kjannette/kongruity
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

edit readme

Browse Source
This commit is contained in:
KS Jannette
2026-08-22 18:23:09 -04:00
parent da0d5984ee
commit 539df1edff
1 changed files with 4 additions and 4 deletions
Download Patch File Download Diff File Expand all files Collapse all files

8
README.md
View File

@@ -8,10 +8,6 @@ In kongruity, the artifacts become "sticky notes." A board full of them looks ch
With a click, they are semantically evaluated, grouped into thematic clusters with descriptive headers, rankable and exportable to project planning and execution tools. With a click, they are semantically evaluated, grouped into thematic clusters with descriptive headers, rankable and exportable to project planning and execution tools.
## Voyage AI voyage-3.5
![Embedding model benchmarking.](Voyage.jpg)
## Clustering and evaluation: methodology ## Clustering and evaluation: methodology
Two models run in parallel, and neither sees the other's work. Anthropic's `claude-sonnet-5` (`backend/services/clustering.service.js`) reads the raw text of every note and groups them into labeled thematic clusters. Two models run in parallel, and neither sees the other's work. Anthropic's `claude-sonnet-5` (`backend/services/clustering.service.js`) reads the raw text of every note and groups them into labeled thematic clusters.
@@ -26,6 +22,10 @@ This yields an empirical groundedness evaluation. One model proposes the groupin
Note that: before scoring, structural validation confirms that each note landed in exactly one cluster, that no cluster is empty, and that no hallucinated note IDs appear. A malformed response to the validation completely fails, rather than quietly returning a partial board. Note that: before scoring, structural validation confirms that each note landed in exactly one cluster, that no cluster is empty, and that no hallucinated note IDs appear. A malformed response to the validation completely fails, rather than quietly returning a partial board.
## Voyage AI voyage-3.5: best-in-class embedding
![Embedding model benchmarking.](Voyage.jpg)
## Reading the cohesion score ## Reading the cohesion score
Average silhouette width is a widely-used measure of clustering quality. Higher values indicate: Average silhouette width is a widely-used measure of clustering quality. Higher values indicate: