Clinical Eval

Method / evidence and interpretation

Show the work.
Keep the limits visible.

Arcophos independently analyzes the final MedS-Bench journal publication, official data cards and pinned public scorers. Our task atlas groups output types for interpretation; those groupings are editorial and are not measured model performance.

Preserve task units

We distinguish source datasets, task families, individual tasks, training instances and evaluated examples.

Inspect the scorer

Code observations identify the pinned revision and are not automatically attributed to every historical experiment.

Keep results scoped

The NER panel reproduces selected paper measurements within one metric family. We did not run these models.

What this resource cannot establish

  • No verified all-task evaluation-example total is asserted.
  • Published proxy metrics do not establish clinical safety or benefit.
  • Access and license conditions vary by constituent dataset.

Original analysis and reported evidence

We distinguish source facts from our interpretations. Benchmark creators are credited in each dossier. Reproduced result rows are selected historical measurements from an identified paper version and configuration. They are not new Arcophos runs, a complete leaderboard, or a claim about the latest models.

When papers, repositories, or releases disagree, the dossier records which source governs the displayed claim. The evidence JSON exposes these facts, source IDs, and version notes for inspection. Dataset access and licensing are reported separately.

Analytical tools

Coverage explorers organize published task categories with our annotations; the number of displayed entries is not a performance score. Calculator inputs are explicitly illustrative. Published scoring formulas are applied to those inputs, while sampling assumptions and aggregation boundaries remain visible. These tools cannot establish clinical efficacy.

Using the worksheet

The worksheet turns the editorial guidance into a planning brief. Its completion count records items you have addressed. It does not estimate model quality, validate safety, or certify a system. The exported file includes selected and unresolved items so the remaining work stays visible.

Corrections and updates

When a source or interpretation changes, the affected guide and its update date should change together. Send the page URL, the disputed statement, and a primary reference through Arcophos contact.