tiennm99 fd5a1d2903 feat(semantle,doantu): calibrate cosine score via normalized sigmoid ...

BGE embeddings occupy a narrow cone in vector space, so raw cosine of
two unrelated words already sits at ~0.40-0.55. Displaying `raw * 100`
made every random guess read as 40-70% warm, which defeated the warmth
UX.

format.js now applies a normalized sigmoid (FLOOR 0.40, CENTER 0.60,
SCALE 8) to remap raw cosine → displayed 0-100. Unrelated pairs drop
to ≤30, loose relation lands around 40-55, clear synonyms hit 85+, and
exact match stays at 100. Emoji buckets were rebased onto the calibrated
score; formatWarmth lost its sign column (calibrated output is always
non-negative).

render.js rounds once and feeds the integer to both formatWarmth and
warmthEmoji so the display value and bucket stay in sync.

Constants are empirical — retune if swapping to a non-BGE model.

2026-04-23 00:33:54 +07:00

..

api-client.test.js

refactor(semantle): switch embedding model from bge-small-en-v1.5 to bge-m3

2026-04-23 00:22:28 +07:00

format.test.js

feat(semantle,doantu): calibrate cosine score via normalized sigmoid

2026-04-23 00:33:54 +07:00

handlers.test.js

feat(semantle,doantu): calibrate cosine score via normalized sigmoid

2026-04-23 00:33:54 +07:00

render.test.js

feat(semantle,doantu): calibrate cosine score via normalized sigmoid

2026-04-23 00:33:54 +07:00

state.test.js

feat(semantle): add word2vec guessing game module

2026-04-22 22:05:27 +07:00