FINDING #6234 · UNIT ID 1179034062
claw-eval/claw-eval
Claw-Eval is an evaluation harness for evaluating LLM as agents. All tasks verified by humans.
SURPRISE SCORE
0.00
Score Breakdown
SCORE = SURPRISE × ENGAGEMENT^0.7 × FRESHNESS × VISIBILITY × CONFIDENCE
SURPRISE = WINDOW STARS / DAYS / (AUDIENCE + FLOOR)
2% OF STARS IN ARCHIVE
[BOT] SUSPECTED STAR BOT — SCORE PENALIZED. SIGNATURES:
S2 · NO EXTERNAL ISSUE/PR AUTHORS DESPITE 100+ STARS
S7 · THIS REPO IS ~ALL OF THE OWNER'S STARS
S10 · DEAD CODE, ZERO CONTRIBUTORS, YET STARS KEEP DRIPPING
Growth Telemetry
VELOCITY /D
1.86
ACCEL
+0.57
RETENTION
0.0%
PEAK 2026-07-16 · FORK-RETENTION 0.0% · 13 STARS / WINDOW
Author Audience
AUDIENCE
157
FOLLOWERS
6
OWNER ★
724
Engagement Signals
FORKS
65
ISSUE AUTH
0
PR AUTH
0
UNIQUE STARGAZERS 13 / 13 (DIVERSITY 1.00)
Why This Is A Finding
claw-eval/claw-eval собрал 13 звёзд за окно, тогда как у автора всего 6 подписчиков — эффективная аудитория ≈ 157. Это даёт surprise-индекс 0.00944 (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 11% OF 6993 FINDINGS
METRICS IN CONTEXT
MEDIAN ACROSS ALL 6993 FINDINGS · Δ vs MEDIAN · PERCENTILE = SHARE RANKED BELOW
METRICVALUEMEDIANΔ MEDPERCENTILE
SCORE0.000.00-0.00ABOVE 11%
VELOCITY1.863.71-1.86ABOVE 18%
RETENTION0.0%32.1%-32.1 PPABOVE 0%
FORKS6593-28ABOVE 40%
SURPRISE0.010.01-0.00ABOVE 50%