arXiv subjects

Francisco Castro

Publications and source records attributed to Francisco Castro.

15 recordsLinked to original sources

arXiv2026

The Effects of Structured LLM-Generated Feedback on Programming Assignment Performance

When programming students encounter errors in their code, compiler messages or static analysis output often provide limited guidance, particularly for novice programmers. Personalized feedback from instructors can be effective but does not scale well. Recent advances in large language models (LLMs) enable automated feedback generation at scale. This study examines whether LLM-generated feedback with different levels of guidance is associated with differences in students' problem-solving behavior. We analyze effects on time to solution and number of attempts, and examine whether these effects differ by programming experience. We design three feedback types and compare them to a baseline in which students receive only compiler error messages. Results from an online programming course show that LLM-generated feedback is associated with faster time to solution compared to the no-feedback baseline, with less guided feedback showing slightly stronger effects. Overall, the findings suggest that feedback structure plays an important role in how students progress toward correct solutions and motivate further work on adaptive feedback designs and longer-term learning outcomes.

cs.HC↗

arXiv2025

XAIxArts Manifesto: Explainable AI for the Arts

Explainable AI (XAI) is concerned with how to make AI models more understandable to people. To date these explanations have predominantly been technocentric - mechanistic or productivity oriented. This paper introduces the Explainable AI for the Arts (XAIxArts) manifesto to provoke new ways of thinking about explainability and AI beyond technocentric discourses. Manifestos offer a means to communicate ideas, amplify unheard voices, and foster reflection on practice. To supports the co-creation and revision of the XAIxArts manifesto we combine a World Caf\'e style discussion format with a living manifesto to question four core themes: 1) Empowerment, Inclusion, and Fairness; 2) Valuing Artistic Practice; 3) Hacking and Glitches; and 4) Openness. Through our interactive living manifesto experience we invite participants to actively engage in shaping this XIAxArts vision within the CHI community and beyond.

cs.HC↗

arXiv2024

Idle wage as a tool to regulate the relationship between ride-hailing platforms and drivers

Ride-hailing platforms typically classify drivers as either employees or independent contractors. These classifications tend to emphasize either wage certainty or flexibility, but rarely both. We study an alternative or complementary approach: the \textit{Idle wage,} which provides with a fixed payment drivers even when they are connected without passengers on board. We adapt a well-known economic model of the supply-demand equilibrium in ride-hailing platforms and analyse how the optimal welfare and profit change with the introduction of an idle wage when drivers are risk-averse. We show that in a single-period setting, risk aversion implies that it is optimal to pay the drivers only through an idle wage. However, if the pool of available drivers is large, even a small idle wage could attract too many drivers, rendering the system unprofitable. When the demand fluctuates throughout multiple periods, we show that if the idle wage has to be constant, then it is optimal to combine the idle wage with the traditional payment via trips, so that surge pricing influences the number of drivers connected. This illustrates a relevant trade-off: Risk-aversion favours using the idle wage to attract drivers; however, if the platform is not allowed to fully adjust the idle wage over time, there may be periods in which the idle wage cannot resolve the mismatch between supply and demand. We propose a partially flexible constraint that still makes the idle wage-only solution viable. It allows the idle wage to adapt per period, as long as it fulfills a total minimum wage requirement. Numerical simulations suggest that the idle wage policy, if properly implemented, could be beneficial for the system as a whole.

math.OC↗

arXiv2024

Learning about Data, Algorithms, and Algorithmic Justice on TikTok in Personally Meaningful Ways

TikTok, a popular short video sharing application, emerged as the dominant social media platform for young people, with a pronounced influence on how young women and people of color interact online. The application has become a global space for youth to connect with each other, offering not only entertainment but also opportunities to engage with artificial intelligence/machine learning (AI/ML)-driven recommendations and create content using AI/M-powered tools, such as generative AI filters. This provides opportunities for youth to explore and question the inner workings of these systems, their implications, and even use them to advocate for causes they are passionate about. We present different perspectives on how youth may learn in personally meaningful ways when engaging with TikTok. We discuss how youth investigate how TikTok works (considering data and algorithms), take into account issues of ethics and algorithmic justice and use their understanding of the platform to advocate for change.

cs.CY↗

arXiv2023

Reduced-order models of wall shear stress patterns in the left atrial appendage from a data-augmented atrial database

Background: Atrial fibrillation (AF) is the most common sustained cardiac arrhythmia, affecting over 1% of the population. It is usually triggered by irregular electrical impulses that cause the atria to contract irregularly and ineffectively. It increases blood stasis and the risk of thrombus formation within the left atrial appendage (LAA) and aggravates adverse atrial remodeling. Despite recent efforts, LAA flow patterns representative of AF conditions and their association with LAA stasis remain poorly characterized. Aim: To develop reduced-order data-driven models of LAA flow patterns during atrial remodeling in order to uncover flow disturbances concurrent with LAA stasis that could add granularity to clinical decision criteria. Methods: We combined a geometric data augmentation process with projection of results from 180 CFD atrial simulations on a universal LAA coordinate (ULAAC) system. The projection approach enhances data visualization and facilitates direct comparison between different anatomical and functional states. ULAAC projections were used as input for a proper orthogonal decomposition (POD) algorithm to build reduced-order models of hemodynamic metrics, extracting flow characteristics associated with AF and non-AF anatomies. Results: We verified that the ULAAC system provides an adequate representation to visualize data distributions on the LAA surface and to build POD-based reduced-order models. These models revealed significant differences in LAA flow patterns for atrial geometries that underwent adverse atrial remodeling and experienced elevated blood stasis. Together with anatomical morphing-based patient-specific data augmentation, this approach could facilitate data-driven analyses to identify flow features associated with thrombosis risk due to atrial remodeling.

physics.med-ph↗

arXiv2023

Human-AI Interactions and Societal Pitfalls

When working with generative artificial intelligence (AI), users may see productivity gains, but the AI-generated content may not match their preferences exactly. To study this effect, we introduce a Bayesian framework in which heterogeneous users choose how much information to share with the AI, facing a trade-off between output fidelity and communication cost. We show that the interplay between these individual-level decisions and AI training may lead to societal challenges. Outputs may become more homogenized, especially when the AI is trained on AI-generated content, potentially triggering a homogenization death spiral. And any AI bias may propagate to become societal bias. A solution to the homogenization and bias issues is to reduce human-AI interaction frictions and enable users to flexibly share information, leading to personalized outputs without sacrificing productivity.

cs.AI↗

arXiv2023

Electric Vehicle Fleet and Charging Infrastructure Planning

We study electric vehicle (EV) fleet and charging infrastructure planning in a spatial setting. With customer requests arriving continuously at rate $\lambda$ throughout the day, we determine the minimum number of vehicles and chargers for a target service level, along with matching and charging policies. While non-EV systems require extra $\Theta(\lambda^{2/3})$ vehicles due to pickup times, EV systems differ. Charging increases nominal capacity, enabling pickup time reductions and allowing for an extra fleet requirement of only $\Theta(\lambda^{\nu})$ for $\nu \in (1/2, 2/3]$, depending on charging infrastructure and battery pack sizes. We propose the Power-of-$d$ dispatching policy, which achieves this performance by selecting the closest vehicle with the highest battery level from $d$ options. We extend our results to accommodate time-varying demand patterns and discuss conditions for transitioning between EV and non-EV capacity planning. Extensive simulations verify our scaling results, insights, and policy effectiveness while also showing the viability of low-range, low-cost fleets.

math.OC↗

arXiv2023

Making Sense of Machine Learning: Integrating Youth's Conceptual, Creative, and Critical Understandings of AI

Understanding how youth make sense of machine learning and how learning about machine learning can be supported in and out of school is more relevant than ever before as young people interact with machine learning powered applications everyday; while connecting with friends, listening to music, playing games, or attending school. In this symposium, we present different perspectives on understanding how learners make sense of machine learning in their everyday lives, how sensemaking of machine learning can be supported in and out of school through the construction of applications, and how youth critically evaluate machine learning powered systems. We discuss how sensemaking of machine learning applications involves the development and integration of conceptual, creative, and critical understandings that are increasingly important to prepare youth to participate in the world.

cs.CY↗

arXiv2022

Power-of-$d$ Choices Load Balancing in the Sub-Halfin Whitt Regime

We consider the load balancing system under Poisson arrivals, exponential services, and homogeneous servers. Upon arrival, a job is to be routed to one of the servers, where it is queued until service. We consider the Power-of-$d$ choices routing algorithm, which chooses the queue with minimum length among $d$ randomly sampled queues. We study this system in the many-server heavy-traffic regime where the number of servers goes to infinity simultaneously when the load approaches the capacity. In particular, we consider a sequence of systems with $n$ servers and the arrival rate is given by $\lambda=n-n^{1-\gamma}$ for some $\gamma \in (0, 0.5)$, known as the sub-Halfin-Whitt regime. It was shown by [Liu Ying (2020)] that under Power-of-$d$ choices routing with $d \geq n^\gamma \log n$, the queue length behaves similarly to that of JSQ and that there are asymptotically zero queueing delays. The focus of this paper is to characterize the behavior when $d$ is below this threshold. We obtain high probability bounds on the queue lengths for various values of $d$ and large enough $n$. In particular, we show that when $d$ grows polynomially in $n$ but slower than in [Liu Ying (2020)], i.e., if $d$ is $\Theta\left((n^\gamma\log n)^{1/m})\right)$ for some integer $m>1$, then the asymptotic queue length is $m$ with high probability. Moreover, if $d$ grows polylog in $n$, i.e., slower than any polynomial, but is at least $\Omega(\log (n)^3)$, the queue length blows up to infinity asymptotically. We obtain these results by using an iterative state space collapse approach. We first establish a weak state-space collapse (SSC) on the queue lengths. Then, we bootstrap on weak SSC to iteratively narrow down the region of the collapse. After enough steps, this inductive refinement provides the bounds we seek. We establish these sequences of collapse using Lyapunov drift arguments.

math.PR↗

arXiv2022

Mechanism Design under Approximate Incentive Compatibility

A fundamental assumption in classical mechanism design is that buyers are perfect optimizers. However, in practice, buyers may be limited by their computational capabilities or a lack of information, and may not be able to perfectly optimize. This has motivated the introduction of approximate incentive compatibility (IC) as an appealing solution concept for practical mechanism design. While most of the literature focuses on the analysis of particular approximate IC mechanisms, this paper is the first to study the design of optimal mechanisms in the space of approximate IC mechanisms and to explore how much revenue can be garnered by moving from exact to approximate incentive constraints. We study the problem of a seller facing one buyer with private values and analyze optimal selling mechanisms under $\varepsilon$-incentive compatibility. We establish that the gains that can be garnered depend on the local curvature of the seller's revenue function around the optimal posted price when the buyer is a perfect optimizer. If the revenue function behaves locally like an $α$-power for $α\in (1,\infty)$, then no mechanism can garner gains higher than order $\varepsilon^{α/(2α-1)}$. This improves upon state-of-the-art results which imply maximum gains of $\varepsilon^{1/2}$ by providing the first parametric bounds that capture the impact of revenue function's curvature on revenue gains. Furthermore, we establish that an optimal mechanism needs to randomize as soon as $\varepsilon>0$ and construct a randomized mechanism that is guaranteed to achieve order $\varepsilon^{α/(2α-1)}$ additional revenues, leading to a tight characterization of the revenue implications of approximate IC constraints. Our work brings forward the need to optimize not only over allocations and payments but also over best responses, and we develop a new framework to address this challenge.

econ.TH↗

arXiv2021

Randomized FIFO Mechanisms

We study the matching of jobs to workers in a queue, e.g. a ridesharing platform dispatching drivers to pick up riders at an airport. Under FIFO dispatching, the heterogeneity in trip earnings incentivizes drivers to cherry-pick, increasing riders' waiting time for a match and resulting in a loss of efficiency and reliability. We first present the direct FIFO mechanism, which offers lower-earning trips to drivers further down the queue. The option to skip the rest of the line incentivizes drivers to accept all dispatches, but the mechanism would be considered unfair since drivers closer to the head of the queue may have lower priority for trips to certain destinations. To avoid the use of unfair dispatch rules, we introduce a family of randomized FIFO mechanisms, which send declined trips gradually down the queue in a randomized manner. We prove that a randomized FIFO mechanism achieves the first best throughput and the second best revenue in equilibrium. Extensive counterfactual simulations using data from the City of Chicago demonstrate substantial improvements of revenue and throughput, highlighting the effectiveness of using waiting times to align incentives and reduce the variability in driver earnings.

cs.GT↗

arXiv2021

Third-Degree Price Discrimination Versus Uniform Pricing

We compare the profit of the optimal third-degree price discrimination policy against a uniform pricing policy. A uniform pricing policy offers the same price to all segments of the market. Our main result establishes that for a broad class of third-degree price discrimination problems with concave profit functions (in the price space) and common support, a uniform price is guaranteed to achieve one half of the optimal monopoly profits. This profit bound holds for any number of segments and prices that the seller might use under third-degree price discrimination. We establish that these conditions are tight and that weakening either common support or concavity can lead to arbitrarily poor profit comparisons even for regular or monotone hazard rate distributions.

econ.GN↗

arXiv2021

Near Optimal Control in Ride Hailing Platforms with Strategic Servers

Motivated by applications in online marketplaces such as ride-hailing, we study how strategic servers impact the system performance. We consider a discrete-time process in which, heterogeneous types of customers and servers arrive. Each customer joins their type's queue, while servers might join a different type's queue depending on the prices posted by the system operator and an inconvenience cost. Then the system operator, constrained by a compatibility graph, decides the matching. The objective is to design an optimal control (pricing and matching scheme) to maximize the profit minus the expected waiting times. We develop a general framework that enables us to analyze a broad range of strategic behaviors. In particular, we encode servers' behavior in a properly defined \emph{cost function} that can be tailored to various settings. Using this general cost function, we introduce a novel probabilistic fluid problem. The probabilistic fluid model provides an upper bound on the achievable net profit. We then study the system under a large market regime in which the arrival rates are scaled by $η$ and present a probabilistic two-price policy and a max-weight matching policy which results in a net profit-loss of at most $O(η^{1/3})$. In addition, under a broad class of customer pricing policies, we show that any matching policy has net profit-loss of at least $Ω(η^{1/3})$. To show generality of our framework, we present multiple extensions to our model and analysis. We conclude the discussion by presenting numerical simulations comparing different cost models and analyzing performance of the proposed pricing and matching policies.

math.OC↗

arXiv2020

Matching Queues, Flexibility and Incentives

Problem definition: In many matching markets, some agents are fully flexible, while others only accept a subset of jobs. For example, ridesharing drivers can specify on the platform the destinations they are willing to accept. Conventional wisdom suggests reserving flexible agents, but this can backfire: anticipating higher matching chances, agents may misreport as specialized, reducing overall matches. We ask how platforms can design simple matching policies that remain effective when agents act strategically. Methodology/results: We model job allocation as a bipartite matching queueing system and analyze equilibrium throughput performance under different policies when agents choose which queue to join. We show that flexibility reservation is optimal under full information but can perform poorly with private information, sometimes substantially worse than random assignment. To address this, we propose a new policy -- flexibility reservation with fallback -- that guarantees robust performance across settings, without requiring precise knowledge of system parameters or agent utility functions. Managerial implications: Our results underscore the importance of accounting for strategic reporting in the design of matching policies: the proposed fallback policy both preserves flexibility and exploits latent flexibility when explicitly flexible agents are exhausted. Its simplicity and parameter-free nature also make it practical to implement in platforms such as ridesharing and affordable housing allocation.

cs.GT↗

arXiv2020

Matching Queues with Reneging: a Product Form Solution

Motivated by growing applications in two-sided markets, we study a parallel matching queue with reneging. Demand and supply units arrive to the system and are matched in an FCFS manner according to a compatibility graph specified by an N-system. If they cannot be matched upon arrival, they queue and may abandon the system as time goes by. We derive explicit product forms of the steady state distributions of this system by identifying a partial balance condition.

math.PR↗