aperivue/medsci-skills · skills/explainability/SKILL.md

explainability skillA

Produce or audit the interpretability/explainability analysis of a medical-imaging model — Grad-CAM / Grad-CAM++ / attention-rollout / saliency / integrated-gradients — so it clears the rigor bar a reviewer expects: mandatory Adebayo sanity checks (model- and data-randomisation), a quantitative localisation metric against ground truth (IoU / pointing game / Dice) instead of eyeballed examples, a cohort-level result rather than cherry-picked cases, and attribution framing rather than "proof the m

Latest version
mdr add aperivue/medsci-skills/explainability@git:20260703.0978297
Exact content
mdr add aperivue/medsci-skills/explainability@sha256:4d1c082ad48393ad
Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_2xnyugi46g34nb6e.svg)](https://markdownregistry.com/a/art_2xnyugi46g34nb6e)

0 badge views in 30 days

Versions

versioncommittedcommitsizeaudit
git:20260703.0978297 latest2026-07-03 0978297 6,474 BA view

Audit of the latest version

A  17 of 17 checks passed. Deterministic, no model, same answer every run.

Source

GitHub

aperivue/medsci-skills · 283 stars · license MIT · pushed 2026-09-05 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_2xnyugi46g34nb6e
GET https://markdownregistry.com/api/v1/resolve?ref=aperivue/medsci-skills/explainability
GET https://markdownregistry.com/api/v1/blob/4d1c082ad48393adb65203ffbedf63f772fdc521d873f657cbfc81150c7b36de