state, and for open Multi-Agent Systems, where heterogeneous agents can join or leave the system at any stage o…

This https://arxiv.org/abs/2106.16081 has been replaced.
link: https://scholar.google.com/scholar?q=a

Quantal Response Equilibrium and Rationalizability: Inside the Black Box
This paper aims to connect epistemic and behavioral game theory by examining the epistemic foundations of quantal response equilibrium (QRE) in static games. We focus on how much information agents possess about the probability distributions of idiosyncratic payoff shocks, in addition to the standard assumptions of rationality and common belief in rationality. When these distributions are transparent, we obtain a solution concept called $Δ^p$-rationalizability, which includes action distributi…

Intention-Aware Control Based on Belief-Space Specifications and Stochastic Expansion
Zengjie Zhang, Zhiyong Sun, Sofie Haesaer
https://arxiv.org/abs/2404.09037

Intention-Aware Control Based on Belief-Space Specifications and Stochastic Expansion
This paper develops a correct-by-design controller for an autonomous vehicle interacting with opponent vehicles with unknown intentions. We use discrete-valued random variables to model unknown intentions. Based on this, we define an intention-aware control problem for an autonomous vehicle and a collection of opponent agents with epistemic uncertainty. To this end, we focus on a control objective specified in the belief space with temporal logic specifications. From this stochastic control pro…

Conformalized Credal Set Predictors
Alireza Javanmardi, David Stutz, Eyke H\"ullermeier
https://arxiv.org/abs/2402.10723 https://

Conformalized Credal Set Predictors
Credal sets are sets of probability distributions that are considered as candidates for an imprecisely known ground-truth distribution. In machine learning, they have recently attracted attention as an appealing formalism for uncertainty representation, in particular due to their ability to represent both the aleatoric and epistemic uncertainty in a prediction. However, the design of methods for learning credal set predictors remains a challenging problem. In this paper, we make use of conforma…

Conformalized Credal Set Predictors
Alireza Javanmardi, David Stutz, Eyke H\"ullermeier
https://arxiv.org/abs/2402.10723 https://

Conformalized Credal Set Predictors
Credal sets are sets of probability distributions that are considered as candidates for an imprecisely known ground-truth distribution. In machine learning, they have recently attracted attention as an appealing formalism for uncertainty representation, in particular due to their ability to represent both the aleatoric and epistemic uncertainty in a prediction. However, the design of methods for learning credal set predictors remains a challenging problem. In this paper, we make use of conforma…