FINDING #7790 · UNIT ID 1381271129
Shanghua-Gao/RSI-Jev
Typed-decision models (noul / choice / score) trained by a self-improving loop of AI agents — checkpoints, the code that produced them, and every version that failed.
SURPRISE SCORE
0.00
Score Breakdown
SCORE = SURPRISE × ENGAGEMENT^0.7 × FRESHNESS × VISIBILITY × CONFIDENCE
SURPRISE = WINDOW STARS / DAYS / (AUDIENCE + FLOOR)
56% 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
8.86
ACCEL
+0.21
RETENTION
47.9%
PEAK 2026-10-04 · FORK-RETENTION 0.0% · 62 STARS / WINDOW
Author Audience
AUDIENCE
116
FOLLOWERS
7
OWNER ★
510
Engagement Signals
FORKS
8
ISSUE AUTH
0
PR AUTH
0
UNIQUE STARGAZERS 62 / 62 (DIVERSITY 1.00)
Why This Is A Finding
Shanghua-Gao/RSI-Jev собрал 62 звёзд за окно, тогда как у автора всего 7 подписчиков — эффективная аудитория ≈ 116. Это даёт surprise-индекс 0.0568 (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 20% OF 9757 FINDINGS
METRICS IN CONTEXT
MEDIAN ACROSS ALL 9757 FINDINGS · Δ vs MEDIAN · PERCENTILE = SHARE RANKED BELOW
METRICVALUEMEDIANΔ MEDPERCENTILE
SCORE0.000.00-0.00ABOVE 20%
VELOCITY8.863.57+5.29ABOVE 75%
RETENTION47.9%40.0%+7.9 PPABOVE 64%
FORKS8112-104ABOVE 7%
SURPRISE0.060.01+0.05ABOVE 90%