facebookresearch/flow_matching — GitHub trend

FINDING #8867 · UNIT ID 900093817

facebookresearch/flow_matching

A PyTorch library for implementing flow matching algorithms, featuring continuous and discrete flow matching implementations. It includes practical examples for both text and image modalities.

[ PYTHON ][ ORG ][ VERIFIED ][ GITHUB ↗ ]

SURPRISE SCORE

0.00

Score Breakdown

SURPRISE0.00000298

ENGAGEMENT0.40

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

2.67

ACCEL

+2.00

RETENTION

100.0%

PEAK 2026-08-21 · FORK-RETENTION 0.0% · 8 STARS / WINDOW

Author Audience

AUDIENCE

895,028

FOLLOWERS

37,143

OWNER ★

713,620

Engagement Signals

FORKS

370

ISSUE AUTH

PR AUTH

UNIQUE STARGAZERS 8 / 8 (DIVERSITY 1.00)

Why This Is A Finding

facebookresearch/flow_matching собрал 8 звёзд за окно, тогда как у автора всего 37,143 подписчиков — эффективная аудитория ≈ 895,028. Это даёт surprise-индекс 0.00000298 (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.

Related Findings

RANKS ABOVE 3% OF 9125 FINDINGS

#02xdreizein666/getcontact-cli[ PYTHON ]0.98 #07LBH-123-AI/Comfyui_Minimax_h3_latent_Upscaler[ PYTHON ]0.72 #23guillaumemeyer/watermarks-remover[ PYTHON ]0.42 #24securo-finance/securo[ PYTHON ]0.42 #28awesome-dsh-plugin/awesome-dsh-plugin[ PYTHON ]0.39

METRICS IN CONTEXT

MEDIAN ACROSS ALL 9125 FINDINGS · Δ vs MEDIAN · PERCENTILE = SHARE RANKED BELOW

METRICVALUEMEDIANΔ MEDPERCENTILE

SCORE0.000.00-0.00ABOVE 3%

VELOCITY2.675.33-2.67ABOVE 0%

RETENTION100.0%20.6%+79.4 PPABOVE 97%

FORKS370343+27ABOVE 52%

SURPRISE0.000.00-0.00ABOVE 1%