AIR-hl/llm-interview-code — GitHub trend

◂ BACK TO LEADERBOARD

FINDING #4738 · UNIT ID 1039448547

AIR-hl/llm-interview-code

LLM面试常见手撕合集

[ JUPYTER NOTEBOOK ][ GITHUB ↗ ]

SURPRISE SCORE

0.00

Score Breakdown

SURPRISE0.0136

ENGAGEMENT0.14

FRESHNESS1.00

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

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

2% OF STARS IN ARCHIVE

Growth Telemetry

VELOCITY /D

1.57

ACCEL

+0.21

RETENTION

58.3%

PEAK 2026-09-08 · FORK-RETENTION 0.0% · 11 STARS / WINDOW

Author Audience

AUDIENCE

FOLLOWERS

OWNER ★

639

Engagement Signals

FORKS

ISSUE AUTH

PR AUTH

UNIQUE STARGAZERS 11 / 11 (DIVERSITY 1.00)

Why This Is A Finding

AIR-hl/llm-interview-code собрал 11 звёзд за окно, тогда как у автора всего 12 подписчиков — эффективная аудитория ≈ 76. Это даёт surprise-индекс 0.0136 (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 52% OF 9789 FINDINGS

#524philshiu/Drosophila_brain_model[ JUPYTER NOTEBOOK ]0.0302 #992xbsheng/atguigu-note[ JUPYTER NOTEBOOK ]0.0178 #1033Lordog/dive-into-llms[ JUPYTER NOTEBOOK ]0.0171 #1276gmonce/scikit-learn-book[ JUPYTER NOTEBOOK ]0.0139 #1458MLO-lab/LeVJEPA[ JUPYTER NOTEBOOK ]0.0123

METRICS IN CONTEXT

MEDIAN ACROSS ALL 9789 FINDINGS · Δ vs MEDIAN · PERCENTILE = SHARE RANKED BELOW

METRICVALUEMEDIANΔ MEDPERCENTILE

SCORE0.000.00+0.00ABOVE 52%

VELOCITY1.573.43-1.86ABOVE 7%

RETENTION58.3%37.5%+20.8 PPABOVE 79%

FORKS21120-99ABOVE 17%

SURPRISE0.010.01+0.01ABOVE 65%