An Enhanced FAIRed and eXplainable (eFAIR-X) AI Model and Dashboard for Open, Interdisciplinary Computational Research Reproducibility

Computational research is becoming increasingly dependent on code, data, workflows, software environments and model configurations that must be preserved and understood before findings can be reproduced. The FAIR Guiding Principles have significantly improved data stewardship, but they do not by themselves provide an executable, explainable and evidence-linked mechanism for verifying computational claims. This article presents eFAIR-X, an implementation-oriented and AI-enabled extension of FAIR for interdisciplinary computational reproducibility. The framework connects publications, claims, datasets, code, workflows, environments and verification evidence through a semantic research knowledge graph. It also defines a Dashboard for Reproducibility (DfR) that reports bounded, auditable and calibratable indicators for artefact availability, metadata completeness, workflow executability, output agreement, contribution-evidence coverage, relevance longevity and originality risk. In response to the need for stronger technical precision, the model separates three issues that are often combined: FAIR principle extension, FAIR assessment and operational reproducibility verification. A browser-based proof-of-concept prototype has now been implemented and exercised using structured JSON study files to demonstrate the dashboard, knowledge-graph view, evidence table, claim-evidence mapping and validation panel. The proposed metrics are explicitly treated as provisional operational indicators that require calibration through benchmark experiments, expert agreement analysis, case-based evaluation and sensitivity testing before they can be used as decision-support evidence. The paper further specifies local and global explainability mechanisms, human contestability, knowledge-graph node and edge semantics, metadata requirements and dashboard evidence drill-downs. eFAIR-Xis therefore positioned not as a replacement for FAIR, FAIR4RS or FAIRification frameworks, but as a complementary verification-centred infrastructure for making computational reproducibility more measurable, inspectable and actionable.