FINDING #1608 · UNIT ID 1177608268
wanshuiyin/Auto-claude-code-research-in-sleep
ARIS ⚔️ (Auto-Research-In-Sleep) — Lightweight Markdown-only skills for autonomous ML research: cross-model review loops, idea discovery, and experiment automation. No framework, no lock-in — works with Claude Code, Codex, OpenClaw, or any LLM agent.
SURPRISE SCORE
0.00
Score Breakdown
SCORE = SURPRISE × ENGAGEMENT^0.7 × FRESHNESS × VISIBILITY × CONFIDENCE
SURPRISE = WINDOW STARS / DAYS / (AUDIENCE + FLOOR)
0% OF STARS IN ARCHIVE
Growth Telemetry
VELOCITY /D
13.33
ACCEL
-20.00
RETENTION
0.0%
PEAK 2026-10-15 · FORK-RETENTION 0.0% · 40 STARS / WINDOW
Author Audience
AUDIENCE
2,298
FOLLOWERS
387
OWNER ★
19,105
Engagement Signals
FORKS
1,596
ISSUE AUTH
0
PR AUTH
0
UNIQUE STARGAZERS 40 / 40 (DIVERSITY 1.00)
Why This Is A Finding
wanshuiyin/Auto-claude-code-research-in-sleep собрал 40 звёзд за окно, тогда как у автора всего 387 подписчиков — эффективная аудитория ≈ 2,298. Это даёт surprise-индекс 0.0057 (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 68% OF 4978 FINDINGS
METRICS IN CONTEXT
MEDIAN ACROSS ALL 4978 FINDINGS · Δ vs MEDIAN · PERCENTILE = SHARE RANKED BELOW
METRICVALUEMEDIANΔ MEDPERCENTILE
SCORE0.000.00+0.00ABOVE 68%
VELOCITY13.335.33+8.00ABOVE 78%
RETENTION0.0%0.0%0.0 PPABOVE 0%
FORKS1,596346+1,250ABOVE 76%
SURPRISE0.010.00+0.00ABOVE 53%