Github Trends®
6380 findingsmedian surprise 0.0122window 90 days
UNIT / TREND-MONITOR · REV 2.6
[ 90 days window ]
SOURCE: gharchive
FINDING #5574 · UNIT ID 948264786
LLMQuant/quant-mind
QuantMind is an intelligent knowledge extraction and retrieval framework for quantitative finance.
[ PYTHON ][ ORG ][ GITHUB ↗ ]
SURPRISE SCORE
0.00

Score Breakdown

SURPRISE0.00533
ENGAGEMENT0.20
FRESHNESS1.34
SCORE = SURPRISE × ENGAGEMENT^0.7 × FRESHNESS × VISIBILITY × CONFIDENCE
SURPRISE = WINDOW STARS / DAYS / (AUDIENCE + FLOOR)
93% OF STARS IN ARCHIVE
[BOT] SUSPECTED STAR BOT — SCORE PENALIZED. SIGNATURES:
S2 · NO EXTERNAL ISSUE/PR AUTHORS DESPITE 100+ STARS
S5 · PREDATES WINDOW, YET HALF+ OF ALL ITS STARS LANDED IN IT

Growth Telemetry

VELOCITY /D
20.78
ACCEL
+0.46
RETENTION
8.9%
PEAK 2026-06-11 · FORK-RETENTION 0.0% · 1,870 STARS / WINDOW

Author Audience

AUDIENCE
3,859
FOLLOWERS
1,264
OWNER ★
6,657

Engagement Signals

FORKS
345
ISSUE AUTH
0
PR AUTH
0
UNIQUE STARGAZERS 1,870 / 1,870 (DIVERSITY 1.00)

Why This Is A Finding

LLMQuant/quant-mind собрал 1,870 звёзд за окно, тогда как у автора всего 1,264 подписчиков — эффективная аудитория ≈ 3,859. Это даёт surprise-индекс 0.00533 (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 6380 FINDINGS · Δ vs MEDIAN · PERCENTILE = SHARE RANKED BELOW
METRICVALUEMEDIANΔ MEDPERCENTILE
SCORE0.000.00-0.00ABOVE 13%
VELOCITY20.783.99+16.78ABOVE 89%
RETENTION8.9%17.1%-8.3 PPABOVE 26%
FORKS34590+256ABOVE 82%
SURPRISE0.010.01-0.01ABOVE 32%