Supervisor onboarding · MSCA PF 2026
For the supervisor
Dr Jenny Kidd · Cardiff University
Phased checklist:
protected workbook →
· canonical repo file docs/WORKBOOK.md
Objectives
O1
Writing Provenance Layer
Bind AI-generated text to archival sources, extraction nodes, and model operations.
O2
Voice fidelity
Evaluate when fine-tuning preserves rather than flattens authorial and cultural voice.
O3
Open toolkit
Deployable open-source prototype and responsible-design methodology for practitioners.
Research progress since shortlisting
Computational Provenance for AI-Assisted Digital Heritage
How can an AI system preserve the genealogy of knowledge — not merely cite a source, but expose the chain of transformations through which generated text became what it is?
Computational Provenance
The Writing Provenance Layer (O1) formalised as a W3C PROV-O extension aligned to CIDOC-CRM — grounding the methodology in a standard two decades older than LLMs.
Document Intelligence
A falsifiable novelty test: does any published system anchor knowledge construction in precise page/bounding-box coordinates, as the applicant's own extraction pipeline already does? A rigorous negative result is itself the finding.
GraphRAG remains one evaluated technology among several — this reframing sharpens the approved objectives, it does not change them.
See the full pitch deck (Gap and Evidence slides) →Key dates
- Portal + Part A
- 7 Aug 2026 — eiro@cardiff.ac.uk
- Submission
- 9 Sep 2026, 16:00 UK
Cardiff PIC 999979694 · Draft SEP-211353721