FINDING #4808 · UNIT ID 1209946634
Sim2Reason/Sim2Reason
Sim2Reason: Solving Physics Olympiad via Reinforcement Learning on Physics Simulators. We present a method for turning physics simulators into scalable generators of question–answer pairs for improving LLM physical reasoning.
SURPRISE SCORE
0.00
Score Breakdown
SCORE = SURPRISE × ENGAGEMENT^0.7 × FRESHNESS × VISIBILITY × CONFIDENCE
SURPRISE = WINDOW STARS / DAYS / (AUDIENCE + FLOOR)
84% 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
1.60
ACCEL
-0.07
RETENTION
1.8%
PEAK 2026-05-05 · FORK-RETENTION 0.0% · 144 STARS / WINDOW
Author Audience
AUDIENCE
46
FOLLOWERS
6
OWNER ★
171
Engagement Signals
FORKS
25
ISSUE AUTH
0
PR AUTH
0
UNIQUE STARGAZERS 144 / 144 (DIVERSITY 1.00)
Why This Is A Finding
Sim2Reason/Sim2Reason собрал 144 звёзд за окно, тогда как у автора всего 6 подписчиков — эффективная аудитория ≈ 46. Это даёт surprise-индекс 0.0186 (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 25% OF 6380 FINDINGS
METRICS IN CONTEXT
MEDIAN ACROSS ALL 6380 FINDINGS · Δ vs MEDIAN · PERCENTILE = SHARE RANKED BELOW
METRICVALUEMEDIANΔ MEDPERCENTILE
SCORE0.000.00-0.00ABOVE 25%
VELOCITY1.603.99-2.39ABOVE 4%
RETENTION1.8%17.1%-15.4 PPABOVE 3%
FORKS2590-64ABOVE 15%
SURPRISE0.020.01+0.01ABOVE 62%