explainable ai

Sapience Without Sentience: The Consciousness Conditions and the Architecture of LLM Collectives

A previous case study of the Hugging Face AI collective closed with a prediction: a population of large language models, organised as a multi-agent system, could in principle sustain its own existence (generating and maintaining the conditions of its continued operation) while being nonconscious. This paper asks what t...

Scientific Research

This chapter introduces the fundamental purpose of scientific research and explains the scientific method as a systematic approach to knowledge generation. The author outlines each step of the scientific method, emphasizing its logical and empirical structure. The chapter also explores the interrelationship between sci...

Literature Review

This chapter focuses on the systematic review of existing scholarly information relevant to a research topic. It discusses strategies for locating, evaluating, and organizing scientific sources, including journals, textbooks, conference proceedings, and theses. The chapter also explains proper bibliographic formatting...

AI Influence on Human Thought and Action: A Lexicon and Taxonomy of a Fragmented Literature

Human oversight of artificial intelligence is often justified by having a person who can reject the system's recommendation. Yet AI may already have shaped what that person sees, notices, and thinks. This article brings together terms from several disciplines to classify these influences and examine their ethical impli...

Separating AI-assisted authoring from governed execution through specification-driven composition A design framework and industrial experience report for explainable automation in regulated data transformation

Beyond Simulation: What Would It Take for Matter to Feel? An Explainer on a Falsifiable Programme for Primary Interoceptive Sentience

A popular-science explainer (not a scientific contribution in its own right) on the research programme "Necessary Conditions for Primary Interoceptive Sentience in Continuous Substrates: A Falsifiable Programme" (doi:10.5281/zenodo.22895484). It covers the No-Go Theorem for Consciousness on a Chip as heuristic motivati...

Characterizing LLM-Based Family Education through the Lens of Activity Theory: A Scoping Review of the HCI Literature

A scoping review analyzes 53 HCI studies and offers a framework explaining how LLM capabilities become organized through family participation, using activity theory and AODM to relate participants and educational objects to mediation, labour, and rules.

Explainable Federated Learning for Trustworthy Thoracic Disease Detection Under Non-IID Data Distributions

Comparison of SHAP and Grad-CAM attribution maps confirms clinically coherent disease-specific localisation, and reveals monotonic performance degradation, identifying minimal regularisation as optimal for multi-label medical imaging.

Are Mechanisms Important for AI to Identify Oscillation Sources? A Case Study

Grid-connected wind turbine generators (WTGs) may induce sub-synchronous oscillations (SSOs) in a power system. Due to the difficulty to gain the detailed parameters of the WTGs in practice, data-driven AI method is considered to be a potential solution to identify the trouble-making WTGs (or SSO sources) in the power...

Centering Knowledge Along the Responsible LLM Supply Chain: An Empirical Study & Multi-Stakeholder Taxonomy

This work draws on semi-structured interviews with 71 LLM practitioners to examine the knowledge required to produce responsible LLM systems, and how practitioners acquire it within LLM supply chains, and synthesizes knowledge needs into a multi-dimensional taxonomy that characterizes knowledge based on its abstraction...

Machine Semiology in Practice: Clinician Strategies for Interpreting AI-Generated Visual Explanations

It is found that saliency maps function as underspecified, indexical sign systems that often conflict with radiological semiology, suggesting that explainability emerges as a sociotechnical accomplishment, with implications for the design of interactive, practice-aligned XAI systems.

GiriNeoSeizure™ CDSS — Neonatal Seizures: Stabilise, Confirm, Treat & Reassess (Edition 1, Version 2.0)

GiriNeoSeizure™ CDSS is a single-file, offline, interactive clinical decision-support system for neonatal seizures. It is part of the NeonatAIlogy™ series in the GAIR Innovation Registry and is governed by the GIRISH™ Prompting Architecture. The tool turns the 2023 ILAE Task Force guideline, Cochrane evidence on antise...