google-research/timesfm — GitHub trend

FINDING #7399 · UNIT ID 793784055

google-research/timesfm

TimesFM (Time Series Foundation Model) is a pretrained time-series foundation model developed by Google Research for time-series forecasting.

[ PYTHON ][ ORG ][ GITHUB ↗ ]

SURPRISE SCORE

0.00

Score Breakdown

SURPRISE0.000427

ENGAGEMENT0.39

FRESHNESS1.27

SCORE = SURPRISE × ENGAGEMENT^0.7 × FRESHNESS × VISIBILITY × CONFIDENCE

SURPRISE = WINDOW STARS / DAYS / (AUDIENCE + FLOOR)

4% OF STARS IN ARCHIVE

Growth Telemetry

VELOCITY /D

37.40

ACCEL

+1.64

RETENTION

8.9%

PEAK 2026-08-17 · FORK-RETENTION 34.4% · 1,122 STARS / WINDOW

Author Audience

AUDIENCE

87,603

FOLLOWERS

17,096

OWNER ★

267,189

Engagement Signals

FORKS

2,768

ISSUE AUTH

PR AUTH

UNIQUE STARGAZERS 1,122 / 1,122 (DIVERSITY 1.00)

Why This Is A Finding

google-research/timesfm собрал 1,122 звёзд за окно, тогда как у автора всего 17,096 подписчиков — эффективная аудитория ≈ 87,603. Это даёт surprise-индекс 0.000427 (звёзды относительно охвата автора, а не в абсолюте). Удержание форков 34.4% и 0 внешних контрибьюторов отделяют реальный инструмент от разовой вспышки. Акселерация положительная — рост ещё не выдохся.

Related Findings

RANKS ABOVE 23% OF 9591 FINDINGS

#02guillaumemeyer/watermarks-remover[ PYTHON ]0.42 #09awesome-dsh-plugin/awesome-dsh-plugin[ PYTHON ]0.38 #11wang2122/sprix-sage-router[ PYTHON ]0.36 #16virgiliojr94/book-to-skill[ PYTHON ]0.31 #19ayghri/i-have-adhd[ PYTHON ]0.29

METRICS IN CONTEXT

MEDIAN ACROSS ALL 9591 FINDINGS · Δ vs MEDIAN · PERCENTILE = SHARE RANKED BELOW

METRICVALUEMEDIANΔ MEDPERCENTILE

SCORE0.000.00-0.00ABOVE 23%

VELOCITY37.403.63+33.77ABOVE 95%

RETENTION8.9%24.8%-16.0 PPABOVE 19%

FORKS2,768120+2,648ABOVE 96%

SURPRISE0.000.01-0.01ABOVE 10%