▲РЕПО НЕТ В ОКНЕ 90D. ПОКАЗАН FINDING ИЗ ОКНА 180D (180 days) — РАНГ #1668.
FINDING #1668 · UNIT ID 287463830
microsoft/qlib
Qlib is an AI-oriented Quant investment platform that aims to use AI tech to empower Quant Research, from exploring ideas to implementing productions. Qlib supports diverse ML modeling paradigms, including supervised learning, market dynamics modeling, and RL, and is now equipped with https://github.com/microsoft/RD-Agent to automate R&D process.
SURPRISE SCORE
0.00
Score Breakdown
SCORE = SURPRISE × ENGAGEMENT^0.7 × FRESHNESS × VISIBILITY × CONFIDENCE
SURPRISE = WINDOW STARS / DAYS / (AUDIENCE + FLOOR)
2% OF STARS IN ARCHIVE
Growth Telemetry
VELOCITY /D
5.34
ACCEL
-0.09
RETENTION
10.7%
PEAK 2026-04-02 · FORK-RETENTION 60.0% · 962 STARS / WINDOW
Author Audience
AUDIENCE
3,820,953
FOLLOWERS
128,576
OWNER ★
2,754,002
Engagement Signals
FORKS
7,606
ISSUE AUTH
4
PR AUTH
5
UNIQUE STARGAZERS 962 / 962 (DIVERSITY 1.00)
Why This Is A Finding
microsoft/qlib собрал 962 звёзд за окно, тогда как у автора всего 128,576 подписчиков — эффективная аудитория ≈ 3,820,953. Это даёт surprise-индекс 0.0000014 (звёзды относительно охвата автора, а не в абсолюте). Удержание форков 60.0% и 9 внешних контрибьюторов отделяют реальный инструмент от разовой вспышки. Акселерация отрицательная — внимание остывает после пика.
Related Findings
RANKS ABOVE 2% OF 1696 FINDINGS
METRICS IN CONTEXT
MEDIAN ACROSS ALL 1696 FINDINGS · Δ vs MEDIAN · PERCENTILE = SHARE RANKED BELOW
METRICVALUEMEDIANΔ MEDPERCENTILE
SCORE0.000.00-0.00ABOVE 2%
VELOCITY5.342.82+2.52ABOVE 75%
RETENTION10.7%4.8%+5.8 PPABOVE 80%
FORKS7,6061,584+6,023ABOVE 86%
SURPRISE0.000.00-0.00ABOVE 2%