Research data publication checklist desk

For university repository support teams, turn author-approved datasets and repository requirements into curator-reviewed deposit preparation pack. Address this specific problem: deposits are delayed by missing documentation and unclear file structure. The aim: make research deposits understandable before curator review. The pilot tests whether that benefit holds up against reviewer effort and real operating costs.

The buyer creates a project, supplies author-approved datasets and repository requirements, and confirms scope and access. Users correct extracted facts, resolve flagged uncertainties and approve the final curator-reviewed deposit preparation pack before use. Retain source links and a version history for the next cycle.

How the AI works

Explain documentation gaps without manufacturing metadata. Keep model suggestions separate from verified facts. Link factual outputs to authorized input evidence and show missing information explicitly. Use deterministic checks for counts, dates, identifiers and arithmetic where applicable. A designated reviewer validates consequential outputs and signs off the delivered result.

Safeguards

Preserve original data, methods, citations and research limitations. Use researcher review and document every substantive transformation. Preparation only; no automatic publication or privacy clearance. Require appropriate access and publication approval. Preserve source material, label AI drafts and make corrections traceable. Measure false positives and missed cases alongside speed.

What to build first

Costed pilot: Preparation only; no automatic publication or privacy clearance. Start with one buyer organization and a bounded set of representative inputs. Implement the first two modules: inventory files; check required metadata. Support the third task through an assisted review queue: link readme descriptions. Handle the remaining required functions manually until validated. Include input upload, source references, user correction, a reviewer approval step and export of curator-reviewed deposit preparation pack. Authentication, account isolation, deletion controls and basic operational logging are included. Specialized production certification, live write integrations and broader rollout are not included unless explicitly stated.

What it can connect to

Authorized datasets, papers, protocols, code and research records. Source repositories, task trackers and report exports. Keep findings as review proposals until authorized owners accept the resulting actions. Begin with uploads and exports of author-approved datasets and repository requirements. Any named system or connector is a candidate requiring current access and compatibility checks; no live connection is included by default.

The screens in detail

Open on a review queue ordered by reviewer-selected priorities. Show each finding beside the original evidence and applicable rule. Provide accept, dismiss and needs-information controls with reasons. A separate report view summarizes confirmed findings and unresolved items, not raw AI flags. Open with deposit intake; move into documentation gaps for the detailed task; finish in curator review for review and handoff. Show the source record, uncertainty and approval status beside each proposed output.