pediatric-ai-scribe-v3/src
Daniel f7cd8b39a3
Some checks failed
Forgejo Android APK / Root app tests (push) Successful in 49s
Forgejo Docker Build / Root app tests (push) Successful in 47s
Forgejo Android APK / Build signed APK (push) Successful in 2m0s
Forgejo Docker Build / Build Docker image (push) Successful in 8s
Forgejo Docker Build / Deploy to the host (push) Failing after 0s
feat: a grounded resource ends with the references it drew on
The grounding metadata went to the API response and the logs, which is no use to
someone holding the deck. A teaching resource shown to trainees should carry its
own provenance, so a grounded one now ends with a References section — the final
slide in a presentation — listing the library excerpts it actually used, by
title and page.

Restricted deliberately: only excerpts actually drawn on, nothing invented. That
was worth checking rather than trusting. Generated a deck and compared every
citation against the source metadata: "Kliegman R. Nelson Textbook of
Pediatrics, 22nd ed., 2024, p. 2604" against a stored title of "Kliegman R.
Nelson Textbook of Pediatrics 2-Volume Set 22ed 2024" at page 2604, and the same
for Fleisher & Ludwig, Rosen's, Understanding Pathophysiology and the AAP
compendium. The model reformatted filename-derived titles into readable
citations using only what it was given.

Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01Dv6sqaY6Vq3ChZHMem3cnU
2026-09-11 14:23:49 +02:00
..
db feat: keep the screen awake while recording, and keep every recording 24h 2026-09-10 16:42:31 +02:00
middleware fix: enforce sessions, escape quiz metadata and isolate ED drafts 2026-09-06 07:44:08 +02:00
routes feat: a grounded resource ends with the references it drew on 2026-09-11 14:23:49 +02:00
utils feat: Learning resources can be grounded in the clinical corpus 2026-09-11 14:03:05 +02:00