The complete publication and citation record lives on Google Scholar. This page organizes the main intellectual threads so collaborators can quickly see where the work came from and where it is going.
The entries below link to publisher, repository and public records, distinguishing preprints from peer-reviewed articles. Google Scholar and ORCID remain the live source for the complete record.
Zenodo · v1.0.0
Source-data tables for the main and Extended Data figures, registered-extension summaries, P5b practitioner-equivalence outputs and second-judge robustness summaries, so the reported results can be audited. Third-party benchmark corpora are not redistributed.
Open source → Zenodo · DOI 10.5281/zenodo.22974727Zenodo · v1.0
A framework and nine-chapter implementation for human-owned engineering judgment in systems containing AI. It combines evidence, explicit limits, changed conditions and justified revision; learning effectiveness remains an evaluation question.
Open source → Zenodo · DOI 10.5281/zenodo.22964248Scientific Reports
With Redhwan Nour, this study evaluates selective, context-aware AI assistance for chest X-ray interpretation rather than assuming AI should always be shown.
Open source → Nature / Scientific ReportsJournal of Clinical Pharmacology
A clinically interpretable DDI framework combining ontology-based embeddings with deep learning to predict pharmacokinetic and pharmacodynamic interaction mechanisms.
Open source → PubMedarXiv
A biomedical Urdu named-entity recognition benchmark built from 153K annotated tokens and evaluated with classical, deep-learning and multilingual transformer baselines.
Open source → arXivScientific Reports
A machine-learning study of EV energy-consumption prediction using real-world data, hyperparameter optimization and a stacking ensemble.
Open source → Nature / Scientific ReportsKing Abdulaziz University · FCIT
The Faculty of Computing and Information Technology publicly announced the Scientific Council decision promoting Adeeb Noor to Full Professor in the Information Technology Department.
Open source → FCIT KAU on XThese projects are in development; inclusion does not imply journal acceptance or publication.
RIDI research project
In a preregistered retrieval experiment, five standard retrieval metrics were identical, yet benchmark-defined answer correctness changed for 17.27% of 800 queries. Registered extensions, an exact control frontier and a production update test the limits of that result. Submission-ready; not yet peer reviewed, accepted or published.
Explore research → RIDI project pageFor the authoritative publication list, use Google Scholar. For research-network context and institutional lineage, use ResearchGate, KAUST and the doctoral repository.
Rather than reproduce a long bibliography here, these themes show how individual papers, systems and ventures fit into one larger research program.
Research on allocation identity, ranking-to-action systems and consequential evaluation asks what changes when a model is forced to act under limited capacity.
Explore RIDI →Doctoral and later work on drug–drug interactions, pharmacovigilance and biomedical knowledge asks how incompleteness and heterogeneity affect computational and clinical inference.
See doctoral foundations →Work in genetic screening and drug response extends the same principle to personalized medicine: better decisions require evidence that is specific enough to the person and context.
Explore GenomeFit →Research and system-building in AI-assisted curriculum design, readiness and institutional governance asks how evidence can remain visible when systems scale across courses and organizations.
Explore teaching →Use Scholar for the full record, or contact me directly if you are exploring collaboration around a particular question.