huhusmang/Awesome-LLMs-for-Vulnerability-Detection — GitHub trend

▲РЕПО НЕТ В ОКНЕ 180D. ПОКАЗАН FINDING ИЗ ОКНА 1D (1 day) — РАНГ #1068.

FINDING #1068 · UNIT ID 851138183

huhusmang/Awesome-LLMs-for-Vulnerability-Detection

The community's most comprehensive, continuously-updated index of research on Large Language Models for software vulnerability detection — papers across function-level, repository-level, agentic, and smart-contract detection, plus datasets, benchmarks, and surveys.

[ PYTHON ][ GITHUB ↗ ]

SURPRISE SCORE

0.00

Score Breakdown

SURPRISE0.0301

ENGAGEMENT0.33

FRESHNESS1.00

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

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

1% OF STARS IN ARCHIVE

Growth Telemetry

VELOCITY /D

12.00

ACCEL

0.00

RETENTION

0.0%

PEAK 2026-08-28 · FORK-RETENTION 0.0% · 12 STARS / WINDOW

Author Audience

AUDIENCE

358

FOLLOWERS

OWNER ★

2,603

Engagement Signals

FORKS

126

ISSUE AUTH

PR AUTH

UNIQUE STARGAZERS 12 / 12 (DIVERSITY 1.00)

Why This Is A Finding

huhusmang/Awesome-LLMs-for-Vulnerability-Detection собрал 12 звёзд за окно, тогда как у автора всего 98 подписчиков — эффективная аудитория ≈ 358. Это даёт surprise-индекс 0.0301 (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 82% OF 5892 FINDINGS

#12wang2122/sprix-sage-router[ PYTHON ]0.75 #15HRuiCcc/music-geshizhuanhuan[ PYTHON ]0.61 #20User0332/rewards-farmer[ PYTHON ]0.54 #22framepipe-dev/media-inference-worker[ PYTHON ]0.54 #24openJiuwen-ai/jiuwenswarm[ PYTHON ]0.48

METRICS IN CONTEXT

MEDIAN ACROSS ALL 5892 FINDINGS · Δ vs MEDIAN · PERCENTILE = SHARE RANKED BELOW

METRICVALUEMEDIANΔ MEDPERCENTILE

SCORE0.010.00+0.01ABOVE 82%

VELOCITY12.009.00+3.00ABOVE 59%

RETENTION0.0%0.0%0.0 PPABOVE 0%

FORKS126433-307ABOVE 29%

SURPRISE0.030.01+0.02ABOVE 75%