Github Trends®
9789 findingsmedian surprise 0.00728window 7 days
UNIT / TREND-MONITOR · REV 2.6
[ 7 days window ]
SOURCE: own snapshots
FINDING #9334 · 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

SURPRISE0.00000953
ENGAGEMENT0.49
FRESHNESS1.00
SCORE = SURPRISE × ENGAGEMENT^0.7 × FRESHNESS × VISIBILITY × CONFIDENCE
SURPRISE = WINDOW STARS / DAYS / (AUDIENCE + FLOOR)
1% OF STARS IN ARCHIVE

Growth Telemetry

VELOCITY /D
8.57
ACCEL
-0.18
RETENTION
38.8%
PEAK 2026-09-08 · FORK-RETENTION 90.9% · 60 STARS / WINDOW

Author Audience

AUDIENCE
899,571
FOLLOWERS
37,459
OWNER ★
715,630

Engagement Signals

FORKS
1,765
ISSUE AUTH
0
PR AUTH
0
UNIQUE STARGAZERS 60 / 60 (DIVERSITY 1.00)

Why This Is A Finding

facebookresearch/sam3 собрал 60 звёзд за окно, тогда как у автора всего 37,459 подписчиков — эффективная аудитория ≈ 899,571. Это даёт surprise-индекс 0.00000953 (звёзды относительно охвата автора, а не в абсолюте). Удержание форков 90.9% и 0 внешних контрибьюторов отделяют реальный инструмент от разовой вспышки. Акселерация отрицательная — внимание остывает после пика.

METRICS IN CONTEXT

MEDIAN ACROSS ALL 9789 FINDINGS · Δ vs MEDIAN · PERCENTILE = SHARE RANKED BELOW
METRICVALUEMEDIANΔ MEDPERCENTILE
SCORE0.000.00-0.00ABOVE 5%
VELOCITY8.573.43+5.14ABOVE 76%
RETENTION38.8%37.5%+1.3 PPABOVE 51%
FORKS1,765120+1,645ABOVE 94%
SURPRISE0.000.01-0.01ABOVE 1%