Github Trends®
9747 findingsmedian surprise 0.00854window 7 days
UNIT / TREND-MONITOR · REV 2.6
[ 7 days window ]
SOURCE: own snapshots
FINDING #9106 · UNIT ID 1307762938
phoenix-zhou/industrial-general-rag
The project integrates the RAG and FAQ dual mechanisms, introduces intent recognition, dynamic adaptive retrieval, and the RAGAS automated evaluation system, achieving a transformation from empirical optimization to data-driven optimization.
[ PYTHON ][ GITHUB ↗ ]
SURPRISE SCORE
0.00

Score Breakdown

SURPRISE0.0063
ENGAGEMENT0.19
FRESHNESS1.00
SCORE = SURPRISE × ENGAGEMENT^0.7 × FRESHNESS × VISIBILITY × CONFIDENCE
SURPRISE = WINDOW STARS / DAYS / (AUDIENCE + FLOOR)
5% OF STARS IN ARCHIVE
[BOT] SUSPECTED STAR BOT — SCORE PENALIZED. SIGNATURES:
S2 · NO EXTERNAL ISSUE/PR AUTHORS DESPITE 100+ STARS
S10 · DEAD CODE, ZERO CONTRIBUTORS, YET STARS KEEP DRIPPING

Growth Telemetry

VELOCITY /D
3.71
ACCEL
-0.46
RETENTION
70.0%
PEAK 2026-10-06 · FORK-RETENTION 0.0% · 26 STARS / WINDOW

Author Audience

AUDIENCE
550
FOLLOWERS
175
OWNER ★
3,748

Engagement Signals

FORKS
25
ISSUE AUTH
0
PR AUTH
0
UNIQUE STARGAZERS 26 / 26 (DIVERSITY 1.00)

Why This Is A Finding

phoenix-zhou/industrial-general-rag собрал 26 звёзд за окно, тогда как у автора всего 175 подписчиков — эффективная аудитория ≈ 550. Это даёт surprise-индекс 0.0063 (звёзды относительно охвата автора, а не в абсолюте). Удержание форков 0.0% и 0 внешних контрибьюторов отделяют реальный инструмент от разовой вспышки. Акселерация отрицательная — внимание остывает после пика.

METRICS IN CONTEXT

MEDIAN ACROSS ALL 9747 FINDINGS · Δ vs MEDIAN · PERCENTILE = SHARE RANKED BELOW
METRICVALUEMEDIANΔ MEDPERCENTILE
SCORE0.000.00-0.00ABOVE 7%
VELOCITY3.713.57+0.14ABOVE 51%
RETENTION70.0%33.3%+36.7 PPABOVE 92%
FORKS25104-79ABOVE 21%
SURPRISE0.010.01-0.00ABOVE 42%