Didactctopus is a multi-talented AI system to assist autodidacts in gaining mastery of a chosen topic. Want to learn and get an assist doing it? Didactopus fits the bill.

Go to file

welsberr d682d2774f Weighted evidence update		2026-03-12 21:42:40 -04:00
.github/workflows	Initial ChatGPT sources	2026-03-12 19:59:59 -04:00
artwork	Added dependency graph checks, artwork.	2026-03-12 21:12:53 -04:00
configs	Weighted evidence update	2026-03-12 21:42:40 -04:00
docs	Weighted evidence update	2026-03-12 21:42:40 -04:00
domain-packs	Evidence engine update	2026-03-12 21:40:34 -04:00
src/didactopus	Weighted evidence update	2026-03-12 21:42:40 -04:00
tests	Weighted evidence update	2026-03-12 21:42:40 -04:00
.gitignore	Initial ChatGPT sources	2026-03-12 19:59:59 -04:00
Dockerfile	Initial ChatGPT sources	2026-03-12 19:59:59 -04:00
LICENSE	Initial ChatGPT sources	2026-03-12 19:59:59 -04:00
Makefile	Initial ChatGPT sources	2026-03-12 19:59:59 -04:00
README.md	Weighted evidence update	2026-03-12 21:42:40 -04:00
docker-compose.yml	Initial ChatGPT sources	2026-03-12 19:59:59 -04:00
pyproject.toml	Added dependency graph checks, artwork.	2026-03-12 21:12:53 -04:00

README.md

Didactopus

Didactopus is a local-first AI-assisted autodidactic mastery platform.

This revision upgrades the evidence layer from simple averaging to a more realistic weighted and recency-aware mastery model.

Added in this revision

evidence-type weighting
recency weighting
confidence estimation from weighted evidence mass
dimension-level rubric storage
weighted concept summaries
mastery decisions using weighted score and confidence
resurfacing from recent weak evidence
tests for weighted scoring and recency behavior

Why this matters

Not all evidence should count equally.

A capstone project or transfer task should usually matter more than a short explanation, and recent poor performance should sometimes matter more than older success. This revision begins to model that explicitly.