arXiv subjects

Antonios Saravanos

Publications and source records attributed to Antonios Saravanos.

16 recordsLinked to original sources

arXiv2026

Global drivers and barriers to the public acceptance of autonomous vehicles: Evidence from 17 countries

This study investigated the public acceptance of Society of Automotive Engineers Level 3 conditionally automated cars, which can self-drive under certain specified conditions but require the human driver to remain ready to resume control when requested. Previous Unified Theory of Acceptance and Use of Technology 2 (UTAUT2)-based research has focused mainly on European samples, and so it is still unclear whether the same factors shape acceptance across broader world regions. This knowledge gap was addressed using the L3Pilot Global User Acceptance Survey. From an original dataset of 18,631 respondents, the final analytic sample comprised 18,603 respondents from 17 countries across Africa, Asia, Europe, North America, and South America. The data were analyzed using a UTAUT2-based structural equation model to examine how performance expectancy, effort expectancy, social influence, facilitating conditions, and hedonic motivation shape the intention to use Level 3 cars. The model showed strong explanatory power. Across the analytic sample, the intention to use Level 3 cars was driven mainly by performance expectancy, social influence, and hedonic motivation. Effort expectancy and facilitating conditions also contributed, but they played smaller direct roles. Age, gender, and previous experience with advanced driver assistance systems were statistically significant, but comparatively weak predictors. Overall, the findings suggest that the acceptance of Level 3 automated cars depends less on demographic characteristics or ease-of-use concerns and more on whether people see the technology as useful, socially supported, and enjoyable to use.

cs.ET↗

arXiv2026

Three Roles, One Model: Role Orchestration at Inference Time to Close the Performance Gap Between Small and Large Agents

Large language model (LLM) agents show promise on realistic tool-use tasks, but deploying capable agents on modest hardware remains challenging. We study whether inference-time scaffolding alone, without any additional training compute, can improve the performance of a small model in complex multi-step environments. Operating on a single 24GB GPU, we evaluate Qwen3-8B on the AppWorld benchmark under both full-precision and 4-bit quantized configurations. Without any intervention, the raw model achieves just 5.4% (FP16) and 3.0% (AWQ) task goal completion. Guided by a systematic failure mode analysis, we introduce a three-tier inference scaffolding pipeline that deploys the same frozen model in three distinct roles: (1) a summarization model that preserves critical artifacts (tokens, credentials, API responses) while compressing dialogue history; (2) the main agent model that reasons over the compressed context; and (3) an isolated correction model that reviews and revises the agent's code output without access to conversation history, breaking repetitive failure loops. Applied to the same unmodified model, this scaffolding yields 8.9% (FP16) and 5.9% (AWQ) task goal completion, roughly doubling performance in both settings, with particularly strong gains on difficulty-1 tasks (15.8% to 26.3% FP16; 5.3% to 14.0% AWQ). On full-precision inference, our scaffolded 8B model surpasses DeepSeek-Coder 33B Instruct (7.1%) from the original AppWorld evaluation, demonstrating that structured inference-time interventions can make small models competitive with systems 4 times their size. We formalize the approach as a scaffolded policy over a frozen base model, three invocations of the same weights with different conditioning, drawing connections to test-time compute scaling and action-space shaping in reinforcement learning.

cs.AI↗

arXiv2026

Hidden Dynamics of Massive Activations in Transformer Training

We present the first comprehensive analysis of massive activation development throughout transformer training, using the Pythia model family as our testbed, and release our full dataset publicly to support further research. Through systematic analysis of various model sizes across multiple training checkpoints, we demonstrate that massive activation emergence follows highly predictable mathematical patterns that can be accurately modeled using an exponentially-modulated logarithmic function with five key parameters. Additionally, We develop a machine learning framework to predict these mathematical parameters from architectural specifications alone, achieving high accuracy for steady-state behavior and moderate accuracy for emergence timing and magnitude. These findings enable architects to predict and potentially control key aspects of massive activation emergence through design choices, with significant implications for model stability, training cycle length, interpretability, and optimization. Our findings demonstrate that the emergence of massive activations is governed by model design and can be anticipated, and potentially controlled, before training begins. Code is available at https://github.com/Aimpoint-Digital/massive-activations-fork

cs.AI↗

arXiv2026

The Opaque Pointer Design Pattern in Python: Towards a Pythonic PIMPL for Modularity, Encapsulation, and Stability

Python libraries often need to maintain a stable public API even as internal implementations evolve, gain new backends, or depend on heavy optional libraries. In Python, where internal objects are easy to inspect and import, users can come to rely on "reachable internals" that were never intended to be public, making refactoring risky and slowing long-term maintenance. This paper revisits the pointer-to-implementation (PIMPL) idiom from C++ and reinterprets it as a Pythonic pattern of opaque delegation: a small public object (or module) that delegates its behavior to a separate implementation object treated as internal. We situate this pattern within a broader taxonomy of encapsulation techniques in Python, relate it to existing practices such as module-level indirection, facade objects, and backend dispatch, and identify PIMPL-like structures already used in the standard library and the scientific Python ecosystem. We then show how a Pythonic PIMPL can be used in existing codebases to isolate heavy dependencies, support lazy imports, and enable runtime selection of alternative backends without changing the public API. Finally, we discuss the benefits and trade-offs of the approach and offer practical guidance on when the pattern is appropriate and how to apply it in large, long-lived Python libraries.

cs.SE↗

arXiv2025

How Warm-Glow Alters the Usability of Technology

As technology increasingly aligns with users' personal values, traditional models of usability, focused on functionality and specifically effectiveness, efficiency, and satisfaction, may not fully capture how people perceive and evaluate it. This study investigates how the warm-glow phenomenon, the positive feeling associated with doing good, shapes perceived usability. An experimental approach was taken in which participants evaluated a hypothetical technology under conditions designed to evoke either the intrinsic (i.e., personal fulfillment) or extrinsic (i.e., social recognition) dimensions of warm-glow. A Multivariate Analysis of Variance as well as subsequent follow-up analyses revealed that intrinsic warm-glow significantly enhances all dimensions of perceived usability, while extrinsic warm-glow selectively influences perceived effectiveness and satisfaction. These findings suggest that perceptions of usability extend beyond functionality and are shaped by how technology resonates with users' broader sense of purpose. We conclude by proposing that designers consider incorporating warm-glow into technology as a strategic design decision.

cs.HC↗

arXiv2025

Waterfall Model Simulation: A Systematic Mapping Study

This paper systematically maps peer-reviewed research and graduate theses/dissertations that explicitly simulate the waterfall model. Following Petersen's mapping guidelines and Kitchenham's systematic literature review practices, major databases (ACM Digital Library, IEEE Xplore, Scopus, Springer, Google Scholar, and Web of Science) were searched for studies published between 2000-2024 using the title query ("simulation" OR "simulating") AND "waterfall". A PRISMA workflow guided the screening process, and approximately 9% of retrieved records met the inclusion criteria. A repeated extraction process captured methods, tools, venues, geography, publication years, comparative scope, and fidelity to Royce's original model; findings were synthesized thematically. Discrete-event simulation dominates (80%) compared to system dynamics (20%). Reported tools center on Simphony.NET (40%) and SimPy (20%), while 40% of studies omit tool details, limiting reproducibility. Research is distributed across Italy, Lebanon, India, Japan, and the United States; publication venues include 60% journals and 40% conferences. Sixty percent of studies are comparative, while 40% model only the waterfall approach. No study reproduces Royce's original model; all employ adaptations. The paper concludes by presenting a consolidated view of waterfall simulation research and recommending clearer model reporting, fuller tool disclosure, and wider adoption of open-source platforms.

cs.SE↗

arXiv2025

A Brief History of the Waterfall Model: Past, Present, and Future

The waterfall model, one of the earliest software development methodologies, has played a foundational role in shaping contemporary software engineering practices. This paper provides a historical and critical overview of the model, tracing its conceptual origins in software engineering, its formalization by Royce, and its evolution through decades of industry adoption and critique. Although often criticized for its rigidity, shortcomings, and high failure rates, the waterfall model persists in specific domains. Its principles continue to influence contemporary hybrid development frameworks that combine traditional and agile methods. Drawing on a range of scholarly sources, this study synthesizes key developments in the perception and application of the waterfall model. The analysis highlights how the model has shifted from a standalone framework to a component within modern hybrid methodologies. By revisiting its origins, assessing its present utility, and examining its role in contemporary development practices, this paper argues that the waterfall model remains relevant, not as a relic of the past but as part of context-aware development strategies. The paper contends that the model's enduring relevance lies in its adaptability. By recognizing both its limitations and its strengths, and by understanding its integration within hybrid approaches, practitioners can make more informed decisions about methodology selection and process design in diverse development environments.

cs.SE↗

arXiv2025

The Effect of Warm-Glow on User Behavioral Intention to Adopt Technology: Extending the UTAUT2 Model

In this study, we enhance the Unified Theory of Acceptance and Use of Technology (UTAUT2) by incorporating the warm-glow phenomenon to clarify its impact on user decisions regarding the adoption of technology. We introduce two additional constructs aimed at capturing both the external and internal aspects of warm-glow, thus creating what we refer to as the UTAUT2 + WG model. To evaluate the effectiveness of our model, we conducted an experimental study in which participants were presented with a scenario describing a hypothetical technology designed to evoke warm-glow sensations. Using the partial least squares method, we analyzed the collected data to assess our expanded model. Our findings indicate that warm-glow significantly influences user behavior, with the internal aspect having the strongest influence, followed by hedonic motivation, performance expectancy, and finally the external aspect of warm-glow. We conclude by discussing the implications of our research, acknowledging its limitations, and suggesting directions for future exploration.

cs.HC↗

arXiv2024

Gauging Public Acceptance of Conditionally Automated Vehicles in the United States

Public acceptance of conditionally automated vehicles is a crucial step in the realization of smart cities. Prior research in Europe has shown that the factors of hedonic motivation, social influence, and performance expectancy, in decreasing order of importance, influence acceptance. Moreover, a generally positive acceptance of the technology was reported. However, there is a lack of information regarding the public acceptance of conditionally automated vehicles in the United States. In this study, we carried out a web-based experiment where participants were provided information regarding the technology and then completed a questionnaire on their perceptions. The collected data was analyzed using PLS-SEM to examine the factors that may lead to public acceptance of the technology in the United States. Our findings showed that social influence, performance expectancy, effort expectancy, hedonic motivation, and facilitating conditions determine conditionally automated vehicle acceptance. Additionally, certain factors were found to influence the perception of how useful the technology is, the effort required to use it, and the facilitating conditions for its use. By integrating the insights gained from this study, stakeholders can better facilitate the adoption of autonomous vehicle technology, contributing to safer, more efficient, and user-friendly transportation systems in the future that help realize the vision of the smart city.

cs.CY↗

arXiv2023

Simulating the Software Development Lifecycle: The Waterfall Model

This study employs a simulation-based approach, adapting the waterfall model, to provide estimates for software project and individual phase completion times. Additionally, it pinpoints potential efficiency issues stemming from suboptimal resource levels. We implement our software development lifecycle simulation using SimPy, a Python discrete-event simulation framework. Our model is executed within the context of a software house on 100 projects of varying sizes examining two scenarios. The first provides insight based on an initial set of resources, which reveals the presence of resource bottlenecks, particularly a shortage of programmers for the implementation phase. The second scenario uses a level of resources that would achieve zero-wait time, identified using a stepwise algorithm. The findings illustrate the advantage of using simulations as a safe and effective way to experiment and plan for software development projects. Such simulations allow those managing software development projects to make accurate, evidence-based projections as to phase and project completion times as well as explore the interplay with resources.

cs.SE↗

arXiv2022

Reputation, Risk, and Trust on User Adoption of Internet Search Engines: The Case of DuckDuckGo

This paper investigates the determinants of end-user adoption of the DuckDuckGo search engine coupling the standard UTAUT model with factors to reflect reputation, risk, and trust. An experimental approach was taken to validate our model, where participants were exposed to the DuckDuckGo product using a vignette. Subsequently, answering questions on their perception of the technology. The data was analyzed using the partial least squares-structural equation modeling (PLS-SEM) approach. From the nine distinct factors studied, we found that 'Performance Expectancy' played the greatest role in user decisions on adoption, followed by 'Firm Reputation', 'Initial Trust in Technology', 'Social Influence', and an individual's 'Disposition to Trust'. We conclude by exploring how these findings can explain DuckDuckGo's rising prominence as a search engine.

cs.CR↗

arXiv2022

Investigating End-user Acceptance of Last-mile Delivery by Autonomous Vehicles in the United States

This paper investigates the end-user acceptance of last-mile delivery carried out by autonomous vehicles within the United States. A total of 296 participants were presented with information on this technology and then asked to complete a questionnaire on their perceptions to gauge their behavioral intention concerning acceptance. Structural equation modeling of the partial least squares flavor (PLS-SEM) was employed to analyze the collected data. The results indicated that the perceived usefulness of the technology played the greatest role in end-user acceptance decisions, followed by the influence of others, and then the enjoyment received by interacting with the technology. Furthermore, the perception of risk associated with using autonomous delivery vehicles for last-mile delivery led to a decrease in acceptance. However, most participants did not perceive the use of this technology to be risky. The paper concludes by summarizing the implications our findings have on the respective stakeholders and proposing the next steps in this area of research.

cs.CY↗

arXiv2022

Extending the Technology Acceptance Model 3 to Incorporate the Phenomenon of Warm-Glow

In this paper, we extend the third evolution of the Technology Acceptance Model (TAM3) to incorporate warm-glow with the aim of understanding the role this phenomenon plays on user adoption decisions. Warm-glow is the feeling of satisfaction or pleasure (or both) that is experienced by individuals after they do something "good" for their fellow human. Two constructs - perceived extrinsic warm-glow (PEWG) and perceived intrinsic warm-glow (PIWG) - were incorporated into the TAM3 model to measure the two dimensions of user-experienced warm-glow, forming what we refer to as the TAM3 + WG model. An experimental approach was taken to evaluate the suitability of the proposed model (i.e., TAM3 + WG). A vignette was created to present users with a hypothetical technology designed to evoke warm-glow in participants. Our TAM3 + WG model was found to be superior in terms of fit to the TAM3 model. Furthermore, the PEWG and PIWG constructs were confirmed to be unique within the original TAM3 model. The findings indicate that the factors that have the greatest influence on consumer decisions are (in decreasing order) perceived usefulness (PU), PIWG, subjective norm (SN), and PEWG. Additionally, a higher PEWG resulted in the technology being perceived as more useful. In other words, both extrinsic and intrinsic warm-glow play a prominent role in user decisions as to whether or not to adopt a particular technology.

cs.CY↗

arXiv2022

Measuring Consumer Perceived Warm-Glow for Technology Adoption Modeling

In this paper, we adapt and validate two constructs-perceived extrinsic warm-glow (PEWG) and perceived intrinsic warm-glow (PIWG)-to measure the two dimensions of consumer perceived warm-glow (i.e., extrinsic and intrinsic) for use with the practice of technology adoption modeling. Taking an experimental approach, participants were exposed to one of four vignettes designed to simulate either the absence or the presence of warm-glow (specifically, extrinsic warm-glow, intrinsic warm-glow, and concurrently extrinsic and intrinsic warm-glow). The results revealed that both constructs measured their respective forms of warm-glow with two caveats. Firstly, singularly trying to evoke extrinsic warm-glow led to only a slight increase in consumer perception of extrinsic warm-glow. We attributed this finding to individuals not being attracted to technology products that overtly target and seek to satisfy their vanity, instead preferring technology that does so in a more subtle way. The second is that singularly trying to evoke intrinsic warm-glow also resulted in the manifestation of extrinsic warm-glow. Thus, warm-glow appears as a blend of extrinsic and intrinsic dimensions. This finding serves to reinforce what has already been reported in existing literature regarding warm-glow and the idea of impure altruism.

cs.CY↗

arXiv2021

Exploring the Effect of Resolution on the Usability of Locimetric Authentication

Locimetric authentication is a form of graphical authentication in which users validate their identity by selecting predetermined points on a predetermined image. Its primary advantage over the ubiquitous text-based approach stems from users' superior ability to remember visual information over textual information, coupled with the authentication process being transformed to one requiring recognition (instead of recall). Ideally, these differentiations enable users to create more complex passwords, which theoretically are more secure. Yet locimetric authentication has one significant weakness: hot-spots. This term refers to areas of an image that users gravitate towards, and which consequently have a higher probability of being selected. Although many strategies have been proposed to counter the hot-spot problem, one area that has received little attention is that of resolution. The hypothesis here is that high-resolution images would afford the user a larger password space, and consequently any hot-spots would dissipate. We employ an experimental approach, where users generate a series of locimetric passwords on either low- or high-resolution images. Our research reveals the presence of hot-spots even in high-resolution images, albeit at a lower level than that exhibited with low-resolution images. We conclude by reinforcing that other techniques - such as existing or new software controls or training - need to be utilized to mitigate the emergence of hot-spots with the locimetric scheme.

cs.CR↗

arXiv2021

The Hidden Cost of Using Amazon Mechanical Turk for Research

In this study, we investigate the attentiveness exhibited by participants sourced through Amazon Mechanical Turk (MTurk), thereby discovering a significant level of inattentiveness amongst the platform's top crowd workers (those classified as 'Master', with an 'Approval Rate' of 98% or more, and a 'Number of HITS approved' value of 1,000 or more). A total of 564 individuals from the United States participated in our experiment. They were asked to read a vignette outlining one of four hypothetical technology products and then complete a related survey. Three forms of attention check (logic, honesty, and time) were used to assess attentiveness. Through this experiment we determined that a total of 126 (22.3%) participants failed at least one of the three forms of attention check, with most (94) failing the honesty check - followed by the logic check (31), and the time check (27). Thus, we established that significant levels of inattentiveness exist even among the most elite MTurk workers. The study concludes by reaffirming the need for multiple forms of carefully crafted attention checks, irrespective of whether participant quality is presumed to be high according to MTurk criteria such as 'Master', 'Approval Rate', and 'Number of HITS approved'. Furthermore, we propose that researchers adjust their proposals to account for the effort and costs required to address participant inattentiveness.

cs.HC↗