FINDING #497 · 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)
50% OF STARS IN ARCHIVE
[BOT] SUSPECTED STAR BOT — SCORE PENALIZED. SIGNATURES:
S2 · NO EXTERNAL ISSUE/PR AUTHORS DESPITE 100+ STARS
S5 · PREDATES WINDOW, YET HALF+ OF ALL ITS STARS LANDED IN IT
S7 · THIS REPO IS ~ALL OF THE OWNER'S STARS
Growth Telemetry
VELOCITY /D
74.79
ACCEL
-0.74
RETENTION
30.1%
PEAK 2026-05-13 · FORK-RETENTION 0.0% · 6,731 STARS / WINDOW
Author Audience
AUDIENCE
1,656
FOLLOWERS
263
OWNER ★
13,929
Engagement Signals
FORKS
1,212
ISSUE AUTH
0
PR AUTH
0
UNIQUE STARGAZERS 6,731 / 6,731 (DIVERSITY 1.00)
Why This Is A Finding
wanshuiyin/Auto-claude-code-research-in-sleep собрал 6,731 звёзд за окно, тогда как у автора всего 263 подписчиков — эффективная аудитория ≈ 1,656. Это даёт surprise-индекс 0.0441 (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 34% OF 751 FINDINGS
METRICS IN CONTEXT
MEDIAN ACROSS ALL 751 FINDINGS · Δ vs MEDIAN · PERCENTILE = SHARE RANKED BELOW
METRICVALUEMEDIANΔ MEDPERCENTILE
SCORE0.000.00-0.00ABOVE 34%
VELOCITY74.796.61+68.18ABOVE 91%
RETENTION30.1%22.2%+7.9 PPABOVE 66%
FORKS1,21297+1,115ABOVE 91%
SURPRISE0.040.03+0.02ABOVE 75%