Negative / Null Result ReportOpen accessComputer Science
Ali Raza, Fareeha Hanif, Heba Abdelgader Mohammed · 2026 · Scientific Reports
Lung cancer remains one of the leading causes of cancer-related mortality worldwide, and accurate early diagnosis plays a critical role in improving patient survival. In this study, a comparative analysis of multiple lightweight Convolutional Neural Network (CNN) variants is presented for multi-class lung cancer classification using histopathological images. Four CNN architectures were designed to systematically explore the trade-off between model complexity and classification performance. Each variant was trained and evaluated within a unified experimental framework incorporating data augment
View details →Negative / Null Result ReportOpen accessComputer Science
Dunigan Parker Folk, Elizabeth Dunn · 2026 · Psychological Science
Advances in AI have enabled chatbots to provide warm, personalized support. Yet little is known about the long-term consequences of AI companionship. Across a 12-month longitudinal study with more than 2,000 adults from four Western…
View details →Negative / Null Result ReportOpen accessComputer Science
Joshua D Wenger, C. Daryl Cameron, Michael Inzlicht · 2026 · Communications Psychology
Recent advances in AI have enabled large language models to produce expressions that seem empathetic to human users, raising scientific and ethical questions about how people perceive and choose between human and AI sources of emotional support. Although an increasing number of studies have examined how people rate empathy generated by AI, little to no work has examined whether people would choose to receive empathy from AI. We conducted four studies investigating whether people prefer to receive empathetic expressions from humans or AI, and how they evaluate these expressions. Across diverse
View details →Negative / Null Result ReportOpen accessComputer Science
Mohammadreza Farrokhnia, Saeed Latifi, Pantelis M. Papadopoulos et al. · 2026 · International Journal of Educational Technology in Higher Education
Abstract Providing high-quality feedback on student writing is essential yet increasingly difficult due to rising class sizes and limited instructional capacity. Generative AI (GenAI) offers a promising and scalable alternative, but its effectiveness compared to traditional teacher feedback, particularly across different prompting techniques, remains uncertain. This study employed a quantitative, randomized three-group experimental design with 70 graduate students to compare the effects of teacher feedback and GenAI feedback generated using two prompting techniques: Zero-shot and chain-of-thou
View details →Negative / Null Result ReportOpen accessComputer Science
Ramteja Sajja, Yusuf Sermet, Brian Fodale et al. · 2026 · Scientific Reports
As generative AI becomes increasingly integrated into higher education, understanding how students engage with these technologies is essential for responsible adoption. This study evaluates the Educational AI Hub, an AI-powered learning…
View details →Negative / Null Result ReportComputer Science
Pertti Vakkari · 2011 · Online Information Review
Purpose This paper seeks to evaluate to what extent Google retrieved correct answers to queries inferred from factual and topical requests in a digital Ask‐a‐Librarian service. Design/methodology/approach In total, 100 factual and 100…
View details →Negative / Null Result ReportOpen accessComputer Science
Alex Cloud, Minh Le, James Chua et al. · 2026 · Nature
. Here we show that distillation can lead to subliminal learning-the transmission of behavioural traits through semantically unrelated data. In our main experiments, a 'teacher' model with some trait T (such as disproportionately generating responses favouring owls or showing broad misaligned behaviour) generates datasets consisting solely of number sequences. Remarkably, a 'student' model trained on these data learns T, even when references to T are rigorously removed. More realistically, we observe the same effect when the teacher generates math reasoning traces or code. The effect occurs on
View details →Negative / Null Result ReportOpen accessComputer Science
Sebastian Schorcht, Fabian Anton Müller, Nils Frederik Buchholtz · 2026 · ZDM
Abstract Large Language Models (LLMs) are increasingly discussed as tools for supporting mathematical problem solving. However, existing research predominantly evaluates LLM performance in terms of correctness, while the mathematics educational quality of AI-generated worked-out solutions remains largely unexplored. This study investigates how the mathematics educational quality (a set of quality criteria relating to teaching and learning mathematics) of AI-generated problem solutions can be influenced by model choice and prompt engineering. Four LLMs (Gemini 1.5 Pro (Advanced), Claude 3.5 Son
View details →Negative / Null Result ReportOpen accessComputer Science
Prabha M. Kumarage, Mirka Saarela · 2026 · AI
Generative Artificial Intelligence (GenAI) models produce increasingly sophisticated outputs, yet their underlying mechanisms remain opaque. To clarify how explainability is conceptualized and implemented in GenAI research, this two-stage review systematically examined 261 articles retrieved from six major databases. After removing duplicates and applying predefined inclusion criteria, 63 articles were retained for full analysis. In the first stage, an umbrella review synthesized insights from 18 review papers to identify prevailing frameworks, strategies, and conceptual challenges surrounding
View details →Negative / Null Result ReportOpen accessComputer Science
Mohammadreza Kamsari, Soroush Sadeghi, Gabriel Gomes de Oliveira et al. · 2025 · Scientific Reports
This study conducts a comprehensive analysis of various configurations of the UNet + ConvNeXt Tiny architecture for breast tumor segmentation. We assess the influence of data augmentation, skip connections, attention mechanisms, and…
View details →Negative / Null Result ReportOpen accessComputer Science
Christian Basil Omeh, Musa Adekunle Ayanwale, Lindelani Mnguni et al. · 2025 · Journal of New Approaches in Educational Research
Abstract Despite the increasing emphasis on computational literacy in higher education, we observed that many undergraduate students particularly in developing contexts struggle to master fundamental programming skills and develop critical thinking. Conventional instructional approaches often lack interactivity and personalized scaffolding, which are essential for teaching abstract programming concepts. In response to this challenge, we examined the effect of artificial intelligence (AI)-assisted problem-based learning (PBL) on students’ programming skills, critical thinking, and problem-solvi
View details →Negative / Null Result ReportOpen accessComputer Science
Eisha Hassan, Fazila‐Tun‐Nesa Malik, Qazi Waqas Khan et al. · 2025 · IEEE Access
Document Clustering has attracted the interest of many researchers who have created several solutions to this problem by combining different techniques, models, and algorithms. While famous for its simplicity, the most commonly used algorithm, K-Means, suffers from issues such as finding the optimal value for k and random initialization of the centroids. In this paper, we propose a hybrid methodology combining K-Means++ with the metaheuristic algorithm PSO to overcome the challenges of both these algorithms. K-Means++ is a smart initialization technique that selects clusters based on probabili
View details →Negative / Null Result ReportOpen accessComputer Science
Chrysanthi Melanou, Maik Beege · 2026 · Education Sciences
Generative artificial intelligence (AI) is increasingly used in higher education as an interactive tutoring partner rather than a passive information tool. While AI offers opportunities to support learning, concerns remain regarding cognitive offloading, reduced engagement, and unreflective use. Although instructional scaffolding is a well-established design principle for supporting complex learning, its role in shaping cognitive and metacognitive processes in AI-supported settings remains underexplored. This quasi-experimental pre–post study examined how varying levels of scaffolding influenc
View details →Negative / Null Result ReportOpen accessComputer Science
Sterling Williams-Ceci, Maurice Jakesch, Advait Bhat et al. · 2026 · Science Advances
Artificial intelligence (AI) writing assistants powered by large language models (LLMs) are increasingly used to make autocomplete suggestions to people as they write text. Can these AI writing assistants affect people’s attitudes in this…
View details →Negative / Null Result ReportOpen accessComputer Science
Muhammad Dawood, Kim Branson, Sabine Tejpar et al. · 2026 · Nature Biomedical Engineering
Deep learning models that infer clinically relevant biomarker status from tissue images are being explored as rapid and low-cost alternatives to molecular testing. Here we show, through statistical analysis across multiple cancer types, datasets and modelling approaches, that the datasets used to train these models contain strong dependencies between biomarkers and clinicopathological features, which prevent models from isolating the effect of a single biomarker and lead them to learn confounded signals. Consequently, their prediction accuracy varies substantially with the status of codependen
View details →Negative / Null Result ReportOpen accessComputer Science
Andrea Espis, Chiara Marzi, Stefano Diciotti · 2025 · Scientific Reports
Self-supervised learning (SSL) in computer vision has shown its potential to reduce reliance on labeled data. However, most studies focused on balanced, large, broad-domain datasets like ImageNet, whereas, in real-world medical applications, dataset size is typically limited. This study compares the performance of SSL versus supervised learning (SL) on small, imbalanced medical imaging datasets. We experimented with four binary classification tasks: age prediction and diagnosis of Alzheimer's disease from brain magnetic resonance imaging scans, pneumonia from chest radiograms, and retinal dise
View details →Negative / Null Result ReportOpen accessComputer Science
M. Said Doğru, Emily Faulconer · 2025 · Research in Science Education
Abstract The emergence of ChatGPT brings an opportunity to lighten the workload of in-person teaching assistance in science laboratory courses. We investigated the use of the language model developed by OpenAI as a virtual teaching assistant for an introductory undergraduate biology laboratory course. Student-generated questions related to a laboratory exercise on enzyme activity were separately provided to ChatGPT and a cohort of graduate teaching assistants (TAs). Responses were evaluated for content accuracy and teaching effectiveness. Results revealed that human TAs were more accurate in t
View details →Negative / Null Result ReportComputer Science
Simon Holmbacka, Robert Müller · 2017
Current benchmark suites for evaluating energy efficiency of modern computer systems fail to replicate real-world streaming applications accurately enough because of indeterministic load pattern which depends heavily on the input data of…
View details →Negative / Null Result ReportOpen accessComputer Science
Michael Vaccaro, Mikayla Friday, Arash E. Zaghi · 2025 · Applied Sciences
Multi-agent large language models promise flexible, modular architectures for delivering personalized educational content. Drawing on a pilot randomized controlled trial with middle school students (n = 23), we introduce a two-agent GPT-4 framework in which a Profiler agent infers learner-specific preferences and a Rewrite agent dynamically adapts science passages via an explicit message-passing protocol. We implement structured system and user prompts as inter-agent communication schemas to enable real-time content adaptation. The results of an ordinal logistic regression analysis hinted that
View details →Negative / Null Result ReportOpen accessComputer Science
Tristan Piater, Niklas Penzel, Gideon Stein et al. · 2024 · arXiv
A substantial body of research has focused on developing systems that assist medical professionals during labor-intensive early screening processes, many based on convolutional deep-learning architectures. Recently, multiple studies explored the application of so-called self-attention mechanisms in the vision domain. These studies often report empirical improvements over fully convolutional approaches on various datasets and tasks. To evaluate this trend for medical imaging, we extend two widely adopted convolutional architectures with different self-attention variants on two different medical
View details →Negative / Null Result ReportOpen accessComputer Science
J. X. Lu, Shibaji Roy, Zhao-Long Wang et al. · 2007 · arXiv
Following \cite{Bai:2006vv} we here consider the supergravity solutions representing the charged non-supersymmetric $p$-brane (for $1\leq p \leq 6$) intersecting with chargeless non-supersymmetric 1-brane and 0-brane of type II string theories. We show how these solutions nicely interpolate between black $p$-branes and the Kaluza-Klein "bubble of nothing" (BON) by continuously varying some parameters characterizing the solutions from one set of values to another. By performing a time symmetric general bubble initial data analysis, we show that the interpolation implies a possible transition fr
View details →Negative / Null Result ReportOpen accessComputer Science
Joao V. C. Evangelista, Georges Kaddoum, Zeeshan Sattar · 2021 · arXiv
5G cellular networks are designed to support a new range of applications not supported by previous standards. Among these, ultra-reliable low-latency communication (URLLC) applications are arguably the most challenging. URLLC service requires the user equipment (UE) to be able to transmit its data under strict latency constraints with high reliability. To address these requirements, new technologies, such as mini-slots, semi-persistent scheduling and grant-free access were introduced in 5G standards. In this work, we formulate a spatiotemporal mathematical model to evaluate the user-plane late
View details →Negative / Null Result ReportOpen accessComputer Science
Thorsten Brants · 1995 · arXiv
A technique for reducing a tagset used for n-gram part-of-speech disambiguation is introduced and evaluated in an experiment. The technique ensures that all information that is provided by the original tagset can be restored from the reduced one. This is crucial, since we are interested in the linguistically motivated tags for part-of-speech disambiguation. The reduced tagset needs fewer parameters for its statistical model and allows more accurate parameter estimation. Additionally, there is a slight but not significant improvement of tagging accuracy.
View details →Negative / Null Result ReportOpen accessComputer Science
Shamima Mithun, Leila Kosseim · 2017 · arXiv
The work presented in this paper attempts to evaluate and quantify the use of discourse relations in the context of blog summarization and compare their use to more traditional and factual texts. Specifically, we measured the usefulness of 6 discourse relations - namely comparison, contingency, illustration, attribution, topic-opinion, and attributive for the task of text summarization from blogs. We have evaluated the effect of each relation using the TAC 2008 opinion summarization dataset and compared them with the results with the DUC 2007 dataset. The results show that in both textual genr
View details →Negative / Null Result ReportOpen accessComputer Science
Zhifei Dou, Shabnam Hassani, Ou Wei · 2026 · arXiv
Flowcharts are widely used in industrial requirements, but usually remain embedded as static images. Vision Language Models (VLMs) show promise in the conversion of these flowcharts into machine-readable models for RE activities, yet, when directly applied to flowchart conversion, they often fail on topology-critical visual details. To address this, we propose EdgeFlow that augments a VLM's original input with a deterministically extracted Canny edge map-acting as a structural prior-to improve flowchart-to-Mermaid conversion, without requiring annotated training data or domain-specific model f
View details →Negative / Null Result ReportOpen accessComputer Science
Yibo Wang, Yuanyuan Mao, Lik-Hang Lee et al. · 2024 · arXiv
The AR 3D book has shown significant potential in enhancing students' learning outcomes. However, the creation process of 3D books requires a significant investment of time, effort, and specialized skills. Thus, in this paper, we first conduct a three-day workshop investigating how AI can support the automated creation of 3D books. Informed by the design insights derived from the workshop, we developed Metabook, a system that enables even novice users to create 3D books from text automatically. To our knowledge, Metabook is the first system to offer end-to-end 3D book generation. A follow-up s
View details →Negative / Null Result ReportOpen accessComputer Science
Mandar Patil, Pankaj S. Joshi, Masashi Kimura et al. · 2011 · arXiv
We explore the Reissner-Nordström naked singularities with a charge $Q$ larger than its mass $M$ from the perspective of the particle acceleration. We first consider a collision between two test particles following the radial geodesics in the Reissner-Nordström naked singular geometry. An initially radially ingoing particle turns back due to the repulsive effect of gravity in the vicinity of naked singularity. Such a particle then collides with an another radially ingoing particle. We show that the center of mass energy of collision taking place at $r \approx M$ is unbound, in the limit where
View details →Negative / Null Result ReportOpen accessComputer Science
Seyed Amir Kasaei, Arash Marioriyad, Mahbod Khaleti et al. · 2026 · arXiv
Large Vision-Language Models (LVLMs) have achieved remarkable proficiency in explicit visual recognition, effectively describing what is directly visible in an image. However, a critical cognitive gap emerges when the visual input serves only as a clue rather than the answer. We identify that current models struggle with the complex, multi-step reasoning required to solve problems where information is not explicitly depicted. Successfully solving a rebus puzzle requires a distinct cognitive workflow: the model must extract visual and textual attributes, retrieve linguistic prior knowledge (suc
View details →Negative / Null Result ReportOpen accessComputer Science
Keith Harrigian, Tina Tang, Anthony Gonzales et al. · 2023 · arXiv
Diabetic eye disease is a major cause of blindness worldwide. The ability to monitor relevant clinical trajectories and detect lapses in care is critical to managing the disease and preventing blindness. Alas, much of the information necessary to support these goals is found only in the free text of the electronic medical record. To fill this information gap, we introduce a system for extracting evidence from clinical text of 19 clinical concepts related to diabetic eye disease and inferring relevant attributes for each. In developing this ophthalmology phenotyping system, we are also afforded
View details →Negative / Null Result ReportOpen accessComputer Science
Harsh Deshpande, Kushal Chawla, Sangwoo Cho et al. · 2026 · arXiv
Production agentic systems routinely face evolving constraints and must comply from the very next interaction. Scenarios like a tool-call notification changing a compliance threshold or a policy update adding disclosure requirements fit this criteria, having close to no room for errors in production. This proactive adaptation setting is common in deployment, but absent from current benchmarks, which assume either static constraint sets or reactive protocols with evaluation feedback. We introduce RECAP, a benchmark that measures continual-learning phenomena (forgetting, regression, forward tran
View details →