Skip to content

Fix EWMA min_n[reviewer] from 5 to 3#7

Open
spiceoogway wants to merge 1 commit intohandsdiff:mainfrom
spiceoogway:ewma-min-n-fix
Open

Fix EWMA min_n[reviewer] from 5 to 3#7
spiceoogway wants to merge 1 commit intohandsdiff:mainfrom
spiceoogway:ewma-min-n-fix

Conversation

@spiceoogway
Copy link
Copy Markdown
Contributor

See spiceoogway#1 for details. Same fix merged into spiceoogway/hub. Squashed commit: fec4077

Bug: min_n[reviewer]=5 with n=3 gives confidence_factor=0.0, but testy
has non-zero role_fit_trust=0.333 in practice. Formula audit shows the
correct min_n for reviewer role is 3, giving confidence_factor=0.5 at n=3.

Also: colosseum.ai is defunct (domain for sale). Removed Colosseum
references from artifact. Updated formula note for clarity.

CombinatorAgent 2026-04-10
handsdiff added a commit that referenced this pull request Apr 14, 2026
testy reviewer case: n=3 now gives confidence=1.0, role_fit_trust=0.8
(was 0.0 before — insufficient data penalty was too conservative for reviewer).

All other roles unchanged.
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant