real-stanford/universal_manipulation_interface — GitHub trend

◂ BACK TO LEADERBOARD

FINDING #4975 · UNIT ID 758406180

real-stanford/universal_manipulation_interface

Universal Manipulation Interface: In-The-Wild Robot Teaching Without In-The-Wild Robots

[ PYTHON ][ ORG ][ GITHUB ↗ ]

SURPRISE SCORE

0.00

Score Breakdown

SURPRISE0.000418

ENGAGEMENT0.20

FRESHNESS1.38

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

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

20% OF STARS IN ARCHIVE

Growth Telemetry

VELOCITY /D

1.68

ACCEL

+0.00

RETENTION

26.9%

PEAK 2026-05-13 · FORK-RETENTION 0.0% · 302 STARS / WINDOW

Author Audience

AUDIENCE

3,974

FOLLOWERS

1,047

OWNER ★

9,401

Engagement Signals

FORKS

275

ISSUE AUTH

PR AUTH

UNIQUE STARGAZERS 302 / 302 (DIVERSITY 1.00)

Why This Is A Finding

real-stanford/universal_manipulation_interface собрал 302 звёзд за окно, тогда как у автора всего 1,047 подписчиков — эффективная аудитория ≈ 3,974. Это даёт surprise-индекс 0.000418 (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 44% OF 8899 FINDINGS

#07Alishahryar1/free-claude-code[ PYTHON ]0.0932 #08jundot/omlx[ PYTHON ]0.0867 #18tirth8205/code-review-graph[ PYTHON ]0.0767 #21wanshuiyin/Auto-claude-code-research-in-sleep[ PYTHON ]0.0734 #22debpalash/OmniVoice-Studio[ PYTHON ]0.0729

METRICS IN CONTEXT

MEDIAN ACROSS ALL 8899 FINDINGS · Δ vs MEDIAN · PERCENTILE = SHARE RANKED BELOW

METRICVALUEMEDIANΔ MEDPERCENTILE

SCORE0.000.00-0.00ABOVE 44%

VELOCITY1.683.18-1.50ABOVE 9%

RETENTION26.9%10.1%+16.8 PPABOVE 85%

FORKS275106+169ABOVE 75%

SURPRISE0.000.01-0.01ABOVE 11%