Skip to content

Category

explainable ai

2,280 papers

#explainable ai Dataset Open access Sep 2026

Code for Benchmarking machine learning for cardiovascular disease classification across 46 countries with geographic and temporal transportability assessment

Background: Machine-learning models for cardiovascular disease (CVD) are often evaluated with random participant splits, which may overstate performance when countries differ in prevalence, risk-factor distributions, healthcare access, and survey implementation. We benchmarked statistical and machine-learning classifie...

Wingston Felix Ng'ambi · 0 citations
#explainable ai Open access Sep 2026

Ammonix Specialized AI Agent Technology: A Local, Auditable Architecture for Specialized AI Agents in High-Stakes Domains

We introduce Ammonix, a foundation architecture for local, specialized, explainable AI agents in high-stakes operational domains such as clinical diagnosis, industrial and power-grid control rooms, and mission control. In these domains the responsible human operator must remain in charge, and needs an always-available...

Lea Grieder, Matthew Todorov, Adele Glauser et al. · 0 citations
#explainable ai Dataset Open access Sep 2026

The Kotlyar–Riemann Postulate: Radial Stability, Kernel Curvature, and a Conditional Framework for the Riemann Hypothesis — Version 1.4

This research preprint consolidates the Kotlyar Stability Postulate, quantum ground-state proposal, and Global Stable Radial Class framework into a conditional postulate on the Riemann Hypothesis. Version 1.3 develops Lemma 1—the radial-flux calculation—and Lemma 2—the proposed global-stability selection principle—whil...

David Kotlyar · 0 citations
#explainable ai Open access Sep 2026

Intelligence: information use and adaptive capability

Intelligence depends on how a system makes information usable, retains it and changes through experience. This perspective connects five established dependencies across biological and artificial systems: the conditional value of information, access through available operations, persistence relative to future demands, c...

Brendan Barlow · 0 citations
#explainable ai Open access Sep 2026

Shift Intent Left: Intent Contracts, Agency Budgets, and Drift Verification for Securing the Agentic Software Development Lifecycle

“Shift left” moved security activities toward the earliest artifact of the software development lifecycle (SDLC): source code. Autonomous coding agents invalidate the premise that code is that earliest artifact. An agent equipped with a shell, a package manager, credentials, and tool connectors performs security-releva...

Animesh Shaw · 0 citations
#explainable ai Open access Sep 2026

AI-generisani mnogojezični leksiprevodilac (AML)

AML je besplatna referentna, obrazovna i istraživačka onlajn alatka: pruža objašnjene prevode reči i drugih leksičkih jedinica, van rečeničnog konteksta ili unutar njega. Primarni par jezika je englesko-srpski / srpsko-engleski, kao i bilo koji drugi par jezika kojim je ovladao odabrani AI-četbot. Zadatak ‘Prevedi’ utv...

Tvrtko Prćić · 0 citations
#explainable ai Open access Sep 2026

AI-generisani onomazi / semazi leksikon (AOSL)

AOSL je besplatna referentna, obrazovna i istraživačka onlajn alatka: onomazi(ološki) — predlagač reči, a semazi(ološki) — tumač reči. AOSL može da obavlja devet leksičkih zadataka u oba smera (1-5 onomazi, 6-9 semazi): (1) tačno pronalaženje reči, (2) približno pronalaženje reči, (3) istraživanje sinonima / hiposinoni...

Tvrtko Prćić · 0 citations
#explainable ai Open access Sep 2026

AI-generisani mnogojezični leksiprevodilac (AML)

AML je besplatna referentna, obrazovna i istraživačka onlajn alatka: pruža objašnjene prevode reči i drugih leksičkih jedinica, van rečeničnog konteksta ili unutar njega. Primarni par jezika je englesko-srpski / srpsko-engleski, kao i bilo koji drugi par jezika kojim je ovladao odabrani AI-četbot. Zadatak ‘Prevedi’ utv...

Tvrtko Prćić · 0 citations
#explainable ai Open access Sep 2026

AI-generisani onomazi / semazi leksikon (AOSL)

AOSL je besplatna referentna, obrazovna i istraživačka onlajn alatka: onomazi(ološki) — predlagač reči, a semazi(ološki) — tumač reči. AOSL može da obavlja devet leksičkih zadataka u oba smera (1-5 onomazi, 6-9 semazi): (1) tačno pronalaženje reči, (2) približno pronalaženje reči, (3) istraživanje sinonima / hiposinoni...

Tvrtko Prćić · 0 citations
#explainable ai Dataset Open access Sep 2026

The Kotlyar–Riemann Postulate: Radial Stability, Kernel Curvature, and a Conditional Framework for the Riemann Hypothesis — Version 1.4

This research preprint consolidates the Kotlyar Stability Postulate, quantum ground-state proposal, and Global Stable Radial Class framework into a conditional postulate on the Riemann Hypothesis. Version 1.3 develops Lemma 1—the radial-flux calculation—and Lemma 2—the proposed global-stability selection principle—whil...

David Kotlyar · 0 citations
#explainable ai Open access Sep 2026

Fullseye: an explainable classical-vision operator library and workbench for Physical AI

Fullseye is a numpy-native library of typed classical image-processing and geometric-vision operators (2-D and 3-D), with an evolutionary pipeline-design mode evaluated under held-out gates, a Physical-AI perception stack (stereo → depth → point cloud → 6-DoF pose), and an HDevelop-style IDE (Fullseye Studio). Every op...

Kazufumi Furuse · 0 citations
#explainable ai Open access Sep 2026

子空间稳定、轴语义易位与连续谱:跨城市路网形态主成分表征的测量条件审计 (Stable Subspaces, Variable Axes, and the Morphological Continuum: Auditing Measurement Conditions in Cross-City Street-Network PCA)

【目的】 跨城市路网形态比较常依赖开放地理空间数据(OSM)与主成分分析(PCA)构建低维表征,但既有研究多预设离散分类范式,且普遍忽视数据质量异质性、空间尺度推移与特征共线性对主成分轴语义的构造性干扰。本文旨在检验跨城市路网形态主成分表征的前提假设是否成立,对数据适用性、空间尺度与特征共线性等关键测量条件实施系统审计,评估低维形态...

Wenhao Wang · 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.