William-Liwei/EnergyPatchTST — GitHub trend

FINDING #5247 · UNIT ID 961009669

William-Liwei/EnergyPatchTST

This is an official implementation of "EnergyPatchTST: Multi-scale Time Series Transformers with Uncertainty Estimation for Energy Forecasting".

[ PYTHON ][ GITHUB ↗ ]

SURPRISE SCORE

0.00

Score Breakdown

SURPRISE0.0204

ENGAGEMENT0.0426

FRESHNESS1.00

SCORE = SURPRISE × ENGAGEMENT^0.7 × FRESHNESS × VISIBILITY × CONFIDENCE

SURPRISE = WINDOW STARS / DAYS / (AUDIENCE + FLOOR)

8% OF STARS IN ARCHIVE

Growth Telemetry

VELOCITY /D

4.43

ACCEL

+2.25

RETENTION

3.3%

PEAK 2026-10-11 · FORK-RETENTION 0.0% · 31 STARS / WINDOW

Author Audience

AUDIENCE

177

FOLLOWERS

OWNER ★

1,600

Engagement Signals

FORKS

ISSUE AUTH

PR AUTH

UNIQUE STARGAZERS 31 / 31 (DIVERSITY 1.00)

Why This Is A Finding

William-Liwei/EnergyPatchTST собрал 31 звёзд за окно, тогда как у автора всего 17 подписчиков — эффективная аудитория ≈ 177. Это даёт surprise-индекс 0.0204 (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 46% OF 9747 FINDINGS

#06rehan-remade/universal-modder[ PYTHON ]0.81 #10ardeyouxipianyi/workbuddy2api-hub[ PYTHON ]0.62 #19zhongerxin/iPhone-use[ PYTHON ]0.51 #28ithtelab/workbuddy-manager[ PYTHON ]0.38 #35StayLameBro/backburner[ PYTHON ]0.35

METRICS IN CONTEXT

MEDIAN ACROSS ALL 9747 FINDINGS · Δ vs MEDIAN · PERCENTILE = SHARE RANKED BELOW

METRICVALUEMEDIANΔ MEDPERCENTILE

SCORE0.000.00-0.00ABOVE 46%

VELOCITY4.433.57+0.86ABOVE 57%

RETENTION3.3%33.3%-30.0 PPABOVE 20%

FORKS4104-100ABOVE 4%

SURPRISE0.020.01+0.01ABOVE 71%