elizabetht/100-days-of-inference — GitHub trend

◂ BACK TO LEADERBOARD

FINDING #6622 · UNIT ID 1196855016

elizabetht/100-days-of-inference

100 days of LLM inference engineering — daily posts, experiments, and visualizations

[ JUPYTER NOTEBOOK ][ GITHUB ↗ ]

SURPRISE SCORE

0.00

Score Breakdown

SURPRISE0.0115

ENGAGEMENT0.20

FRESHNESS1.00

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

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

11% 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

1.57

ACCEL

-0.50

RETENTION

12.5%

PEAK 2026-07-18 · FORK-RETENTION 0.0% · 11 STARS / WINDOW

Author Audience

AUDIENCE

FOLLOWERS

OWNER ★

176

Engagement Signals

FORKS

ISSUE AUTH

PR AUTH

UNIQUE STARGAZERS 11 / 11 (DIVERSITY 1.00)

Why This Is A Finding

elizabetht/100-days-of-inference собрал 11 звёзд за окно, тогда как у автора всего 79 подписчиков — эффективная аудитория ≈ 97. Это даёт surprise-индекс 0.0115 (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.

Related Findings

RANKS ABOVE 12% OF 7487 FINDINGS

#331Dashboard-Design/Power-BI-Design-Files[ JUPYTER NOTEBOOK ]0.017 #681GiovanniPasq/agentic-rag-for-dummies[ JUPYTER NOTEBOOK ]0.0101 #1137teddylee777/machine-learning[ JUPYTER NOTEBOOK ]0.00675 #1227CalvinXKY/InfraTech[ JUPYTER NOTEBOOK ]0.00629 #1302baijiuyang/collision-avoidance2[ JUPYTER NOTEBOOK ]0.00591

METRICS IN CONTEXT

MEDIAN ACROSS ALL 7487 FINDINGS · Δ vs MEDIAN · PERCENTILE = SHARE RANKED BELOW

METRICVALUEMEDIANΔ MEDPERCENTILE

SCORE0.000.00-0.00ABOVE 12%

VELOCITY1.573.43-1.86ABOVE 7%

RETENTION12.5%30.6%-18.1 PPABOVE 18%

FORKS22125-103ABOVE 13%

SURPRISE0.010.01+0.00ABOVE 63%