Github Trends®
8833 findingsmedian surprise 0.00433window 3 days
UNIT / TREND-MONITOR · REV 2.6
[ 3 days window ]
SOURCE: own snapshots
FINDING #8456 · 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

SURPRISE0.0000063
ENGAGEMENT1.00
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
5.67
ACCEL
+1.50
RETENTION
0.0%
PEAK 2026-09-12 · FORK-RETENTION 0.0% · 17 STARS / WINDOW

Author Audience

AUDIENCE
899,499
FOLLOWERS
37,459
OWNER ★
715,630

Engagement Signals

FORKS
1,765
ISSUE AUTH
0
PR AUTH
0
UNIQUE STARGAZERS 17 / 17 (DIVERSITY 1.00)

Why This Is A Finding

facebookresearch/sam3 собрал 17 звёзд за окно, тогда как у автора всего 37,459 подписчиков — эффективная аудитория ≈ 899,499. Это даёт surprise-индекс 0.0000063 (звёзды относительно охвата автора, а не в абсолюте). Удержание форков 0.0% и 0 внешних контрибьюторов отделяют реальный инструмент от разовой вспышки. Акселерация положительная — рост ещё не выдохся.

METRICS IN CONTEXT

MEDIAN ACROSS ALL 8833 FINDINGS · Δ vs MEDIAN · PERCENTILE = SHARE RANKED BELOW
METRICVALUEMEDIANΔ MEDPERCENTILE
SCORE0.000.00-0.00ABOVE 4%
VELOCITY5.675.670.00ABOVE 49%
RETENTION0.0%45.9%-45.9 PPABOVE 0%
FORKS1,765344+1,421ABOVE 80%
SURPRISE0.000.00-0.00ABOVE 2%