FINDING #3241 · 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.
SURPRISE SCORE
0.00
Score Breakdown
SCORE = SURPRISE × ENGAGEMENT^0.7 × FRESHNESS × VISIBILITY × CONFIDENCE
SURPRISE = WINDOW STARS / DAYS / (AUDIENCE + FLOOR)
7% OF STARS IN ARCHIVE
Growth Telemetry
VELOCITY /D
2.90
ACCEL
+0.22
RETENTION
35.9%
PEAK 2026-08-24 · FORK-RETENTION 27.8% · 87 STARS / WINDOW
Author Audience
AUDIENCE
358
FOLLOWERS
98
OWNER ★
2,603
Engagement Signals
FORKS
126
ISSUE AUTH
0
PR AUTH
0
UNIQUE STARGAZERS 87 / 87 (DIVERSITY 1.00)
Why This Is A Finding
huhusmang/Awesome-LLMs-for-Vulnerability-Detection собрал 87 звёзд за окно, тогда как у автора всего 98 подписчиков — эффективная аудитория ≈ 358. Это даёт surprise-индекс 0.00728 (звёзды относительно охвата автора, а не в абсолюте). Удержание форков 27.8% и 0 внешних контрибьюторов отделяют реальный инструмент от разовой вспышки. Акселерация положительная — рост ещё не выдохся.
Related Findings
RANKS ABOVE 66% OF 9591 FINDINGS
METRICS IN CONTEXT
MEDIAN ACROSS ALL 9591 FINDINGS · Δ vs MEDIAN · PERCENTILE = SHARE RANKED BELOW
METRICVALUEMEDIANΔ MEDPERCENTILE
SCORE0.010.00+0.00ABOVE 66%
VELOCITY2.903.63-0.73ABOVE 39%
RETENTION35.9%24.8%+11.1 PPABOVE 71%
FORKS126120+6ABOVE 51%
SURPRISE0.010.01-0.00ABOVE 48%