arXiv subjects

Tapio Pitkäranta

Publications and source records attributed to Tapio Pitkäranta.

4 recordsLinked to original sources

arXiv2025

The NordDRG AI Benchmark for Large Language Models

Large language models (LLMs) are being piloted for clinical coding and decision support, yet no open benchmark targets the hospital-funding layer where Diagnosis-Related Groups (DRGs) determine reimbursement. In most OECD systems, DRGs route a substantial share of multi-trillion-dollar health spending through governed grouper software, making transparency and auditability first-order concerns. We release NordDRG-AI-Benchmark, the first public, rule-complete test bed for DRG reasoning. The package includes (i) machine-readable approximately 20-sheet NordDRG definition tables and (ii) expert manuals and change-log templates that capture governance workflows. It exposes two suites: a 13-task Logic benchmark (code lookup, cross-table inference, grouping features, multilingual terminology, and CC/MCC validity checks) and a 13-task Grouper benchmark that requires full DRG grouper emulation with strict exact-match scoring on both the DRG and the triggering drg_logic.id. Lightweight reference agents (LogicAgent, GrouperAgent) enable artefact-only evaluation. Under an artefact-only (no web) setting, on the 13 Logic tasks GPT-5 Thinking and Opus 4.1 score 13/13, o3 scores 12/13; mid-tier models (GPT-5 Thinking Mini, o4-mini, GPT-5 Fast) achieve 6-8/13, and remaining models score 5/13 or below. On full grouper emulation across 13 tasks, GPT-5 Thinking solves 7/13, o3 6/13, o4-mini 3/13; GPT-5 Thinking Mini solves 1/13, and all other tested endpoints score 0/13. To our knowledge, this is the first public report of an LLM partially emulating the complete NordDRG grouper logic with governance-grade traceability. Coupling a rule-complete release with exact-match tasks and open scoring provides a reproducible yardstick for head-to-head and longitudinal evaluation in hospital funding. Benchmark materials available in Github.

cs.AI↗

arXiv2025

HADA: Human-AI Agent Decision Alignment Architecture

We present HADA (Human-AI Agent Decision Alignment), a protocol- and framework agnostic reference architecture that keeps both large language model (LLM) agents and legacy algorithms aligned with organizational targets and values. HADA wraps any algorithm or LLM in role-specific stakeholder agents -- business, data-science, audit, ethics, and customer -- each exposing conversational APIs so that technical and non-technical actors can query, steer, audit, or contest every decision across strategic, tactical, and real-time horizons. Alignment objectives, KPIs, and value constraints are expressed in natural language and are continuously propagated, logged, and versioned while thousands of heterogeneous agents run on different orchestration stacks. A cloud-native proof of concept packages a production credit-scoring model (getLoanDecision) and deploys it on Docker/Kubernetes/Python; five scripted retail-bank scenarios show how target changes, parameter tweaks, explanation requests, and ethics triggers flow end to end through the architecture. Evaluation followed the Design-Science Research Methodology. Walkthrough observation and log inspection demonstrated complete coverage of six predefined objectives: every role could invoke conversational control, trace KPIs and value constraints, detect and mitigate ZIP-code bias, and reproduce full decision lineage, independent of the underlying LLM or agent library. Contributions: (1) an open-source HADA architecture, (2) a mid-range design theory for human-AI alignment in multi-agent systems, and (3) empirical evidence that framework-agnostic, protocol-compliant stakeholder agents improve accuracy, transparency, and ethical compliance in real-world decision pipelines.

cs.AI↗

arXiv2025

Semantic Web and Software Agents -- A Forgotten Wave of Artificial Intelligence?

The history of Artificial Intelligence (AI) is a narrative of waves -- rising optimism followed by crashing disappointments. AI winters, such as the early 2000s, are often remembered as barren periods of innovation. This paper argues that such a perspective overlooks a crucial wave of AI that seems to be forgotten: the rise of the Semantic Web, which is based on knowledge representation, logic, and reasoning, and its interplay with intelligent Software Agents. Fast forward to today, and ChatGPT has reignited AI enthusiasm, built on deep learning and advanced neural models. However, before Large Language Models (LLMs) dominated the conversation, another ambitious vision emerged -- one where AI-driven Software Agents autonomously served Web users based on a structured, machine-interpretable Web. The Semantic Web aimed to transform the World Wide Web into an ecosystem where AI could reason, understand, and act. Between 2000 and 2010, this vision sparked a significant research boom, only to fade into obscurity as AI's mainstream narrative shifted elsewhere. Today, as LLMs edge toward autonomous execution, we revisit this overlooked wave. By analyzing its academic impact through bibliometric data, we highlight the Semantic Web's role in AI history and its untapped potential for modern Software Agent development. Recognizing this forgotten chapter not only deepens our understanding of AI's cyclical evolution but also offers key insights for integrating emerging technologies.

cs.SI↗

arXiv2025

Why are we living the age of AI applications right now? The long innovation path from AI's birth to a child's bedtime magic

Today a four-year-old child who does not know how to read or write can now create bedtime stories with graphical illustrations and narrated audio, using AI tools that seamlessly transform speech into text, generate visuals, and convert text back into speech in a natural and engaging manner. This remarkable example demonstrates why we are living in the age of AI applications. This paper examines contemporary leading AI applications and traces their historical development, highlighting the major advancements that have enabled their realization. Five key factors are identified: 1) The evolution of computational hardware (CPUs and GPUs), enabling the training of complex AI models 2) The vast digital archives provided by the World Wide Web, which serve as a foundational data resource for AI systems 3) The ubiquity of mobile computing, with smartphones acting as powerful, accessible small computers in the hands of billions 4) The rise of industrial-scale cloud infrastructures, offering elastic computational power for AI training and deployment 5) Breakthroughs in AI research, including neural networks, backpropagation, and the "Attention is All You Need" framework, which underpin modern AI capabilities. These innovations have elevated AI from solving narrow tasks to enabling applications like ChatGPT that are adaptable for numerous use cases, redefining human-computer interaction. By situating these developments within a historical context, the paper highlights the critical milestones that have made AI's current capabilities both possible and widely accessible, offering profound implications for society.

cs.CY↗