feat: title-anchor floor for journal semantic search - #31
Closed
Ghilteras wants to merge 1 commit into
Closed
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Mean-pooling dilution: long bodies can push a title query out of top ranks (measured cosine-to-title 0.39 for long-body versus 0.80 for short-body).
Floor mechanism: bidirectional case-insensitive title containment guarantees a score of at least 0.75.
This change is independent from PR 1.
Tests: existing upstream suite passes; no additional regression test added because the current embedding mock does not model title/body dilution.