kami/Maven
1
0
Fork 0
Code Issues 1 Pull Requests 1 Actions Packages Projects Releases Wiki Activity

Gate note recall on the margin, not the raw score #19

Closed
claude wants to merge 3 commits from overnight/recall-margin into overnight/router-on
pull from: overnight/recall-margin
merge into: kami:overnight/router-on
Conversation 2 Commits 3 Files Changed 10
+322 -52

3 Commits

Author SHA1 Message Date
kami 5a1d465db5 Merge commit '4383844' into overnight-jul31 
# Conflicts:
#	deploy/mavend.json
#	internal/config/config.go
 2026-07-31 11:52:21 +04:00
kami 43838445ab Write up the margin gate results 
Third section: why the absolute gate could not separate the two
distributions, the delta sweep, and the before/after. Marks next-steps
item 3 done.

Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01CGeSZxh1DCtRxmFVSYVGvJ
 2026-07-31 11:51:21 +04:00
kami 11831c6ace Gate recall on the margin over the runner-up, not just the score 
The e5 embedder puts every cosine in one narrow band (0.79-0.89), so the
absolute query_min_score gate cannot tell a real hit from a made-up
question: any value under the band answers everything, any value above it
answers nothing. False recall was 5/5.

New gate asks whether one note is clearly the best instead: top1 - top2 >
delta. New query_min_margin config knob, default 0.008, read off the sweep
in the recall harness. The absolute floor stays as a second check.

On the recall fixture with e5: answered 72% -> 68%, false recall 5/5 -> 1/5.

Vikunja #359

Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01CGeSZxh1DCtRxmFVSYVGvJ
 2026-07-31 11:50:39 +04:00