explainable ai

FlowCF: Sparse Counterfactual Explanations for Mixed-Type Tabular Data using Flow Matching

In the field of Explainable AI (XAI), counterfactual (CF) explanations interpret a model's decision by suggesting the changes to the input that would lead to a more favourable outcome. To be useful in practice, such an explanation should change few features and change them as little as possible, properties known as spa...

From Research Gaps to Theoretical Opportunities: Theory-Oriented GenAI for Research Opportunity Evaluation

A theory-oriented agentic AI system that helps researchers identify potential theorizing opportunities by incorporating established theorizing approaches into literature exploration and evaluation and demonstrates the system through an end-to-end analysis of human oversight of agentic AI systems in organizations.

ARTIFICIAL INTELLIGENCE IN MEDICAL EDUCATION AND CLINICAL PRACTICE: A NARRATIVE REVIEW

AI delivers its greatest value when deployed as a collaborative instrument that augments rather than replaces clinical judgment, which depends on sustained investment in digital literacy, explainable systems, clinician involvement in design, and equitable institutional infrastructure.

Strategically timed UAS data acquisition for wheat yield prediction using explainable AI: A multi-year phenology-aligned study

Artificial intelligence driven framework for enhancing sustainability and resilience in communal cattle insurance in Lupane District Zimbabwe

Communal cattle farming in Sub-Saharan Africa continues to face destabilization from non-linear climate variability, yet insurance penetration remains negligible. In Lupane District, Zimbabwe, uptake is exceptionally low at approximately 0.01%, despite recurrent droughts that threaten household livelihoods. This study...

ECHO: Explainable Co-editing with Human-in-the-loop Operations for Presentation Slide Refinement

Authoring and refining presentation slides is time-consuming in academic and professional settings. Although generative AI lowers the barrier to creating initial drafts, its black-box, one-way workflow often limits fine-grained control. A formative study with 10 frequent presentation authors identified trial-and-error...

Teaching Data Cleaning in Machine Learning: A Misconception-Driven Pedagogical Framework for Explainable and Ethical Data Preprocessing

This paper proposes a four-phase instructional sequence — Motivational Grounding, Mechanism Diagnosis, Algorithm-Context Mapping, Algorithm-Context Mapping, and Explainability and Ethical Reflection — operationalized through a multi-dimensional Instructor Cleaning Strategy Matrix, embedding explainability and ethical r...

METHODS AND MODELS FOR OPTIMIZING FINANCIAL AND ADMINISTRATIVE PROCESSES THROUGH ARTIFICIAL INTELLIGENCE

The rapid development of artificial intelligence (AI), machine learning (ML), natural language processing (NLP), predictive analytics, and intelligent automation is transforming the organization of financial and administrative processes. Financial administration traditionally depends on large volumes of structured and...

A proof of a conjecture of R. Ford: semi-meanders with two mountain ranges and Euler's totient function

We prove a conjecture of R. Ford stated in 2017 in the OEIS entry A000010 (Euler's totient function): for n > 1, the number of semi-meander solutions for n whose top arches contain exactly 2 mountain ranges and exactly 2 arches of length 1 equals phi(n). In Ford's setting, the points 1, ..., 2n lie on a line, the botto...

Phonon–Photon–Spin Transduction: A First-Principles Pedagogical Derivation from Lattice Vibrations to Conditional Spin Response

This pedagogical technical note derives a connected model from a one-dimensional monoatomic lattice through acoustic phonons, strain, photoelastic refractive-index modulation, Stokes and anti-Stokes optical sidebands, and a conditional spin-population response. It explains why a realistic optical-to-spin step requires...

Causal-Reasoning World Models: Toward AI’s Subjectivity through Backward Generation

Machine learning and Voronoi-based decision boundaries for Bacterial vaginosis to determine population- specific microbial interactions.

In this study we utilize machine learning techniques to create predictive models and determine key bacterial interactions for the diagnosis of Bacterial vaginosis. Bacterial vaginosis (BV) is a common vaginal syndrome affecting reproductive-age women globally. It is associated with various adverse obstetric and gynecol...