Github Trends®
9769 findingsmedian surprise 0.00716window 7 days
UNIT / TREND-MONITOR · REV 2.6
[ 7 days window ]
SOURCE: own snapshots
FINDING #9406 · UNIT ID 1021587722
facebookresearch/sam3
The repository provides code for running inference and finetuning with the Meta Segment Anything Model 3 (SAM 3), links for downloading the trained model checkpoints, and example notebooks that show how to use the model.
[ PYTHON ][ ORG ][ VERIFIED ][ GITHUB ↗ ]
SURPRISE SCORE
0.00

Score Breakdown

SURPRISE0.00000929
ENGAGEMENT0.50
FRESHNESS1.00
SCORE = SURPRISE × ENGAGEMENT^0.7 × FRESHNESS × VISIBILITY × CONFIDENCE
SURPRISE = WINDOW STARS / DAYS / (AUDIENCE + FLOOR)
0% OF STARS IN ARCHIVE

Growth Telemetry

VELOCITY /D
8.43
ACCEL
-0.32
RETENTION
46.4%
PEAK 2026-10-11 · FORK-RETENTION 36.4% · 59 STARS / WINDOW

Author Audience

AUDIENCE
907,104
FOLLOWERS
38,016
OWNER ★
718,333

Engagement Signals

FORKS
1,821
ISSUE AUTH
0
PR AUTH
0
UNIQUE STARGAZERS 59 / 59 (DIVERSITY 1.00)

Why This Is A Finding

facebookresearch/sam3 собрал 59 звёзд за окно, тогда как у автора всего 38,016 подписчиков — эффективная аудитория ≈ 907,104. Это даёт surprise-индекс 0.00000929 (звёзды относительно охвата автора, а не в абсолюте). Удержание форков 36.4% и 0 внешних контрибьюторов отделяют реальный инструмент от разовой вспышки. Акселерация отрицательная — внимание остывает после пика.

METRICS IN CONTEXT

MEDIAN ACROSS ALL 9769 FINDINGS · Δ vs MEDIAN · PERCENTILE = SHARE RANKED BELOW
METRICVALUEMEDIANΔ MEDPERCENTILE
SCORE0.000.00-0.00ABOVE 4%
VELOCITY8.433.57+4.86ABOVE 75%
RETENTION46.4%28.6%+17.9 PPABOVE 78%
FORKS1,821126+1,695ABOVE 94%
SURPRISE0.000.01-0.01ABOVE 1%