Skip to content

Category

explainable ai

2,181 papers

#explainable ai Open access Oct 2026

AI Safety Measures Are Advancing: The Policy–User Gap in Autonomous AI Governance and Operational Control

As AI providers introduce new capabilities and safety controls, what must businesses and individual users change in their own operations? This conceptual paper examines the Policy–User Gap: the distance between provider-side changes and users’ practical ability to understand those changes, reassess their workflows and...

Masaki Hoshino · 0 citations
#explainable ai Open access Oct 2026

PV-PP FRAMEWORK GETTING STARTED V2.1 PRODUCTIVE VALUE–PRODUCTIVE POWER (PV-PP)

About This Book This is the shortest way into the Productive Value–Productive Power (PV-PP) runtime. It explains what the PV-PP framework is and what the runtime does, recommends building with an AI assistant, shows how to install and verify the runtime, and then builds one small application, a battery-powered sensor,...

Lance Amundsen · 0 citations
#explainable ai Open access Oct 2026

Data Management Plan — Strategic Decision-Making and Optimization: Empowering SMEs with Data-Driven Systems for Resilience and Digital Competitiveness

Data management plan for an industrial doctorate on evaluative AI for strategic decision-making in SMEs, produced with CORA.eiNa DMP (CSUC) using the UOC doctoral-student template. It is maintained as a living document, revised when the facts change rather than filed once. The plan covers data collection from public UK...

Gines Molina-Abril · 0 citations
#explainable ai Open access Oct 2026

AI Safety Measures Are Advancing: The Policy–User Gap in Autonomous AI Governance and Operational Control

As AI providers introduce new capabilities and safety controls, what must businesses and individual users change in their own operations? This conceptual paper examines the Policy–User Gap: the distance between provider-side changes and users’ practical ability to understand those changes, reassess their workflows and...

Masaki Hoshino · 0 citations
#explainable ai Open access Oct 2026

Scientific Computing Verification Stack

Documentation-only R3 addendum to Scientific Computing Verification Stack R2 (https://doi.org/10.5281/zenodo.22861401). The new PDF walks through four distinct questions in the finite R15 Maxwell sequence: measured source-problem refinement, the separately reported conforming R5 spectral comparator, failure of the hist...

Riccardo Giudici · 0 citations
#explainable ai Open access Oct 2026

Data Management Plan — Strategic Decision-Making and Optimization: Empowering SMEs with Data-Driven Systems for Resilience and Digital Competitiveness

Data management plan for an industrial doctorate on evaluative AI for strategic decision-making in SMEs, produced with CORA.eiNa DMP (CSUC) using the UOC doctoral-student template. It is maintained as a living document, revised when the facts change rather than filed once. The plan covers data collection from public UK...

Gines Molina-Abril · 0 citations
#explainable ai Open access Oct 2026

AI Is the Junior Employee: Training AI Can Also Train Humans through On-the-Job Training and Operational Governance

As AI takes over tasks traditionally assigned to junior employees, how can organizations preserve opportunities for people to develop professional judgment? This conceptual paper proposes treating AI as a junior employee and designing its on-the-job training (OJT) as an opportunity for human development. AI mistakes ca...

Masaki Hoshino · 0 citations
#explainable ai Open access Oct 2026

Scientific Computing Verification Stack

Documentation-only R3 addendum to Scientific Computing Verification Stack R2 (https://doi.org/10.5281/zenodo.22861401). The new PDF walks through four distinct questions in the finite R15 Maxwell sequence: measured source-problem refinement, the separately reported conforming R5 spectral comparator, failure of the hist...

Riccardo Giudici · 0 citations
#generative ai Open access Sep 2026

Beyond Usefulness: How Cognitive Evaluations and Relational Perceptions Shape ChatGPT Continued Subscription Intention

As generative AI adopts subscription models, understanding continued payment intentions is essential. Drawing on the expectation-confirmation model, this study integrates technical quality and human–AI relational perceptions to explain continued subscription intention for ChatGPT. Survey data from 565 paid users show t...

Liucun Zhu, Chunlin Duan · 1 citation
#large language models Open access Sep 2026

Seamful Design Considerations for Human-in-the-Loop Digital Phenotyping of Mental Health

Digital Phenotyping of Mental Health (DPMH) through passive sensing is a promising approach for personal health informatics and digital wellbeing. Its appeal lies in unobtrusiveness, making it appear seamless. However, this very quality leads users to find it impersonal, untrustworthy, and disengaging. To counteract ch...

Vedant Das Swain, Tunwa Tongtawee, Olivia Wang et al. · 1 citation
#explainable ai Open access Oct 2026

ARTIFICIAL INTELLIGENCE IN DIABETES MANAGEMENT: EMERGING APPLICATIONS, CLINICAL OPPORTUNITIES AND CHALLENGES

Diabetes mellitus is a serious chronic metabolic disease marked by continuous problems in the regulation of glucose and is linked to a wide range of cardiovascular, renal, neurological, ophthalmic and other complications. Because of the growing number of people with diabetes, the difficulty of providing individualized...

Sachin Kumar1, Vijay Vaishnav1, Surabhi Raviprakash Singh2* · 0 citations

From tech blogs

See all →
Microsoft Research Blog Oct 7, 2026

Agent Lightning v1.0: A 3,500-Line Lightweight Agentic RL Framework for Training Agents with Real Harnesses

Training AI agents with reinforcement learning can be challenging because their tools, context, and decision-making are managed by complex frameworks. Agent Lightning connects existing agents to RL training, making it easier to improve them without rebuilding them. The post Agent Lightning v1.0: A 3,500-Line Lightweight Agentic RL Framework for Training Agents with Real Harnesses appeared first on Microsoft Research.

Microsoft Research Blog Oct 6, 2026

What AI gets wrong and what failure teaches us

Jennifer Neville did not want to go into computer science—but that’s exactly where she landed. Neville discusses the starts and stops that led to her professional sweet spot and her work identifying “surprising failures” making it hard for AI to handle complexity.  The post What AI gets wrong and what failure teaches us appeared first on Microsoft Research.

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.