Model card
Intended use, users, architecture, input and output boundaries, training and evaluation descriptions, limitations, known failure modes, model version and change history.
Research and transparency
Research made inspectable.
This hub is the home for model documentation, evaluation protocols, benchmark reports, dataset records when available, and versioned changes. Availability and evidence status are stated separately so a planned artefact cannot be mistaken for a published one.
Current evidence status: the work described here is internal and retrospective. It is not independent replication, prospective clinical validation, evidence of improved patient outcomes, or a substitute for regulatory assessment.
Documentation register
What belongs in the research record.
Each resource receives a clear status, scope and version. Items that are not public are labelled as such rather than represented by placeholder findings.
Evaluation protocols
Research question, cohort rules, endpoints, comparators, grading procedure, statistical analysis, subgroup plan, missing-data handling and deviations from the protocol.
Status: protocol records will be linked here as they are approved for public release.
Benchmark reports
Internal retrospective evaluations should disclose the exact system version, case source and dates, inclusion rules, comparator settings, grading method, uncertainty, limitations and reproducibility materials that can be shared.
Status: current work is internal and retrospective.
Dataset records
If a dataset or benchmark set is released, its record should state provenance, permissions, license, inclusion and exclusion rules, de-identification approach, version and known limitations.
Status: no public dataset is listed on this page.
Research change log
Material changes to a model, protocol, cohort, endpoint, analysis or report should be dated and described, with previous versions retained or clearly marked as superseded.
Status: entries will appear with the resources they govern.
Corrections and limitations
Known errors, post-publication corrections, unresolved questions, negative findings and limits on interpretation belong alongside favourable results, not in a separate marketing narrative.
Status: correction notes will be versioned with affected material.
Interpretation guide
Different evidence answers different questions.
These labels prevent one kind of evaluation from implying a stronger claim than its design supports.
| Label | What it can examine | What it does not establish by itself |
|---|---|---|
| Internal retrospective evaluation | Performance on previously assembled cases under a documented test procedure | Independent reproducibility, prospective performance or clinical benefit |
| Independent replication | Whether results can be reproduced by investigators outside the development team | Safe and effective performance in routine clinical workflow |
| Prospective validation | Performance on cases or data collected after a protocol is set | Improved patient outcomes unless outcomes and study design address that claim |
| Clinical outcomes study | Effects on prespecified care, safety or patient outcomes in a defined setting | Generalisation to populations, settings or uses outside the study |
Minimum disclosure
A benchmark needs more than a headline result.
Before an internal evaluation is suitable for public interpretation, its method and boundaries need to be visible.
System identity
- Exact model and application version
- Prompting, retrieval and tool configuration
- Evaluation date and frozen settings
Evaluation design
- Prespecified question and endpoints
- Case provenance and eligibility rules
- Comparators, grading and analysis method
Interpretive limits
- Uncertainty and missing data
- Subgroups, bias and error analysis
- Generalisability and unresolved risks
Release discipline
From internal work to a citable record.
Publication status should progress only when the corresponding material is actually available.
Define
State the research question, intended claim, protocol, system version and analysis before interpreting results.
Run and audit
Preserve outputs, errors, deviations and exclusions. Separate exploratory analysis from prespecified analysis.
Report
Publish methods, results, uncertainty, limitations and a version identifier together. Clearly label internal authorship and retrospective design.
Invite verification
Provide reproducibility material where permissions allow, distinguish independent work from internal work, and link corrections without erasing the record.
Change log format
Every material change gets context.
Research pages will use a consistent record rather than silently replacing previous claims or methods.
Each entry records
- Date and version affected
- Resource, model or protocol changed
- Plain-language summary and reason
- Whether results or interpretation changed
Each status distinguishes
- Draft or internal material
- Publicly released documentation
- Corrected or superseded material
- Independent work linked from this hub
Continue exploring